UTS site search

Professor Gamini Dissanayake

Biography

Gamini Dissanayake is the James N Kirby Professor of Mechanical and Mechatronic Engineering at University of Technology, Sydney (UTS). He has expertise in a broad range of topics in robotics including sensor fusion, localisation, mapping, SLAM and human-robot interaction. He leads the UTS node of the Australian Research Council Centre of Excellence for Autonomous Systems (CAS), UTS Centre for Intelligent Mechatronic Systems (CIMS) and the UTS robotics team. He graduated in Mechanical/Production Engineering from the University of Peradeniya, Sri Lanka in 1977. He received his M.Sc. in Machine Tool Technology and Ph.D. in Mechanical Engineering (Robotics) from the University of Birmingham, England in 1981 and 1985 respectively.

Image of Gamini Dissanayake
Director, Research, School of Elec, Mech and Mechatronic Systems
Director, CAS - Centre for Autonomous Systems
Core Member, CAS - Centre for Autonomous Systems
BSc (Eng) (Hons) (Sri Lanka), MSc (Birm), PhD (Birm)
Member, The Institution of Electrical and Electronic Engineers
 
Phone
+61 2 9514 2683

Research Interests

Localization and map building for mobile robots, navigation systems, field robotics, dynamics and control of mechanical systems, optimisation and path planning.

Can supervise: Yes
Can supervise PhD students.

Mechatronics and Robotics

Books

Wang, Z., Huang, S. & Dissanayake, G. 2011, Simultaneous Localization and Mapping: Exactly Sparse Information Filters, 1, World Scientific, Singapore.
View/Download from: UTS OPUS
Simultaneous localization and mapping (SLAM) is a process where an autonomous vehicle builds a map of an unknown environment while concurrently generating an estimate for its location. This book is concerned with computationally efficient solutions to the large scale SLAM problems using exactly sparse Extended Information Filters (EIF). The invaluable book also provides a comprehensive theoretical analysis of the properties of the information matrix in EIF-based algorithms for SLAM. Three exactly sparse information filters for SLAM are described in detail, together with two efficient and exact methods for recovering the state vector and the covariance matrix. Proposed algorithms are extensively evaluated both in simulation and through experiments.

Chapters

Dantanarayana, L., Ranasinghe, R., Tran, A., Liu, D. & Dissanayake, G. 2014, 'A Novel Collaboratively Designed Robot to Assist Carers', pp. 105-114.
View/Download from: UTS OPUS
Wang, Z., Huang, S. & Dissanayake, G. 2008, 'Tradeoffs in SLAM with sparse information filters' in Laugier, C. & Siegwart, R. (eds), Field and Service Robotics, Springer, Berlin Heidelberg, pp. 339-348.
View/Download from: UTS OPUS or Publisher's site
Designing filters exploiting the sparseness of the information matrix for efficiently solving the simultaneous localization and mapping (SLAM) problem has attracted significant attention during the recent past. The main contribution of this paper is a review of the various sparse information filters proposed in the literature to date, in particular, the compromises used to achieve sparseness. Two of the most recent algorithms that the authors have implemented, Exactly Sparse Extended Information Filter (ESEIF) by Walter et al. [5] and the D-SLAM by Wang et al. [6] are discussed and analyzed in detail. It is proposed that this analysis can stimulate developing a framework suitable for evaluating the relative merits of SLAM algorithms.
Herath, H.D., Kodagoda, S. & Dissanayake, G. 2007, 'Stereo Vision Based SLAM: Issues and Solutions' in Obinata, G. & Dutta, A. (eds), Vision Systems, ITECH, Austria, pp. 555-582.
View/Download from: UTS OPUS
Wang, Z., Huang, S. & Dissanayake, G. 2006, 'Implementation Issues and Experimental Evaluation of D-SLAM' in Corke, P. & Sukkarieh, S. (eds), Field and Service Robotics, Springer-Verlag, Berlin, Heidelberg, pp. 155-166.
View/Download from: UTS OPUS
Furukawa, T., Dissanayake, G. & Durrant-Whyte, H. 2004, 'An Application of Multi-objective Evolutionary Algorithms in Autonomous Vehicle Navigation' in Coello, C.A.C. (ed), Applications of Multi-Objective Evolutionary Algorithms, World Scientific, Singapore, pp. 125-153.
View/Download from: UTS OPUS
NA

Conferences

Takami, K., Furukawa, T., Kumon, M. & Dissanayake, G. 2016, 'Non-field-of-view acoustic target estimation in complex indoor environment', Springer Tracts in Advanced Robotics, pp. 577-592.
View/Download from: Publisher's site
© Springer International Publishing Switzerland 2016. This paper presents a new approach which acoustically localizes a mobile target outside the Field-of-View (FOV), or the Non-Field-of-View (NFOV), of an optical sensor, and its implementation to complex indoor environments. In this approach, microphones are fixed sparsely in the indoor environment of concern. In a prior process, the Interaural Level Difference IID of observations acquired by each set of two microphones is derived for different sound target positions and stored as an acoustic cue. When a newsound is observed in the environment, a joint acoustic observation likelihood is derived by fusing likelihoods computed from the correlation of the IID of the new observation to the stored acoustic cues. The location of the NFOVtarget is finally estimated within the recursive Bayesian estimation framework. After the experimental parametric studies, the potential of the proposed approach for practical implementation has been demonstrated by the successful tracking of an elderly person needing health care service in a home environment.
Abeywardena, D.M. & Dissanayake, G. 2015, 'Tightly-Coupled Model Aided Visual-Inertial Fusion for Quadrotor Micro Air Vehicles', Results of the 9th International Conference, 9th International Conference on Field and Service Robotics, Springer, Toronto, Canada, pp. 153-166.
View/Download from: UTS OPUS or Publisher's site
The main contribution of this paper is a tightly-coupled visual-inertial fusion algorithm for simultaneous localisation and mapping (SLAM) for a quadrotor micro aerial vehicle (MAV). Proposed algorithm is based on an extended Kalman filter that uses a platform specific dynamic model to integrate information from an inertial measurement unit (IMU) and a monocular camera on board the MAV. MAV dynamic model exploits the unique characteristics of the quadrotor, making it possible to generate relatively accurate motion predictions. This, together with an undelayed feature initialisation strategy based on inverse depth parametrisation enables more effective feature tracking and reliable visual SLAM with a small number of features even during rapid manoeuvres. Experimental results are presented to demonstrate the effectiveness of the proposed algorithm.
Wu, K., Dissanayake, G. & Ranasinghe, R. 2015, 'Active Recognition and Pose Estimation of Household Objects in Clutter', Proceedings of 2015 IEEE International Conference on Robotics and Automation (ICRA), International Conference on Robotics and Automation, IEEE, Seattle, pp. 4230-4237.
View/Download from: UTS OPUS or Publisher's site
This paper presents an active object recognition and pose estimation system for household objects in a highly cluttered environment. A sparse feature model, augmented with the characteristics of features when observed from different viewpoints is used for recognition and pose estimation while a dense point cloud model is used for storing geometry. This strategy makes it possible to accurately predict the expected information available during the Next-Best-View planning process as both the visibility as well as the likelihood of feature matching can be considered simultaneously. Experimental evaluations of the object recognition and pose estimation with an RGB-D sensor mounted on a Turtlebot are presented.
Wijerathna, B.S., Kodagoda, S., Valls Miro, J. & Dissanayake, G. 2015, 'Iterative Coarse to Fine Approach for Interpretation of Defect Profiles Using MFL Measurements', Proceedings of the IEEE Conference on Industrial Electronics and Applications, IEEE Conference on Industrial Electronics and Applications, IEEE, Auckland, New Zealand.
View/Download from: UTS OPUS or Publisher's site
Magnetic Flux Leakage (MFL) is a commonly used technology for non destructive evaluation of ferromagnetic materials. MFL in general is used to estimate isolated defect geometry. In this study, a coarse to fine approach is proposed to interpret MFL measurements for continuous defect profiling. The coarse solution is implemented using a Gaussian Processes (GP) model and the fine approach is implemented using an unconstrained non-linear optimiser. This framework was tested on a 100 year old 600mm diameter cast iron pipe line. Some pipe sections were extracted, grit blasted and profiled using a sub millimetre accurate 3 - D laser scanner. The coarse to fine predictions were compared with the laser measured ground truth with just 1.2 mm RMS error.
Khosoussi, K., Huang, S. & Dissanayake, G. 2015, 'Exploiting the separable structure of SLAM', Robotics: Science and Systems, Rome, Italy.
View/Download from: UTS OPUS
In this paper we point out an overlooked structure of SLAM that distinguishes it from a generic nonlinear least squares problem. The measurement function in most common forms of SLAM is linear with respect to robot and features' positions. Therefore, given an estimate for robot orientation, the conditionally optimal estimate for the rest of state variables can be easily obtained by solving a sparse linear-Gaussian estimation problem. We propose an algorithm to exploit this intrinsic property of SLAM by stripping the problem down to its nonlinear core, while maintaining its natural sparsity. Our algorithm can be used together with any Newton-based iterative solver and is applicable to 2D/3D pose-graph and feature-based problems. Our results suggest that iteratively solving the nonlinear core of SLAM leads to a fast and reliable convergence as compared to the state-of-the-art back-ends.
Furukawa, T., Dantanarayana, L.I., Ziglar, J., Ranasinghe, R. & Dissanayake, G. 2015, 'Fast Global Scan Matching for High-Speed Vehicle Navigation', IEEE Xplore, Multisensor Fusion and Integration for Intelligent Systems (MFI), 2015 IEEE International Conference on, IEEE, San Diego, CA, USA, pp. 37-42.
View/Download from: UTS OPUS or Publisher's site
Ghaffari Jadidi, M., Valls Miro, J. & Dissanayake, G. 2015, 'Mutual Information-based Exploration on Continuous Occupancy Maps', IEEE/RSJ International Conference on Intelligent Robots and Systems, Hamburg Germany.
View/Download from: UTS OPUS or Publisher's site
The problem of active perception with an autonomous robot is studied in this paper. It is proposed that the exploratory behavior of the robot be controlled using mutual information (MI) surfaces between the current map and a one-step look ahead measurements. MI surfaces highlight informative areas for exploration. A novel method for computing these surfaces is described. An approach that exploits structural dependencies of the environment and handles sparse sensor measurements to build a continuous model of the environment, that can then be used to generate MI surfaces is also proposed. A gradient field of occupancy probability distribution is regressed from sensor data as a Gaussian Process and provide frontier boundaries for further exploration. The continuous global frontier surface completely describes unexplored regions and, inherently, provides an automatic termination criterion for a desired sensitivity. The results from publicly available datasets confirm an average improvement of the proposed methodology over comparable standard and state-of-the-art exploratory methods available in the literature by more than 20% and 13% in travel distance and map entropy reduction rate, respectively.
Dantanarayana, L., Dissanayake, G., Ranasinghe, R. & Furukawa, T. 2015, 'An extended Kalman filter for localisation in occupancy grid maps', 2015 IEEE 10th International Conference on Industrial and Information Systems (ICIIS), IEEE, pp. 419-424.
View/Download from: UTS OPUS or Publisher's site
Abeywardena, D.M., Pounds, P., Hunt, D. & Dissanayake, G. 2015, 'Design and Development of ReCOPTER: An Open source ROS-based Multirotor Platform for Research', Website Proceedings of Australasian Conference on Robotics and Automation 2015, Australasian Conference on Robotics and Automation 2015, ARAA, Australia, pp. 1-10.
Selection of multi-rotor aircraft systems for robotics research is a trade-off between competing objectives. While Commercial Off The Shelf systems are fast to set up and provide a ready-made platform, they often lack complete documentation and have limited extensibility for allowing researchers to modify them for scientific work. Conversely, developing an aircraft from the ground up is labour intensive and time consuming, and requires substantial experience to ensure a satisfactory result. This paper ranks common robotic multi-rotor aircraft used in research against several criteria for openness, extensibility and performance. We propose a standard platform using open components and an open-source design, specifically geared to the needs of the research community
To, A.W., Paul, G., Rushton-Smith, D., Liu, D. & Dissanayake, G. 2012, 'Automated and Frequent Calibration of a Robot Manipulator-mounted IR Range camera for Steel Bridge Maintenance', Field and Service Robotics Vol 92 - Results of the 8th International Conference on Field and Service Robotics, International Conference on Field and Service Robotics, Springer-Verlag, Matsushima, Miyagi, Japan, pp. 205-218.
View/Download from: UTS OPUS or Publisher's site
This paper presents an automated and cost-effective approach to frequent hand-eye calibration of an IR range camera mounted to the end-effector of a robot manipulator for use in a field environment. A set of three reflector discs arranged in a structured pattern attached to the robot platform is used to provide high contrast image features with corresponding range readings for accurate calculation of the camera-to-robot base transform. Using this approach the hand-eye transform between the IR range camera and robot end-effector can be determined by considering the robot manipulator model. Experimental results show that a structured lightingbased IR range camera can be reliably hand-eye calibrated to a 6DOF robot manipulator using the presented automated approach. Once calibrated, the IR range camera can be positioned with the manipulator so as to generate a high resolution geometric map of the surrounding environment suitable for performing the grit-blasting task.
Zhao, L., Huang, S. & Dissanayake, G. 2014, 'Linear MonoSLAM: A Linear Approach to Large-Scale Monocular SLAM Problems', 2014 IEEE International Conference on Robotics & Automation (ICRA), IEEE, Hong Kong, China, pp. 1517-1523.
View/Download from: UTS OPUS
This paper presents a linear approach for solving monocular simultaneous localization and mapping (SLAM) problems. The algorithm rst builds a sequence of small initial submaps and then joins these submaps together in a divideand-conquer (D&C) manner. Each of the initial submap is built using three monocular images by bundle adjustment (BA), which is a simple nonlinear optimization problem. Each step in the D&C submap joining is solved by a linear least squares together with a coordinate and scale transformation. Since the only nonlinear part is in the building of the initial submaps, the algorithm makes it possible to solve large-scale monocular SLAM while avoiding issues associated with initialization, iteration, and local minima that are present in most of the nonlinear optimization based algorithms currently used for large-scale monocular SLAM. Experimental results based on publically available datasets are used to demonstrate that the proposed algorithms yields solutions that are very close to those obtained using global BA starting from good initial guess.
Nguyen, V., Kodagoda, S., Ranasinghe, R. & Dissanayake, G. 2014, 'Mobile Robotic Wireless Sensor Networks for Efficient Spatial Prediction', 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Chicago, IL, USA, pp. 1176-1181.
View/Download from: UTS OPUS
This paper addresses the issue of monitoring physical spatial phenomena of interest utilizing the information collected by a network of mobile, wireless and noisy sensors that can take discrete measurements as they navigate through the environment. The spatial phenomenon is statistically modelled by a Gaussian Markov Random Field (GMRF) with hyperparameters that are learnt as the measurements accumulate over time. In this context, the GMRF approximately represents the spatial field on an irregular lattice of triangulation by exploiting a stochastic partial differential equation (SPDE) approach, which benefits remarkably in computation due to the sparsity of the precision matrix. A technique of the one-step-ahead forecast is employed to predict the future measurements that are required to find the optimal sampling locations. It is shown that optimizing the sampling path problem with the logarithm of the determinant either of a covariance matrix using a GP model or of a precision matrix using a GMRF model for mobile robotic wireless sensor networks (MRWSNs) even by a greedy algorithm is impractical. This paper proposes an efficient novel optimality criterion for the adaptive sampling strategy to find the most informative locations in taking future observations that minimize the uncertainty at unobserved locations. The computational complexity of our proposed method is linear, which makes the MRWSN scalable and practically feasible. The effectiveness of the proposed approach is compared and demonstrated using a pre-published data set with appealing results.
Abeywardena, D.M., Wang, Z., Dissanayake, G., Waslander, S.L. & Kodagoda 2014, 'Model-aided State Estimation for Quadrotor Micro Air Vehicles amidstWind Disturbances', Proceedings of the ... IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE/RSJ International Conference on Intelligent Robots and Systems, EEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Chicago, Illinois, pp. 4813-4818.
View/Download from: UTS OPUS
This paper extends the recently developed Model-Aided Visual-Inertial Fusion (MA-VIF) technique for quadrotor Micro Air Vehicles (MAV) to deal with wind disturbances. The wind effects are explicitly modelled in the quadrotor dynamic equations excluding the unobservable wind velocity component. This is achieved by a nonlinear observability of the dynamic system with wind effects. We show that using the developed model, the vehicle pose and two components of the wind velocity vector can be simultaneously estimated with a monocular camera and an inertial measurement unit. We also show that the MA-VIF is reasonably tolerant to wind disturbances, even without explicit modelling of wind effects and explain the reasons for this behaviour. Experimental results using a Vicon motion capture system are presented to demonstrate the effectiveness of the proposed method and validate our claims.
Barnes, B., Abeywardena, D.M., Kodagoda, S. & Dissanayake, G. 2014, 'Evaluation of Feature Detectors for KLT based Feature Tracking usingthe Odroid U3', Australian Conference on Robotics and Automation (ACRA 2014), Australian Robotics and Automation Association, Melbourne.
View/Download from: UTS OPUS
Feature tracking is an integral part of most vision-based state estimation frameworks. However, tracking features at a sufficient frame rate is a challenging task for mobile robots such as Micro Aerial Vehicles (MAVs) due to their fast dynamics and limited on-board computing resources. Recent developments in smartphone processors have led to embedded computing platforms that are ideal on-board computers for MAV state estimation. This paper analyses the performance of a Kanade-Lucas-Thomasi (KLT) based feature tracker on a state-of-the-art embedded computing platform suitable for on-board MAV state estimation. It compares the performance of different implementations of the feature tracker using four different low-complexity feature detectors. The experimental results presented herein may serve as guidelines for the selection of a feature detector, image resolution, framerate and feature quantity when developing on-board feature tracking systems based on ARM Cortex-A9 embedded computers.
Liu, D.K., Dissanayake, G., Valls Miro, J. & Waldron, K.J. 2014, 'Infrastructure robotics: Research challenges and opportunities', 31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Proceedings, pp. 43-49.
View/Download from: UTS OPUS
Infrastructure robotics is about research on and development of methodologies that enable robotic systems to be used in civil infrastructure inspection, maintenance and rehabilitation. This paper briefly discusses the current research challenges and opportunities in infrastructure robotics, and presents a review of the research activities and projects in this field at the Centre for Autonomous Systems, University of Technology Sydney.
Khosoussi, K., Huang, S. & Dissanayake, G. 2014, 'Novel insights into the impact of graph structure on SLAM', IEEE International Conference on Intelligent Robots and Systems, pp. 2707-2714.
View/Download from: UTS OPUS or Publisher's site
© 2014 IEEE. SLAM can be viewed as an estimation problem over graphs. It is well known that the topology of each dataset affects the quality of the corresponding optimal estimate. In this paper we present a formal analysis of the impact of graph structure on the reliability of the maximum likelihood estimator. In particular, we show that the number of spanning trees in the graph is closely related to the D-optimality criterion in experimental design. We also reveal that in a special class of linear-Gaussian estimation problems over graphs, the algebraic connectivity is related to the E-optimality design criterion. Furthermore, we explain how the average node degree of the graph is related to the ratio between the minimum of negative log-likelihood achievable and its value at the ground truth. These novel insights give us a deeper understanding of the SLAM problem. Finally we discuss two important applications of our analysis in active measurement selection and graph pruning. The results obtained from simulations and experiments on real data confirm our theoretical findings.
Norouzi, M., Valls Miro, J., Dissanayake, G. & Vidal-Calleja, T. 2014, 'Path planning with stability uncertainty for articulated mobile vehicles in challenging environments', IEEE International Conference on Intelligent Robots and Systems, Institute of Electrical and Electronics Engineers Inc., pp. 1748-1753.
View/Download from: UTS OPUS or Publisher's site
This article proposes a probabilistic approach to account for robot stability uncertainty when planing motions over uneven terrains. A novel probabilistic stability criterion derived from the cumulative distribution of a tip-over metric is introduced that allows a safety constraint to be dynamically updated by available sensor data as it becomes available. The proposed safety constraint authorizes the planner to generates more conservative motion plans for areas with higher levels of uncertainty, while avoids unnecessary caution in well-known areas. The proposed systematic approach is particularly applicable to reconfigurable robots that can assume safer postures when required, although is equally valid for fixed-configuration platforms to choose safer paths to follow. The advantages of planning with the proposed probabilistic stability metric are demonstrated with data collected from an indoor rescue arena, as well as an outdoor rover testing facility.
Kanzhi, W.U., RANASINGHE, R. & DISSANAYAKE, G. 2014, 'A Fast Pipeline for Textured Object Recognition in Clutter using an RGB-D Sensor', Control Automation Robotics Vision (ICARCV), 2014 13th International Conference on, International Conference on Control, Automation, Robotics and Vision, IEEE, Marina Bay Sands, Singapore, pp. 1650-1655.
View/Download from: UTS OPUS
This paper presents a modular algorithm pipeline for recognizing textured household objects in cluttered environment and estimating 6 DOF poses using an RGB-D sensor. The method draws from recent advances in this area and introduces a number of innovations that enable improved performances and faster operational speed in comparison with the state-of-the-art. The pipeline consists of (i) support plane subtraction (ii) SIFT feature extraction and approximate nearest neighbour based matching (iii) feature clustering using 3D Eculidean distances (iv) SVD based pose estimation in combination with a outlier rejection strategy named SORSAC ( Spatially ORdered RAndom Consensus ) and (v) a pose combination and refinement step to combine overlapping identical instances and to refine the pose estimation result by removing incorrect hypothesis. Quantitative comparisons with the MOPED [1] system on self-constructed dataset are presented to demonstrate the effectiveness of the pipeline.
Nguyen, V., Kodagoda, S., Ranasinghe, R. & Dissanayake, G. 2014, 'Spatially-Distributed Prediction with Mobile Robotic Wireless Sensor Networks', 2014 13th International Conference on Control, Automation, Robotics & Vision, International Conference on Control, Automation, Robotics & Vision, Institute of Electrical and Electronics Engineers Inc., Marina Bay Sands, Singapore, pp. 1153-1158.
View/Download from: UTS OPUS or Publisher's site
This paper presents a distributed spatial estimation and prediction approach to address the centrally-computed scheme of Gaussian Process regression at each robotic sensor in resource-constrained networks of mobile, wireless and noisy agents monitoring physical phenomena of interest. A mobile sensor independently estimate its own parameters using collective measurements from itself and local neighboring agents as they navigate through the environment. A spatially-distributed prediction algorithm is designed utilizing methods of Jacobi overrelaxation and discrete-time average consensus to enable a robotic sensor to update its estimation of obtaining the global model parameters and recursively compute the global goal of inference. A distributed navigation strategy is also considered to drive sensors to the most uncertain locations enhancing the quality of prediction and learning parameters. Experimental results in a real-world data set illustrate the effectiveness of the proposed approach and is highly comparable to those of the centralized scheme.
Nguyen, V., Kodagoda, S., Ranasinghe, R., Dissanayake, G., Bustamante, H., Vitanage, D. & Nguyen, T. 2014, 'Spatial Prediction of Hydrogen Sulfide in Sewers with a Modified Gaussian Process Combined Mutual Information', 2014 13th International Conference on Control, Automation, Robotics & Vision, International Conference on Control, Automation, Robotics & Vision, Institute of Electrical and Electronics Engineers Inc., Marina Bay Sands, Singapore, pp. 1130-1135.
View/Download from: UTS OPUS or Publisher's site
This paper proposes a data driven machine learning model for spatial prediction of hydrogen sulfide (H2S) in a gravity sewer system. The gaseous H2S in the overhead of the gravity sewer is modelled using a Gaussian Process with a new covariance function due to constraints of sewer boundaries. The covariance function is proposed based on the distance between two locations computed along the lengths of the sewer network. A mutual information based strategy is used to choose the best k sensor measurements and their locations from among n potential sensor observations and their locations. This provably NP-hard combinatorial sensor selection problem is addressed by maximizing the mutual information between the selected locations and the locations that are not selected or do not have any sensor deployments. A proof-of-concept study was carried out comparing the spatial prediction of H2S with a complex model currently used by Sydney Water. The proposed approach is shown to be effective in both modelling and predicting the H2S spatial concentrations in sewers as well as identifying optimal number of H2S sensors and their locations for a required level of prediction accuracy.
Hassan, M., Liu, Huang & Dissanayake 2014, 'Task Oriented Area Partitioning and Allocation for Optimal Operation of Multiple Industrial Robots in Unstructured Environments', International Conference on Control, Automation, Robotics and Vision, ICARCV, IEEE Xplore, Marina Bay Sands, Singapore, pp. 1184-1189.
View/Download from: UTS OPUS
When multiple industrial robots are deployed in field applications such as grit blasting and spray painting of steel bridges, the environments are unstructured for robot operation and the robot positions may not be arranged accurately. Coordination of these multiple robots to maximize productivity through area partitioning and allocation is crucial. This paper presents a novel approach to area partitioning and allocation by utilizing multiobjective optimization and voronoi partitioning. Multiobjective optimization is used to minimize: (1) completion time, (2) proximity of the allocated area to the robot, and (3) the torque experienced by each joint of the robot during task execution. Seed points of the voronoi graph for voronoi partitioning are designed to be the design variables of the multiobjective optimization algorithm. Results of three different simulation scenarios are presented to demonstrate the effectiveness of the proposed approach and the advantage of incorporating robots' torque capacity.
Patel, M., Valls Miro, J. & Dissanayake, D. 2015, 'A Probabilistic Approach to Learn Activities of Daily Living of a Mobility Aid Device User', Proceedings of 2014 IEEE International Conference on Robotics and Automation (ICRA), IEEE International Conference on Robotics and Automation, IEEE, Hong Kong, pp. 969-974.
View/Download from: UTS OPUS or Publisher's site
The problem of inferring human behaviour is naturally complex: people interact with the environment and each other in many different ways, and dealing with the often incomplete and uncertain sensed data by which the actions are perceived only compounds the difficulty of the problem. In this paper, we propose a framework whereby these elaborate behaviours can be naturally simplified by decomposing them into smaller activities, whose temporal dependencies can be more efficiently represented via probabilistic hierarchical learning models. In this regard, patterns of a number of activities typically carried out by users of an ambulatory aid device have been identified with the aid of a Hierarchical Hidden Markov Model (HHMM) framework. By decomposing the complex behaviours into multiple layers of abstraction the approach is shown capable of modelling and learning these tightly coupled human-machine interactions. The inference accuracy of the proposed model is proven to compare favourably against more traditional discriminative models, as well as other compatible generative strategies to provide a complete picture that highlights the benefits of the proposed approach, and opens the door to more intelligent assistance with a robotic mobility aid.
Ward, P.K., Quin, P., Pagano, D., Yang, C., Liu, D., Waldron, K., Dissanayake, D., Paul, G., Brooks, P., Mann, P., Kaluarachchi, W., Manamperi, P. & Matkovic, L. 2014, 'Climbing Robot for Steel Bridge Inspection: Design Challenges', Austroads Publications Online, 9th Austroads Bridge Conference, ARRB Group, New South Wales.
View/Download from: UTS OPUS
Inspection of bridges often requires high risk operations such as working at heights, in confined spaces, in hazardous environments; or sites inaccessible by humans. There is significant motivation for robotic solutions which can carry out these inspection tasks. When inspection robots are deployed in real world inspection scenarios, it is inevitable that unforeseen challenges will be encountered. Since 2011, the New South Wales Roads & Maritime Services and the Centre of Excellence for Autonomous Systems at the University of Technology, Sydney, have been working together to develop an innovative climbing robot to inspect high risk locations on the Sydney Harbour Bridge. Many engineering challenges have been faced throughout the development of several prototype climbing robots, and through field trials in the archways of the Sydney Harbour Bridge. This paper will highlight some of the key challenges faced in designing a climbing robot for inspection, and then present an inchworm inspired robot which addresses many of these challenges.
Nguyen, V., Kodagoda, S., Ranasinghe, R. & Dissanayake, G. 2013, 'Locational Optimization based Sensor Placement for Monitoring Gaussian Processes Modeled Spatial Phenomena', Proc. 2013 IEEE 8th Conference on Industrial Electronics and Applications, 2013 IEEE 8th Conference on Industrial Electronics and Applications, IEEE, Melbourne, Australia, pp. 1-6.
View/Download from: UTS OPUS
This paper addresses the sensor placement problem associated with monitoring spatial phenomena, where mobile sensors are located on the optimal sampling paths yielding a lower prediction error. It is proposed that the spatial phenomenon to be monitored is modeled using a Gaussian Process and a variance based density function is employed to develop an expected-value function. A locational optimization based effective algorithm is employed to solve the resulting minimization of the expectedvalue function. We designed a mutual information based strategy to select the most informative subset of measurements effectively with low computational time. Our experimental results on realworld datasets have verified the superiority of the proposed approach.
Quin, P.D., Paul, G., Alempijevic, A., Liu, D. & Dissanayake, G. 2013, 'Efficient Neighbourhood-Based Information Gain Approach for Exploration of Complex 3D Environments', 2013 IEEE International Conference on Robotics and Automation (ICRA), IEEE International Conference on Robotics and Automation (ICRA), IEEE, Karlsruhe, Germany, pp. 1343-1348.
View/Download from: UTS OPUS or Publisher's site
This paper presents an approach for exploring a complex 3D environment with a sensor mounted on the end effector of a robot manipulator. In contrast to many current approaches which plan as far ahead as possible using as much environment information as is available, our approach considers only a small set of poses (vector of joint angles) neighbouring the robot's current pose in configuration space. Our approach is compared to an existing exploration strategy for a similar robot. Our results demonstrate a significant decrease in the number of information gain estimation calculations that need to be performed, while still gathering an equivalent or increased amount of information about the environment.
Dantanarayana, L.I., Ranasinghe, R. & Dissanayake, G. 2013, 'C-LOG: A Chamfer Distance Based Method for Localisation in Occupancy Grid-maps', IEEE/RSJ International Conference on Intelligent Robots and Systems 2013, IEEE/RSJ International Conference on Intelligent Robots and Systems 2013, IEEE, Tokyo, Japan, pp. 376-381.
View/Download from: UTS OPUS or Publisher's site
In this paper, the problem of localising a robot within a known two-dimensional environment is formulated as one of minimising the Chamfer Distance between the corresponding occupancy grid map and information gathered from a sensor such as a laser range finder. It is shown that this nonlinear optimisation problem can be solved efficiently and that the resulting localisation algorithm has a number of attractive characteristics when compared with the conventional particle filter based solution for robot localisation in occupancy grids. The proposed algorithm is able to perform well even when robot odometry is unavailable, insensitive to noise models and does not critically depend on any tuning parameters. Experimental results based on a number of public domain datasets as well as data collected by the authors are used to demonstrate the effectiveness of the proposed algorithm.
Abeywardena, D.M., Wang, Z., Kodagoda, S. & Dissanayake, G. 2013, 'Visual-Inertial Fusion for Quadrotor Micro Air Vehicles with Improved Scale Observability', IEEE International Conference on Robotics and Automation, International Conference on Robotics and Automation, IEEE, Karlsruhe-Germany, pp. 3148-3153.
View/Download from: UTS OPUS or Publisher's site
This paper presents a novel algorithm for fusing monocular vision and inertial information for quadrotor Micro Air Vehicles by incorporating the unique dynamic characteristics of that platform into the state estimation process. The dynamics of a quadrotor is unique in that a dual axis accelerometer mounted parallel to the propeller plane provides measurements that are directly proportional to vehicle velocities in that plane. By exploiting these dynamic characteristics, we show that all vehicle states, including the absolute scale, become observable in all motion patterns. This distinguishes our method with other visual-inertial fusion methods, which either assume zero accelerometer bias, or require sufficiently exciting motion, such as non-zero acceleration, to ensure observability of the scale. The advantages of our method over existing visual-inertial fusion algorithms are proved through a theoretical analysis using Lie Derivatives and verified by extensive simulations and experiments.
Zainudin, Z., Kodagoda, S. & Dissanayake, G. 2013, 'Mutual Information Based Data Selection in Gaussian Processes for 2D Laser Range Finder Based People Tracking', IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), IEEE, Wollongong, Australia, pp. 477-482.
View/Download from: UTS OPUS
In general, a model to describe human motion patterns should have a capability of enhancing tracking performance even with long term occlusions. One way of effectively learn these patterns is to apply Gaussian Processes (GP). However, with the increase of the amount of training data with time, the GP becomes computationally expensive. In this work, we have proposed a Mutual Information (MI) based technique along with the Mahalanobis Distance (MD) measure to keep the most informative data while discarding the least informative data. The algorithm is tested with data collected in an office environment with a Segway robot equipped with a laser range finder. It leads to more than 90% data reduction while keeping the limit of Average Route Mean Square Error (ARMSE). We have also implemented a GP based Particle filter tracker for long term people tracking with occlusions. The comparison results with Extended Kalman Filter (EKF) based tracker shows the superiority of the proposed approach.
Fang, G., Kwok, N. & Dissanayake, G. 2013, 'Skin colour detection using the statistical decision theory', Advanced Materials Research - Proceedings of the 4th International Conference on Manufacturing Science and Engineering, International Conference on Manufacturing Science and Engineering, Scientific.net, Dalian, China, pp. 1891-1895.
View/Download from: UTS OPUS or Publisher's site
Skin colour is an important attribute that can be used to detect human presence in an image. In this paper, a new method is introduced to detect skin pixels in an image based on statistical decision theory. The proposed method uses a parametric model to
Norouzi, M., Valls Miro, J. & Dissanayake, G. 2013, 'A Statistical Approach for Uncertain Stability Analysis of Mobile Robots', IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Germany, pp. 191-196.
View/Download from: UTS OPUS or Publisher's site
Stability prediction is an important concern for mobile robots operating in rough environments. Having the capacity to predict areas of instability means pro-actively being able to plan safer traversable paths. The most influential tip-over stability measures are based on two criteria, the robot's center of mass (CM) and the supporting polygon (SP) defined by the convex area spanned between the ground contact-points. However, there is significant uncertainty associated with many parameters in the planning pipe-line: the actual robot kino-dynamic model, its localisation in the ground, and the terrain models, particularly in uneven terrain. This article proposes a statistical analysis of stability prediction to account for some of the uncertainties. This is accomplished using the force angle (FA) stability measure for a reconfigurable multi-tracked vehicle fitted with flippers, a manipulator arm and a sensor head. Probability density function (PDF) of contact-points, CM and the FA stability measure are numerically estimated, with simulation results performed on the open dynamics engine (ODE) simulator based on uncertain parameters. Two techniques are presented: a conventional Monte Carlo scheme, and a structured unscented transform (UT) which results in significant improvement in computational efficiency. Experimental results on maps obtained from a range camera fitted on the sensor head while the robot traverses over a ramp and a series of steps are presented that confirms the validity of the proposed probabilistic stability prediction method.
Zhao, L., Huang, S. & Dissanayake, G. 2013, 'Linear SLAM: A Linear Solution to the Feature-based and Pose Graph SLAM based on Submap Joining', 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Tokyo, Japan, pp. 24-30.
View/Download from: UTS OPUS or Publisher's site
This paper presents a strategy for large-scale SLAM through solving a sequence of linear least squares problems. The algorithm is based on submap joining where submaps are built using any existing SLAM technique. It is demonstrated that if submaps coordinate frames are judiciously selected, the least squares objective function for joining two submaps becomes a quadratic function of the state vector. Therefore, a linear solution to large-scale SLAM that requires joining a number of local submaps either sequentially or in a more efficient Divide and Conquer manner, can be obtained. The proposed Linear SLAM technique is applicable to both feature-based and pose graph SLAM, in two and three dimensions, and does not require any assumption on the character of the covariance matrices or an initial guess of the state vector. Although this algorithm is an approximation to the optimal full nonlinear least squares SLAM, simulations and experiments using publicly available datasets in 2D and 3D show that Linear SLAM produces results that are very close to the best solutions that can be obtained using full nonlinear optimization started from an accurate initial value. The C/C++ and MATLAB source codes for the proposed algorithm are available on OpenSLAM.
Ghaffari Jadidi, M., Valls Miro, J., Valencia, R., Andrade-Cetto, J. & Dissanayake, G. 2013, 'Exploration using an Information-Based Reaction-Diffusion Process', Proceedings of the 2013 Australasian Conference on Robotics & Automation, Australasian Conference on Robotics and Automation, Australian Robtocis and Automation Association, Sydney, Australia, pp. 1-10.
View/Download from: UTS OPUS
Exploration using an Information-Based Reaction-Diffusion Process
Norouzi, M., Valls Miro, J. & Dissanayake, G. 2013, 'Planning Stable and Efficient Paths for Articulated Mobile Robots On Challenging Terrains', Australasian Conference on Robotics and Automation, Australasian Conference on Robotics and Automation, Australasian Robotics and Automation Association, Sydney, Australia, pp. 1-10.
View/Download from: UTS OPUS
An analytical strategy to generate stable paths for a reconfigurable vehicle while also meeting additional navigational objectives is herein proposed. The work is motivated by robots traversing over challenging terrains during search and rescue operations, such as those equipped with manipulator arms and/or flippers. The proposed solution looks at minimizing the length of the traversed path and the energy expenditure in changing postures, yet also accounts for additional constraints in terms of sensor visibility (i.e arm configurations close to those orthogonal to the horizontal global plane which can afford a wider sensor view) and traction (i.e. flipper angles that provide the largest trackterrain interaction area). The validity of the proposed planning approach is evaluated with a multitracked robot fitted with flippers and a range camera at the end of a manipulator arm while navigating over two challenging 3D terrain data sets: one in a mock-up urban search and rescue arena (USAR), and a second one from a publicly available quasi-outdoor rover testing facility (UTIAS).
Valls Miro, J., Black, R., Andonovski, B. & Dissanayake, G. 2013, 'Development of a Novel Evidence-Based Automated Powered Mobility Device Competency Assessment', Proceedings of the 2013 IEEE International Conference on Rehabilitation Robotics, IEEE, Seattle, WA, USA, pp. 1-8.
View/Download from: UTS OPUS or Publisher's site
This paper describes the outcomes of a clinical study to assess the validity of a stand-alone sensor package and algorithms to aid the assessment by an occupational therapist (OT) whether a person has the capacity to safely and effectively operate a powered mobility device such as a wheelchair in their daily activities. The proposed solution consists of a suite of sensors capable of inferring navigational characteristics from the platform it is attached to (e.g. trajectories, map of surroundings, speeds, distance to doors, etc). Such information presents occupational therapists with the ability to augment their own observations and assessments with correlated, quantitative, evidence-based data acquired with the sensor array. Furthermore, OT reviews can take place at the therapist's discretion as the data from the trials is logged. Results from a clinical evaluation of the proposed approach, taking as reference the commonly-used Power-Mobility Indoor Driving Assessment (PIDA) assessment, were conducted at the premises of the Prince of Wales (PoW) Hospital in Sydney by four users, showing consistency with the OT scores, and setting the scene to a larger study with wider targeted participation.
Ryu, K., Furukawa, T., Antol, S. & Dissanayake, G. 2013, 'Grid-based scan-to-map matching for accurate simultaneous localization and mapping: Theory and preliminary numerical study', Proceedings of the ASME Design Engineering Technical Conference.
View/Download from: Publisher's site
This paper presents a grid-based scan-to-map matching technique for accurate simultaneous localization and mapping (SLAM). At every acquisition of a new scan, the proposed technique estimates the relative position from which the previous scan was taken, and further corrects its estimation error by matching the new scan to the globally defined map. In order to achieve best scan-to-map matching at each acquisition, the map to match is represented as a grid map with multiple normal distributions (NDs) in each cell. Additionally, the new scan is also represented by NDs, developing a novel ND-to-ND matching technique. The ND-to-ND matching technique has significant potential in the enhancement of the global matching as well as the computational efficiency. Experimental results first show that the proposed technique successfully matches new scans to the map generating very small position and orientation errors, and then demonstrates the effectiveness of the multi-ND representation in comparison to the single-ND representation. Copyright © 2013 by ASME.
Van Nguyen, L., Kodagoda, S., Ranasinghe, R. & Dissanayake, G. 2013, 'Locational optimization based sensor placement for monitoring Gaussian processes modeled spatial phenomena', Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013, pp. 1706-1711.
View/Download from: Publisher's site
This paper addresses the sensor placement problem associated with monitoring spatial phenomena, where mobile sensors are located on the optimal sampling paths yielding a lower prediction error. It is proposed that the spatial phenomenon to be monitored is modeled using a Gaussian Process and a variance based density function is employed to develop an expected-value function. A locational optimization based effective algorithm is employed to solve the resulting minimization of the expected-value function. We designed a mutual information based strategy to select the most informative subset of measurements effectively with low computational time. Our experimental results on real-world datasets have verified the superiority of the proposed approach. © 2013 IEEE.
Ghaffari Jadidi, M., Valls Miro, J., Valencia, R., Andrade-Cetto, J. & Dissanayake, G. 2013, 'Exploration in Information Distribution Maps', Robotics Science and Systems - Workshop on Robotic Exploration, Monitoring and Information Collection, Robotics Science and Systems, Technische Universitat Berlin, Berlin, Germany.
View/Download from: UTS OPUS
In this paper, a novel solution for autonomous robotic exploration is proposed. The distribution of information in an unknown environment is modeled as an unsteady diffusion process, which can be an appropriate mathematical formulation and analogy for expanding, time-varying, and dynamic environments. This information distribution map is the solution of the diffusion process partial differential equation, and is regressed from sensor data as a Gaussian Process. Optimization of the process parameters leads to an optimal frontier map which describes regions of interest for further exploration. Since the presented approach considers a continuous model of the environment, it can be used to plan smooth exploration paths exploiting the structural dependencies of the environment whilst handling sparse sensors measurements. The performance of the proposed approach is evaluated through simulation results in the well-known Freiburg and Cave maps.
Wang, H., Hu, G., Huang, S. & Dissanayake, G. 2013, 'On the structure of nonlinearities in pose graph SLAM', Robotics: Science and Systems, pp. 425-432.
© 2013 Massachusetts Institute of Technology. Pose graphs have become an attractive representation for solving Simultaneous Localization and Mapping (SLAM) problems. In this paper, we analyze the structure of the nonlinearities in the 2D SLAM problem formulated as the optimizing of a pose graph. First, we prove that finding the optimal configuration of a very basic pose graph with 3 nodes (poses) and 3 edges (relative pose constraints) with spherical covariance matrices, which can be formulated as a six dimensional least squares optimization problem, is equivalent to solving a one dimensional optimization problem. Then we show that the same result can be extended to the optimizing of a pose graph with "two anchor nodes" where every edge is connecting to one of the two anchor nodes. Furthermore, we prove that the global minimum of the resulting one dimensional optimization problem must belong to a certain interval and there are at most 3 minima in that interval. Thus the globally optimal pose configuration of the pose graph can be obtained very easily through the bisection method and closed-form formulas.
Huang, S., Wang, H., Frese, U. & Dissanayake, G. 2012, 'On the Number of Local Minima to the Point Feature Based SLAM Problem', 2012 IEEE International Conference on Robotics and Automation, 2012 IEEE International Conference on Robotics and Automation, IEEE, Saint Paul, Minnesota, USA, pp. 2074-2079.
View/Download from: UTS OPUS
Map joining is an efficient strategy for solving feature based SLAM problems. This paper demonstrates that joining of two 2D local maps, formulated as a nonlinear least squares problem has at most two local minima, when the associated uncertainties can be described using spherical covariance matrices. Necessary and sufficient condition for the existence of two minima is derived and it is shown that more than one minimum exists only when the quality of the local maps used for map joining is extremely poor. The analysis explains to some extent why a number of optimization based SLAM algorithms proposed in the recent literature that rely on local search strategies are successful in converging to the globally optimal solution from poor initial conditions, particularly when covariance matrices are spherical. It also demonstrates that the map joining problem has special properties that may be exploited to reliably obtain globally optimal solutions to the SLAM problem.
Hu, G., Huang, S., Zhao, L., Alempijevic, A. & Dissanayake, G. 2012, 'A Robust RGB-D SLAM algorithm', Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on, Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on, IEEE, Algarve, Portugal, pp. 1174-1179.
View/Download from: UTS OPUS or Publisher's site
Recently RGB-D sensors have become very popular in the area of Simultaneous Localisation and Mapping (SLAM). The major advantage of these sensors is that they provide a rich source of 3D information at relatively low cost. Unfortunately, these sensors in their current forms only have a range accuracy of up to 4 metres. Many techniques which perform SLAM using RGB-D cameras rely heavily on the depth and are restrained to office type and geometrically structured environments. In this paper, a switching based algorithm is proposed to heuristically choose between RGB-BA and RGBD-BA based local maps building. Furthermore, a low cost and consistent optimisation approach is used to join these maps. Thus the potential of both RGB and depth image information are exploited to perform robust SLAM in more general indoor cases. Validation of the proposed algorithm is performed by mapping a large scale indoor scene where traditional RGB-D mapping techniques are not possible.
Ahmad, A., Huang, S., Wang, J. & Dissanayake, G. 2012, 'A new state vector and a map joining algorithm for range-only SLAM', International Conference on Control, Automation, Robotics & Vision, IEEE, Guangzhou, China, pp. 1024-1029.
View/Download from: UTS OPUS or Publisher's site
This paper considers the simultaneous localization and mapping (SLAM) problem where the range-only sensor is used. Landmark initialization is a critical issue in range-only SLAM due to the lack of bearing information from the robot to the landmarks. A new state vector is proposed to be used in solving the range-only SLAM. In the new state vector, the landmark position is represented in different ways under different situations. This new representation avoids the need of multiple hypotheses on the landmark positions implemented in most of the existing range-only SLAM algorithms. Simulation and experimental results demonstrate the effectiveness of the new range-only SLAM algorithm using the new state vector within the least squares framework.
Liu, M., Huang, S., Dissanayake, G. & Wang, H. 2012, 'A convex optimization based approach for pose only SLAM problems', IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Algarve, Portugal, pp. 1898-1903.
View/Download from: UTS OPUS or Publisher's site
This paper demonstrates that 2D pose SLAM has an underlining near convex structure when formulated as a least squares (LS) optimization problem. By introducing new variables and some approximations, the LS pose SLAM problem can be formulated as a quadratically constrained quadratic programming (QCQP) problem. The QCQP formulation can then be relaxed into a semi-definite programming (SDP) problem which is convex. Unique solution to the convex SDP problem can be obtained without initial state estimate and can be used to construct a candidate solution to the original LS pose SLAM problem. Simulation datasets and the Intel Research Lab dataset have been used to demonstrate that when the relative pose information contain noises with reasonable level, the candidate solution obtained through the relaxation is very close to the optimal solution to the LS SLAM problem. Thus in practice, the candidate solution can serve as either an approximate solution or a good initial guess for a local optimization algorithm to obtain the optimal solution to the LS pose SLAM problem.
Shi, L., Kodagoda, S. & Dissanayake, G. 2012, 'Application of Semi-supervised Learning with Voronoi Graph for Place Classification', 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Vilamoura, Algarve, Portugal, pp. 2991-2996.
View/Download from: UTS OPUS or Publisher's site
Representation of spaces including both geometric and semantic information enables a robot to perform high-level tasks in complex environments. Therefore, in recent years identifying and semantically labeling the environments based on onboard sensors has become an important competency for mobile robots. Supervised learning algorithms have been extensively used for this purpose with SVM-based solutions showing good generalization properties. The CRF-based approaches take the advantage of connectivity information of samples thereby provide a mechanism to capture complex dependencies. Blending the complementary strengths of Support Vector Machine (SVM) and Conditional Random Field (CRF), there have been algorithms to exploit the advantages of both to enhance the overall accuracy of place classification in indoor environments. However, experiments show that none of the above approaches deal well with diversified testing data. In this paper, we focus mainly on the generalization ability of the model and propose a semi-supervised learning strategy, which essentially improves the performance of the system. Experiments have been carried out on six real-world maps from different universities around the world and the results from rigorous testing demonstrate the feasibility of the approach.
Khushaba, R.N., Kodagoda, S., Dissanayake, G., Greenacre, L.M., Burke, S. & Louviere, J.J. 2012, 'A neuroscientific approach to choice modeling: electroencephalogram (EEG) and user preferences', Proceedings of the 2012 International Joint Conference on Neural Networks, The 2012 International Joint Conference on Neural Networks, IEEE, Brisbane, Australia, pp. 1-8.
View/Download from: UTS OPUS or Publisher's site
Paper available at: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6252561&contentType=Conference+Publications&sortType%3Ddesc_p_Publication_Year%26queryText%3Dkhushaba
Nguyen, V., Kodagoda, S., Ranasinghe, R. & Dissanayake, G. 2012, 'Simulated Annealing Based Approach for Near-Optimal Sensor Selection in Gaussian Processes', Proc. 2012 IEEE International Conference on Control, Automation and Information Sciences, 2012 IEEE International Conference on Control, Automation and Information Sciences, IEEE, Ho Chi Minh City, Vietnam, pp. 142-147.
View/Download from: UTS OPUS or Publisher's site
This paper addresses the sensor selection problem associated with monitoring spatial phenomena, where a subset of k sensor measurements from among a set of n potential sensor measurements is to be chosen such that the root mean square prediction error is minimised. It is proposed that the spatial phenomena to be monitored is modelled using a Gaussian Process and a simulated annealing based approximately heuristic algorithm is used to solve the resulting minimisation problem. The algorithm is shown to be computationally efficient and is illustrated using both indoor and outdoor environment monitoring scenarios. It is shown that, although the proposed algorithm is not guaranteed to find the optimum, it always provides accurate solutions for broad range real-world and computer generated datasets.
Shi, L., Kodagoda, S., Khushaba, R.N. & Dissanayake, G. 2012, 'Application of CRF and SVM based Semi-supervised Learning for Semantic Labeling of Environments', 2012 12th International Conference on Control, Automation, Robotics & Vision, 12th International Conference on Control, Automation, Robotics & Vision, IEEE, Guangzhou, pp. 835-840.
View/Download from: UTS OPUS or Publisher's site
Understanding the environment in both geometric and semantic levels enables a robot to perform high-level tasks in complex environments. Therefore in recent years research towards identifying and semantically labeling the environments based on onboard sensors for mobile robots has been gaining popularity. After the era of heuristic and rule-based approaches, supervised learning algorithms like Support Vector Machines (SVM) and AdaBoost have been extensively used for this purpose showing satisfactory performance. With the introduction of graphical models, approaches like Conditional Random Fields (CRF) which take the advantage of connectivity of samples provide more flexibility to capture complex dependencies. In this paper, we focus on a real-world task which challenges the generalization ability of the model, evaluate some graph based features, propose a semi-supervised learning algorithm by iteratively utilizing the results from SVM and CRF, and suggest a solution for CRF parameter estimation with partially labeled training data. Experiments have been conducted on six realworld indoor environments demonstrating the competence of the algorithm.
Ahmad, A., Zhao, L., Huang, S. & Dissanayake, G. 2012, 'Convergence comparison of least squares based bearing-only SLAM algorithms using different landmark parametrizations', International Conference on Control, Automation, Robotics & Vision, ICARCV 2012, IEEE, Guangzhou, China, pp. 1006-1011.
View/Download from: UTS OPUS or Publisher's site
This paper compares the convergence of least squares based 2D bearing-only SLAM algorithms using different landmark parametrizations. It is shown that the requirement on the accuracy of the initial value vary significantly when using different landmark parametrizations. Especially, for small scale bearing-only SLAM problems, the region of attraction of the global minimum for Gauss-Newton iteration based bearing-only SLAM algorithm using parallax angle landmark parametrization is significantly larger as compared with those of bearing-only SLAM algorithms using other landmark parametrizations.
Patel, M.N., Valls Miro, J. & Dissanayake, G. 2012, 'A Hierarchical Hidden Markov Model to support activities of daily living with an assistive robotic walker', A Hierarchical Hidden Markov Model for Inferring Activities of Daily Living with an Assistive Robotic Walker, IEEE RAS/EMBS International Conference on Biomedical and Biomechatronics, IEEE RAS/EMBS International Conference on Biomedical and Biomechatronics, Rome, Italy, pp. 1071-1076.
View/Download from: UTS OPUS or Publisher's site
This paper proposes a Hierarchical Hidden Markov Model (HHMM) framework as the most suitable tool to exploit the interactions between an intelligent mobility aid and their human operator. The framework presented is capable of learning a mixed array of the Activities of Daily Living (ADL) that the typical user of these supportive devices would normally engage in, both navigational and non-navigational in nature, and provide assistance as and when required. The main contribution of this paper is the demonstration of how this probabilistic tool capable of modelling behaviours at multiple levels of abstraction is a natural embodiment of machine intelligence to support user activities. Effectiveness of the proposed HHMM framework is evaluated with a number of healthy volunteers using a conventional rolling walker equipped with sensing and navigational aids whilst operating in a structured environment resembling a home. A comparison with more traditional discriminative models and mixed generativediscriminative models is also presented to provide a complete picture that highlights the benefits of the proposed approach
Norouzi, M., Valls Miro, J. & Dissanayake, G. 2012, 'Planning High-Visibility Stable Paths for Reconfigurable Robots on Uneven Terrain', IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Algarve, Portugal, pp. 2844-2849.
View/Download from: UTS OPUS or Publisher's site
This paper proposes a motion planning strategy for reconfigurable mobile robots in uneven terrain. Paths that guarantee stability while at the same time maximise the height of the sensor payload, thereby enhancing the capacity of the robot to explore the environment are obtained using a search algorithm based on A*. This is particularly applicable to operations such as search and rescue where observing the environment for locating victims is the major objective, although the proposed technique can be generalised to incorporate other potentially conflicting objectives such as minimising energy. The proposed planning strategy looks at exploiting the (possibly incomplete) environment information available to the robot and/or operator as it explores novel terrain. The effectiveness of the approach is evaluated using data obtained from a multitracked robot fitted with a manipulator arm and a range camera in a mock-up search and rescue arena.
Valencia, R., Valls Miro, J., Dissanayake, G. & Andrade-Cetto, J. 2012, 'Active Pose SLAM', IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Algarve, Portugal, pp. 1885-1891.
View/Download from: UTS OPUS or Publisher's site
We present an active exploration strategy that complements Pose SLAM and optimal navigation in Pose SLAM. The method evaluates the utility of exploratory and place revisiting sequences and chooses the one that minimizes overall map and path entropies. The technique considers trajectories of similar path length taking marginal pose uncertainties into account. An advantage of the proposed strategy with respect to competing approaches is that to evaluate information gain over the map, only a very coarse prior map estimate needs to be computed. Its coarseness is independent and does not jeopardize the Pose SLAM estimate. Moreover, a replanning scheme is devised to detect significant localization improvement during path execution. The approach is tested in simulations in a common publicly available dataset comparing favorably against frontier based exploration.
Wang, H., Hu, G., Huang, S. & Dissanayake, G. 2012, 'On the Structure of Nonlinearities in Pose Graph SLAM', 2012 Robotics: Science and Systems Conference, The MIT Press, Sydney, Australia, pp. 1-8.
View/Download from: UTS OPUS
Pose graphs have become an attractive representation for solving Simultaneous Localization and Mapping (SLAM) problems. In this paper, we analyze the structure of the nonlinearities in the 2D SLAM problem formulated as the optimizing of a pose graph. First, we prove that finding the optimal configuration of a very basic pose graph with 3 nodes (poses) and 3 edges (relative pose constraints) with spherical covariance matrices, which can be formulated as a six dimensional least squares optimization problem, is equivalent to solving a one dimensional optimization problem. Then we show that the same result can be extended to the optimizing of a pose graph with two anchor nodes where every edge is connecting to one of the two anchor nodes. Furthermore, we prove that the global minimum of the resulting one dimensional optimization problem must belong to a certain interval and there are at most 3 minima in that interval. Thus the globally optimal pose configuration of the pose graph can be obtained very easily through the bisection method and closed-form formulas.
Nguyen, V., Ranasinghe, R., Kodagoda, S. & Dissanayake, G. 2012, 'Sensor Selection Based Routing for Monitoring Gaussian Processes Modeled Spatial Phenomena', Australasian Conference on Robotics and Automation 2012, Australasian Conference on Robotics and Automation, The ACRA 2012 Organising Committee, Wellington, New Zealand, pp. 1-7.
View/Download from: UTS OPUS
This paper addresses the trade-off between the sensing quality and the energy consumption in the wireless sensor network associated with monitoring spatial phenomena. We use a non-parametric Gaussian Process to model the spatial phenomena to be monitored and simulated annealing based approximately heuristic algorithm for sensor selection. Our novel Sensor Selection based Routing (SSR) algorithm uses this model to identify the most informative nodes, which gives the root mean square prediction error less than a specified threshold, to construct the minimal energy expended routing tree rooted at the sink. Our experiments have verified that the proposed computationally efficient SSR algorithm has significant advantages over conventional techniques.
Wang, Z. & Dissanayake, G. 2012, 'Exploiting vehicle motion information in monocular SLAM', 2012 12th International Conference onControl Automation Robotics & Vision (ICARCV), International Conference onControl Automation Robotics & Vision (ICARCV), IEEE, Guangzhou, China, pp. 1030-1035.
View/Download from: UTS OPUS or Publisher's site
It is now well known that increasing the number of features maintained in the mapping process of the monocular SLAM improves the accuracy of the outcome. This, however, increases the state dimension and the associated computational cost. This paper investigates and evaluates the improvement on SLAM results by exploiting camera motion information. For a camera mounted on a vehicle, its motion is subject to the vehicle motion model. The work of this paper shows that by introducing relative pose constraints calculated from image points by considering the underlying vehicle motion model (for example the non-holonomic vehicle motion model), it is possible to incorporate vehicle motion information into the system and achieve even more accurate SLAM results than maintaining all extracted features in the map. It is demonstrated that in this process, the state dimension is not increased, and the sparse structure of the SLAM problem is maintained. So the underlying sparseness in the SLAM problem structure can still be exploited for computational efficiency. Simulation and experiment results are presented to demonstrate the relative merits of incorporating vehicle motion information for motion estimation and mapping.
Liu, M., Huang, S. & Dissanayake, G. 2011, 'Feature based SLAM using laser sensor data with maximized information usage', Proceedings of the 2011 IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Shanghai, China, pp. 1811-1816.
View/Download from: UTS OPUS
This paper formulates the SLAM problem using 2D laser data as an optimization problem. The environment is modeled as a set of curves and the variables of the optimization problem are the robot poses as well as the parameters describing the curves. There are two key differences between this SLAM formulation and existing SLAM methods. First, the environment is represented by continuous curves instead of point clouds or occupancy grids. Second, all the laser readings, including laser beams which returns its maximum range value, have been included in the objective function. As the objective function to be optimized contains discontinuities, it can not be solved by standard gradient based approaches and thus a Genetic Algorithm (GA) based method is applied. Matching of laser scans acquired from relatively far apart robot poses is achieved by applying GA on top of the Iterative closest point (ICP) algorithm. The new SLAM formulation and the use of a global optimization algorithm successfully avoid the convergence to local minimum for both the scan matching and the SLAM problem. Both simulated and experimental data are used to demonstrate the effectiveness of the proposed techniques.
Patel, M.N., Valls Miro, J. & Dissanayake, G. 2011, 'Activity Recognition from the Interactions between an Assistive Robotic Walker and Human Users', 6th ACM/IEEE International Conference on Human-Robot Interaction, ACM/IEEE International Conference on Human-Robot Interaction, ACM, Lausanne, Switzerland, pp. 221-222.
View/Download from: UTS OPUS or Publisher's site
Abstract Detection of individuals intention from a sequence of actions is an open and complex problem. In this paper we present a smart walker as mobility aid which can interpret the users behaviour patterns to recognize their intentions and consequently act as an intelligent assistant. The result of the experiments performed in this paper demonstrates the potential of dynamic bayesian networks (DBN), in relation to their dynamic and unsupervised nature, for realistic human-robot interaction modelling.
Cai, B., Huang, S., Liu, D., Yuan, S., Dissanayake, G., Lau, H. & Pagac, D. 2011, 'Optimisation model and exact algorithm for Autonomous Straddle Carrier Scheduling at automated container terminals', Proceedings of 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, San Francisco, California, USA, pp. 3686-3693.
View/Download from: UTS OPUS or Publisher's site
In this paper, an optimisation model based on Pickup and Delivery Problem with Time Windows (PDPTW), and an exact algorithm based on Branch-and-Bound with Column Generation (BBCG), are presented for Autonomous Straddle Carriers Scheduling (ASCS) problem at automated container terminals. The ASCS problem is firstly modeled into a PDPTW, which is formulated as a Binary Integer Programming (BIP) and then solved by Column Generation (CG) in the Branch-and-Bound (BB) framework. The BBCG algorithm is also compared to another two exact algorithms [i.e., Binary integer Programming with Dynamic Programming (BPDP) and Exhaustive Search with Permutation and Combination (ESPC)] for the ASCS problem solving. Based on the map of an actual automated container terminal, simulation results and discussions are presented to demonstrate the effectiveness and efficiency of the presented model and algorithm for autonomous vehicle scheduling.
Sehestedt, S.A., Kodagoda, S. & Dissanayake, G. 2011, 'Robust People Tracking and SHMM learning using SHMMs', Proceedings of the Australasian Conference on Robotics and Automation 2011 (ACRA 2011), Australasian Conference on Robotics and Automation, Australian Robotics and Automation Association Inc., Melbourne, pp. 1-6.
View/Download from: UTS OPUS
For effective Human Robot Interaction (HRI), it is necessary for the robot to be aware of its human peers and be able to anticipate and predict their actions. This paper explores an improved strategy for people tracking using Sampled Hidden Markov Models (SHMM) for capturing common human motion patterns. Such an SHMM contains rich information about human spatial behavior and it can be learned on-line during robot operation. The proposed integration of people tracking and learning offers significant improvements to the outcomes when compared to existing techniques. Real world experiments that demonstrate the viability and effectiveness of the approach are presented.
Khushaba, R.N., Kodagoda, S., Lal, S. & Dissanayake, G. 2011, 'Intelligent driver drowsiness detection system using Uncorrelated Fuzzy Locality Preserving Analysis', 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, San Francisco, USA, pp. 4608-4614.
View/Download from: UTS OPUS or Publisher's site
One of the leading causes of automobile accidents is related to driving impairment due to drowsiness. A large percentage of these accidents occur due to drivers' unawareness of the degree of impairment. An automatic detection of drowsiness levels could lead to lower accidents and hence lower fatalities. However, the significant fluctuations of the drowsiness state within a short time poses a major challenge in this problem. In response to such a challenge, we present the Uncorrelated Fuzzy Locality Preserving Analysis (UFLPA) feature projection method. The proposed UFLPA utilizes the changes in driver behavior, by means of the corresponding Electroencephalogram (EEG), Electrooculogram (EOG), and Electrocardiogram (ECG) signals to extract a set of features that can highly discriminate between the different drowsiness levels. Unlike existing methods, the proposed UFLPA takes into consideration the fuzzy nature of the input measurements while preserving the local discriminant and manifold structures of the data. Additionally, UFLPA also utilizes Singular Value Decomposition (SVD) to avoid the singularity problem and produce a set of uncorrelated features. Experiments were performed on datasets collected from thirty-one subjects participating in a simulation driving test with practical results indicating the significance of the results achieved by UFLPA of 94%â95% accuracy on average across all subjects.
Zhao, L., Huang, S., Yan, L. & Dissanayake, G. 2011, 'Parallax angle parametrization for monocular SLAM', Proceedings of the 2011 IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Shanghai, China, pp. 3117-3124.
View/Download from: UTS OPUS
This paper presents a new unified feature parametrization approach for monocular SLAM. The parametrization is based on the parallax angle and can reliably represent both nearby and distant features, as well as features in the direction of camera motion and features observed only once. A new bundle adjustment (BA) algorithm using the proposed parallax angle parametrization is developed and shown to be more reliable as compared with existing BA algorithms that use Euclidean XYZ or inverse depth parametrizations. A new map joining algorithm that allows combining a sequence of local maps generated using BA with the proposed parametrization, that avoids the large computational cost of a global BA, and can automatically optimize the relative scales of the local maps without any loss of information, is also presented. Extensive simulations and a publicly available large-scale real dataset with centimeter accuracy ground truth are used to demonstrate the accuracy and consistency of the BA and map joining algorithms using the new parametrization. Especially, since the relative scales are optimized automatically in the proposed BA and map joining algorithms, there is no need to compute any relative scales even for a loop more than 1km.
Ahmad, A., Huang, S., Wang, J. & Dissanayake, G. 2011, 'A new state vector for range-only SLAM', Proceedings of the 2011 Chinese Control and Decision Conference, Chinese Control and Decision Conference, IEEE, Mianyang, Sichuan, China, pp. 3413-3418.
View/Download from: UTS OPUS
This paper considers the simultaneous localization and mapping (SLAM) problem where the range-only sensor is used. Landmark initialization is a critical issue in rangeonly SLAM due to the lack of bearing information from the robot to the landmarks. A new state vector is proposed to be used in solving the range-only SLAM. In the new state vector, the landmark position is represented in different ways under different situations. This new representation avoids the need of multiple hypotheses on the landmark positions implemented in most of the existing range-only SLAM algorithms. Simulation and experimental results demonstrate the effectiveness of the new range-only SLAM algorithm using the new state vector within the least squares framework.
Dissanayake, G., Huang, S., Wang, Z. & Ranasinghe, R. 2011, 'A Review of Recent Developments in Simultaneous Localization and Mapping', Proceedings of the 6th International Conference on Industrial and Information Systems, International Conference on Industrial and Information Systems, IEEE, Sri Lanka, pp. 477-482.
View/Download from: UTS OPUS or Publisher's site
Simultaneous Localization and Mapping (SLAM) problem has been an active area of research in robotics for more than a decade. Many fundamental and practical aspects of SLAM have been addressed and some impressive practical solutions have been demonstrated. The aim of this paper is to provide a review of the current state of the research on feature based SLAM, in particular to examine the current understanding of the fundamental properties of the SLAM problem and associated issues with the view to consolidate recent achievements.
Khushaba, R.N., Kodagoda, S., Liu, D. & Dissanayake, G. 2011, 'Electromyogram (EMG) based Fingers Movement Recognition Using Neighborhood Preserving Analysis with QR-Decomposition', Intelligent Sensor, Sensor Network, and Information Processing (ISSNIP2011), IEEE, Adelaide - Australia, pp. 1-6.
View/Download from: UTS OPUS
Surface Electromyogram (EMG) signals recorded from an amputee's residual muscles have been investigated as a source of control for prosthetic devices for many years. Despite the extensive research focus on the EMG control of arm and gross hand movements, more dexterous individual and combined prosthetic finger control has not received the same amount of attention. To facilitate such a control scheme, the first and the most significant step is the extraction of a set of highly discriminative feature set that can well separate between the different fingers movements and to do so in a computationally efcient manner. In this paper, an accurate and efcient feature projection method based on Fuzzy Neighborhood Preserving Analysis (FNPA) with QR-decomposition, is proposed and denoted as FNPA. Unlike existing attempts in fuzzy linear discriminant analysis, the objective of the proposed FNPA is to minimize the distance between samples that belong to the same class and maximize the distance between the centers of different classes, while taking into account the contribution of the samples to the different classes. The method also aims to efciently overcome the singularity problems of classical LDA and Fuzzy LDA. The proposed FNPA is validated on EMG datasets collected from nine subjects performing 10 classes of individual and combined fingers movements. Practical results indicate the significance of FNPA in comparison to many other feature projection methods with an average accuracy of 91%, using only two EMG electrodes.
Abeywardena, D.M., Kodagoda, S., Munasinghe, R. & Dissanayake, G. 2011, 'A Virtual Odometer for a Quadrotor Micro Aerial Vehicle', Proceedings of the Australian Conference on Robotics and Automation (ACRA 2011), Australian Conference on Robotics and Automation (ACRA 2011), Australian Robotics and Automation Association, Monash University, Melbourne, pp. 1-8.
View/Download from: UTS OPUS
This paper describes the synthesis and evaluation of a âvirtual odometerâ for a Quadrotor Micro Aerial Vehicle. Availability of a velocity estimate has the potential to enhance the accuracy of mapping, estimation and control algorithms used with quadrotors, increasing the effectiveness of their applications. As a result of the unique dynamic characteristics of the quadrotor, a dual axis accelerometer mounted parallel to the propeller plane provides measurements that are directly proportional to vehicle velocities in that plane. Exploiting this insight, we encapsulate quadrotor dynamic equations which relate acceleration, attitude and the aerodynamic propeller drag in an extended Kalman filter framework for the purpose of state estimation. The result is a drift free estimation of lateral and longitudinal components of translational velocity and roll and pitch components of attitude of the quadrotor. Real world data sets gathered from two different quadrotor platforms, together with ground truth data from a Vicon system, are used to evaluate the effectiveness of the proposed algorithm and demonstrate that drift free estimates for the velocity and attitude can be obtained.
Manamperi, P., Brooks, P.A., Kaluarachchi, W., Peters, G., Ho, A., Lie, S., To, A.W., Paul, G., Rushton-Smith, D., Webb, S.S., Liu, D. & Dissanayake, G. 2011, 'Robotic Grit-blasting: Engineering Challenges', Sustainable Bridges: The Thread of Society, Sustainable Bridges: The Thread of Society, 2011 Austroads Bridge Conference (ABC 2011), Sydney, Australia, pp. 321-330.
View/Download from: UTS OPUS
Infrastructure shortage and aging are worldwide issues. Australia, in particular, faces unique challenges in maintaining infrastructures such as roadways and bridges. Corrosion is the primary cause of failure in steel bridges, and is minimised by painting the steel structure. Stripping of rust and deteriorated paint by grit-blasting is an effective and practical method. However, grit-blasting operation is extremely labour intensive and hazardous. It is one of the biggest expenditure items in bridge maintenance operations. Robotics technologies can provide effective solutions to assist bridge maintenance workers in grit blasting. Since 2005, the NSW Roads & Traffic Authority (RTA) and the Centre of Excellence for Autonomous Systems at the University of Technology, Sydney have been working together in developing a robotic system for assisting bridge maintenance workers, with the ultimate objective of preventing human exposure to hazardous and dangerous dust containing rust, paint particles and lead, relieving human workers from labor intensive tasks, and reducing costs associated with bridge maintenance. A prototype robotic system has been developed and tested in both lab setup and on-site. Many engineering issues have been identified for deploying such a system in the field. This paper will present these issues and discuss the solutions.
Chotiprayanakul, P., Liu, D. & Dissanayake, G. 2011, 'An Extended Hand Movement Model for Haptic-based Remote Operation of a Steel Bridge Maintenance Robot', 28th International Symposium on Automation and Robotics in Construction (ISARC 2011), ISARC2011 conference organiser, Seoul, Korea, pp. 1196-1202.
Taha, T., Valls Miro, J. & Dissanayake, G. 2011, 'A POMDP Framework for Modelling Human Interaction with Assistive Robots', IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Shanghai, China, pp. 544-549.
View/Download from: UTS OPUS or Publisher's site
This paper presents a framework for modelling the interaction between a human operator and a robotic device, that enables the robot to collaborate with the human to jointly accomplish tasks. States of the system are captured in a model based on a partially observable Markov decision process (POMDP). States representing the human operator are motivated by behaviours from the psychology of the human action cycle. Hierarchical nature of these states allows the exploitation of data structures based on algebraic decision diagrams (ADD) to efficiently solve the resulting POMDP. The proposed framework is illustrated using two examples from assistive robotics; a robotic wheel chair and an intelligent walking device. Experimental results from trials conducted in an office environment with the wheelchair is used to demonstrate the proposed technique.
Valls Miro, J., Zhou, W. & Dissanayake, G. 2012, 'A Strategy for Efficient Observation Pruning in Multi-Objective 3D SLAM', 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, San Francisco, CA, USA, pp. 1640-1646.
View/Download from: UTS OPUS or Publisher's site
An efficient automatic solution to the featurebased simultaneous localisation and mapping (SLAM) of mobile robots operating in conditions where a number of competing objectives operate simultaneously is proposed. The formulation quantitatively measures the merit of incoming data with respect to multiple priorities, automatically adjusting the amount of observations to be used in the estimation process for the best possible combined outcome. The methodology enables a selection mechanism which can efficiently exploit the observations available to the robot to best fulfil the objectives of differing tasks throughout the course of a mission, e.g. localisation, mapping, exploration, feature distribution, searching for specific objects or victims, etc. The work is particularly motivated by navigation in three-dimensional terrains, and an example considering the objectives of robot localisation and map expansion in a search and rescue environment using an RGB-D camera is utilised for discussion and results.
Kirchner, N.G., Alempijevic, A. & Dissanayake, G. 2011, 'Nonverbal Robot-Group Interaction Using an Imitated Gaze Cue', Proceedings of the 6th international conference on Human-robot interaction (HRI'11), Proceedings of the 6th international conference on Human-robot interaction, ACM, Lausanne, Switzerland, pp. 497-504.
View/Download from: UTS OPUS or Publisher's site
Ensuring that a particular and unsuspecting member of a group is the recipient of a salient-item hand-over is a complicated interaction. The robot must effectively, expediently and reliably communicate its intentions to advert any tendency within the group towards antinormative behaviour. In this paper, we study how a robot can establish the participant roles of such an interaction using imitated social and contextual cues. We designed two gaze cues, the first was designed to discourage antinormative behaviour through individualising a particular member of the group and the other to the contrary. We designed and conducted a feld experiment (456 participants in 64 trials) in which small groups of people (between 3 and 20 people) assembled in front of the robot, which then attempted to pass a salient object to a particular group member by presenting a physical cue, followed by one of two variations of a gaze cue. Our re-sults showed that presenting the individualising cue had a significant (z=3.733, p=0.0002 ) effect on the robot's ability to ensure that an arbitrary group member did not take the salient object and that the selected participant did.
Wang, S., Kodagoda, S., Wang, Z. & Dissanayake, G. 2011, 'Multiple Sensor Based Terrain Classification', Australasion Conference on Robotics and Automation, Australasion Conference on Robotics and Automation, Australasion Conference on Robotics and Automation, Melbourne, Australia, pp. 1-7.
View/Download from: UTS OPUS
In the context of road vehicles, knowledge of terrain types is useful for improving passenger safety and comfort. This paper presents a method for terrain classification based on multiple sensors including an accelerometer, wheel encoders and a camera. The vertical accelerations and the speed of the vehicle together with a dynamic vehicle model are used to predict the road profile. Features extracted from the road profile are fused with image features to produce a speed invariant feature set. A supervised learning algorithm based on Neural network (NN) is used to classify different road types. Experiments carried out on an instrumented road vehicle (CRUISE), by manually driving on a variety of road types at different speeds are presented to demonstrate that the fusion of multiple sensory cues can significantly improve the road type classification accuracy.
Valls Miro, J., De Bruijn, F., Dissanayake, G., Boisard, O. & Ton, P. 2011, 'Robot-Assisted Inspection of Concrete Box Girders in Bridges', Austroads Bridge Conference 2011: Sustainable Bridges - The Thread of Society, Austroads Bridge Conference 2011, Austroads Ltd., Sydney, pp. 335-346.
View/Download from: UTS OPUS
This paper describes a robotic solution to the structural health inspection of concrete box girders. A combination of sensors including a laser range finder, a depth (RGB-D) camera, an inertial measurement unit and a high-resolution camera are mounted on a tracked robot. The robot can be driven inside a box girder even when there are steps present, to collect high-resolution images of the concrete structure. Software that allows the information captured to be registered with a 3D geometric map of the inside of a box girder, and a visualization tool that can be used to evaluate location-annotated highly-detailed surface condition pictures by the human operator has been developed. The proposed remote evaluation technique makes it feasible to safely monitor areas over a sequence of inspections, leading to more effective maintenance procedures. The effectiveness of the system is illustrated using data gathered during a field trial where the robot was deployed within the Overpass at Huntleyâs Point, in the junction between Victoria Road and Burns Bay Road in Sydney. Functionality to automatically identify defects/regions of interest is also being investigated. It is anticipated that supplementing manual inspection tasks with robotic aids will mitigate the risk to manual entry into a confined space with a consequential saving in associated cost. This project is collaboration between the University of Technology Sydney (UTS) and the Roads & Traffic Authority (RTA) of NSW.
Valls Miro, J., Black, R., De Bruijn, F. & Dissanayake, G. 2011, 'Semi-Autonomous Competency Assessment of Powered Mobility Device Users', IEEE International Conference on Rehabilitation Robotics, IEEE International Conference on Rehabilitation Robotics, IEEE, Zurich, Switzerland, pp. 1-6.
View/Download from: UTS OPUS or Publisher's site
This paper describes a stand-alone sensor package and algorithms for aiding the assessment by an occupational therapist whether a person has the capacity to safely and effectively operate a powered mobility device such as a walking aid or a wheelchair. The sensor package employed consists of a laser range finder, an RGB camera and an inertial measurement unit that can be attached to any mobility device with minimal modifications. Algorithms for capturing the data received by the sensor package and for generating the map of the environment as well as the trajectory of the mobility device have been developed. Such information presents occupational therapists with the capability to provide a quantitative assessment of whether patients are ready to be safely deployed with mobile aids for their daily activities. Preliminary evaluation of the sensor package and associated algorithms based on experiments, conducted at the premises of the Prince of Wales Hospital in Sydney, are presented.
Ahmad, A., Huang, S., Wang, J.J. & Dissanayake, G. 2011, 'A new state vector for range-only SLAM', Proceedings of the 2011 Chinese Control and Decision Conference, CCDC 2011, pp. 3404-3409.
View/Download from: Publisher's site
This paper considers the simultaneous localization and mapping (SLAM) problem where the range-only sensor is used. Landmark initialization is a critical issue in range-only SLAM due to the lack of bearing information from the robot to the landmarks. A new state vector is proposed to be used in solving the range-only SLAM. In the new state vector, the landmark position is represented in different ways under different situations. This new representation avoids the need of multiple hypotheses on the landmark positions implemented in most of the existing range-only SLAM algorithms. Simulation and experimental results demonstrate the effectiveness of the new range-only SLAM algorithm using the new state vector within the least squares framework. © 2011 IEEE.
Furukawa, T., Tong, X., Dissanayake, G. & Durrant-Whyte, H.F. 2011, 'Parallel grid-based method and belief fusion Real-time cooperative non-Gaussian estimation', 2011 6th International Conference on Industrial and Information Systems, ICIIS 2011 - Conference Proceedings, pp. 370-375.
View/Download from: Publisher's site
This paper presents a parallel grid-based method and belief fusion for real-time cooperative Bayesian estimation. The grid-based recursive Bayesian estimation (RBE) method effectively maintains the belief of objects even with no detection event but requires large computation for its prediction and correction processes as well as fusion process in cooperative estimation. In order for real-time estimation, the belief fusion proposed in the paper carries out the fusion of belief outside the RBE loop. The parallelization of the entire grid-based method and belief fusion further accelerates the RBE so that real-time estimation is possible even in highly dynamical environments. Numerical examples have first demonstrated the validity of the proposed approach through parametric studies. The proposed approach was then applied to the cooperative search by autonomous unmanned ground vehicles (UGVs), and its real-time capability has been demonstrated. © 2011 IEEE.
Kodagoda, S., Zhang, Z. & Dissanayake, G. 2009, 'Crop and weed classification based on a colour and NIR sensory setup', Proc. Innovative Production Machines and Systems - 5th I*PROMS Virtual International Conference, International Conference on Innovative Production Machines and Systems, Whittles Publishing, Virtual conference, pp. 212-217.
View/Download from: UTS OPUS
This paper presents a multi-modal sensing approach for detecting Bidens pilosa L (commonly known as cobbler's peg) in wheat farms. Bidens is an annual broad leaf weed in tropical and sub-tropical regions and reported to be a weed that needs to be identified and eliminated when farming thirty one different crop varieties. Both Bidens and wheat leaves can have similar visual cues due to the curled up nature of the wheat leaves. This makes a straightforward visual image (RGB) based classification nontrivial. Therefore, we have integrated another informative band in the spectrum, which is the NIR band. Information retrieved is processed to generate a series of cues that are then fed into a classification algorithm. Bidens and wheat plant species are used to verify the classification algorithm. The proposed technique is able to achieve an accuracy of 88% - 95% even when there is substantial overlapping between Bidens and wheat leaves.
Yuan, S., Skinner, B., Huang, S., Liu, D., Dissanayake, G., Lau, H., Pagac, D. & Pratley, T. 2010, 'Mathematical Modelling of Container Transfers for a Fleet of Autonomous Straddle Carriers', Proceedings of the 2010 IEEE International Conferences on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Anchorage, Alaska, USA, pp. 1261-1266.
View/Download from: UTS OPUS or Publisher's site
The main contribution of this paper is a mathematical model describing performance metrics for coordinating multiple mobile robots in a seaport container terminal. The scenario described here requires dealing with many difficult practical challenges such as the presence of multiple levels of container stacking and sequencing, variable container orientations, and vehicular dynamics that require finite acceleration and deceleration times. Furthermore, in contrast to the automatically guided vehicle planning problem in a manufacturing environment, the container carriers described here are free ranging. Although, the port structure imposes a set of âvirtualâ roadways along which the vehicles are allowed to travel, path planning is essential in preventing contention and collisions. A performance metric which minimises total yard-vehicle usage, while producing robust traffic plans by encouraging both early starting and finishing of jobs is presented for different vehicle fleet sizes and job allocation scenarios.
Paul, G., Webb, S.S., Liu, D. & Dissanayake, G. 2010, 'A Robotic System for Steel Bridge Maintenance: Field Testing', Proceedings of the Australasian Conference on Robotics and Automation 2010 (ACRA 2010), Proceedings of the Australasian Conference on Robotics and Automation, Australasian Conference on Robotics and Automation, Brisbane, Queensland, Australia, pp. 1-8.
View/Download from: UTS OPUS
This paper presents the field testing results of an autonomous manipulator-based robotic system that strips the paint and rust from steel bridges [Liu et al., 2008]. The key components of this system are sensing and planning, which have been presented in other research papers. The grit-blasting field trial presented in this paper spanned 6 weeks, and included 20 hours over 4.5 days of actual grit-blasting operation. The field testing has verified the algorithms developed for exploration, mapping, surface segmentation, robot motion planning and collision avoidance. It has also proved that the robotic system is able to perform bridge maintenance operations (grit-blasting), reduce human workers' exposure to hazardous and dangerous debris (containing rust, lead-based paint particles), and relieve workers from labour-intensive tasks. The system has been shown to position a grit-blast nozzle so as to remove the paint and rust at the same rate that is expected of a worker with equivalent equipment: small grit-blasting pot and medium-sized hose nozzle. Testing in the field has also highlighted important issues that need to be addressed.
Patel, M.N., Valls Miro, J. & Dissanayake, G. 2010, 'Dynamic Bayesian Networks for Learning Interactions between Assistive Robotic Walker and Human Users', Proceedings of the 33rd Annual German Conference on Artificial Intelligence (KI 2010): Advances in Artificial Intelligence, Annual German Conference on Artificial Intelligence, Springer-Verlag Berlin Heidelberg, Germany, pp. 333-340.
View/Download from: UTS OPUS or Publisher's site
Detection of individuals intentions and actions from a stream of human behaviour is an open problem. Yet for robotic agents to be truly perceived as human-friendly entities they need to respond naturally to the physical interactions with the surrounding environment, most notably with the user. This paper proposes a generative probabilistic approach in the form of Dynamic Bayesian Networks (DBN) to seamlessly account for users attitudes. A model is presented which can learn to recognize a subset of possible actions by the user of a gait stability support power rollator walker, such as standing up, sitting down or assistive strolling, and adapt the behaviour of the device accordingly. The communication between the user and the device is implicit, without any explicit intention such as a keypad or voice.The end result is a decision making mechanism that best matches the users cognitive attitude towards a set of assistive tasks, effectively incorporating the evolving activity model of the user in the process. The proposed framework is evaluated in real-life condition.
Shi, L., Kodagoda, S. & Dissanayake, G. 2010, 'Laser Range Data Based Semantic Labeling of Places', Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Taipei, Taiwan, pp. 5941-5946.
View/Download from: UTS OPUS or Publisher's site
Extending metric space representations of an environment with other high level information, such as semantic and topological representations enable a robotic device to efficiently operate in complex environments. This paper proposes a methodology for a robot to classify indoor environments into semantic categories. Classification task, using data collected from a laser range finder, is achieved by a machine learning approach based on the logistic regression algorithm. The classification is followed by a probabilistic temporal update of the semantic labels of places. The innovation here is that the new algorithm is able to classify parts of a single laser scan into different semantic labels rather than the conventional approach of gross categorization of locations based on the whole laser scan. We demonstrate the effectiveness of the algorithm using a data set available in the public domain.
Shi, L., Kodagoda, S. & Dissanayake, G. 2010, 'Multi-class Classification for Semantic Labeling of Places', Proceedings of the 11th International Conference on Control, Automation, Robotics and Vision (ICARCV 2010), International Conference on Control, Automation, Robotics & Vision, IEEE, Singapore, pp. 2307-2312.
View/Download from: UTS OPUS or Publisher's site
AbstractâHuman robot interaction is an emerging area of research, where human understandable robotic representations can play a major role. Knowledge of semantic labels of places can be used to effectively communicate with people and to develop efficient navigation solutions in complex environments. In this paper, we propose a new approach that enables a robot to learn and classify observations in an indoor environment using a labeled semantic grid map, which is similar to an Occupancy Grid like representation. Classification of the places based on data collected by laser range finder (LRF) is achieved through a machine learning approach, which implements logistic regression as a multi-class classifier. The classifier output is probabilistically fused using independent opinion pool strategy. Appealing experimental results are presented based on a data set gathered in various indoor scenarios.
Shi, L., Kodagoda, S. & Dissanayake, G. 2010, 'Environment Classification and Semantic Grid Map Building Based on Laser Range Finder Data', IROS 2010 Workshop on Semantic Mapping and Autonomous Knowledge Acquisition, Workshop on Semantic Mapping and Autonomous Knowledge Acquisition, online proceeding of IROS 2010 workshop, Taipei, pp. 1-6.
View/Download from: UTS OPUS
Human robot interaction has become an important area of research in the robotics community. High level abstractions, which are commonly used by humans, can be learnt by robots to effectively communicate with humans. In this paper, we propose a Semantic Grid Map (SGM) to represent an environment. SGM is similar to an Occupancy Grid (OG) map, however with high level information as environment type labels. We use a robot-mounted laser range finder (LRF) data to learn and classify an environment into various area types. Then the classification results are combined probabilistically to update the semantic grid map. The classification accuracy is further improved by outlier rejection and topological correction. Finally we present a labeling strategy while a robot is exploring an unknown environment. Experimental results of a robot exploring in a university environment are presented to assess the performance of the algorithm.
Patel, M.N., Khushaba, R.N., Valls Miro, J. & Dissanayake, G. 2010, 'Probabilistic Models versus Discriminate Classifiers for Human Activity Recognition with an Instrumented Mobility-Assistance Aid', Proceedings of the Australasian Conference on Robotics and Automation 2010 (ACRA 2010), Proceedings of the Australasian Conference on Robotics and Automation, Australasian Conference on Robotics and Automation, Brisbane, Queensland, Australia, pp. 1-8.
View/Download from: UTS OPUS
Detection of individuals' intentions and actions from a stream of human behaviour is an open and complex problem. There is however an intrinsic need to automatically recognise the activities performed by users of mobility assistive aids to better understand their behavioural patterns, with the ultimate objective of improving the utility of these devices. While discriminative algorithms such as Support Vector Machines (SVM) are well understood, generative probabilistic approaches to machine learning such as Dynamic Bayesian Networks (DBN) have only recently started gaining increasing interest within the robotics community. In this paper, a comprehensive evaluation of these techniques is carried out for human activity recognition in the context of their applicability to assistive robotics. Results show comparable recognition rates, offering valuable insights into the advantageous characteristics of DBN in relation to their dynamic and unsupervised nature for realistic human-robot interaction modelling.
Ahmad, A., Huang, S. & Dissanayake, G. 2010, 'Accurate Large-Scale Bearing-Only SLAM by Map Joining', Proceedings of the Australasian Conference on Robotics and Automation 2010 (ACRA 2010), Proceedings of the Australasian Conference on Robotics and Automation, Australasian Conference on Robotics and Automation, Brisbane, Queensland, Australia, pp. 1-10.
View/Download from: UTS OPUS
This paper presents a bearing-only SLAM algorithm that generates accurate and consistent maps of large environments by joining a series of small local maps. The local maps are built by least squares optimization with a proper landmark initialization technique. The local maps are then combined to build global map using Iterated Sparse Local Submap Joining Filter (I-SLSJF). The accuracy and consistency of the proposed algorithm is evaluated using simulation data sets. The algorithm is also tested using the DLR-Spatial-Cognition data set and the preprocessed Victoria Park data where the range information is ignored. The global map results are very similar to the result of full least squares optimization starting with very accurate initial values. As I-SLSJF is able to join a given set of local maps and associated uncertainties efficiently without any information loss, these results demonstrate that focusing on generating accurate local maps is a promising direction for solving large-scale bearing-only SLAM problems.
Wang, Z. & Dissanayake, G. 2010, 'Map-aided 6-DOF Relative Pose Estimation for Monocular SLAM using Sparse Information Filters', Proc. of the 11th. Int. Conf. Control, Automation, Robotics and Vision (ICARCV 2010), Int. Conf. Control, Automation, Robotics and Vision, IEEE, Singapore, pp. 1006-1011.
View/Download from: UTS OPUS or Publisher's site
This paper addresses the problem of mapping three dimensional environments from a sequence of images taken by a calibrated camera, and simultaneously generating the camera motion trajectory. This is the Monocular SLAM problem in robotics, and is akin to the Structure from Motion (SFM) problem in computer vision. We present a novel map-aided 6-DOF relative pose estimation method based on a new formulation of the Monocular SLAM that is able to provide better initial estimates of new camera poses than the simple triangulation traditionally used in this context. The '6-DOF' means relative to the map which itself is up to an unobservable scale. The proposed pose estimator also allows more effective outlier rejection in matching features present in the map and features extracted from two consecutive images. Our Monocular SLAM algorithm is able to deal with arbitrary camera motion, making the smooth motion assumption, which is required by the typically used constant velocity model, unnecessary. In the new Monocular SLAM formulation, the measurements of extracted features from images are partitioned into those used for the estimation of the environment and those used for estimating the camera motion. The new formulation enables the current map estimate to aid achieving the full 6-DOF relative pose estimation up to the mapping scale while maximally exploiting the geometry information in images. Experiment results are provided to verify the proposed algorithm.
Zhao, L., Huang, S., Yan, L., Wang, J., Hu, G. & Dissanayake, G. 2010, 'Large-Scale Monocular SLAM by Local Bundle Adjustment and Map Joining', Proc. of the 11th. Int. Conf. Control, Automation, Robotics and Vision (ICARCV 2010), Int. Conf. Control, Automation, Robotics and Vision, IEEE, Singapore, pp. 431-436.
View/Download from: UTS OPUS or Publisher's site
This paper first demonstrates an interesting property of bundle adjustment (BA), âscale drift correctionâ. Here âscale drift correctionâ means that BA can converge to the correct solution (up to a scale) even if the initial values of the camera pose translations and point feature positions are calculated using very different scale factors. This property together with other properties of BA makes it the best approach for monocular Simultaneous Localization and Mapping (SLAM), without considering the computational complexity. This naturally leads to the idea of using local BA and map joining to solve large-scale monocular SLAM problem, which is proposed in this paper. The local maps are built through Scale-Invariant Feature Transform (SIFT) for feature detection and matching, random sample consensus (RANSAC) paradigm at different levels for robust outlier removal, and BA for optimization. To reduce the computational cost of the large-scale map building, the features in each local map are judiciously selected and then the local maps are combined using a recently developed 3D map joining algorithm. The proposed large-scale monocular SLAM algorithm is evaluated using a publicly available dataset with centimeter-level ground truth.
Liu, M., Huang, S., Dissanayake, G. & Kodagoda, S. 2010, 'Towards a Consistent SLAM Algorithm using B-Splines to Represent Environments', Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Taipei, Taiwan, pp. 2065-2070.
View/Download from: UTS OPUS or Publisher's site
This paper presents a statistically consistent SLAM algorithm where the environment is represented using a collection of B-Splines. The use of B-Splines allow environment to be represented without having to extract specific geometric features such as lines or points. Our previous work proposed a new observation model that enables raw measurements taken from a laser range finder to be transferred into relative position information between the control points of a B-Spline and the robot pose where the observation is made. One of the unresolved issues in the work was the estimation of the observation covariance, which is addressed through an analytical approach in this paper. As the uncertainty associated with the observation model is accurately defined and an optimization approach is used in the estimation process, the proposed SLAM algorithm can produce consistent estimates. Both simulation and experimental data are used for evaluation of the results.
Huang, S., Lai, Y., Frese, U. & Dissanayake, G. 2010, 'How far is SLAM from a linear least squares problem?', Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Taipei, Taiwan, pp. 3011-3016.
View/Download from: UTS OPUS or Publisher's site
Most people believe SLAM is a complex nonlinear stimation/optimization problem. However, recent research shows that some simple iterative methods based on linearization can sometimes provide surprisingly good solutions to SLAM without being trapped into a local minimum. This demonstrates that hidden structure exists in the SLAM problem that is yet to be understood. In this paper, we first analyze how far SLAM is from a convex optimization problem. Then we show that by properly choosing the state vector, SLAM problem can be formulated as a nonlinear least squares problem with many quadratic terms in the objective function, thus it is clearer how far SLAM is from a linear least squares problem. Furthermore, we explain that how the map joining approaches reduce the nonlinearity/nonconvexity of the SLAM problem.
Behrens, M.J., Huang, S. & Dissanayake, G. 2010, 'Models for pushing objects with a mobile robot using single point contact', Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Taipei, Taiwan, pp. 2964-2969.
View/Download from: UTS OPUS or Publisher's site
In many mobile robotic manipulation tasks it is desirable to interact with the robots surroundings without actually grasping the object being manipulated. Non-prehensile manipulation allows a robot to interact in situations which would otherwise be impossible due to size or weight. This paper presents the derivation of a mathematical model of an object pushed by a single point and sliding in the presence of friction where the dynamic effects of mass and inertia are significant. This model is validated using numerical simulation. The derived dynamic model is also compared with a kinematic approximation from literature, showing that under certain conditions, the motion of a pushed object is similar to the motion of a non-holonomic vehicle. Finally, the results of experimental investigations are discussed and promising directions for further work are proposed.
Sehestedt, S.A., Kodagoda, S. & Dissanayake, G. 2010, 'Models of Motion Patterns for Mobile Robotic Systems', Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Taipei, Taiwan, pp. 4127-4132.
View/Download from: UTS OPUS or Publisher's site
Human robot interaction is an emerging area of research with many challenges. Knowledge about human behaviors could lead to more effective and efficient interactions of a robot in populated environments. This paper presents a probabilistic framework for the learning and representation of human motion patterns in an office environment. It is based on the observation that most human trajectories are not random. Instead people plan trajectories based on many considerations, such as social rules and path length. Motion patterns are learned using an incrementally growing Sampled Hidden Markov Model. This model has a number of interesting properties which can be of use in many applications. For example, the learned knowledge can be used to predict motion, infer social rules, thus improve a robotâs operation and its interaction with people in a populated space. The proposed learning method is extensively validated in real world experiments.
Valls Miro, J., Dumonteil, G., Beck, C. & Dissanayake, G. 2010, 'A kyno-dynamic metric to plan stable paths over uneven terrain', Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Taipei, Taiwan, pp. 294-299.
View/Download from: UTS OPUS or Publisher's site
A generic methodology to plan increasingly stable paths for mobile platforms travelling over uneven terrain is proposed in this paper. This is accomplished by extending the Fast Marching level-set method of propagating interfaces in 3D lattices with an analytical kyno-dynamic metric which embodies robot stability in the given terrain. This is particularly relevant for reconfigurable platforms which significantly modify their mass distribution through posture adaptation, such as robots equipped with manipulator arms or varying traction arrangements. Results obtained from applying the proposed strategy in a mobile rescue robot operating on simulated and real terrain data illustrate the validity of the proposed strategy.
Hu, G., Huang, S. & Dissanayake, G. 2010, 'Evaluation of Pose Only SLAM', Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Taipei, Taiwan, pp. 3732-3737.
View/Download from: UTS OPUS or Publisher's site
In recent SLAM (simultaneous localization and mapping) literature, Pose Only optimization methods have become increasingly popular. This is greatly supported by the fact that these algorithms are computationally more efficient, as they focus more on the robots trajectory rather than dealing with a complex map. Implementation simplicity allows these to handle both 2D and 3D environments with ease. This paper presents a detailed evaluation on the reliability and accuracy of Pose Only SLAM, and aims at providing a definitive answer to whether optimizing poses is more advantages than optimizing features. Focus is centered around TORO, a Tree based network optimization algorithm, which has gained increased recognition within the robotics community. We compare this with Least Squares, which is often considered one of the best Maximum Likelihood method available. Results are based on both simulated and real 2D environments, and presented in a way where our conclusions can be substantiated.
Shi, L., Kodagoda, S. & Dissanayake, G. 2010, 'Semantic Grid Map Building', Proceedings of the Australasian Conference on Robotics and Automation 2010 (ACRA 2010), Proceedings of the Australasian Conference on Robotics and Automation, Australasian Conference on Robotics and Automation, Brisbane, Australia, pp. 1-7.
View/Download from: UTS OPUS
Conventional Occupancy Grid (OG) map which contains occupied and unoccupied cells can be enhanced by incorporating semantic labels of places to build semantic grid map. Map with semantic information is more understandable to humans and hence can be used for efficient communication, leading to effective human robot interactions. This paper proposes a new approach that enables a robot to explore an indoor environment to build an occupancy grid map and then perform semantic labeling to generate a semantic grid map. Geometrical information is obtained by classifying the places into three different semantic classes based on data collected by a 2D laser range finder. Classification is achieved by implementing logistic regression as a multi-class classifier, and the results are combined in a probabilistic framework. Labeling accuracy is further improved by topological correction on robot position map which is an intermediate product, and also by outlier removal process on semantic grid map. Simulation on data collected in a university environment shows appealing results.
Valls Miro, J. & Dissanayake, G. 2010, 'Automatic Fine Motor Control Behaviours for Autonomous Mobile Agents Operating on Uneven Terrains', The 3rd International Symposium on Practical Cognitive Agents and Robots, Practical Cognitive Agents and Robots, ACM, Toronto, Canada, pp. 33-40.
View/Download from: UTS OPUS
A novel mechanism able to produce increasingly stable paths for mobile robotic agents travelling over uneven terrain is proposed in this paper. In doing so, cognitive agents can focus on higher-level goal planning, with the increased confidence the resulting tasks will be automatically accomplished via safe and reliable paths within the lower-level skills of the platform. The strategy proposes the extension of the Fast Marching level-set method of propagating interfaces in 3D lattices with a metric to reduce robot body instability. This is particularly relevant for kinematically reconfigurable platforms which significantly modify their mass distribution through posture adaptation, such as humanoids or mobile robots equipped with manipulator arms or varying traction arrangements. Simulation results of an existing reconfigurable mobile rescue robot operating on real scenarios illustrate the validity of the proposed strategy.
Wang, Z. & Dissanayake, G. 2010, 'Efficient Monocular SLAM using sparse information filters', Proceedings of the 2010 Fifth International Conference on Information and Automation for Sustainability (ICIAfS10), International Conference on Information and Automation for Sustainability, IEEE, Colombo, Sri Lanka, pp. 311-316.
View/Download from: UTS OPUS or Publisher's site
A new method for efficiently mapping three dimensional environments from a platform carrying a single calibrated camera, and simultaneously localizing the platform within this map is presented in this paper. This is the Monocular SLAM problem in robotics, which is equivalent to the problem of extracting Structure from Motion (SFM) in computer vision. A novel formulation of Monocular SLAM which exploits recent results from multi-view geometry to partition the feature location measurements extracted from images into providing estimates of environment representation and platform motion is developed. Proposed formulation allows rich geometric information from a large set of features extracted from images to be maximally incorporated during the estimation process, without a corresponding increase in the computational cost, resulting in more accurate estimates. A sparse Extended Information Filter (EIF) which fully exploits the sparse structure of the problem is used to generate camera pose and feature location estimates. Experimental results are provided to verify the algorithm.
Zainudin, Z., Kodagoda, S. & Dissanayake, G. 2010, 'Torso Detection and Tracking using a 2D Laser Range Finder', Proceedings of the Australasian Conference on Robotics and Automation 2010, Proceedings of the Australasian Conference on Robotics and Automation, Australasian Conference on Robotics and Automation, Queensland University of Technology, Brisbane, QueenslandE, Australia, pp. 1-6.
View/Download from: UTS OPUS
Detecting and tracking people in populated environments has various applications including, robotics, healthcare, automotive, security and defence. In this paper, we present an algorithm for people detection and tracking based on a two dimensional laser rage finder (LRF). The LRF was mounted on a mobile robotic platform to scan a torso section of a person. The tracker is designed to discard spurious targets based on the log likelihood ratio and can effectively handle short term occlusions. Long term occlusions are considered as new tracks. Performance of the algorithm is analysed based on experiments, which shows appealing results.
Sehestedt, S.A., Kodagoda, S. & Dissanayake, G. 2010, 'Using Common Motion Patterns to Improve a Robot's Operation in Populated Environments', Proc. of the 11th. Int. Conf. Control, Automation, Robotics and Vision (ICARCV 2010), Int. Conf. Control, Automation, Robotics and Vision, IEEE, Singapore, pp. 2036-2041.
View/Download from: UTS OPUS or Publisher's site
Robotic devices are increasingly penetrating the human work spaces as stand alone units and helpers. It is believed that a robot could be easily integrated with humans, if the robot can learn how to behave in a socially acceptable manner. This involves a robot to observe, learn and comply with basic rules of human behaviors. As an example, one would expect a robot to travel in an environment without intruding human workspaces unnecessarily. Thus, identifying common motion patterns of people by observing a specific environment is an important task as people's trajectories are usually not random, however are tailored to the way the environment is structured. We propose a learning algorithm to construct a Sampled Hidden Markov Model (SHMM) that captures behavior of people through observations and then demonstrate how this model could be exploited for planning socially aware paths. Experimental results are presented to demonstrate the viability of the proposed approach.
Sehestedt, S.A., Kodagoda, S. & Dissanayake, G. 2010, 'Robot Path Planning in a Social Context', Proceedings of The International Conference on Robotics, Automation and Mechatronics (RAM), The International Conference on Robotics, Automation and Mechatronics, IEEE, Singapore, pp. 206-211.
View/Download from: UTS OPUS or Publisher's site
Human robot interaction has attracted significant attention over the last couple of years. An important aspect of such robotic systems is to share the working space with humans and carry out the tasks in a socially acceptable way. In this paper, we address the problem of fusing socially acceptable behaviours into robot path planning. By observing an environment for a while, the robot learns human motion patterns based on sampled Hidden Markov Models and utilises them in a Probabilistic Roadmap based path planning algorithm. This will minimise the social distractions, such as going through someone else's working space (due to the shortest path), by planning the path through minimal distractions, leading to human-like behaviours. The algorithm is implemented in Orca/C++ with appealing results in real world experiments.
Alempijevic, A., Kodagoda, S. & Dissanayake, G. 2009, 'Cross-Modal Localization Through Mutual Information', IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS 2009), International Conference on Intelligent Robots and Systems, IEEE, St Louis, Missouri, pp. 5596-5602.
View/Download from: UTS OPUS or Publisher's site
Relating information originating from disparate sensors observing a given scene is a challenging task, particularly when an appropriate model of the environment or the behaviour of any particular object within it is not available. One possible strategy to address this task is to examine whether the sensor outputs contain information which can be attributed to a common cause. In this paper, we present an approach to localise this embedded common information through an indirect method of estimating mutual information between all signal sources. Ability of L1 regularization to enforce sparseness of the solution is exploited to identify a subset of signals that are related to each other, from among a large number of sensor outputs. As opposed to the conventional L2 regularization, the proposed method leads to faster convergence with much reduced spurious associations. Simulation and experimental results are presented to validate the findings.
Alempijevic, A., Kodagoda, S. & Dissanayake, G. 2009, 'Mutual Information Based Data Association', Fifth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP 2009)Fifth International Conference on Intelligent Sensors, Sensor Networks and Information Processing, International Conference on Intelligent Sensors, Sensor Networks and Information Processing, IEEE, Melbourne, Australia, pp. 97-102.
View/Download from: UTS OPUS or Publisher's site
Relating information originating from disparate sensors without any attempt to model the environment or the behaviour of any particular object within it is a challenging task. Inspired by human perception, the focus of this paper will be on observing objects moving in space using sensors that operate based on different physical principles and the fact that motion has in principle, greater power to specify properties of an object than purely spatial information captured as a single observation in time. The contribution of this paper include the development of a novel strategy for detecting a set of signals that are statistically dependent and correspond to each other related by a common cause. Mutual Information is proposed as a measure of statistical dependence. The algorithm is evaluated through simulations and three application domains, which includes, (1.) Grouping problem in images, (2.) Data association problem in moving observers with dynamic targets, and (3.) Multi-modal sensor fusion.
Valls Miro, J., Osswald, V., Patel, M.N. & Dissanayake, G. 2009, 'Robotic Assistance with Attitude: a Mobility Agent for Motor Function Rehabilitation and Ambulation Support', IEEE 11th International Conference on Rehabilitation Robotics (ICORR 2009), IEEE International Conference on Rehabilitation Robotics, IEEE, Kyoto, Japan, pp. 529-534.
View/Download from: UTS OPUS or Publisher's site
This paper presents the design of an intelligent walking aid for the frail and elderly as well as for patients who are recovering from surgical procedures, in order to enhance safer mobility for these study populations. The device augments a conventional rolling walker aid with sensing and navigational abilities to safely travel through an environment following user's perceived intentions, unless collisions or instability is imminent. The agent, embodied as a partially observable Markov decision process (POMDP), critically relies on minimal user input to seamlessly recognise user's short-term intended behaviour, constantly updating this projection to allow for inconspicuous user-robot integration. This, in turn, shifts user's focus from fine motor-skilled control to coarse indications broadly intended to convey intention. Overall, the system can afford an increase in safety for the cognitive user through preventative care - reduced number of falls or collision with surrounding objects, minimising health-care expenses as well as increasing independent living for people with gait disorders. Successful simulation and experimental results demonstrate the validity of the proposed architecture for a practical robotic rollator design.
Yuan, S., Lau, H., Liu, D., Huang, S., Dissanayake, G., Pagac, D. & Pratley, T. 2009, 'Simultaneous dynamic scheduling and collision-free path planning for multiple autonomous vehicles', Proceedings of the 2009 IEEE International Conference on Information and Automation (ICIA-2009), IEEE International Conference on Information and Automation, IEEE, Zhuhai/Macau, China, pp. 522-527.
View/Download from: UTS OPUS or Publisher's site
When autonomous vehicles are deployed to perform transportation tasks within a confined space and strict time constraint, the problem of optimizing the assignment of tasks to vehicles is complicated by the need to ensure safety (they do not collide with or impede each other) and maximize the efficiency and productivity. With the increasing number of autonomous vehicles in practical settings, the ability to schedule tasks in a manner that inherently considers the effects of task allocations on space contention (which in turn compromises efficiency) is important to performance improvement. The main contribution of this paper is an approach to simultaneously conduct dynamic task allocation and collision-free path planning in an environment where multiple autonomous vehicles operate on a network of paths and where each path segment can only be occupied by one vehicle at a given instant. In particular, a generic algorithm for effective task allocation is investigated and applied in conjunction with an application-specific objective function. The proposed approach is able to solve the dynamic scheduling, planning and collision avoidance problem in an integrated way such that the overall productivity of the transportation system is improved. Simulation results based on a real-world industrial material handling environment demonstrate the feasibility and effectiveness of the proposed method.
Brooks, P.A., Manamperi, P., Liu, D. & Dissanayake, G. 2009, 'A robotic grit-blasting system for steel bridge maintenance', The 2009 Australasian Corrosion Association (ACA) conference, 15-18 November 2009,, Coffs Harbour, NSW, Australia.
Corrosion is the primary cause of failure in steel bridges. Stripping of rust and deteriorated paint and then repainting the steel are the procedures in steel bridge maintenance, and is one of the biggest expenditure items in bridge maintenance activities. Grit-blasting, which is an effective and efficient method of paint stripping, is extremely labour intensive and hazardous. Workers have to not only spend long periods of time handling forces of 100N and above, but also need to take precautions to avoid exposure to the dust containing hazardous materials and chemicals. Thus supplementing manual labour in grit-blasting with robotic aids has a significant health, safety and economic impact.
Manamperi, P., Brooks, P.A., Liu, D. & Dissanayake, G. 2009, 'Advanced robotic technologies for steel bridge maintenance', The 7th Austroads Bridge Conference website, The 7th Austroads Bridge Conference, Austroads, Auckland, New Zealand, pp. 1-8.
Bridges are essential in transport infrastructure worldwide. Corrosion is the primary cause of failure in steel bridges, and is minimized by painting the steel structure. Steel bridge coating maintenance consists of two procedures: the stripping of rust and deteriorated paint and then repainting the steel; and is one of the biggest expenditure items in bridge maintenance activities. An effective and efficient method of paint stripping is grit blasting, and herein lies the critical problem. Grit blasting is extremely labour intensive and hazardous. Workers have to not only spend long periods of time handling forces of 100N and above, but also need to take precautions to avoid exposure to the dust containing hazardous materials and chemicals. Thus supplementing manual labour in grit blasting with robotic aids will have a significant health, safety and economic impact.
Wang, J., Hu, G., Huang, S. & Dissanayake, G. 2009, '3D Landmarks Extraction from a Range Imager Data for SLAM', Proceedings of the 2009 Australasian Conference on Robotics and Automation, Australasian Conference on Robotics and Automation, Australian Robotics and Automation Association Inc., Sydney, Australia, pp. 1-8.
View/Download from: UTS OPUS
This paper introduces a new 3D landmark extraction method using the range and intensity images captured by a single range camera. Speeded up robust features (SURF) detection and matching is used to extract and match features from the intensity images. The range image information is used to transfer the selected 2D features into 3D points. The range measurement bias and uncertainty of the range camera are analysed, and their models are developed for improving the range estimation. After outliersâ detection and removal using random sampling consensus (RANSAC), reliable 3D points are obtained. 3D landmarks for imultaneous localisation and mapping (SLAM) are selected from the 3D points considering several factors, such as the uncertainty and geometry of their locations. Because of the availability of the SURF descriptor, the data association in SLAM has been performed using both the geometry and the descriptor information. The proposed method is tested in unstructured indoor environments, where the range camera moves in six degrees of freedom. Experimental results demonstrate the success of the proposed 3D landmark extraction method for SLAM.
Liu, M., Huang, S. & Dissanayake, G. 2009, 'A new observation model for B-Spline SLAM', Proceedings of the 2009 Australasian Conference on Robotics and Automation, Australasian Conference on Robotics and Automation, Australian Robotics and Automation Association Inc., Sydney, Australia, pp. 1-8.
View/Download from: UTS OPUS
Recently, a novel laser data based SLAM algorithm using B-Spline as features has been developed in [Pedraza et al., 2007]. EKF is used in the proposed BS-SLAM algorithm and the state vector contains the current robot pose together with the control points of the splines. The obervation model used for the EKF update is the intersections of the laser beams with the splines contained in the map. In this paper, we propose a new observation model for B-Spline SLAM. By properly defining the control points for the splines, the observation model can be expressed as a function of relative positions between control points and the robot pose, which is the same format as what used in point feature based SLAM. This new observation model make it possible to apply optimization based techniques to B-Spline SLAM, which has the potential to resolve the inconsistency issues of B-Spline SLAM.
Hu, G., Huang, S. & Dissanayake, G. 2009, '3D I-SLSJF: A consistent sparse local submap joining algorithm for building large-scale 3D Map', Proceedings of the 48th IEEE Conference on Decision and Control, 2009 held jointly with the 2009 28th Chinese Control Conference. CDC/CCC 2009., IEEE Conference on Decision and Control, IEEE, Shanghai, China, pp. 6040-6045.
View/Download from: UTS OPUS or Publisher's site
This paper presents an efficient and reliable algorithm for autonomous robots to build large-scale three dimensional maps by combining small local submaps. The algorithm is a generalization of our recent work on two dimensional map joining algorithm â Iterated Sparse Local Submap Joining Filter (I-SLSJF). The 3D local submap joining problem is formulated as a least squares optimization problem and solved by Extended Information Filter (EIF) together with smoothing and iterations. The resulting information matrix is exactly sparse and this makes the algorithm efficient. The smoothing and iteration steps improve the accuracy and consistency of the estimate. The consistency and efficiency of 3D I-SLSJF is demonstrated by comparing the algorithm with some existing algorithms using computer simulations.
Beck, C., Valls Miro, J. & Dissanayake, G. 2009, 'Trajectory Optimisation for Increased Stability of Mobile Robots Operating in Uneven Terrains', Seventh IEEE International Conference on Control and Automation, IEEE International Conference on Control and Automation, IEEE, Christchurch, NZ, pp. 1913-1919.
View/Download from: UTS OPUS or Publisher's site
A mechanism capable of enhancing the safety of paths followed by mobile robots which significantly modify their mass distribution while operating in uneven terrains is presented. This is the case, for instance, of kinematically reconfigurable platforms or robots equipped with manipulator arms. For a given path, a trajectory optimiser that finds suitably safer paths in terms of tip-over prevention and equal force distribution over the supporting contact points is proposed. Other kinematic considerations such as operating within given nominal joint positions or low energy motions can also be exploited to improve system stability while being deployed in specific domains such as security, rescue, etc. Simulation results of the proposed optimised motion planner for an iRobot Explorer tracked vehicle are presented. They are also compared with a non-optimised planners to show the validity of the approach.
Sehestedt, S.A., Kodagoda, S., Alempijevic, A. & Dissanayake, G. 2009, 'Efficient Learning of Motion Patterns for Robots', Proceedings of the 2009 Australasian Conference on Robotics and Automation, Australasian Conference on Robotics and Automation, Australian Robotics and Automation Association Inc., Sydney, Australia, pp. 1-7.
View/Download from: UTS OPUS
In this work we present a novel approach to learning dynamics of an environment perceived by a mobile robot. More precisely, we are interested in general motion patterns occurring in the environment rather than object dependent ones. A sampling algorithm is used to update a sample set, which represents observed dynamics, using the Bayes rule. From this set of samples a Hidden Markov Model is learnt online, which allows fast and efficient matching and prediction in the learnt model. Such models are useful for a number of tasks such as path planning, localisation and compliant motion. The approach is validated through simulation as well as experiments.
Wang, J.J., Kodagoda, S. & Dissanayake, G. 2009, 'Vision aided GPS/INS system for robust land vehicle navigation', 22nd International Technical Meeting of the Satellite Division of the Institute of Navigation 2009, ION GNSS 2009, pp. 195-204.
This paper introduces a new approach for improving land vehicle navigation by integrating a digital camera with a GNSS receiver and a MEMS INS, to provide seamless robust navigation solutions in urban environment. As a camera has the ability to detect surrounding environment, it can measure its relative position and direction to the surrounding objects. The integration of heterogeneous sensors with very different characters, such as GNSS, INS and image in this approach, can complement each other and provide cost-effective and robust navigation solutions. In the proposed system, INS is selected as the reference navigation sensor as it provides complete navigation solutions without disruptions. The navigation errors caused by its inherent nonlinear and time-varying characteristics can be corrected by the camera and GNSS. Vision based navigation (VBN) is one of the fundamental issues in computer vision and is relatively well developed. In this paper mono vision (MV) based navigation technologies are merged with GNSS and INS measurement, termed as GNSS/INS/MV (GlMV) integration. VBN is at the core of proposed robust navigation system, in which a relative range scale factor is estimated by continuously applying structure-from-motion in the MV navigation. Due to the complexity of multi-sensor integration, it needs an optimal sensor fusion framework with reliable system design, modeling and quality control procedures. The proposed sensor fusion method consists of two local and one master data fusion units, based on extended Kalman filter and fuzzy logic. It takes the advantages of federate architecture, and can select using either GNSS or VBN navigation solutions for PNS correction according to their quality. GNSS/INS integration is the mainstream for navigation when the vehicle travels in an open area with good GNSS signal. At the same time, the modeling parameters of INS and camera are estimated. When the system is navigating in areas with weak GNSS signals, such as u...
Alempijevic, A., Kodagoda, S. & Dissanayake, G. 2007, 'Sensor Registration for Robotic Applications', Springer Tracts in Advanced Robotics: Volume 42: Proceedings of the 6th International Conference on Field and Service Robotics, International Conference on Field and Service Robotics, Springer, France, pp. 233-242.
View/Download from: UTS OPUS or Publisher's site
Multi-sensor data fusion plays an essential role in most robotic applications. Appropriate registration of information from different sensors is a fundamental requirement in multi-sensor data fusion. Registration requires significant effort particularly when sensor signals do not have direct geometric interpretations, observer dynamics are unknown and occlusions are present. In this paper, we propose Mutual Information (MI) based sensor registration which exploits the effect of a common cause in the observed space on the sensor outputs that does not require any prior knowledge of relative poses of the observers. Simulation results are presented to substantiate the claim that the algorithm is capable of registering the sensors in the presence of substantial observer dynamics.
Herath, H.D., Kodagoda, S. & Dissanayake, G. 2008, 'New Framework for Simultaneous Localization and Mapping Multi Map SLAM', Proceeding of 2008 IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Pasadena, California, pp. 1892-1897.
View/Download from: UTS OPUS or Publisher's site
The main contribution of this paper arise from the development of a new framework for the problem of Simultaneous Localization and Mapping (SLAM) in the domain of stereo vision based robot navigation. The new framework has its inspiration in the mechanics of human navigation. At present the solution is specific to a unique instance of SLAM, where the primary sensing device is a short baseline stereo vision system. The new framework addresses several key issues of this particular problem. As observed in our earlier work [1], the particular sensing device has a highly nonlinear observation model resulting in inconsistent state estimations when standard recursive estimators such as the Extended Kalman Filter (EKF) or the Unscented variants are used. Secondly, vision based approaches tend to have issues related to large feature density, narrow field of view and the potential requirement of maintaining large data bases for vision based data association techniques. The proposed Multi Map SLAM solution addresses the first issue by formulating the SLAM problem as a nonlinear batch optimization. Second issue is addressed through a two tier map representation. The two maps have unique attributes assigned to them. The Global Map (GM) is a compact global representation of the robots environment and the Local Map (LM) is exclusively used for low-level navigation between local points in the robots navigation horizon.
Kodagoda, S., Zhang, Z., Ruiz, D. & Dissanayake, G. 2008, 'Sensing and Classification for Autonomous Weed Control', The IEEE International Conference on Robotics and Automation (ICRA 2008), workshop, IEEE International Conference on Robots and Automation, IEEE explorer, Pasadena, California, pp. 1-6.
Autonomous weed control concepts have recently being extensively researched due to the advantages that they possess. One of the critical modules of such systems is the sensing and classification of weeds within crops. In this paper, we systematically chose the sensing setup and cues to be used for classification of two common weed species (Bidens pilosa L. and Lolium rigidum L.) in a wheat crop. An automatic cue selection procedure is proposed. Some classification results and their problems were discussed leading to future direction of research.
Taha, T., Valls Miro, J. & Dissanayake, G. 2008, 'POMDP-Based Long-Term User Intention Prediction for Wheelchair Navigation', Proceeding of 2008 IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Pasadena, USA, pp. 3920-3925.
View/Download from: UTS OPUS or Publisher's site
This paper presents an intelligent decision-making agent to assist wheelchair users in their daily navigation activities. Several navigational techniques have been successfully developed in the past to assist with specific behaviours such as "door passing" or "corridor following". These shared control strategies normally require the user to manually select the level of assistance required during use. Recent research has seen a move towards more intelligent systems that focus on forecasting users' intentions based on current and past actions. However, these predictions have been typically limited to locations immediately surrounding the wheelchair. The key contribution of the work presented here is the ability to predict the users' intended destination at a larger scale, that of a typical office arena. The systems relies on minimal user input - obtained from a standard wheelchair joystick - in conjunction with a learned Partially Observable Markov Decision Process (POMDP), to estimate and subsequently drive the user to his destination. The projection is constantly being updated, allowing for true user- platform integration. This shifts users' focus from fine motor- skilled control to coarse control broadly intended to convey intention. Successful simulation and experimental results on a real wheelchair robot demonstrate the validity of the approach.
Taha, T., Valls Miro, J. & Dissanayake, G. 2008, 'Intention driven assistive wheelchair navigation', Proc. of "Robotic Helpers: User Interaction, Interfaces and Companions in Assistive and Therapy Robotics", a Workshop at ACM/IEEE Human Robot Interaction 2008 (HRI 2008), ACM/IEEE Human Robot Interaction, Technical Report 470, University of Hertfordshire, Amsterdam, the Netherlands, pp. 71-77.
View/Download from: UTS OPUS
This paper presents an intelligent decision-making agent to assist wheelchair users in their daily navigation activities. The system has the ability to predict the users intended destination at a larger scale, that of a typical office or home arena. This system relies on minimal user input - obtained from a standard wheelchair joystick - in conjunction with a learned Partially Observable Markov Decision Process (POMDP), to estimate and subsequently aid in driving the user to the destination. The projection is constantly being updated, allowing for true user-platform integration. This shifts users focus from fine motor-skilled control to coarse guidance, broadly intended to convey intention. Successful simulation and experimental results on a real automated wheelchair platform demonstrate the validity of the approach.
Valls Miro, J. & Dissanayake, G. 2008, 'Robotic 3D Visual Mapping for Augmented Situational Awareness in Unstructured Environments', Proceedings of the EURON/IARP International Workshop on Robotics for Risky Interventions and Surveillance of the Environment (RISE 2008), EURON/IARP Robotics for Risky Interventions and Surveillance of the Environment, University of Jaume I, Technical Report "Colleccio e-Treballs d'Informatica i Technologia" Num. 4, Benicassim, Spain.
Zhou, W., Valls Miro, J. & Dissanayake, G. 2008, 'Information-Driven 6D SLAM Based on Ranging Vision', IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2008, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Nice, France, pp. 2072-2077.
View/Download from: UTS OPUS or Publisher's site
This paper presents a novel solution for building three-dimensional dense maps in unknown and unstructured environment with reduced computational costs. This is achieved by giving the robot the dasiaintelligencepsila to select, out of the steadily collected data, the maximally informative observations to be used in the estimation of the robot location and its surroundings. We show that, although the actual evaluation of information gain for each frame introduces an additional computational cost, the overall efficiency is significantly increased by keeping the matrix compact. The noticeable advantage of this strategy is that the continuously gathered data is not heuristically segmented prior to be input to the filter. Quite the opposite, the scheme lends itself to be statistically optimal and is capable of handling large data sets collected at realistic sampling rates. The strategy is generic to any 3D feature-based simultaneous localization and mapping (SLAM) algorithm in the information form, but in the work presented here it is closely coupled to a proposed novel appearance-based sensory package. It consists of a conventional camera and a range imager, which provide range, bearing and elevation inputs to visual salient features as commonly used by three-dimensional point-based SLAM, but it is also particularly well adapted for lightweight mobile platforms such as those commonly employed for Urban Search and Rescue (USAR), chosen here to demonstrate the excellences of the proposed strategy
Liu, D., Dissanayake, G., Manamperi, P., Fang, G., Paul, G., Kirchner, N.G. & Chotiprayanakul, P. 2008, 'A robotic system for steel bridge maintenance: research challenges and system design', Proceedings of the Australasian Conference on Robotics and Automation, Australasian Conference on Robotics and Automation, Australian Robotics and Automation Association, Australia National University, Canberra, Australia, pp. 1-7.
View/Download from: UTS OPUS
Huang, S., Wang, Z. & Dissanayake, G. 2008, 'Exact state and covariance submatrix recovery for submap based sparse EIF SLAM algorithms', Proceeding of 2008 IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Pasadena, California, pp. 1868-1873.
View/Download from: UTS OPUS or Publisher's site
This paper provides a novel state vector and covariance sub-matrix recovery algorithm for a recently developed submap based exactly sparse extended information filter (EIF) SLAM algorithm - sparse local submap joining filter (SLSJF). The algorithm achieves exact recovery instead of approximate recovery. The recovery algorithm is very efficient because of an incremental Cholesky factorization approach and a natural reordering of the global state vector. Simulation results show that the computation cost of the SLSJF is much lower as compared with the sequential map joining algorithm using extended Kalman filter (EKF). The SLSJF with the proposed recovery algorithm is also successfully applied to the Victoria Park data set.
Leung, C., Huang, S. & Dissanayake, G. 2008, 'Active SLAM for structured environments', Proceeding of 2008 IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Pasadena, USA, pp. 1898-1903.
View/Download from: UTS OPUS or Publisher's site
This paper considers the trajectory planning problem for line-feature based SLAM in structured indoor environments. The robot poses and line features are estimated using smooth and mapping (SAM) which is found to provide more consistent estimates than the extended Kalman filter (EKF) The objective of trajectory planning is to minimise the uncertainty of the estimates and to maximise coverage. Trajectory planning is performed using model predictive control (MPC) with an attractor incorporating long term goals. This planning is demonstrated both in simulation and in a real-time experiment with a Pioneer2DX robot.
Kodagoda, S., Zhang, Z., Ruiz, D. & Dissanayake, G. 2008, 'Weed detection and classification for autonomous farming', Proceedings of Fourth I*PROMS Virtual International Conference, Intelligent Production Machines and Systems, I*PROMS, Cardiff, UK, pp. 1-6.
View/Download from: UTS OPUS
Autonomous weed control concepts have recently being extensively researched due to the advantages that they possess. One of the critical modules of such systems is the sensing and classification of weeds within crops. In this paper, we systematically chose the sensing setup and cues to be used for classification of two common weed species (Bidens pilosa L. and Lolium rigidum L.) in a wheat crop. An automatic cue selection followed by classification procedure is proposed. Some classification results are presented while discussing problems leading to future direction of research.
Zhang, Z., Kodagoda, S., Ruiz, D., Katupitiya, J. & Dissanayake, G. 2008, 'Classification of Bidens in wheat farms', 15th International Conference on Mechatronics and Machine Vision in Practice, M2VIP'08, Mechatronics and Machine Vision in Practice, IEEE, Auckland, NZ, pp. 505-510.
View/Download from: UTS OPUS or Publisher's site
Bidens pilosa L (commonly known as cobbler's peg) is an annual broad leaf weed widely distributed in tropical and subtropical regions of the world and is reported to be a weed of 31 crops including wheat. Automatic detection of Bidens in wheat farms is a nontrivial problem due to their similarity in color and presence of occlusions. This paper proposes a methodology which could be used to discriminate Bidens from wheat to be used in operations such as autonomous weed destruction. A spectrometer is used to analyze the optical properties of Bidens and wheat leaves while achieving high classification results. However, due to the practical constraints of using spectrometers, a color camera based technique is proposed. It is shown that the color based segmentation followed by shape based validation algorithm gives rise to high detection rates with lower false detections. We have experimentally evaluated the algorithm with Bidens detection rate of 80% and a 10% false alarm rate.
Huang, S., Wang, Z., Dissanayake, G. & Frese, U. 2008, 'Iterated SLSJF: A Sparse Local Submap Joining Algorithm with Improved Consistency', Proceeding of ACRA, Australasian Conference on Robotics and Automation, ARAA, Canberra, Australia, pp. 1-9.
View/Download from: UTS OPUS
This paper presents a new local submap joining algorithm for building large-scale feature based maps. The algorithm is based on the recently developed Sparse Local Submap Joining Filter (SLSJF) and uses multiple iterations to improve the estimate and hence is called Iterated SLSJF (I-SLSJF). The input to the I-SLSJF algorithm is a sequence of local submaps. The output of the algorithm is a global map containing the global positions of all the features as well as all the robot start/end poses of the local submaps.
Wang, Z., Dissanayake, G. & IEEE 2008, 'Observability Analysis of SLAM Using Fisher Information Matrix', 2008 10TH INTERNATIONAL CONFERENCE ON CONTROL AUTOMATION ROBOTICS & VISION: ICARV 2008, VOLS 1-4, pp. 1242-1247.
View/Download from: Publisher's site
Pedraza, L., Dissanayake, G., Miro, J.V., Rodriguez-Losada, D. & Matia, F. 2008, 'BS-SLAM: Shaping the world', Robotics: Science and Systems, pp. 169-176.
This paper presents BS-SLAM, a simultaneous localization and mapping algorithm for use in unstructured environments that is effective regardless of whether features correspond to simple geometric primitives such as lines or not. The coordinates of the control points defining a set of B-splines are used to form a complete and compact description of the environment, thus making it feasible to use an extended Kalman filter based SLAM algorithm. The proposed method is the first known EKF-SLAM implementation capable of describing both straight and curve features in a parametric way. Appropriate observation equation that allows the exploitation of virtually all observations from a range sensor such as the ubiquitous laser range finder is developed. Efficient strategies for computing the relevant Jacobians, perform data association, initialization and expanding the map are presented. The effectiveness of the algorithms is demonstrated using experimental data.
Wang, Z., Huang, S. & Dissanayake, G. 2005, 'DSLAM: Decoupled Localization and Mapping for Autonomous Robots', Robotics Research: Springer tracts in Advanced Robotics Vol 28 - 2005 International Symposium of Robotics Research Proceedings, International Symposium on Robotics Research, Springer, San Francisco, USA, pp. 203-213.
View/Download from: UTS OPUS or Publisher's site
The main contribution of this paper is the reformulation of the simultaneous localization and mapping (SLAM) problem for mobile robots such that the mapping and localization can be treated as two concurrent yet separated processes: D-SLAM (decoupled SLAM). It is shown that SLAM can be decoupled into solving a non-linear static estimation problem for mapping and a low-dimensional dynamic estimation problem for localization. The mapping problem can be solved using an Extended Information Filter where the information matrix is shown to be exactly sparse. A significant saving in the computational effort can be achieved for large scale problems by exploiting the special properties of sparse matrices. An important feature of D-SLAM is that the correlation among landmarks are still kept and it is demonstrated that the uncertainty of the map landmarks monotonically decrease. The algorithm is illustrated through computer simulations and experiments.
Sehestedt, S.A., Kodagoda, S., Alempijevic, A. & Dissanayake, G. 2007, 'Efficient Lane Detection and Tracking in Urban Environments', third European Conference on Mobile Robots, European Conference on Mobile Robots, ECMR, Germany, pp. 78-83.
View/Download from: UTS OPUS
Kodagoda, S., Sehestedt, S.A., Alempijevic, A., Zhang, Z., Donikian, A. & Dissanayake, G. 2007, 'Towards an Enhanced Driver Situation Awareness System', Second International Conference on Industrial and Information Systems, IEEE International Conference on Industrial and Information Systems, IEEE, Sri Lanka, pp. 295-300.
View/Download from: UTS OPUS or Publisher's site
This paper outlines our current research agenda to achieve enhanced driver situation awareness. A novel approach that incorporates information gathered from sensors mounted on the neighboring vehicles, in the road infrastructure as well as onboard sensory information is proposed. A solution to the fundamental issue of registering data into a common reference frame when the relative locations of the sensors themselves are changing is outlined. A description of the vehicle test bed, experimental results from information gathered from various onboard sensors, and preliminary results from the sensor registration algorithm are presented.
Chotiprayanakul, P., Liu, D., Wang, D. & Dissanayake, G. 2007, 'A 3-dimensional force field method for robot collision avoidance in complex environments', Proceedings of the 24th International Symposium on Automation and Robotics in Construction (ISARC 2007), International Symposium on Automation and Robotics in Construction, Indian Institute of Technology Madras, Kochi, Kerala, India, pp. 139-145.
View/Download from: UTS OPUS
Kodagoda, S., Alempijevic, A., Sehestedt, S.A. & Dissanayake, G. 2007, 'Towards Improving Driver Situation Awareness at Intersections', the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS 2007), IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, San Diego, California, pp. 3739-3744.
View/Download from: UTS OPUS or Publisher's site
Providing safety critical information to the driver is vital in reducing road accidents, especially at intersections. Intersections are complex to deal with due to the presence of large number of vehicle and pedestrian activities, and possible occlusions. Information available from only the sensors on-board a vehicle has limited value in this scenario. In this paper, we propose to utilize sensors on-board the vehicle of interest as well as the sensors that are mounted on nearby vehicles to enhance the driver situation awareness. The resulting major research challenge of sensor registration with moving observers is solved using a mutual information based technique. The response of the sensors to common causes are identified and exploited for computing their unknown relative locations. Experimental results, for a mock up traffic intersection in which mobile robots equipped with laser range finders are used, are presented to demonstrate the efficacy of the proposed technique.
Chotiprayanakul, P., Liu, D., Wang, D. & Dissanayake, G. 2007, 'Collision-Free Trajectory Planning for Manipulator Using Virtual Force based Approach', Proceedings of the International Conference on Engineering, Applied Sciences, and Technology (ICEAST 2007), International Conference on Engineering, Applied Sciences, and Technology, KMITL, Bangkok, Thailand, pp. 351-354.
Taha, T., Valls Miro, J. & Dissanayake, G. 2007, 'Wheelchair driver assistance and intention prediction using POMDPs', IEEE International Conference on Intelligent Networks, Sensor Networks and Information Processing (ISSNIP 2007), International Conference on Intelligent Sensors, Sensor Networks and Information Processing, IEEE Computer Society, Melbourne, Victoria, pp. 449-454.
View/Download from: UTS OPUS or Publisher's site
Electric wheelchairs give otherwise immobile people the freedom of movement, they significantly increase independence and dramatically increase quality of life. However the physical control systems of such wheelchair can be prohibitive for some users; for example, people with severe tremors. Several assisted wheelchair platforms have been developed in the past to assist such users. Algorithms that assist specific behaviors such as door - passing, follow - corridor, or avoid - obstacles have been successful. Research has seen a move towards systems that predict the users intentions, based on the users input. These predictions have been typically limited to locations immediately surrounding the wheelchair. This paper presents a new assisted wheelchair driving system with large scale intelligent intention recognition based on POMDPs (partially observable Markov decision processes). The systems acts as an intelligent agent/decision-maker, it relies on minimal user input; to predict the users intention and then autonomously drives the user to his destination. The prediction is constantly being updated as new user input is received allowing for true user/system integration. This shifts the users focus from fine motor-skilled control to coarse control intended to convey intention.
Zhou, W., Valls Miro, J. & Dissanayake, G. 2007, 'Information efficient 3D visual SLAM in unstructured domains', IEEE International Conference on Intelligent Networks, Sensor Networks and Information Processing (ISSNIP 2007), International Conference on Intelligent Sensors, Sensor Networks and Information Processing, IEEE, Melbourne, Victoria, pp. 323-328.
View/Download from: UTS OPUS or Publisher's site
This paper presents a strategy for increasing the efficiency of simultaneous localisation and mapping (SLAM) in unknown and unstructured environments using a vision-based sensory package. Traditional feature-based SLAM, using either the extended Kalman filter (EKF) or its dual, the extended information filter (EIF), leads to heavy computational costs while the environment expands and the number of features increases. In this paper we propose an algorithm to reduce computational cost for real-time systems by giving robots the 'intelligence' to select, out of the steadily collected data, the maximally informative observations to be used in the estimation process. We show that, although the actual evaluation of information gain for each frame introduces an additional computational cost, the overall efficiency is significantly increased by keeping the matrix compact. The noticeable advantage of this strategy is that the continuously gathered data is not heuristically segmented prior to be input to the filter. Quite the opposite, the scheme lends itself to be statistically optimal.
Pedraza, L., Dissanayake, G., Valls Miro, J., Rodriguez-Losada, D. & Matia, F. 2007, 'BS-SLAM: shaping the world', Robotics: Science and Systems III(RSS 2007), Robotics: Systems and Science, MIT Press, Atlanta, GA, USA, pp. 1-8.
View/Download from: UTS OPUS
This paper presents BS-SLAM, a simultaneous localization and mapping algorithm for use in unstructured environments that is effective regardless of whether features correspond to simple geometric primitives such as points and lines or not. The coordinates of the control points defining a set of B-splines are used to form a complete and compact description of the environment, thus making it feasible to use an extended Kalman filter based SLAM algorithm. The proposed method is the first known EKF-SLAM implementation capable of describing both straight and curve features in a parametric way. Appropriate observation equation that allows the exploitation of virtually all observations from a range sensor such as the ubiquitous laser range finder is developed. Efficient strategies for computing the relevant Jacobians, perform data association, initialization and expanding the map are presented. The effectiveness of the algorithms is demonstrated using experimental data.
Lau, H., Huang, S. & Dissanayake, G. 2007, 'Multi-Agent Search with Interim Positive Information', IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, Omnipress, San Diego, USA, pp. 3791-3796.
View/Download from: UTS OPUS or Publisher's site
A problem of searching with multiple searchers and scouts is presented. Unlike most search problems that terminate as soon as the target is found, successful detection by scouts only improve on the current knowledge of the moving target's location, such that the searchers can more effectively find and service the target in the future. The team must correspondingly plan not only to maximize the probability of the searchers directly finding the target, but also give them the best chance of exploiting any new information from potential scout detections. It is shown that this need to plan for replanning can be addressed by equivalently solving a series of simpler detection search problems that always do terminate on detection. Optimal and heuristic solution methods for this searcher/scout problem are derived, such that the capabilities of all the sensing platforms in a search task are harnessed even when only a subset are capable of actually servicing the target.
Wang, Z., Huang, S. & Dissanayake, G. 2007, 'Multi-robot simultaneous localization and mapping using D-SLAM framework', The Third International Conference on Intelligent Sensors, Sensor Networks and Information Processing, International Conference on Intelligent Sensors, Sensor Networks and Information Processing, ARC Research Network on Sensor Networks, Melbourne, pp. 317-322.
View/Download from: UTS OPUS or Publisher's site
This paper presents an algorithm for the multi-robot simultaneous localization and mapping (SLAM) problem with the robot initial locations completely unknown. Each robot builds its own local map using the traditional extended Kalman filter (EKF) SLAM algorithm. We provide a new method to fuse the local maps into a jointly maintained global map by first transforming the local map state estimate into relative location information and then conducting the fusion using the decoupled SLAM (D-SLAM) framework (Wang et al., 2007). An efficient algorithm to find the map overlap and corresponding beacons across the maps is developed from a point feature based medical image registration method and the joint compatibility test. By adding the robot initial pose of each local map into the global map state, the algorithm shows valuable properties. Simulation results are provided to illustrate the effectiveness of the algorithm.
Sehestedt, S.A., Kodagoda, S., Alempijevic, A. & Dissanayake, G. 2007, 'Robust Lane Detection in Urban Environments', Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, USA, pp. 123-128.
View/Download from: UTS OPUS or Publisher's site
Most of the lane marking detection algorithms reported in the literature are suitable for highway scenarios. This paper presents a novel clustered particle filter based approach to lane detection, which is suitable for urban streets in normal traffic conditions. Furthermore, a quality measure for the detection is calculated as a measure of reliability. The core of this approach is the usage of weak models, i.e. the avoidance of strong assumptions about the road geometry. Experiments were carried out in Sydney urban areas with a vehicle mounted laser range scanner and a ccd camera. Through experimentations, we have shown that a clustered particle filter can be used to efficiently extract lane markings.
Wang, D., Kwok, N., Liu, D., Lau, H. & Dissanayake, G. 2007, 'PSO-tuned F2 method for multi-robot navigation', 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, San Diego, California, USA, pp. 3765-3770.
View/Download from: UTS OPUS or Publisher's site
The F (Force Field) method is a novel approach for multi-robot motion planning and collision avoidance. The setting of parameters is however vital to its performance. This paper presents an approach using Particle Swarm Optimization (PSO) to properly determine the control parameters for the F2 method. The goal of the optimization is to minimize the resultant path lengths. The approach presented in this paper can be used as a tool to obtain optimal parameters for various tasks before their execution. Simulations are carried out in various environments to show the feasibility of this approac
Valls Miro, J., Taha, T., Wang, D., Dissanayake, G. & Liu, D. 2007, 'An efficient strategy for robot navigation in cluttered environments in the presence of dynamic obstacles', Proceedings of the 8th International Conference on Intelligent Technologies (InTech), International Conference on Intelligent Technologies, University of Technology, Sydney, Sydney, Australia, pp. 74-81.
View/Download from: UTS OPUS
Wang, Z.Z., Huang, S. & Dissanayake, G. 2005, 'Implementation issues and experimental evaluation of D-SLAM', Field And Service Robotics, International Conference on Field and Service Robotics, Springer-Verlag Berlin, Port Douglas, Australia, pp. 155-166.
View/Download from: UTS OPUS
D-SLAM algorithm first described in [1] allows SLAM to be decoupled into solving a non-linear static estimation problem for mapping and a three-dimensional estimation problem for localization. This paper presents a new version of the D-SLAM algorithm tha
Huang, S., Wang, Z.Z. & Dissanayake, G. 2006, 'Mapping large scale environments using relative position information among landmarks', Proceedings of the 2006 IEEE International Conference on Robotics and Automation, IEEE International Conference on Robots and Automation, IEEE, Orlando, FL, pp. 2297-2302.
View/Download from: UTS OPUS or Publisher's site
The main contribution of this paper is a new SLAM algorithm for the mapping of large scale environments by combining local maps. The local maps can be generated by traditional Extended Kalman Filter (EKF) based SLAM. Relationships between the locations o
Ha, Q.P., Ha, H. & Dissanayake, G. 2006, 'Robotic formation control using variable structure systems approach', Dis 2006: Ieee Workshop On Distributed Intelligent Systems: Collective Intelligence And Its Applications, Proceedings, IEEE Workshop on Distributed Intelligent Systems, IEEE Computer Soc, Prague, CZECH REPUBLIC, pp. 37-42.
View/Download from: UTS OPUS
This paper addresses robust control of multiple mobile robots moving in desired formations. A rigorous control technique for such an agent-based robotic system may encounter problems of singularity, parameter sensitivity and inter-robot collision. Our pr
Herath, H.D., Kodagoda, S. & Dissanayake, G. 2006, 'Simultaneous Localisation and Mapping: A Stereo Vision Based Approach', Proceedings of the 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Beijing, China, pp. 922-927.
View/Download from: UTS OPUS or Publisher's site
With limited dynamic range and poor noise performance, cameras still pose considerable challenges in the application of range sensors in the context of robotic navigation, especially in the implementation of simultaneous localisation and mapping (SLAM) with sparse features. This paper presents a combination of methods in solving the SLAM problem in a constricted indoor environment using small baseline stereo vision. Main contributions include a feature selection and tracking algorithm, a stereo noise filter, a robust feature validation algorithm and a multiple hypotheses adaptive window positioning method in 'closing the loop'. These methods take a novel approach in that information from the image processing and robotic navigation domains are used in tandem to augment each other. Experimental results including a real-time implementation in an office-like environment are also presented
Herath, H.D., Kodagoda, S. & Dissanayake, G. 2006, 'Modelling Errors in Small Baseline Stereo for SLAM', Proceedings of the 9th International Conference on Control, Automation, Robotics and Vision, International Conference on Control, Automation, Robotics and Vision, IEEE, Singapore, pp. 836-841.
View/Download from: UTS OPUS or Publisher's site
In the past few years, there has been significant advancement in localization and mapping using stereo cameras. Despite the recent successes, reliably generating an accurate geometric map of a large indoor area using stereo vision still poses significant challenges due to the accuracy and reliability of depth information especially with small baselines. Most stereo vision based applications presented to date have used medium to large baseline stereo cameras with Gaussian error models. Here we make an attempt to analyze the significance of errors in small baseline (usually <0.1m) stereo cameras and the validity of the Gaussian assumption used in the implementation of Kalman filter based SLAM algorithms. Sensor errors are analyzed through experimentations carried out in the form of a robotic mapping. Then we show that SLAM solutions based on the extended Kalman filter (EKF) could become inconsistent due to the nature of the observation models used
Lau, H., Huang, S. & Dissanayake, G. 2006, 'Probabilistic Search for a Moving Target in an Indoor Environment', 2006 IEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Beijing, China, pp. 3393-3398.
View/Download from: UTS OPUS or Publisher's site
We consider a search for a target moving within a known indoor environment partitioned into interconnected regions of varying sizes. The knowledge of target location is described as a probability distribution over the regions, and the searcher can only move from one region to another as the structure allows. The objective is to find a feasible path through the regions that maximizes the probability of locating the target within fixed time. This problem generalizes the existing optimal searcher path problem (OSP) by additionally stipulating a minimum amount of time that a finite-speed searcher must spend to travel through a region before reaching the next. We propose a technique to obtain the upper bound of detection for solving the problem in a branch and bound framework. Comparisons show that the technique is also superior to known bounding methods for the original optimal searcher path problem
Huang, S. & Dissanayake, G. 2006, 'Convergence Analysis for Extended Kalman Filter based SLAM', Proceedings of the 2006 IEEE International Conference on Robotics and Automation, IEEE International Conference on Robots and Automation, IEEE, Orlando, USA, pp. 412-417.
View/Download from: UTS OPUS or Publisher's site
The main contribution of this paper is a theoretical analysis of the extended Kalman filter (EKF) based solution to the simultaneous localisation and mapping (SLAM) problem. The convergence properties for the general nonlinear two-dimensional SLAM are provided. The proofs clearly show that the robot orientation error has a significant effect on the limit and/or the lower bound of the uncertainty of the landmark location estimates. Furthermore, some insights to the performance of EKF SLAM and a theoretical analysis on the inconsistencies in EKF SLAM that have been recently observed are given
Leung, C., Huang, S. & Dissanayake, G. 2006, 'Active SLAM Using Model Predictive Control and Attractor Based Exploration', 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Beijing, China, pp. 5026-5031.
View/Download from: UTS OPUS or Publisher's site
Active SLAM poses the challenge for an autonomous robot to plan efficient paths simultaneous to the SLAM process. The uncertainties of the robot, map and sensor measurements, and the dynamic and motion constraints need to be considered in the planning process. In this paper, the active SLAM problem is formulated as an optimal trajectory planning problem. A novel technique is introduced that utilises an attractor combined with local planning strategies such as model predictive control (a.k.a. receding horizon) to solve this problem. An attractor provides high level task intentions and incorporates global information about the environment for the local planner, thereby eliminating the need for costly global planning with longer horizons. It is demonstrated that trajectory planning with an attractor results in improved performance over systems that have local planning alone
Kodagoda, S., Alempijevic, A., Underwood, J., Kumar, S. & Dissanayake, G. 2006, 'Sensor Registration and Calibration Using Moving Targets', Proceedings of the 9th International Conference on Control, Automation, Robotics and Vision, International Conference on Control, Automation, Robotics and Vision, IEEE, Singapore, pp. 830-835.
View/Download from: UTS OPUS or Publisher's site
Multimodal sensor registration and calibration are crucially important aspects in distributed sensor fusion. Unknown relationships of sensors and joint probability distribution between sensory signals make the sensor fusion nontrivial. In this paper, we adopt a Mutual Information (MI) based approach for sensor registration and calibration. It is based on unsupervised learning of a nonparametric sensing model by maximizing mutual information between signal streams. Experiments were carried out in an office like environment with two laser sensors capturing arbitrarily moving people. Attributes of the moving targets are used. Problems due to target occlusions are alleviated by the multiple model tracker. The registration and calibration methodology does not require any artificially generated patterns or motions unlike other calibration methodologies
Kulatunga, A.K., Liu, D., Dissanayake, G. & Siyambalapitiya, S.B. 2006, 'Ant Colony Optimization based Simultaneous Task Allocation and Path Planning of Autonomous Vehicles', Proceedings of the IEEE Conference on Cybernetics and Intelligent Systems, IEEE International Conference on Cybernetics and Intelligent Systems, IEEE, Bangkok, Thailand, pp. 823-828.
View/Download from: UTS OPUS or Publisher's site
This paper applies a meta-heuristic based ant colony optimization (ACO) technique for simultaneous task allocation and path planning of automated guided vehicles (AGV) in material handling. ACO algorithm allocates tasks to AGVs based on collision free path obtained by a proposed path and motion planning algorithm. The validity of this approach is investigated by applying it to different task and AGV combinations which have different initial settings. For small combinations, i.e. small number of tasks and vehicles, the quality of the ACO solution is compared against the optimal results obtained from exhaustive search mechanism. This approach has shown near optimal results. For larger combinations, ACO solutions are compared with simulated annealing algorithm which is another commonly used meta-heuristic approach. The results show that ACO solutions have slightly better performance than that of simulated annealing algorithm
Liu, D., Wang, D. & Dissanayake, G. 2006, 'A Force field Method Based Multi Robot Collaboration', Proceedings of IEEE Conference on Robotics, Automation and Mechatronics, 2006, IEEE Conference on Robotics, Automation and Mechatronics, IEEE, Bangkok, Thailand, pp. 662-667.
View/Download from: UTS OPUS or Publisher's site
A force field (F2) based multi-robot collaboration method is presented in this paper. In this method, a virtual force field is generated for every moving robot and continuously changing based on the robot status including its traveling speed, dimension, priority, location and environment, etc. The interactions among robots' force fields and obstacles provide a natural way for collision avoidance and collaboration while robots are on their way to goals. In this paper, the definition of reaction force direction is modified to reduce robot orientation oscillations which occur when a robot approaches obstacles or other robots. Then the influence of task priority on motion planning and the problem of deadlock in multi-robot cases are discussed. Simulations in a real indoor environment were carried out and demonstrated the feasibility and effectiveness of this method
Alempijevic, A., Kodagoda, S., Underwood, J., Kumar, S. & Dissanayake, G. 2006, 'Mutual Information Based Sensor Registration and Calibration', Proceedings of the 2006 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Beijing, China, pp. 25-30.
View/Download from: UTS OPUS or Publisher's site
Knowledge of calibration, that defines the location of sensors relative to each other, and registration, that relates sensor response due to the same physical phenomena, are essential in order to be able to fuse information from multiple sensors. In this paper, a mutual information (MI) based approach for automatic sensor registration and calibration is presented. Unsupervised learning of a nonparametric sensing model by maximizing mutual information between signal streams is used to relate information from different sensors, allowing unknown sensor registration and calibration to be determined. Experiments conducted in an office environment are used to illustrate the effectiveness of the proposed technique. Two laser sensors are used to capture people mobbing in an arbitrarily manner in the environment and MI from a number of attributes of the motion are used for relating the signal streams from the sensors. Thus the sensor registration and calibration is achieved without using artificial patterns or pre-specified motions
Liu, D., Wu, X., Kulatunga, A.K. & Dissanayake, G. 2006, 'Motion Coordination of Multiple Autonomous Vehicles in Dynamic and Strictly Constrained Environments', Proceedings of the IEEE Conference on Cybernetics and Intelligent Systems, IEEE International Conference on Cybernetics and Intelligent Systems, IEEE, Bangkok, Thailand, pp. 204-209.
View/Download from: UTS OPUS or Publisher's site
With the increasing applications of fully autonomous vehicles, efficient motion coordination of multi-autonomous vehicles becomes a very important problem as it significantly affects the productivity. This problem is even harder to solve with the increases of the number of autonomous vehicles employed in a dynamic changing environment and constraints to vehicle movement. This paper presents a simultaneous path and motion planning (SiPaMoP) approach to coordinate motions of multi-autonomous vehicles in dynamic and strictly constrained environments. This approach integrates the path planning, collision avoidance and motion planning into a comprehensive model, which has so far not attracted a lot of attention in the academic literature, and optimizes vehicles' path and speed to minimize the completion time of a set of tasks. Simulation results demonstrated that this approach can effectively coordinate the motion of a team of vehicles, and solve the problems of traffic congestion and collision under various traffic conditions
Wang, D., Liu, D. & Dissanayake, G. 2006, 'A Variable Speed Force Field Method for Multi-Robot Collaboration', Proceedings of the IEEE/RSJ International Conference on Robots and Intelligent Systems, 2006, IEEE/RSJ International Conference on Robots and Intelligent Systems, IEEE, Beijing, China, pp. 2697-2702.
View/Download from: UTS OPUS
Kirchner, N.G., Liu, D. & Dissanayake, G. 2006, 'Bridge Maintenance Robotic Arm: Capacitive Sensor for Obstacle Ranging in Particle Laden Air', Proceedings of the 23rd International Symposium on Automation and Robotics in Construction, International Symposium of Automation and Robotics in Construction, Japan Robot Association, Tokyo, Japan, pp. 596-601.
View/Download from: UTS OPUS
Valls Miro, J., Zhou, W. & Dissanayake, G. 2006, 'Towards Vision Based Navigation in Large Indoor Environments', Proceedings of the 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2006), IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Beijing, China, pp. 2096-2102.
View/Download from: UTS OPUS or Publisher's site
The main contribution of this paper is a novel stereo-based algorithm which serves as a tool to examine the viability of stereo vision solutions to the simultaneous localisation and mapping (SLAM) for large indoor environments. Using features extracted from the scale invariant feature transform (SIFT) and depth maps from a small vision system (SVS) stereo head, an extended Kalman filter (EKF) based SLAM algorithm, that allows the independent use of information relating to depth and bearing, is developed. By means of a map pruning strategy for managing the computational cost, it is demonstrated that statistically consistent location estimates can be generated for a small (6 m times 6 m) structured office environment, and in a robotics search and rescue arena of similar size. It is shown that in a larger office environment, the proposed algorithm generates location estimates which are topologically correct, but statistically inconsistent. A discussion on the possible reasons for the inconsistency is presented. The paper highlights that, despite recent advances, building accurate geometric maps of large environments with vision only sensing is still a challenging task
Ellekilde, L., Valls Miro, J. & Dissanayake, G. 2006, 'Fusing range and intensity images for generating dense models of three-dimensional environments', Proceedings of the 2006 IEEE International Conference on Man-Machine Systems (ICoMMS 2006), IEEE International Conference on Man-Machine Systems, IET, Langkawi, Malaysia, pp. 1-5.
View/Download from: UTS OPUS
Taha, T., Valls Miro, J. & Dissanayake, G. 2006, 'Sampling based time efficient path planning algorithm for mobile platforms', Proceeding of the 2006 IEEE International Conference on Man-Machine Systems (ICoMMS 2006), IEEE International Conference on Man-Machine Systems, IET, Langkawi, Malaysia, pp. 1-6.
View/Download from: UTS OPUS
Dissanayake, G., Paxman, J.P., Valls Miro, J., Thane, O. & Thi, H. 2006, 'Robotics for urban search and rescue', Proceedings of the IEEE First International Conference on Industrial and Information Systems (ICIIS2006), IEEE International Conference on Industrial and Information Systems, IEEE, Peradeniya, Sri Lanka, pp. 294-298.
View/Download from: UTS OPUS or Publisher's site
This paper describes a team of robots that are designed for urban search and rescue applications. The team CASualty consists of four tele-operated robots and one autonomous robot. A brief description of the capabilities of the robot team is presented together with the details of capabilities of the autonomous robot HOMER. In particular, the software architecture, user interface, strategies used for mapping, exploration and the identification of human victims present in the environment are described. The team participated in an international competition on urban search and rescue (RoboCup Rescue) held in Bremen, Germany in June 2006 where HOMER was placed second in the autonomy challenge
Takezawa, S., Ishimoto, T. & Dissanayake, G. 2006, 'Optimal control for simultaneous localisation and mapping problems in indoor environments with stereo vision', IECON Proceedings (Industrial Electronics Conference), pp. 4749-4754.
View/Download from: Publisher's site
This paper proposes a optimal control method for simultaneous localisation and mapping (SLAM) in an indoor environment using stereo vision. Specially designed artificial landmarks distributed in the environment are observed and extracted from a camera image. The disparity map obtained from the stereo vision system is used to obtain the ranges to these landmarks. The main contribution of the paper is the formulation of the mathematical framework for SLAM for a robot moving on a planar surface among landmarks distributed in three dimensional space. The paper also presents the results of experiments for optimal control conducted using a Pioneer robot and a Triclops stereo vision system. It is demonstrated that accurate robot and feature locations can be obtained using the proposed technique. &copy; 2006 IEEE.
Kulatunga, A.K., Liu, D.K., Dissanayake, G., Siyambalapitiya, S.B. & IEEE 2006, 'Ant colony optimization based simultaneous task allocation and path planning of autonomous vehicles', 2006 IEEE Conference on Cybernetics and Intelligent Systems, Vols 1 and 2, pp. 727-732.
Liu, D.K., Wu, X., Kulatunga, A.K., Dissanayake, G. & IEEE 2006, 'Motion coordination of multiple autonomous vehicles in dynamic and strictly constrained environments', 2006 IEEE Conference on Cybernetics and Intelligent Systems, Vols 1 and 2, pp. 683-688.
Dissanayake, G., Paxman, J., Miro, J.V., Thane, O. & Thi, H.T. 2006, 'Robotics for urban search and rescue', 1st International Conference on Industrial and Information Systems, ICIIS 2006, pp. 294-298.
View/Download from: UTS OPUS or Publisher's site
This paper describes a team of robots that are designed for urban search and rescue applications. The team CASualty consists of four tele-operated robots and one autonomous robot. A brief description of the capabilities of the robot team is presented together with the details of capabilities of the autonomous robot HOMER. In particular, the software architecture, user interface, strategies used for mapping, exploration and the identification of human victims present in the environment are described. The team participated in an international competition on urban search and rescue (RoboCup Rescue) held in Bremen, Germany in June 2006 where HOMER was placed second in the autonomy challenge. &copy;2006 IEEE.
Ha, Q.P., Tran, T., Scheding, S., Dissanayake, G. & Durrant-Whyte, H. 2005, 'Control Issues of an Autonomous Vehicle', Proceedings of the 22nd International Symposium on Automation and Robotics in Construction ISARC 2005, International Symposium of Automation and Robotics in Construction, Faculty of Architecture and Engineering, University of Ferrara, Farrara, Italy, pp. 1-7.
View/Download from: UTS OPUS
Ha, Q.P., Trinh, H.M. & Dissanayake, G. 2005, 'A Distributed Approach to Global Feedback Control of Multi-Agent Systems', Proceedings of the 6th International Symposium on Intelligent Technologies, International Symposium on Intelligent Technologies in Tech '05, Faculty of Science and Technology, Assumption University, Phuket, Thailand, pp. 67-72.
Lau, H., Huang, S. & Dissanayake, G. 2005, 'Optimal Search for Multiple Targets in a Built Environment', 2005 IEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE Press, Edmonton, Canada, pp. 228-233.
View/Download from: UTS OPUS or Publisher's site
The main contribution of this paper is an algorithm for autonomous search that minimizes the expected time for detecting multiple targets present in a known built environment. The proposed technique makes use of the probability distribution of the target(s) in the environment, thereby making it feasible to incorporate any additional information, known a-priori or acquired while the search is taking place, into the search strategy. The environment is divided into a set of distinct regions and an adjacency matrix is used to describe the connections between them. The costs of searching any of the regions as well as the cost of travel between them can be arbitrarily specified. The search strategy is derived using a dynamic programming algorithm. The effectiveness of the algorithm is illustrated using an example based on the search of an office environment. An analysis of the computational complexity is also presented.
Leung, C., Huang, S., Dissanayake, G. & Furukawa, T. 2005, 'Trajectory Planning for Multiple Robots in Bearing Only Target Localisation', 2005 IEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Edmonton, Canada, pp. 2312-2317.
View/Download from: UTS OPUS or Publisher's site
This paper provides a solution to the optimal trajectory planning problem in target localisation for multiple heterogeneous robots with bearing-only sensors. The objective here is to find robot trajectories that maximise the accuracy of the locations of the targets at a prescribed terminal time. The trajectory planning is formulated as an optimal control problem for a nonlinear system with a gradually identified model and then solved using nonlinear model predictive control (MPC). The solution to the MPC optimisation problem is computed through exhaustive expansion tree search (EETS) plus sequential quadratic programming (SQP). Simulations were conducted using the proposed methods. Results show that EETS alone performs considerably faster than EETS+SQP with only minor differences in information gain, and that a centralised approach outperforms a decentralised one in terms of information gain. We show that a centralised EETS provides a near optimal solution. We also demonstrate the significance of using a matrix to represent the information gathered.
Huang, S., Kwok, N., Dissanayake, G., Ha, Q.P. & Fang, G. 2005, 'Multi-Step Look-Ahead Trajectory Planning in SLAM: Possibility and Necessity', Proceedings of 2005 IEEE International Conference on Robotics and Automation, IEEE International Conference on Robots and Automation, The Institute of Electrical and Electronic Engineers Inc, Barcelona, Spain, pp. 1103-1108.
View/Download from: UTS OPUS
In this paper, the possibility and necessity of multistep trajectory planning in Extended Kalman Filter (EKF) based SLAM is investigated. The objective of the trajectory planning here is to minimize the estimation error of the robot and landmark locations subject to a given time horizon. We show that the problem can be regarded as an optimization problem for a gradually identified model. A numerical method is proposed for trajectory planning using a variant of the nonlinear Model Predictive Control (MPC). The proposed method is optimal in the sense that the control action is computed using all the information available at the time of decision making. Simulation results are included to compare the results from the one-step look-ahead trajectory planning and the proposed multi-step lookahead technique
Fang, G., Dissanayake, G., Kwok, N. & Huang, S. 2005, 'Near Minimum Time Path Planning for Bearing-Only Localisation and Mapping', 2005 IEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, The Institute of Electrical and Electronic Engineers Inc, Edmonton, Canada, pp. 2763-2768.
View/Download from: UTS OPUS or Publisher's site
The main contribution of this paper is an algorithm for integrating motion planning and simultaneous localisation and mapping (SLAM). Accuracy of the maps and the robot locations computed using SLAM is strongly dependent on the characteristics of the environment, for example feature density, as well as the speed and direction of motion of the robot. Appropriate control of the robot motion is particularly important in bearing-only SLAM, where the information from a moving sensor is essential. In this paper a near minimum time path planning algorithm with a finite planning horizon is proposed for bearing-only SLAM. The objective of the algorithm is to achieve a predefined mapping precision while maintaining acceptable vehicle location uncertainty in the minimum time. Simulation results have shown the effectiveness of the proposed method.
Wang, Z., Huang, S. & Dissanayake, G. 2005, 'Decoupling Localization and Mapping in SLAM Using Compact Relative Maps', Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Edmonton, Canada, pp. 1041-1046.
View/Download from: UTS OPUS or Publisher's site
In this paper, we propose a new algorithm for SLAM that makes use of a state vector consisting of quantities that describes the relative locations among features. In contrast to previous relative map strategies, the new state vector is compact and always consists of 2n &iexcl; 3 elements (in a 2-D environment) where n is the number of features in the map. It is also shown that the information from observations can be transformed and grouped into two parts: first one containing the information about the map and the second one containing the information about the robot location relative to the features in the map. Therefore the SLAM can be decoupled into two processes where mapping uses the first part of the transformed observation vector and localization becomes a 3-dimensional estimation problem. It is also shown that the information matrix of the map is exactly sparse, resulting in potential computational savings when an information filter is used for mapping. The new decoupled SLAM algorithm is called D-SLAM and is illustrated using simulation.
Valls Miro, J., Dissanayake, G. & Zhou, W. 2005, 'Vision-based SLAM using natural features in indoor environments', Proceedings of the 2005 International Conference on Intelligent Sensors, Sensor Networks and Information Processing Conference., International Conference on Intelligent Sensors, Sensor Networks and Information Processing, IEEE Publications, Melbourne, Australia, pp. 151-156.
View/Download from: UTS OPUS
This paper presents a practical approach to solve the simultaneous localization and mapping (SLAM) problem for autonomous mobile platforms by using natural visual landmarks obtained from an stereoscopic camera. It is an attempt to depart from traditional sensors such as laser rangefinders in order to gain the many benefits of nature-inspired information-rich 3D vision sensors. Whilst this makes the system fully observable in that the sensor provide enough information (range and bearing) to compute the full 2D estate of the observed landmarks from a single position, it is also true that depth information is difficult to rely on, particularly on measurements beyond a few meters (in fact the full 3D estate is observable, but here robot motion is constrained to 2D and only the 2D problem is considered). The work presented here is an attempt to overcome such a drawback by tackling the problem from a partially measurable SLAM perspective in that only landmark bearing from one of the cameras is employed in the fusion estimation. Range information estimates from the stereo pair is only used during map building in the landmark initialization phase in order to provide a reasonably accurate initial estimate. An additional benefit of the approach presented here lies in the data association aspect of SLAM. The availability of powerful feature extraction algorithms from the vision community, such as SIFT, permits a more flexible SLAM implementation separated from feature representation, extraction and matching, essentially carrying out matching with minimal recourse to geometry.
Kodagoda, S., Wang, C. & Dissanayake, G. 2005, 'Laser Based Sensing on Roads', Proceedings of the Intelligent Vehicles and Road Infrastructure Conference, Intelligent Vehicles & Road Infrastructure Conference, Society of Automotive Engineers, Australia, Melbourne, Australia, pp. 1-8.
View/Download from: UTS OPUS
Kwok, N., Dissanayake, G. & Ha, Q.P. 2005, 'Bearing-only SLAM using a SPRT Based Gaussian Sum Filter', Proceedings of 2005 IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, The IEEE, Barcelona Spain, pp. 1121-1126.
View/Download from: UTS OPUS
Use of a Gaussian Sum filter (GSF) to efficiently solve the initialisation problem in bearing-only simultaneous localisation and mapping (SLAM) is the main contribution of this paper. When information about the range is not available, the initial probability density function (pdf) of a landmark in the environment can not be represented using a Gaussian. The GSF is an attractive candidate for estimation in this scenario as it can deal with arbitrary pdfs represented as sets of Gaussians. However, the implementation of the GSF requires maintaining a bank of extended Kalman filters. The resulting computational complexity needs to be reduced by employing a minimum number of filters. In this work, the performance of each extended Kalman filter (EKF) in the GSF is evaluated using the sequential probability ratio test (SPRT). As such the number of members in the Gaussian sum can be reduced rapidly and the efficiency of the GSF can be significantly increased, providing a solution to the important problem of bearing-only SLAM. The effectiveness of the proposed approach is demonstrated by simulation and experiment conducted using a Pioneer mobile robot.
Kwok, N.M., Dissanayake, G. & Ha, Q.P. 2005, 'Bearing-only SLAM using a SPRT based gaussian sum filter', Proceedings - IEEE International Conference on Robotics and Automation, pp. 1109-1114.
View/Download from: Publisher's site
Use of a Gaussian Sum filter (GSF) to efficiently solve the initialisation problem in bearing-only simultaneous localisation and mapping (SLAM) is the main contribution of this paper. When information about the range is not available, the initial probability density function (pdf) of a landmark in the environment can not be represented using a Gaussian. The GSF is an attractive candidate for estimation in this scenario as it can deal with arbitrary pdfs represented as sets of Gaussians. However, the implementation of the GSF requires maintaining a bank of extended Kalman filters. The resulting computational complexity needs to be reduced by employing a minimum number of filters. In this work, the performance of each extended Kalman filter (EKF) in the GSF is evaluated using the sequential probability ratio test (SPRT). As such the number of members in the Gaussian sum can be reduced rapidly and the efficiency of the GSF can be significantly increased, providing a solution to the important problem of bearing-only SLAM. The effectiveness of the proposed approach is demonstrated by simulation and experiment conducted using a Pioneer mobile robot. &copy;2005 IEEE.
Takezawa, S. & Dissanayake, G. 2005, 'Simultaneous localisation and mapping problems in indoor environments with stereo vision', IECON Proceedings (Industrial Electronics Conference), pp. 1896-1901.
View/Download from: Publisher's site
This paper proposes a method for simultaneous localisation and mapping (SLAM) in an indoor environment using stereo vision. Specially designed artificial landmarks distributed in the environment are observed and extracted from a camera image. The disparity map obtained from the stereo vision system is used to obtain the ranges to these landmarks. The main contribution of the paper is the formulation of the mathematical framework for SLAM for a robot moving on a planar surface among landmarks distributed in three dimensional space. The paper also presents the results of experiments conducted using a Pioneer robot and a Triclops stereo vision system. It is demonstrated that accurate robot and feature locations can be obtained using the proposed technique. &copy;2005 IEEE.
Huang, S., Kwok, N.M., Dissanayake, G., Ha, Q.P. & Fang, G. 2005, 'Multi-step look-ahead trajectory planning in SLAM: Possibility and necessity', Proceedings - IEEE International Conference on Robotics and Automation, pp. 1091-1096.
View/Download from: Publisher's site
In this paper, the possibility and necessity of multi-step trajectory planning in Extended Kalman Filter (EKF) based SLAM is investigated. The objective of the trajectory planning here is to minimize the estimation error of the robot and landmark locations subject to a given time horizon. We show that the problem can be regarded as an optimization problem for a gradually identified model. A numerical method is proposed for trajectory planning using a variant of the nonlinear Model Predictive Control (MPC). The proposed method is optimal in the sense that the control action is computed using all the information available at the time of decision making. Simulation results are included to compare the results from the one-step look-ahead trajectory planning and the proposed multi-step look-ahead technique. &copy; 2005 IEEE.
Huang, S., Wang, Z. & Dissanayake, G. 2004, 'Time Optimal Robot Motion Control in Simultaneous Localization and Map Building (SLAM) Problem', Proceedings of 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, Publication Committee of IROS 2004, Sendai, Japan, pp. 3110-3115.
View/Download from: UTS OPUS or Publisher's site
This paper provides a technique for minimal time robot motion control in the estimation-theoretic based simultaneous localizations and map building (SLAM) problem. We consider the scenario that the robot needs to go to a destination which is a prescribed location in the coordinate system referenced by its starting position. The task of the robot is to reach the destination within minimal time while localizing itself and building a map of the environment with a prescribed accuracy. This task may be a real navigation task or may be a subtask in a SLAM problem of a large unknown environment. A global sub-optimal control law is derived using dynamic programming techniques
Ha, Q.P., Trinh, H.M. & Dissanayake, G. 2004, 'A Low-Order Linear Functional Observer for Time Delay Systems', Proceedings of the 5th Asian Control Conference, Asian Control Conference, IEEE, Melbourne, Australia, pp. 947-955.
View/Download from: UTS OPUS
Scott, 1)there are two Names H Trinh as stapled to front yellow page. & 2) the page numbers are the same as physically on the print off of Ha's other Public in this Conf "Simultaneous State... " !!
Tran, T., Ha, Q.P. & Dissanayake, G. 2004, 'New Wavelet-Based Pitch Detection Method for Human-Robot Voice Interface', Proceedings of IROS2004 The 2004IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Sendai, Japan, pp. 527-532.
View/Download from: UTS OPUS or Publisher's site
Speech activated interface between human and autonomous/semi-autonomous systems requires accurate voice detection and recognition. In this area, pitch and end-point detection is of vital importance. This paper presents a new method for pitch detection based on the phase of the continuous wavelet transform. The advantage of the proposed technique is that it can serve not only as an accurate pitch detector, but also can offer an efficient solution to the end-point detection problem. Experimental results are provided for the detection of pitch periods and end points in a neural-network based voice enabled wheelchair system.
Takezawa, S., Herath, H.D. & Dissanayake, G. 2004, 'SLAM in Indoor Environments with Stereo Vision', 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2004 (IROS 2004). Proceedings - Volume 2, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Sendai, Japan, pp. 1866-1871.
View/Download from: UTS OPUS or Publisher's site
This paper proposes a method for simultaneous localisation and mapping (SLAM) in an indoor environment using stereo vision. Specially designed artificial landmarks distributed in the environment are observed and extracted from a camera image. The disparity map obtained from the stereo vision system is used to obtain the ranges to these landmarks. The main contribution of the paper is the formulation of the mathematical framework for SLAM for a robot moving on a planar surface among landmarks distributed in three dimensional space. The paper also presents the results of experiments conducted using a pioneer robot and a Triclops stereo vision system. It is demonstrated that accurate robot and feature locations can be obtained using the proposed technique.
Kulatunga, A.K., Liu, D. & Dissanayake, G. 2004, 'Simulated Annealing Algorithm Based Multi-Robot Coordination', Preprints of the 3rd IFAC Symposium on Mechatronic Systems, The 3rd IFAC Symposium on Mechatronic Systems, International Federation of Automatic Control (IFAC), Sydney, Australia, pp. 411-415.
Kwok, N., Liu, D., Fang, G. & Dissanayake, G. 2004, 'Path Planning for Bearing-Only Simultaneous Localisation and Mapping', Proceedings of the 2004 IEEE Conference on Robotics, Automation and Mechatronics (RAM), IEEE Conference on Robotics, Automation and Mechatronics, IEEE, Singapore, pp. 828-833.
View/Download from: UTS OPUS
Simultaneous localisation and mapping (SLAM) is the process of estimating the pose of a mobile robot and the locations of landmarks by using sensors. When SLAM is cast as an information extraction procedure, its quality can be defined as the amount of uncertainty contained in the resultant estimation. Due to the characteristic of the bearing-only sensor and the geometry of the environment, the estimation uncertainty relies critically on the amount of information obtained from measurements and the efficiency of information extraction by the estimator. These quantities are dependent on the relative position between the robot and the landmarks, i.e., the path of the robot motion. Therefore, a well planned path of motion for the robot can significantly improve the SLAM quality. A genetic algorithm is adopted in this research to design a near-optimal one-step-ahead robot path subject to a multiple of planning objectives. The use of genetic algorithm together with a Pareto set, is proved to be efficient in reducing the estimation uncertainty and improving the quality of SLAM by simulation results.
Kwok, N. & Dissanayake, G. 2004, 'An Efficient Multiple Hypothesis Filter for Bearing-only SLAM', Proceedings of the 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Sendai, Japan, pp. 736-741.
View/Download from: UTS OPUS or Publisher's site
This paper presents a multiple hypothesis approach to solve the simultaneous localisation and mapping (SLAM) problem with a bearing-only sensor. The main contribution of the paper is to provide a remedy for the landmark initialisation problem that occurs due to the absence of range information, in a computationally efficient manner. Each landmark is initialised in the form of multiple hypotheses distributed along the direction of the bearing measurement. Using subsequent measurements, the validity of the hypotheses is evaluated based on the sequential probability ratio test (SPRT). Consequently, the best approximation to the landmark location is maintained. This approach enables an extended Kalman filler (EKF) to be used for bearing-only SLAM providing a computational efficient solution. Simulation and experimental results, from using a camera as the bearing-only sensor mounted on a Pioneer robot are included to demonstrate the effectiveness of the proposed technique.
Alempijevic, A. & Dissanayake, G. 2004, 'An Efficient Algorithm for Line Extraction from Laser Scans', Proceedings of the 2004 IEEE Conference on Robotics, Automation and Mechatronics (RAM), IEEE Conference on Robotics, Automation and Mechatronics, IEEE R&A Society Singapore Chapter, Singapore, pp. 970-974.
View/Download from: UTS OPUS
In this paper, an algorithm for extracting line segments from information gathered by a laser rangefinder is presented. The range scan is processed to compute a parameter that is invariant to the position and orientation of straight lines present. This parameter is then used to identify observations that potentially belong to straight lines and compute the slope of these lines. Log-Hough transform, that only explores a small region of the Hough space identified by the slopes computed, is then used to rind the equations of the lines present. The proposed method thus combines robustness of the Hough transform technique with the inherent efficiency of line fitting strategies while carrying out all computation in the sensor coordinate frame yielding a fast and robust algorithm for line extraction from laser range scans. Two practical examples are presented to demonstrate the efficacy of the algorithm and compare its performance to the traditional techniques.
Lim, S.H., Furukawa, T., Durrant-Whyte, H. & Dissanayake, G. 2004, 'A time-optimal control strategy for pursuit-evasion games', Proceedings of IEEE International Conference on Robotics and Automation, IEEE International Conference on Robots and Automation, IEEE, New Orleans, USA, pp. 3962-3967.
View/Download from: UTS OPUS or Publisher's site
This paper presents a control strategy for the pursuer in the pursuit-evasion game problem when the evader behaves intelligently. The pursuer in the proposed technique does not try to react to the evader's behavior instantaneously. The proposed technique therefore does not yield instantaneous optimality but capture the evader in a time-efficient and robust fashion even when the evader is intelligent. The proposed technique was applied to two numerical examples and the results were compared to those by the conventional motion tracking algorithms. The results and comparison show that the proposed technique could capture the evader faster than the conventional motion tracking algorithms in both the examples.
Furukawa, T., Bourgault, F., Durrant-Whyte, H. & Dissanayake, G. 2004, 'Dynamic allocation and control of coordinated UAVs to engage Multiple targets in a time-optimal manner', Proceedings of the IEEE International Conference on Robotics and Automation - Vol 3, IEEE International Conference on Robots and Automation, IEEE, New Orleans, pp. 2353-2358.
View/Download from: UTS OPUS or Publisher's site
This paper presents the real-time control of cooperative unmanned air vehicles (UAV) that dynamically engage multiple targets in a time-optimal manner. Techniques to dynamically allocate vehicles to targets and to subsequently find the time-optimal control actions are proposed. The decentralization of the proposed control strategy is further presented such that the vehicles can be controlled in real-time without significant time delay. The proposed strategy is men applied to various practical battlefield problems, and numerical results show the efficiency of the proposed strategy.
Gong, Z., Mr, J.I., Scheding, S., Rye, D., Durrant-Whyte, H. & Dissanayake, G. 2004, 'A heuristic rule-based switching and adaptive PID controller for a large autonomous tracked vehicle: From development to implementation', IEEE Conference on Control Applications - International Symposium on Intelligent Control Computer Aided Control Systems Design, IEEE International Conference on Control Applications, IEEE, Taipei,Taiwan, pp. 1272-1277.
View/Download from: UTS OPUS
An innovative and effective algorithm to control the speed and heading of B large tracked vehicle is presented. This is part of a larger control system that converts a manual driving vehicle into B computer controlled platform to perform autonomous functions in unshmehlred junglelike terrains Heuristic rule-based switching and adaptive PID eontrol methods m e used in this algorithm. The control system has been physically implemented and extensive field trials proved that the algorithm is robust and effective with excellent performance under various terrain conditions.
Dissanayake, G.M., Chen, L., Pedrycz, W., Fayek, A.R. & Russell, A.D. 2004, 'Fuzzy logic modeling of causal relationships-case study: Reasoning about construction performance', NAFIPS 2004: ANNUAL MEETING OF THE NORTH AMERICAN FUZZY INFORMATION PROCESSING SOCIETY, VOLS 1AND 2, pp. 605-610.
Ha, Q.P., Trinh, H. & Dissanayake, G. 2004, 'A low-order linear functional observer for time delay systems', 2004 5th Asian Control Conference, pp. 948-956.
This paper presents an efficient technique to design loworder state function observers for linear time-delay systems. Assuming the existence of a linear state feedback controller to achieve stability or some control performance criteria of the time-delay system, a design procedure is proposed for reconstruction of the state feedback control action. The procedure involves solving an optimisation problem with the objective to generate a matrix that is as close as possible to the given feedback gain of the required feedback controller. A condition for robust stability of the time-delay system using the observer-based control scheme is given. The attractive features of the proposed design procedure are that the resulted linear functional state observer is of a very low order and it requires information of a small number of outputs. Numerical examples are given to demonstrate the design procedure and its merits.
Fang, G., Dissanayake, G. & Lau, H. 2004, 'A behaviour-based optimisation strategy for multi-robot exploration', 2004 IEEE Conference on Robotics, Automation and Mechatronics, pp. 875-879.
To efficiently explore an unknown environment with a team of robots, a coordinated strategy that maximises the exploration area is required. This is a difficult optimisation problem, as there may exist many suboptimal solutions. In order to reduce the search space to a region that is near the optimal, a behaviour-based exploration strategy is used to define the region in which an optimal solution can be found. A numerical optimisation technique is then used to find the solution in this region. In particular, the proposed strategy uses a potential-fields technique to obtain a coarse movement direction for each robot. A nonlinear optimisation method is then used to calculate the velocity and angle deviation from the coarse direction to achieve the maximum exploration for each move. Simulation results have shown that the proposed method provides an efficient exploration strategy.
Takezawa, S. & Dissanayake, G. 2003, 'Autonomous Robot Control Applied for Slam Problem At Indoor Stereo Artificial Landmarks', Proceedings of the 10th Asia-Pacific Vibration Conference, Asia Pacific Vibration Conference, Queensland University of Technology, Gold Coast, Queensland, Australia, pp. 893-898.
View/Download from: UTS OPUS
Dutta-Roy, T., Zhang, N., Dissanayake, G. & Wang, M. 2003, 'Free Vibrational Analysis of Vehicle Powertrain Equipped With a Half Toroidal CVT', Proceedings of the 10th Asia-Pacific Vibration Conference, Asia Pacific Vibration Conference, Queensland University of Technology, Gold Coast, Queensland, Australia, pp. 109-114.
View/Download from: UTS OPUS
Liu, D., Lau, H. & Dissanayake, G. 2003, 'A Hierachical Approach and A Multilevel Genetic Algorithm For Vehicle Path Plan', Proceedings of International Conference on Computational Intelligence, Robotics and Autonomous Systems, International Conference on Computational Intelligence, Robotics and Autonomous Systems, Centre for Intelligent Control, National University of Singapore, Singapore, pp. 1-6.
Kwok, N. & Dissanayake, G. 2003, 'Bearing-only SLAM in Indoor Environments Using a Modified Particle Filter', Proceedings of the Australasian Conference on Robotics & Automation 2003, Australasian Conference on Robotics and Automation, University of Queensland, Brisbane, Australia, pp. 1-8.
View/Download from: UTS OPUS
Furukawa, T., Durrant-Whyte, H., Bourgault, F. & Dissanayake, G. 2003, 'Time-Optimal Coordinated Control of the Relative Formation of Multiple Vehicles', Proceedings of 2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation, IEEE International Symposium on Computational Intelligence in Robotics and Automation, IEEE Operations Centre, Kobe, Japan, pp. 259-264.
View/Download from: UTS OPUS
This paper presents a solution to the time-optimal control of the relative formation of multiple vehicles. This is a problem in cooperative time-optimal control with a free terminal state constraint. In this paper, a canonical formulation of the problem is first derived. Then, a numerical technique to solve this class of problem is proposed. Numerical results demonstrate the efficacy of the proposed formulation and solution to the problem of expeditiously building and controlling formations of cooperative autonomous vehicles.
Furukawa, T., Durrant-Whyte, H., Dissanayake, G. & Sukkarieh, S. 2003, 'The Coordination of Multiple UAVs for Engaging Multiple Targets in a Time-Optimal Manner', Proceedings of the 2003 IEEE/RSJ International Symposium on Intelligence Robotics and Systems (IROS2003), IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE Service Centre, Las Vegas, USA, pp. 36-41.
View/Download from: UTS OPUS or Publisher's site
This paper presents a solution to the real-time control of cooperative unmanned air vehicles (UAVs) that engage multiple targets in a time-optimal manner. Techniques to dynamically allocate vehicles to targets and to find the time-optimal control actions of vehicles are proposed. The effectiveness of the time-optimal control technique is first demonstrated through numerical examples. The proposed strategy is then applied to a practical battlefield problem where ten vehicles are required to engage four targets, and numerical results show the efficiency of the proposed strategy.
Goktogan, A.H., Furukawa, T., Mathews, G., Sukkarieh, S. & Dissanayake, G. 2003, 'Time-Optimal Cooperation of Multiple UAVs in Real-Time Simulation', Proceedings of the 2nd Computational Intelligence, Robotics and Autonomous Systems (CIRAS 2003), International Conference on Computational Intelligence, Robotics and Autonomous Systems, National University of Singapore, Singapore, pp. 1-6.
View/Download from: UTS OPUS
Kwok, N. & Dissanayake, G. 2003, 'Simultaneous Localization and Mapping in Unstructured Indoor Environments', Proceedings for the 2nd International Conference on Computational Intelligence, Robotics and Autonomous Systems (CIRAS 2003), International Conference on Computational Intelligence, Robotics and Autonomous Systems, Centre for Intelligent Control, National University of Singapore, Singapore, pp. 1-6.
View/Download from: UTS OPUS
Furukawa, T., Durrant-Whyte, H.F. & Dissanayake, G. 2003, 'Time-optimal cooperative control of multiple robot vehicles', Proceedings - IEEE International Conference on Robotics and Automation, pp. 944-950.
This paper presents a formulation and solution of the time-optimal control of multiple cooperative robot vehicles. In particular, a group of robot vehicles reaching a terminal state in absolute and/or relative formations in minimum-time is addressed. A canonical formulation of the problem is first derived and a numerical technique, which can effectively solve this class of problems, is then proposed. Numerical results are presented to demonstrate the efficacy of the proposed formulation and method of solution. The techniques described offer a practical solution to the problem of building and controlling formations of cooperative autonomous vehicles in real-time.
Williams, S.B., Durrant-Whyte, H. & Dissanayake, G. 2003, 'Constrained initialization of the simultaneous localization and mapping algorithm', International Journal of Robotics Research, pp. 541-564.
In this paper we present a novel feature initialization technique for the Simultaneous Localization and Mapping (SLAM) algorithm. The initialization scheme extends previous approaches for identifying new confirmed features and is shown to improve the steady-state performance of the filter by incorporating tentative features into the filter as soon as they are observed. Constraints are then applied between multiple feature estimates when a feature is confirmed. Observations that are subsequently deemed as spurious are removed from the state vector after an appropriate timeout. It is shown that information that would otherwise be lost can therefore be used consistently in the filter. Results of this algorithm applied to data collected using a submersible vehicle are also shown.
Dissanayake, G.M., Fayek, A.R., Campero, O. & Wolf, H. 2003, 'Measuring and classifying construction field rework: A pilot study', Proceedings, Annual Conference - Canadian Society for Civil Engineering, pp. 1-7.
This paper describes the design and analysis of a pilot study on construction field rework measurement and classification. A definition of field rework, components of the field rework index and a detailed 3-tier classification system for the causes of rework are presented. The data collection and reporting methodology to create the field rework index and classification are discussed in detail, together with an implementation strategy. The pilot study findings are presented, to illustrate the types of analyses that are possible using the methodology developed. Identified industry challenges for implementing the proposed methodology are discussed, together with their solutions. A discussion of how the methodology can be expanded and used on future projects concludes the paper.
Madhavan, R., Durrant-Whyte, H. & Dissanayake, G. 2002, 'Natural landmark-based autonomous navigation using curvature scale space', Proceedings of IEEE International Conference on Robotics and Automation - Vol 4, IEEE International Conference on Robots and Automation, Institute of Electrical and Electronic Engineering, Washington DC,USA, pp. 3936-3941.
View/Download from: UTS OPUS or Publisher's site
The paper describes a terrain-aided navigation system that employs points of maximum curvature extracted from laser scan data as primary landmarks. A scale space method is used to extract points of maximum curvature from laser range scans of unmodified outdoor environments. This information is then fused with odometric information to provide localization information for an outdoor vehicle. The method described is invariant to the size and orientation of the range images under consideration (with respect to rotation and translation), is robust to noise, and can reliably detect and localize naturally occurring landmarks in the operating environment. The algorithm is demonstrated in the application of a road vehicle in an unmodified operating domain.
Leal, J., Scheding, S. & Dissanayake, G. 2002, 'Stochastic simulation in surface reconstruction and application to 3D mapping', Proceedings of IEEE International Conference on Robotics and Automation - Vol 2, IEEE International Conference on Robots and Automation, Institute of Electrical and Electronic Engineering, Washington DC,USA, pp. 1765-1770.
View/Download from: UTS OPUS or Publisher's site
Three dimensional terrain maps are useful representations of environments for various robotic applications. Unfortunately, sensor data (from which such maps are built) is uncertain and contains errors which are usually not accounted for in existing terrain building algorithms. In real-time applications, it is necessary to quantify these uncertainties to allow map construction decisions to be made online. This paper addresses this issue by providing a representation that explicitly accounts for sensing uncertainty. This is achieved through the use of stochastic simulation techniques. The result is in an algorithm for online 3D multiresolution surface reconstruction of unknown, and unstructured environments. Results of the surface reconstruction algorithm in a real environment are presented.
Williams, S.B., Dissanayake, G. & Durrant-Whyte, H. 2002, 'An efficient solution to the simultaneous localisation and mapping problem', Proceedings of IEEE International Conference on Robotics and Automation - vol 1, IEEE International Conference on Robots and Automation, Institute of Electrical and Electronic Engineering, Washington DC,USA, pp. 406-411.
View/Download from: UTS OPUS or Publisher's site
This paper presents a novel approach to the simultaneous localisation and mapping algorithm that exploits the manner in which observations are fused into the global map of the environment to manage the computational complexity of the algorithm and improve the data association process. Rather than incorporating every observation directly into the global map of the environment, the constrained local submap filter relies on creating an independent, local submap of the features in the immediate vicinity of the vehicle. This local submap is then periodically fused into the global map of the environment using appropriately formulated constraints between the common feature estimates. This approach is shown to be effective in reducing the computational complexity of maintaining the global map estimates as well as improving the data association process.
Williams, S.B., Dissanayake, G. & Durrant-Whyte, H. 2002, 'Towards multi-vehicle simultaneous localisation and mapping', Proceedings of IEEE International Conference on Robotics and Automation - Vol 3, IEEE International Conference on Robots and Automation, Institute of Electrical and Electronic Engineering, Washington DC,USA, pp. 2743-2748.
View/Download from: UTS OPUS or Publisher's site
This paper presents a novel approach to the multi-vehicle simultaneous localisation and mapping (SLAM) problem that exploits the manner in which observations are fused into the global map of the environment to manage the computational complexity of the algorithm and improve the data association process. Rather than incorporating every observation directly into the global map of the environment, the constrained local submap filter (CLSF) relies on creating an independent, local submap of the features in the immediate vicinity of the vehicle. This local submap is then periodically fused into the global map of the environment. This representation is shown to reduce the computational complexity of maintaining the global map estimates as well as improving the data association process. This paper examines the prospect of applying the CLSF algorithm to the multi-vehicle SLAM problem
Fang, G. & Dissanayake, G. 2002, 'Time-optimal feedback control of a non-holonomic vehicle using neural networks', Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002, pp. 1458-1463.
This paper presents a minimum-time feedback controller for maneuvering a non-holonomic vehicle. A trajectory planning algorithm that generates minimum-time trajectories for moving a vehicle from an arbitrary starting location to the origin is presented. Trajectories generated are used to train a neural network that computes instantaneous velocity and steering commands as a function of the current vehicle state. The proposed strategy is illustrated by developing a neural network based controller for backing up a truck. Computer simulations are presented that demonstrates the effectiveness of the proposed technique in the presence of disturbances.
Durrant-Whyte, H., Nebot, E. & Dissanayake, G. 2001, 'Autonomous localisation and map building in large-scale unstructured environments', Learning 2001, USA, pp. 1-2.
Williams, S.B., Dissanayake, G. & Durrant-Whyte, H. 2001, 'Constrained initialisation of the simultaneous localisation and mapping algorithm', FSR2001 Proc. Int. Conf. on Field and Service Robotics, International Conference on Field and Service Robotics, Helsinki, pp. 315-320.
Dissanayake, G. & Furukawa, T. 2001, 'Model parameter identification of autonomous vehicles', In Proc. of the 2001 Australian Conf. on Robotics and Automation, Australasian Conference on Robotics and Automation, Australia, pp. 32-37.
Furukawa, T., Yoshimura, S. & Dissanayake, G. 2001, 'Human-like Optimisation for Computational Design', Proc. Int. Conf. on Computational Engineering and Sciences, Mexico, pp. 1-6.
Williams, S.B., Dissanayake, G. & Durrant-Whyte, H. 2001, 'Efficient Simultaneous Localisation and Mapping Using Local Submaps', Proc. Australian Conf. on Robotics and Automation, Australasian Conference on Robotics and Automation, Australia, pp. 128-134.
Leal, J., Dissanayake, G. & Scheding, S. 2001, 'Three-dimensional terrain mapping: a stochastic approach', Proc. Australian Conf. on Robotics and Automation, Australasian Conference on Robotics and Automation, Sydney, pp. 135-140.
Gibbens, P.W., Dissanayake, G.M.W.M. & Durrant-Whyte, H.F. 2000, 'A closed form solution to the single degree of freedom simultaneous localisation and map building (SLAM) problem', Proceedings of the IEEE Conference on Decision and Control, pp. 191-196.
This paper presents a closed form solution to the estimation-theoretic simultaneous localisation and map building (SLAM) problem. The solution is obtained by explicit solution of the differential Riccati equation associated with then n-landmark SLAM problem. The solution describes and explains the many experimental and theoretical results obtained so far in the study of the SLAM problem. Further, the solution, for the first time, allows a precise means of analysing the performance of different SLAM algorithms and enables the design of efficient SLAM systems.
Williams, S.B., Newman, P., Dissanayake, G. & Durrant-Whyte, H. 2000, 'Autonomous underwater simultaneous localisation and map building', Proceedings - IEEE International Conference on Robotics and Automation, pp. 1793-1798.
In this paper we present results of the application of a Simultaneous Localisation and Map building (SLAM) algorithm to estimate the motion of a submersible vehicle. Scans obtained from an on-board sonar are processed to extract stable point features in the environment. These point features are then used to build up a map of the environment while simultaneously providing estimates of the vehicle location. Results are shown from deployment in a swimming pool at the University of Sydney as well as from field trials in a natural environment along Sydney's coast. This work represents the first instance of a deployable underwater implementation of the SLAM algorithm.
Dissanayake, G., Durrant-Whyte, H. & Bailey, T. 2000, 'Computationally efficient solution to the simultaneous localisation and map building (SLAM) problem', Proceedings - IEEE International Conference on Robotics and Automation, pp. 1009-1014.
The theoretical basis of the solution to the simultaneous localisation and map building (SLAM) problem where an autonomous vehicle starts in an unknown location in an unknown environment and then incrementally build a map of landmarks present in this environment while simultaneously using this map to compute absolute vehicle location is now well understood. Although a number of SLAM implementations have appeared in the recent literature, the need to maintain the knowledge of the relative relationships between all the landmark location estimates contained in the map makes SLAM computationally intractable in implementations containing more than few tens of landmarks. In this paper, the theoretical basis and a practical implementation of a computationally efficient solution to SLAM is presented. The paper shows that it is indeed possible to remove a large percentage of the landmarks from the map without making the map building process statistically inconsistent. Furthermore, it is shown that the efficiency of the SLAM can be maintained by judicious selection of landmarks, to be preserved in the map, based on their information content.
Scheding, S., Dissanayake, G., Nebot, E. & Durrant-Whyte, H. 1997, 'Slip modelling and aided inertial navigation of an LHD', Proceedings - IEEE International Conference on Robotics and Automation, pp. 1904-1909.
This paper describes the theoretical development and experimental evaluation of a guidance system for an autonomous Load, Haul and Dump truck (LHD) for use in underground mining. The particular contributions of this paper are in designing the navigation system to be able to cope with vehicle slip in rough uneven terrain using information from an Inertial Navigation System (INS) and a bearing only laser. Results are presented using data obtained during field trials.
Scheding, S., Dissanayake, G., Nebot, E. & Durrant-Whyte, H. 1996, 'Inertially aided navigation system for an LHD', Proceedings of the Australian Data Fusion Symposium, pp. 77-82.
This paper describes the theoretical development and experimental evaluation of a guidance system for an autonomous Load, Haul and Dump truck (LHD) for use in underground mining. The particular contributions of this paper are in designing the navigation system to be able to cope with vehicle slip in rough uneven terrain using information from an Inertial Navigation System (INS) and a bearing only laser. Results are presented using data obtained during field trials.
Dissanayake, M.W.M.G. & Poo, A.N. 1988, 'Robot trajectory planning for minimising residual vibrations', pp. 471-474.
An investigation into the effect of the trajectory shape on resulting arm vibrations is presented based on the concept of the shock spectrum. A method to obtain trajectories whose shock spectrum has prescribed properties is briefly described, and some preliminary results are presented. A comparison of various trajectory planning algorithms, in terms of their effectiveness in reducing residual vibrations and the move time, is given. Two performance indices are defined to quantify the information obtained through the shock spectrum and the move time analysis. The superiority of a trajectory based on the simultaneous minimization of the time of travel and residual response is illustrated.
Pham, D.T. & Dissanayake, M.W.M.G. 1985, 'INERTIA-BASED SENSORS WITH ONE AND TWO DEGREES OF FREEDOM FOR LOCATING PARTS.', pp. 223-237.
Two inertia-based sensors for determining the position and orientation of three-dimensional objects are described. One of them involves letting the objects vibrate about two orthogonal axes simultaneously and measuring the angles and velocities of vibration at various instants of time. In the other sensor, the objects are also vibrated about two axes but the vibrations are performed sequentially and the frequencies of vibration are measured. The mathematical procedures for obtaining the position and orientation of the objects from the measurements are outlined for the second sensor. Results of the computer simulations carried out to assess the feasibility of the latter are presented.
Pham, D.T. & Dissanayake, G. 1985, 'FEASIBILITY STUDY OF A VIBRATORY SENSOR FOR LOCATING 3-D OBJECTS.', Proceedings of the International Machine Tool Design and Research Conference, pp. 201-211.
A novel sensor is investigated which is intended to be mounted at the wrist of a robot to enable it to determine the co-ordinates of a part it has picked up from a stack or tray. The device operates by letting the part vibrate about two orthogonal axes and measuring its inertia-dependent instantaneous velocities and angles of vibration. The mathematical procedures for extracting position and orientation data from these measurements are described. The results of computer simulations carried out to determine guidelines for the design of the device are presented and discussed.
Pham, D.T. & Dissanayake, M.W.M.G. 1985, 'THREE-DEGREE-OF-FREEDOM INERTIAL SENSOR FOR LOCATING PARTS.', pp. 613-629.
A compromise solution to the problem of economically feeding parts to industrial robots is investigated. The parts are neither accurately presented as in the case of traditional feeding equipment nor jumbled up as in the case of bin-picking machines. Instead, they are semi-ordered into stacks or trays and then unloaded by the robots as needed. The robots are to be equipped with a novel sensor fitted to their wrists for determining the exact coordinates of the parts they have picked up. The device operates by letting the parts vibrate about three orthogonal axes and measuring their inertia-dependent natural frequencies of vibration. The mathematical procedures for extracting position and orientation data from those measurements are described. The results of computer simulations carried out to determine guidelines for the design of the device are presented and discussed.

Journal articles

Kodagoda, S., Sehestedt, S.A. & Dissanayake, G. 2016, 'Socially aware path planning for mobile robots', Robotica, vol. 34, no. 3, pp. 513-526.
View/Download from: UTS OPUS or Publisher's site
Humanrobot interaction is an emerging area of research where a robot may need to be working in human-populated environments. Human trajectories are generally not random and can belong to gross patterns. Knowledge about these patterns can be learned through observation. In this paper, we address the problem of a robot's social awareness by learning human motion patterns and integrating them in path planning. The gross motion patterns are learned using a novel Sampled Hidden Markov Model, which allows the integration of partial observations in dynamic model building. This model is used in the modified A* path planning algorithm to achieve socially aware trajectories. Novelty of the proposed method is that it can be used on a mobile robot for simultaneous online learning and path planning. The experiments carried out in an office environment show that the paths can be planned seamlessly, avoiding personal spaces of occupants.
Nguyen, L.V., Kodagoda, S., Ranasinghe, R. & Dissanayake, G. 2016, 'Information-Driven Adaptive Sampling Strategy for Mobile Robotic Wireless Sensor Network', IEEE Transactions on Control Systems Technology, vol. 24, no. 1, pp. 372-379.
View/Download from: UTS OPUS or Publisher's site
This brief addresses the issue of monitoring physical spatial phenomena of interest using information collected by a resource-constrained network of mobile, wireless, and noisy sensors that can take discrete measurements as they navigate through the environment. We first propose an efficient novel optimality criterion for designing a sampling strategy to find the most informative locations in taking future observations to minimize the uncertainty at all unobserved locations of interest. This solution is proven to be within bounds. The computational complexity of this proposition is shown to be practically feasible. We then prove that under a certain condition of monotonicity property, the approximate entropy at resulting locations obtained by our proposed algorithm is within 1-(1/e) of the optimum, which is then utilized as a stopping criterion for the sampling algorithm. The criterion enables the prediction results to be within user-defined accuracies by controlling the number of mobile sensors. The effectiveness of the proposed method is illustrated using a prepublished data set.
Norouzi, M., Valls Miro, J. & Dissanayake, G. 2016, 'Probabilistic stable motion planning with stability uncertainty for articulated vehicles on challenging terrains', Autonomous Robots, vol. 40, no. 2, pp. 361-381.
View/Download from: UTS OPUS or Publisher's site
&copy; 2015, Springer Science+Business Media New York. A probabilistic stable motion planning strategy applicable to reconfigurable robots is presented in this paper. The methodology derives a novel statistical stability criterion from the cumulative distribution of a tip-over metric. The measure is dynamically updated with imprecise terrain information, localization and robot kinematics to plan safety-constrained paths which simultaneously allow the widest possible visibility of the surroundings by simultaneously assuming highest feasible vantage robot configurations. The proposed probabilistic stability metric allows more conservative poses through areas with higher levels of uncertainty, while avoiding unnecessary caution in poses assumed at well-known terrain sections. The implementation with the well known grid based A* algorithm and also a sampling based RRT planner are presented. The validity of the proposed approach is evaluated with a multi-tracked robot fitted with a manipulator arm and a range camera using two challenging elevation terrains data sets: one obtained whilst operating the robot in a mock-up urban search and rescue arena, and the other from a publicly available dataset of a quasi-outdoor rover testing facility.
Takami, K., Furukawa, T., Kumon, M., Kimoto, D. & Dissanayake, G. 2016, 'Estimation of a nonvisible field-of-view mobile target incorporating optical and acoustic sensors', Autonomous Robots, vol. 40, no. 2, pp. 343-359.
View/Download from: Publisher's site
&copy; 2015, Springer Science+Business Media New York. This paper presents a nonvisible field-of-view (NFOV) target estimation approach that incorporates optical and acoustic sensors. An optical sensor can accurately localize a target in its field-of-view whereas the acoustic sensor could estimate the target location over a much larger space, but only with limited accuracy. A recursive Bayesian estimation framework where observations of the optical and acoustic sensors are probabilistically treated and fused is proposed in this paper. A technique to construct the observation likelihood when two microphones are used as the acoustic sensor is also described. The proposed technique derives and stores the interaural level difference of observations from the two microphones for different target positions in advance and constructs the likelihood through correlation. A parametric study of the proposed acoustic sensing technique in a controlled test environment, and experiments with an NFOV target in an actual indoor environment are presented to demonstrate the capability of the proposed technique.
Ryu, K., Dantanarayana, L., Furukawa, T. & Dissanayake, G. 2016, 'Grid-based Scan-to-Map Matching for Accurate 2D Map Building', Advanced Robotics, vol. 30, no. 7, pp. 431-448.
View/Download from: UTS OPUS or Publisher's site
This paper presents a grid-based scan-to-map matching technique for accurate 2D map building. At every acquisition of a new scan, the proposed technique matches the new scan to the previous scan similarly to the conventional techniques, but further corrects the error by matching the new scan to the globally defined map. In order to achieve best scan-to-map matching at each acquisition, the map is represented as a grid map with multiple normal distributions (NDs) in each cell, which is one contribution of this paper. Additionally, the new scan is also represented by NDs, developing a novel ND-to-ND matching technique. This ND-to-ND matching technique has significant potential in the enhancement of the global matching as well as the computational efficiency. Experimental results first show that the proposed technique accumulates very small errors after consecutive matchings and identifies that the scans are matched better to the map with the multi-ND representation than one ND representation. The proposed t...
Wang, H., Huang, S., Khosoussi, K., Frese, U., Dissanayake, G. & Liu, B. 2015, 'Dimensionality reduction for point feature SLAM problems with spherical covariance matrices', Automatica, vol. 51, pp. 149-157.
View/Download from: UTS OPUS or Publisher's site
&copy; 2014 Elsevier Ltd. All rights reserved. The main contribution of this paper is the dimensionality reduction for multiple-step 2D point feature based Simultaneous Localization and Mapping (SLAM), which is an extension of our previous work on one-step SLAM (Wang et al.; 2013). It has been proved that SLAM with multiple robot poses and a number of point feature positions as variables is equivalent to an optimization problem with only the robot orientations as variables, when the associated uncertainties can be described using spherical covariance matrices. This reduces the dimension of original problem from 3m+2n to m only (where m is the number of poses and n is the number of features). The optimization problem after dimensionality reduction can be solved numerically using the unconstrained optimization algorithms. While dimensionality reduction may not provide computational saving for all nonlinear optimization problems, for some SLAM problems we can achieve benefits such as improvement on time consumption and convergence. For the special case of two-step SLAM when the orientation information from odometry is not incorporated, an algorithm that can guarantee to obtain the globally optimal solution (in the maximum likelihood sense) is derived. Simulation and experimental datasets are used to verify the equivalence between the reduced nonlinear optimization problem and the original full optimization problem, as well as the proposed new algorithm for obtaining the globally optimal solution for two-step SLAM.
Zhao, L., Huang, S., Yan, L. & Dissanayake, G. 2015, 'A new feature parametrization for monocular SLAM using line features', Robotica, vol. 33, no. 3, pp. 513-536.
View/Download from: UTS OPUS or Publisher's site
&copy; 2014 Cambridge University Press. This paper presents a new monocular SLAM algorithm that uses straight lines extracted from images to represent the environment. A line is parametrized by two pairs of azimuth and elevation angles together with the two corresponding camera centres as anchors making the feature initialization relatively straightforward. There is no redundancy in the state vector as this is a minimal representation. A bundle adjustment (BA) algorithm that minimizes the reprojection error of the line features is developed for solving the monocular SLAM problem with only line features. A new map joining algorithm which can automatically optimize the relative scales of the local maps is used to combine the local maps generated using BA. Results from both simulations and experimental datasets are used to demonstrate the accuracy and consistency of the proposed BA and map joining algorithms.
Sun, Y., Zhao, L., Huang, S., Yan, L. & Dissanayake, G. 2015, 'Line matching based on planar homography for stereo aerial images', ISPRS Journal of Photogrammetry and Remote Sensing, vol. 104, pp. 1-17.
View/Download from: UTS OPUS or Publisher's site
&copy; 2015 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). We propose an efficient line matching algorithm for a pair of calibrated aerial photogrammetric images, which makes use of sparse 3D points triangulated from 2D point feature correspondences to guide line matching based on planar homography. Two different strategies are applied in the proposed line matching algorithm for two different cases. When three or more points can be found coplanar with the line segment to be matched, the points are used to fit a plane and obtain an accurate planar homography. When one or two points can be found, the approximate terrain plane parallel to the line segment is utilized to compute an approximate planar homography. Six pairs of rural or urban aerial images are used to demonstrate the efficiency and validity of the proposed algorithm. Compared with line matching based on 2D point feature correspondences, the proposed method can increase the number of correctly matched line segments. In addition, compared with most line matching methods that do not use 2D point feature correspondences, the proposed method has better efficiency, although it obtains fewer matches. The C/C++ source code for the proposed algorithm is available at http://services.eng.uts.edu.au/~sdhuang/research.htm.
Zhao, L., Huang, S., Sun, Y., Yan, L. & Dissanayake, G. 2015, 'ParallaxBA: Bundle adjustment using parallax angle feature parametrization', International Journal of Robotics Research, vol. 34, no. 4-5, pp. 493-516.
View/Download from: UTS OPUS or Publisher's site
&copy;The Author(s) 2015. The main contribution of this paper is a novel feature parametrization based on parallax angles for bundle adjustment (BA) in structure and motion estimation from monocular images. It is demonstrated that under certain conditions, describing feature locations using their Euclidean XYZ coordinates or using inverse depth in BA leads to ill-conditioned normal equations as well as objective functions that have very small gradients with respect to some of the parameters describing feature locations. The proposed parallax angle feature parametrization in BA (ParallaxBA) avoids both of the above problems leading to better convergence properties and more accurate motion and structure estimates. Simulation and experimental datasets are used to demonstrate the impact of different feature parametrizations on BA, and the improved convergence, efficiency and accuracy of the proposed ParallaxBA algorithm when compared with some existing BA packages such as SBA, sSBA and g2o. The C/C++ source code of ParallaxBA is available on OpenSLAM (https://openslam.org/).
Cai, B., Huang, S., Liu, D. & Dissanayake, G. 2014, 'Rescheduling policies for large-scale task allocation of autonomous straddle carriers under uncertainty at automated container terminals', Robotics And Autonomous Systems, vol. 62, pp. 506-514.
View/Download from: UTS OPUS or Publisher's site
This paper investigates replanning strategies for container transportation task allocation of autonomous Straddle Carriers (SC) at automated container terminals. The strategies address the problem of large-scale scheduling in the context of uncertainty (especially uncertainty associated with unexpected events such as the arrival of a new task). Two rescheduling policies Rescheduling New arrival Jobs (RNJ) policy and Rescheduling Combination of new and unexecuted Jobs (RCJ) policy are presented and compared for long-term Autonomous SC Scheduling (ASCS) under the uncertainty of new job arrival. The long-term performance of the two rescheduling policies is evaluated using a multi-objective cost function (i.e., the sum of the costs of SC travelling, SC waiting, and delay of finishing high-priority jobs). This evaluation is conducted based on two different ASCS solving algorithms an exact algorithm (i.e., branch-and-bound with column generation (BBCG) algorithm) and an approximate algorithm (i.e., auction algorithm) to get the schedule of each short-term planning for the policy. Based on the map of an actual fully-automated container terminal, simulation and comparative results demonstrate the quality advantage of the RCJ policy compared with the RNJ policy for task allocation of autonomous straddle carriers under uncertainty. Long-term testing results also show that although the auction algorithm is much more efficient than the BBCG algorithm for practical applications, it is not effective enough, even when employed by the superior RCJ policy, to achieve high-quality scheduling of autonomous SCs at the container terminals.
Sun, Y., Zhao, L., Huang, S., Yan, L. & Dissanayake, G. 2014, 'L2-SIFT: SIFT feature extraction and matching for large images in large-scale aerial photogrammetry', ISPRS Journal of Photogrammetry and Remote Sensing, vol. 91, pp. 1-16.
View/Download from: UTS OPUS or Publisher's site
The primary contribution of this paper is an efficient feature extraction and matching implementation for large images in large-scale aerial photogrammetry experiments. First, a Block-SIFT method is designed to overcome the memory limitation of SIFT for extracting and matching features from large photogrammetric images. For each pair of images, the original large image is split into blocks and the possible corresponding blocks in the other image are determined by pre-estimating the relative transformation between the two images. Because of the reduced memory requirement, eatures can be extracted and matched from the original images without down-sampling. Next, a red-black tree data structure is applied to create a feature relationship to reduce the search complexity when matching tie points. Meanwhile, tree key exchange and segment matching methods are proposed to match the tie points along-track and across-track. Finally, to evaluate the accuracy of the features extracted and matched from the proposed L2-SIFT algorithm, a bundle adjustment with parallax angle feature parametrization (ParallaxBA) is applied to obtain the Mean Square Error (MSE) of the feature reprojections, where the feature extraction and matching result is the only information used in the nonlinear optimisation system. Seven different experimental aerial photogrammetric datasets are used to demonstrate the efficiency and validity of the proposed algorithm. It is demonstrated that more than 33 million features can be extracted and matched from the Taian dataset with 737 images within 21h using the L2-SIFT algorithm. In addition, the ParallaxBA involving more than 2.7 million features and 6 million image points can easily converge to an MSE of 0.03874. The C/C++ source code for the proposed algorithm is available at http://services.eng.uts.edu.au/~sdhuang/research.htm.
Patel, M., Valls Miro, J., Kragic, D., Ek, C.H. & Dissanayake, G. 2014, 'Learning object, grasping and manipulation activities using hierarchical HMMs', Autonomous Robots, vol. 37, no. 3, pp. 317-331.
View/Download from: UTS OPUS or Publisher's site
This article presents a probabilistic algorithm for representing and learning complex manipulation activities performed by humans in everyday life. The work builds on the multi-level Hierarchical Hidden Markov Model (HHMM) framework which allows decomposition of longer-term complex manipulation activities into layers of abstraction whereby the building blocks can be represented by simpler action modules called action primitives. This way, human task knowledge can be synthesised in a compact, effective representation suitable, for instance, to be subsequently transferred to a robot for imitation. The main contribution is the use of a robust framework capable of dealing with the uncertainty or incomplete data inherent to these activities, and the ability to represent behaviours at multiple levels of abstraction for enhanced task generalisation. Activity data from 3D video sequencing of human manipulation of different objects handled in everyday life is used for evaluation. A comparison with a mixed generative-discriminative hybrid model HHMM/SVM (support vector machine) is also presented to add rigour in highlighting the benefit of the proposed approach against comparable state of the art techniques. &copy; 2014 Springer Science+Business Media New York.
Skinner, B., Yuan, S., Huang, S., Liu, D., Cai, B., Dissanayake, G., Lau, H., Bott, A. & Pagac, D. 2013, 'Optimisation for job scheduling at automated container terminals using genetic algorithm', Computers and Industrial Engineering, vol. 64, no. 1, pp. 511-523.
View/Download from: UTS OPUS or Publisher's site
This paper presents a genetic algorithm (GA)-based optimisation approach to improve container handling operations at the Patrick AutoStrad container terminal located in Brisbane Australia. In this paper we focus on scheduling for container transfers and encode the problem using a two-part chromosome approach which is then solved using a modified genetic algorithm. In simulation experiments, the performance of the GA-based approach and a sequential job scheduling method are evaluated and compared with different scheduling scenarios. The experimental results show that the GA-based approach can find better solutions which improve the overall performance. The GA-based approach has been implemented in the terminal scheduling system and the live testing results show that the GA-based approach can reduce the overall time-related cost of container transfers at the automated container terminal
Khushaba, R.N., Kodagoda, S., Lal, S. & Dissanayake, G. 2013, 'Uncorrelated fuzzy neighborhood preserving analysis based feature projection for driver drowsiness recognition', Fuzzy Sets and Systems, vol. 221, no. 1, pp. 90-111.
View/Download from: UTS OPUS or Publisher's site
Driver drowsiness is reported as one of the main causal factors in many traffic accidents as it progressively impairs the driver's awareness about external events. Drowsiness detection can be approached through monitoring physiological signals while driving to correlate drowsiness with the change in the corresponding patterns of the Electroencephalogram (EEG), Electrooculogram (EOG), and Electrocardiogram (ECG) signals. The main challenge in such an approach is to extract a set of features that can highly discriminate between the different drowsiness levels. This paper proposes a new Fuzzy Neighborhood Preserving Analysis (FNPA) feature projection method that is used to extract the discriminant information relevant to the loss of attention caused by drowsiness. Unlike existing methods, FNPA considers the fuzzy memberships of the input measurements into the different classes while constructing the graph Laplacian. Thus, it is able to identify both the discriminant and the geometrical structure of the input data while accounting for the overlapping nature of the drowsiness patterns. Furthermore, in order to address the singularity problem that occurs in many real world problems, the singular value decomposition (SVD), and later the QR-Decomposition, are utilized to extract a set of statistically uncorrelated features presenting the Uncorrelated FNPA (UFNPA). In the current preliminary study with datasets collected from 31 subjects only, while performing a driving simulation task, the proposed method is capable of accurately classifying the drowsiness levels using a small number of features with an average accuracy of 93%93%. On the other hand, the possibility of developing a subject-independent drowsiness recognition system is also investigated when the problem is converted into a binary classification task, as imposed by the number of drowsiness levels exhibited by the drivers, with accuracies ranging from 82%-to-84%.
Khushaba, R.N., Kodagoda, S., Liu, D. & Dissanayake, G. 2013, 'Muscle Computer Interfaces for Driver Distraction Reduction', Computer Methods and Programs in Biomedicine, vol. 110, no. 2, pp. 137-149.
View/Download from: UTS OPUS or Publisher's site
Driver distraction is regarded as a significant contributor to motor-vehicle crashes. One of the important factors contributing to driver distraction was reported to be the handling and reaching of in-car electronic equipment and controls that usually requires taking the drivers' hands off the wheel and eyes off the road. To minimize the amount of such distraction, we present a new control scheme that senses and decodes the human muscles signals, denoted as Electromyogram (EMG), associated with different fingers postures/pressures, and map that to different commands to control external equipment, without taking hands off the wheel. To facilitate such a scheme, the most significant step is the extraction of a set of highly discriminative feature set that can well separate between the different EMG-based actions and to do so in a computationally efficient manner. In this paper, an accurate and efficient method based on Fuzzy Neighborhood Discriminant Analysis (FNDA), is proposed for discriminant feature extraction and then extended to the channel selection problem. Unlike existing methods, the objective of the proposed FNDA is to preserve the local geometrical and discriminant structures, while taking into account the contribution of the samples to the different classes. The method also aims to efficiently overcome the singularity problems of classical LDA by employing the QR-decomposition. Practical real-time experiments with eight EMG sensors attached on the human forearm of eight subjects indicated that up to fourteen classes of fingers postures/pressures can be classified with <7% error on average, proving the significance of the proposed method.
Wang, H., Huang, S., Frese, U. & Dissanayake, G. 2013, 'The nonlinearity structure of point feature SLAM problems with spherical covariance matrices', Automatica, vol. 49, pp. 3112-3119.
View/Download from: UTS OPUS or Publisher's site
This paper proves that the optimization problem of one-step point feature Simultaneous Localization and Mapping (SLAM) is equivalent to a nonlinear optimization problem of a single variable when the associated uncertainties can be described using spherical covariance matrices. Furthermore, it is proven that this optimization problem has at most two minima. The necessary and sufficient conditions for the existence of one or two minima are derived in a form that can be easily evaluated using observation and odometry data. It is demonstrated that more than one minimum exists only when the observation and odometry data are extremely inconsistent with each other. A numerical algorithm based on bisection is proposed for solving the one-dimensional nonlinear optimization problem. It is shown that the approach extends to joining of two maps, thus can be used to obtain an approximate solution to the complete SLAM problem through map joining.
Cai, B., Huang, S., Liu, D., Yuan, S., Dissanayake, G., Lau, H. & Pagac, D. 2013, 'Multi-objective optimization for autonomous straddle carrier scheduling at automated container terminals', IEEE Transactions on Automation Science and Engineering, vol. 10, no. 3, pp. 711-725.
View/Download from: UTS OPUS or Publisher's site
A multiobjective optimization model is presented in this paper for the Autonomous Straddle Carriers Scheduling (ASCS) problem in automated container terminals, which is more practical than the single objective model. The model considers three objectives [i.e., Straddle Carriers (SCs) traveling time, SC waiting time and finishing time of high-priority container-transferring jobs], and their weighted sum is investigated as the representative example. The presented model is formulated as a pickup and delivery problem with time windows in the form of binary integer programming. An exact algorithm based on Branch-and-Bound with Column Generation (BBCG) is employed for solving the multiobjective ASCS problem. Based on the map of an actual fully automated container terminal, simulation results are compared with the single-objective scheduling to demonstrate the effectiveness and flexibility of the presented multiobjective model, as well as the efficacy of the BBCG algorithm for autonomous SC scheduling.
Abeywardena, D.M., Kodagoda, S., Dissanayake, G. & Munasinghe, R. 2013, 'Improved State Estimation in Quadrotor MAVs: A Novel Drift-Free Velocity Estimator', IEEE Robotics and Automation Magazine, vol. 20, no. 4, pp. 32-39.
View/Download from: UTS OPUS or Publisher's site
In this article, we presented a novel state estimator for quadrotor MAVs, where clear improvements in estimates stemming from the incorporation of quadrotor-specific dynamical constraints were demonstrated. Our design is based on an EKF and is capable of estimating both roll and pitch angles of the attitude, in addition to X and Y components of the body frame translational velocities within a bounded error. This estimator is applied to inertial data gathered from real-world flight experiments. The resulting attitude and velocity estimates obtained match closely with the ground truth and are drift free.
Khushaba, R.N., Kodagoda, S., Takruri, M.S. & Dissanayake, G. 2012, 'Toward Improved Control Of Prosthetic Fingers Using Surface Electromyogram (EMG) Signals', Expert Systems with Applications, vol. 39, no. 12, pp. 10731-10738.
View/Download from: UTS OPUS or Publisher's site
A fundamental component of many modern prostheses is the myoelectric control system, which uses the electromyogram (EMG) signals from an individual's muscles to control the prosthesis movements. Despite the extensive research focus on the myoelectric con
Herath, D.C., Kodagoda, S. & Dissanayake, G. 2012, 'A Two-Tier Map Representation For Compact-Stereo-Vision-Based SLAM', Robotica, vol. 30, pp. 245-256.
View/Download from: UTS OPUS or Publisher's site
Vision sensors are increasingly being used in the implementation of Simultaneous Localization and Mapping (SLAM). Even though the mathematical framework of SLAM is well understood, considerable issues remain to be resolved when a particular sensing modal
Khushaba, R.N., Greenacre, L.M., Kodagoda, S., Louviere, J.J., Burke, S. & Dissanayake, G. 2012, 'Choice modeling and the brain: A study on the Electroencephalogram (EEG) of preferences', Expert Systems with Applications, vol. 39, no. 16, pp. 12378-12388.
View/Download from: UTS OPUS or Publisher's site
Choice conjures the idea of a directed selection of a desirable action or object, motivated by internal likes and dislikes, or other such preferences. However, such internal processes are simply the domain of our human physiology. Understanding the physiological processes of decision making across a variety of contexts is a central aim in decision science as it has a great potential to further progress decision research. As a pilot study in this field, this paper explores the nature of decision making by examining the associated brain activity, Electroencephalogram (EEG), of people to understand how the brain responds while undertaking choices designed to elicit the subjects preferences. To facilitate such a study, the Tobii-Studio eye tracker system was utilized to capture the participants choice based preferences when they were observing seventy-two sets of objects. These choice sets were composed of three images offering potential personal computer backgrounds. Choice based preferences were identified by having the respondent click on their preferred one. In addition, a brain computer interface (BCI) represented by the commercial Emotiv EPOC wireless EEG headset with 14 channels was utilized to capture the associated brain activity during the period of the experiments. Principal Component Analysis (PCA) was utilized to preprocess the EEG data before analyzing it with the Fast Fourier Transform (FFT) to observe the changes in the main principal frequency bands, delta (0.54 Hz), theta (47 Hz), alpha (812 Hz), beta (1330 Hz), and gamma (3040 Hz). A mutual information (MI) measure was then used to study left-to-right hemisphere differences as well as front-to-back difference.
Chotiprayanakul, P., Liu, D. & Dissanayake, G. 2012, 'Human-robot-environment Interaction Interface For Robotic Grit-blasting Of Complex Steel Bridges', Automation In Construction, vol. 27, no. NA, pp. 11-23.
View/Download from: UTS OPUS or Publisher's site
This paper presents a human-robot-environment interaction (HREI) interface using haptic feedback for a grit-blasting robot operating in close proximity to a complex steel bridge structure. The productivity requirements dictate the need for efficient algo
Khushaba, R.N., Kodagoda, S., Lal, S. & Dissanayake, G. 2011, 'Driver Drowsiness Classification Using Fuzzy Wavelet-Packet-Based Feature-Extraction Algorithm', IEEE Transactions On Biomedical Engineering, vol. 58, no. 1, pp. 121-131.
View/Download from: UTS OPUS or Publisher's site
Driver drowsiness and loss of vigilance are a major cause of road accidents. Monitoring physiological signals while driving provides the possibility of detecting and warning of drowsiness and fatigue. The aim of this paper is to maximize the amount of drowsiness-related information extracted from a set of electroencephalogram (EEG), electrooculogram (EOG), and electrocardiogram (ECG) signals during a simulation driving test. Specifically, we develop an efficient fuzzy mutual-information (MI)- based wavelet packet transform (FMIWPT) feature-extraction method for classifying the driver drowsiness state into one of predefined drowsiness levels. The proposed method estimates the required MI using a novel approach based on fuzzy memberships providing an accurate-information content-estimation measure. The quality of the extracted features was assessed on datasets collected from 31 drivers on a simulation test. The experimental results proved the significance of FMIWPT in extracting features that highly correlate with the different drowsiness levels achieving a classification accuracy of 95%-97% on an average across all subjects.
Paul, G., Webb, S.S., Liu, D. & Dissanayake, G. 2011, 'Autonomous Robot Manipulator-Based Exploration And Mapping System For Bridge Maintenance', Robotics And Autonomous Systems, vol. 59, no. 7-8, pp. 543-554.
View/Download from: UTS OPUS or Publisher's site
This paper presents a system for Autonomous eXploration to Build A Map (AXBAM) of an unknown, 3D complex steel bridge structure using a 6 degree-of-freedom anthropomorphic robot manipulator instrumented with a laser range scanner. The proposed algorithm considers the trade-off between the predicted environment information gain available from a sensing viewpoint and the manipulator joint angle changes required to position a sensor at that viewpoint, and then obtains collision-free paths through safe, previously explored regions. Information gathered from multiple viewpoints is fused to achieve a detailed 3D map. Experimental results show that the AXBAM system explores and builds quality maps of complex unknown regions in a consistent and timely manner.
Yuan, S., Skinner, B., Huang, S., Liu, D., Dissanayake, G., Lau, H. & Pagac, D. 2011, 'A job grouping approach for planning container transfers at automated seaport container terminals', Advanced Engineering Informatics, vol. 25, no. 3, pp. 413-426.
View/Download from: UTS OPUS or Publisher's site
This paper proposes a practical job grouping approach, which aims to enhance the time related performance metrics of container transfers in the Patrick AutoStrad container terminal, located in Brisbane, Australia. It first formulates a mathematical model of the automated container transfers in a relatively complex environment. Apart from the consideration on collision avoidance of a fleet of large vehicles in a confined area, it also deals with many other difficult practical challenges such as the presence of multiple levels of container stacking and sequencing, variable container orientations, and vehicular dynamics that require finite acceleration and deceleration times. The proposed job grouping approach aims to improve the makespan of the schedule for yard jobs, while reducing straddle carrier waiting time by grouping jobs using a guiding function. The performance of the current sequential job allocation method and the proposed job grouping approach are evaluated and compared statistically using a pooled t-test for 30 randomly generated yard configurations. The experimental results show that the job grouping approach can effectively improve the schedule makespan and reduce the total straddle carrier waiting time.
Besinger, A., Sztynda, T., Lal, S., Duthoit, C.J., Agbinya, J.I., Jap, B., Eager, D.M. & Dissanayake, G. 2010, 'Optical flow based analyses to detect emotion from human facial image data', Expert Systems with Applications, vol. 37, no. 12, pp. 8897-8902.
View/Download from: UTS OPUS or Publisher's site
Artificial recognition of facial expression has attracted a lot of attention in the last few years and different facial expression detection methods have been developed. The current study uses a feature point tracking technique separately applied to the five facial image regions (eyebrows, eyes and mouth) to capture basic emotions. The used dataset contains a total 60 facial images from subjects different genders and nationality not wearing glasses and/or facial hair. Results show that the used point tracking algorithm separately applied to the five facial image regions can detect emotions in image sequences.
Zhang, Z., Kodagoda, S., Ruiz, D., Katupitiya, J. & Dissanayake, G. 2010, 'Classification of Bidens in wheat farms', International Journal of Computer Applications in Technology, vol. 39, no. 1-3, pp. 123-129.
View/Download from: Publisher's site
Bidens pilosa L. (commonly known as cobbler's peg) is an annual broad leaf weed widely distributed in tropical and subtropical regions of the world and is reported to be a weed of 31 crops, including wheat. Automatic detection of Bidens in wheat farms is a non-trivial problem due to their similarity in colour and presence of occlusions. This paper proposes a methodology which could be used to discriminate Bidens from wheat to be used in operations such as autonomous weed destruction. A spectrometer is used to analyse the optical properties of Bidens and wheat leaves while achieving high classification results. However, due to the practical constraints of using spectrometers, a colour camera-based technique is proposed. It is shown that the colour-based segmentation followed by shape-based validation algorithm gives rise to high detection rates with lower false detections. We have experimentally evaluated the algorithm with Bidens detection rate of 80% and a false alarm rate of 10%. &copy; 2010 Inderscience Enterprises Ltd.
Pedraza, L., Rodriguez-Losada, D., Matia, F., Dissanayake, G. & Valls Miro, J. 2009, 'Extending the Limits of Feature-Based SLAM With B-Splines', IEEE Transactions On Robotics, vol. 25, no. 2, pp. 353-366.
View/Download from: UTS OPUS or Publisher's site
This paper describes a simultaneous localization and mapping (SLAM) algorithm for use in unstructured environments that is effective regardless of the geometric complexity of the environment. Features are described using B-splines as modeling tool, and the set of control points defining their shape is used to form a complete and compact description of the environment, thus making it feasible to use an extended Kalman-filter (EKF) based SLAM algorithm. This method is the first known EKF-SLAM implementation capable of describing general free-form features in a parametric manner. Efficient strategies for computing the relevant Jacobians, perform data association, initialization, and map enlargement are presented. The algorithms are evaluated for accuracy and consistency using computer simulations, and for effectiveness using experimental data gathered from different real environments.
Huang, S., Wang, Z., Dissanayake, G. & Frese, U. 2009, 'Iterated D-SLAM map joining: evaluating its performance in terms of consistency, accuracy and efficiency', Autonomous Robots, vol. 27, no. 4, pp. 409-429.
View/Download from: UTS OPUS or Publisher's site
This paper presents a new map joining algorithm and a set of metrics for evaluating the performance of mapping techniques. The input to the new map joining algorithm is a sequence of local maps containing the feature positions and the final robot pose in a local frame of reference. The output is a global map containing the global positions of all the features but without any robot poses. The algorithm is built on the D-SLAM mapping algorithm (Wang et al. in Int. J. Robot. Res. 26(2):187-204, 2007) and uses iterations to improve the estimates in the map joining step. So it is called Iterated D-SLAM Map Joining (I-DMJ). When joining maps I-DMJ ignores the odometry information connecting successive maps. This is the key to I-DMJ efficiency, because it makes both the information matrix exactly sparse and the size of the state vector bounded by the number of features. The paper proposes metrics for quantifying the performance of different mapping algorithms focusing on evaluating their consistency, accuracy and efficiency. The I-DMJ algorithm and a number of existing SLAM algorithms are evaluated using the proposed metrics. The simulation data sets and a preprocessed Victoria Park data set used in this paper are made available to enable interested researchers to compare their mapping algorithms with I-DMJ.
Paul, G., Liu, D., Kirchner, N.G. & Dissanayake, G. 2009, 'An Effective Exploration Approach to Simultaneous Mapping and Surface Material-Type Identification of Complex Three-Dimensional Environments', Journal of Field Robotics, vol. 26, no. 11-12, pp. 915-933.
View/Download from: UTS OPUS or Publisher's site
This paper presents an integrated exploration approach for geometric mapping and surface material-type identification of complex three-dimensional (3D) environments using a six-degree-of-freedom industrial robot manipulator. Maps of the surface geometry with the surface material type identified are required for an autonomous robotic system to perform operations in steel bridge maintenance. The proposed approach utilizes information theory to enable multiobjective exploration while new 3D geometric and surface-type data are fused via probabilistic updates. It is verified that the integrated approach enables the robotic system to perform exploration and surface inspection in real-world environments.
Kirchner, N.G., Liu, D. & Dissanayake, G. 2009, 'Surface Type Classification With a Laser Range Finder', IEEE Sensors Journal, vol. 9, no. 9, pp. 1160-1168.
View/Download from: UTS OPUS or Publisher's site
This paper presents a system for surface classification using a laser range finder. It is shown that the return intensities and range errors provide sufficient information to distinguish a wide range of surfaces commonly found in a number of environments. A supervised learning scheme (using curves representing the return intensity and range error as a function of angle of incidence) is used to classify the surface type of planar patches. Extensive experimental evidence is presented to demonstrate the potential of the proposed technique. The surface type classification, which uses a typical laser range finder, is targeted for use with autonomous robotic systems in which significantly different interaction is required for each of the various materials present. Results from an on-site experiment demonstrate that the information from the laser range finder is sufficient to identify the different materials (via their surface properties) present in a scene where a bridge structure is being prepared for grit blasting.
Valls Miro, J., Taha, T., Wang, D. & Dissanayake, G. 2008, 'An Adaptive Manoeuvring Strategy for Mobile Robots in Cluttered Dynamic Environments', International Journal of Automation and Control (IJAAC), vol. 2, no. 2/3, pp. 178-194.
View/Download from: UTS OPUS or Publisher's site
A novel method which combines an optimised global path planner with a real-time sensor-based collision avoidance mechanism to accommodate for dynamic changes in the environment (e.g., people) is presented. The basic concept is to generate a continually changing parameterised family of virtual force fields for the robot based on characteristics such as location, travelling speed and dimension of the objects in the vicinity, static and dynamic. The interactions among the repulsive forces associated with the various obstacles provide a natural way for local collision avoidance in a partially known cluttered environment. This is harnessed by locally modifying the planned behaviour of the moving platform in real-time, whilst preserving the optimised nature of the global path. Furthermore, path traversability is continually monitored by the global planner to trigger a complete path re-planning from the current location in case of major changes, most notably when the path is completely blocked by obstacles.
Kirchner, N.G., Hordern, D.L., Liu, D. & Dissanayake, G. 2008, 'Capacitive sensor for object ranging and material type identification', Sensors And Actuators A-Physical, vol. 148, no. 1, pp. 96-104.
View/Download from: UTS OPUS or Publisher's site
This paper presents a system for object ranging and material type identification using a multifrequency approach for a capacitive sensor. it is shown through an experimental study that the deviation in the readings taken at different sensor drive frequen
Lau, H., Huang, S. & Dissanayake, G. 2008, 'Discounted MEAN bound for the optimal searcher path problem with non-uniform travel times', European Journal Of Operational Research, vol. 190, no. 2, pp. 383-397.
View/Download from: UTS OPUS or Publisher's site
We consider an extension of the optimal searcher path problem (OSP), where a searcher moving through a discretised environment may now need to spend a non-uniform amount of time travelling from one region to another before being able to search it for the
Huang, S., Wang, Z. & Dissanayake, G. 2008, 'Sparse Local Submap Joining Filter for Building Large-Scale Maps', IEEE Transactions On Robotics, vol. 24, no. 5, pp. 1121-1130.
View/Download from: UTS OPUS or Publisher's site
This paper presents a novel local submap joining algorithm for building large-scale feature-based maps: sparse local submap joining filter (SLSJF). The input to the filter is a sequence of local submaps. Each local submap is represented in a coordinate f
Nguyen, A., Ngo, V., Ha, Q.P. & Dissanayake, G. 2008, 'Robotic formation: initialisation, trajectory planning and decentralised control', International Journal of Automation and Control, vol. 2, no. 1, pp. 22-45.
View/Download from: UTS OPUS or Publisher's site
Coordination of a group of mobile robots in desired formations requires an integration of motion planning and control strategies subject to communication bandwidth limitations. An architecture combining virtual structure and leader following techniques is proposed in this paper. The robots are initialised using a new Virtual Robot (VR) tracking and l&acirc;l control framework to establish an arbitrary formation without singularities involved and inter-robot collision. Path planning is performed using the modified A&acirc; search, coupled with a proposed smoothing technique to generate feasible trajectories with mobile robots, dynamic and kinematic constraints taken into account. Safe trajectories are obtained based on the predefined formation configuration and the given workspace, where obstacles are avoided by adjusting robot trajectories or by changing formation of the robots appropriately. To accommodate the restriction in information exchange, a decentralised approach is proposed to implement the global feedback controller for the formation by using linear functional observers. The proposed architecture is tested through simulation and experiments to verify its validity.
Zhou, W., Valls Miro, J. & Dissanayake, G. 2008, 'Information-Efficient 3-D Visual SLAM for Unstructured Domains', IEEE Transactions On Robotics, vol. 24, no. 5, pp. 1078-1087.
View/Download from: UTS OPUS or Publisher's site
This paper presents a novel vision-based sensory package and an information-efficient simultaneous localization and mapping (SLAM) algorithm. Together, we offer a solution for building 3-D dense map in an unknown and unstructured environment with minimal
Wang, Z.Z., Huang, S. & Dissanayake, G. 2007, 'D-SLAM: A decoupled solution to simultaneous localization and mapping', International Journal Of Robotics Research, vol. 26, no. 2, pp. 187-204.
View/Download from: UTS OPUS or Publisher's site
The main contribution of this paper is the reformulation of the simultaneous localization and mapping (SLAM) problem for mobile robots such that the mapping and localization can be treated as two concurrent yet separated processes D-SLAM (decoupled SLAM)
Kwok, N., Ha, Q.P., Huang, S., Dissanayake, G. & Fang, G. 2007, 'Mobile robot localization and mapping using a Gaussian sum filter', International Journal of Control, Automation, and Systems, vol. 5, no. 3, pp. 251-268.
View/Download from: UTS OPUS
Ellekilde, L., Huang, S., Valls Miro, J. & Dissanayake, G. 2007, 'Dense 3D Map Construction for Indoor Search and Rescue', Journal of Field Robotics, vol. 24, no. 1/2, pp. 71-89.
View/Download from: UTS OPUS or Publisher's site
The main contribution of this paper is a new simultaneous localization and mapping (SLAM) algorithm for building dense three-dimensional maps using information acquired from a range imager and a conventional camera, for robotic search and rescue in unstr
Huang, S. & Dissanayake, G. 2007, 'Convergence And Consistency Analysis For Extended Kalman Filter Based Slam', IEEE Transactions On Robotics, vol. 23, no. 5, pp. 1036-1049.
View/Download from: UTS OPUS or Publisher's site
This paper investigates the convergence properties and consistency of Extended Kalman Filter (EKF) based simultaneous localization and mapping (SLAM) algorithms. Proofs of convergence are provided for the nonlinear two-dimensional SLAM problem with point
Rozyn, M.K., Zhang, N. & Dissanayake, G. 2007, 'Identification of Inertial Parameters of an On-Road Vehicle', Journal of Passenger Cars - Mechanical Systems, SAE Transactions, vol. 116, no. 6, pp. 1680-1687.
During normal use vehicles are loaded in multiple configurations that directly alter their inertial properties. A method of accurately identifying and tracking these changes would benefit the many vehicle subsystems that rely on the accuracy of these parameters. In this paper a novel method is presented to determine the inertial properties of a vehicle from the measured sprung mass vibration responses, without the need of sophisticated measuring devices or specialized test rigs. After a brief description of the theoretical basis of the method, experimental results are presented which show estimation of the inertial properties is possible. The results validate the accuracy and applicability of the method and illustrate that the vehicle inertial properties can be obtained even when certain system parameters, such as damping coefficients, are assumed unknown.
Leung, C., Huang, S., Kwok, N. & Dissanayake, G. 2006, 'Planning under Uncertainty Using Model Predictive Control for Information Gathering', Robotics and Autonomous Systems, vol. 54, no. 11, pp. 898-910.
View/Download from: UTS OPUS or Publisher's site
This paper considers trajectory planning problems for autonomous robots in information gathering tasks. The objective of the planning is to maximize the information gathered within a finite time horizon. It is assumed that either the Extended Kalman Filter (EKF) or the Extended Information Filter (EIF) is applied to estimate the features of interest and the information gathered is expressed by the covariance matrix, or information matrix. It is shown that the planning process can be formulated as an optimal control problem for a nonlinear control system with a gradually identified model. This naturally leads to the Model Predictive Control (MPC) planning strategy, which uses the updated knowledge about the model to solve a finite horizon optimal control problem at each time step and only executes the first control action. The proposed MPC framework is demonstrated through solutions to two challenging information gathering tasks: (1) Simultaneous planning, localization, and map building (SPLAM) and (2) Multi-robot Geolocation. It is shown that MPC can effectively deal with dynamic constraints, multiple robots/features and a range of objective functions.
Kwok, N., Liu, D. & Dissanayake, G. 2006, 'Evolutionary Computing Based Mobile Robot Localization', Engineering Applications of Artificial Intelligence, vol. 19, no. 8, pp. 857-868.
View/Download from: UTS OPUS or Publisher's site
Evolutionary computing techniques, including genetic algorithms (GA), particle swarm optimization (PSO) and ants system (AS) are applied to the localization problem of a mobile robot. Salient features of robot localization are that the system is partially dynamic and information for fitness evaluation is incomplete and corrupted by noise. In this research, variations to the above three evolutionary computing techniques are proposed to tackle the specific dynamic and noisy system. Their performances are compared based on simulation and experiment results and the feasibility of the proposed approach to mobile robot localization is demonstrated.
Liu, D., Wu, X., Paul, G. & Dissanayake, G. 2006, 'Case Studies on an Approach to Multiple Autonomous Vehicle Motion Coordination', Journal of Wuhan University of Technology, vol. 26, no. 164, pp. 26-31.
Ha, Q.P. & Dissanayake, G. 2006, 'Robust Formation Using Reactive Variable Structure Systems', International Transactions on Systems Science and Applications, vol. 1, no. 2, pp. 181-189.
View/Download from: UTS OPUS
Ha, Q.P., Tran, T. & Dissanayake, G. 2005, 'A wavelet- and neural network-based voice interface system for wheelchair control', International Journal of Intelligent Systems Technologies and Applications, vol. 1, no. 1/2, pp. 49-65.
View/Download from: UTS OPUS
Voice control has long been considered as a natural mechanism to assist powered wheelchair users. However, one implementation difficulty is that a voice input system may fail to recognise a user's voice. Indeed, speech activated interface between human and autonomous/semi-autonomous systems requires accurate detection and recognition. In this area pitch and end-point detection are of vital importance. This paper presents a new method for pitch detection based on the continuous wavelet transform phase. The proposed technique can serve as an accurate pitch detector, and also can offer an efficient solution to the end-point detection problem. The extracted features from a user's speech are then used to train a neural network for speech recognition. Experimental results are provided for the detection of pitch periods and end points and the recognition of a number of commands of male and female users. Laboratory tests are reported for the proposed voice control wheelchair system.
Takezawa, S., Gulrez, T., Herath, D.C. & Dissanayake, G. 2005, 'Environmental recognition for autonomous robot using Simultaneous Localization and Map Building (SLAM) (real time path planning with dynamical localized voronoi diyision)', Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C, vol. 71, no. 3, pp. 904-911.
The Goal of this work is to provide a more in depth understanding of the navigation in the autonomous robot using stable visual points derived from the repeated experimentation by the stereo vision in a natural featured environment. In order to identify the position of the robot as well as to establish the 3 D obstacle map under the unknown environment, we discuss the simultaneous stereo type localization and map building (SLAM) problem. The design of the planning algorithm for a vision guided mobile robot depends upon the two main characteristics of visual environmental recognition i.e. Uncertainty and Efficiency. The uncertainty is reduced by the Extended Kalman Filter algorithm based on the process and observation model of the mobile robot. Regarding the efficiency, the optimal path planning algorithm which uses the dynamical localized Voronoi division is a new concept in our proposal. This method has the ability to make the path for mobile robot with only suitable number of natural features.
Ha, Q.P., Tran, T.H. & Dissanayake, G. 2005, 'A wavelet- and neural network-based voice interface system for wheelchair control', International Journal of Intelligent Systems Technologies and Applications, vol. 1, no. 1-2, pp. 49-65.
Voice control has long been considered as a natural mechanism to assist powered wheelchair users. However, one implementation difficulty is that a voice input system may fail to recognise a user's voice. Indeed, speech activated interface between human and autonomous/semi-autonomous systems requires accurate detection and recognition. In this area pitch and end-point detection is of vital importance. This paper presents a new method for pitch detection based on the continuous wavelet transform phase. The proposed technique can serve as an accurate pitch detector, and also can offer an efficient solution to the end-point detection problem. The extracted features from a user's speech are then used to train a neural network for speech recognition. Experimental results are provided for the detection of pitch periods and end points and the recognition of a number of commands of male and female users. Laboratory tests are reported for the proposed voice control wheelchair system. &copy; 2005 Inderscience Enterprises Ltd.
Williams, S.B., Durrant-Whyte, H. & Dissanayake, G. 2003, 'Constrained initialization of the simultaneous localization and mapping algorithm', International Journal Of Robotics Research, vol. 22, no. 7-8, pp. 541-564.
View/Download from: UTS OPUS or Publisher's site
In this paper we present a novel feature initialization technique for the Simultaneous Localization and Mapping (SLAM) algorithm. The initialization scheme extends previous approaches for identifying new confirmed features and is shown to improve the steady-state performance of the filter by incorporating tentative features into the filter as soon as they are observed. Constraints are then applied between multiple feature estimates when a feature is confirmed. Observations that are subsequently deemed as spurious are removed from the state vector after an appropriate timeout. It is shown that information that would otherwise be lost can therefore be used consistently in the filter. Results of this algorithm applied to data collected using a submersible vehicle are also shown.
Dissanayake, G., Williams, S.B., Durrant-Whyte, H. & Bailey, T. 2002, 'Map management for efficient simultanneous localisation and map building (SLAM) problem', Autonomous Robots, vol. 12, no. N/A, pp. 265-286.
View/Download from: UTS OPUS
Furukawa, T. & Dissanayake, G. 2002, 'Parameter identification of autonomous vehicles using multi-objective optimisation', Engineering Optimization, vol. 34, no. N/A, pp. 369-395.
View/Download from: UTS OPUS
Dissanayake, G., Williams, S.B., Durrant-Whyte, H. & Bailey, T. 2002, 'Map management for efficient simultaneous localization and mapping (SLAM)', Autonomous Robots, vol. 12, no. 3, pp. 267-286.
View/Download from: Publisher's site
The solution to the simultaneous localization and map building (SLAM) problem where an autonomous vehicle starts in an unknown location in an unknown environment and then incrementally build a map of landmarks present in this environment while simultaneously using this map to compute absolute vehicle location is now well understood. Although a number of SLAM implementations have appeared in the recent literature, the need to maintain the knowledge of the relative relationships between all the landmark location estimates contained in the map makes SLAM computationally intractable in implementations containing more than a few tens of landmarks. This paper presents the theoretical basis and a practical implementation of a feature selection strategy that significantly reduce the computation requirements for SLAM. The paper shows that it is indeed possible to remove a large percentage of the landmarks from the map without making the map building process statistically inconsistent. Furthermore, it is shown that the computational cost of the SLAM algorithm can be reduced by judicious selection of landmarks to be preserved in the map.
Furukawa, T. & Dissanayake, G. 2002, 'Parameter identification of autonomous vehicles using multi-objective optimization', Engineering Optimization, vol. 34, no. 4, pp. 369-395.
View/Download from: Publisher's site
In order to properly operate an autonomous vehicle navigation system, it is important that the vehicle and sensor models of the vehicle are defined by an accurate parameter set. This paper presents a technique for identifying parameters of an autonomous vehicle using multi-objective optimization, which enables the identification process without introducing additional parameters. A multi-objective optimization method has been further proposed to solve the optimization problem defined for the identification efficiently and promisingly. Results of numerical examples first show that the proposed optimization method can work well for various multi-objective optimization problems. Then, the proposed identification technique has been applied to the actual parameter identification of the autonomous vehicle developed by the authors, and an appropriate parameter set has been obtained.
Dissanayake, G., Newman, P., Clark, S., Durrant-Whyte, H. & Csorba, M. 2001, 'A solution to the simultaneous localisation and map building (SLAM) problem', IEEE Transactions on Robotics & Automation, vol. 17, no. 3, pp. 229-241.
Dissanayake, G., Sukkarieh, S., Nebot, E. & Durrant-Whyte, H. 2001, 'The aiding of a low cost, strapdown inertial unit using modelling constraints in land vehicle applications', IEEE Transactions on Robotics & Automation, vol. 17, no. 5, pp. 731-747.
Lee, K.Y. & Dissanayake, G. 2001, 'Dynamic Modelling and Motion Planning for a Hybrid Legged-Wheeled Mobile Robot', Institution of Mechanical Engineers. Proceedings. Part C: Journal of Mechanical Engineering Science, vol. 215, no. 1, pp. 7-25.
View/Download from: Publisher's site
Dissanayake, G. & Fang, G. 2001, 'Minimum-time trajectories for reducing load sway in quay-cranes', Engineering Optimization, vol. 33, pp. 643-662.
View/Download from: Publisher's site
Williams, S.B., Dissanayake, G. & Durrant-Whyte, H. 2001, 'Terrain-Aided Navigation for Underwater Robotics', Advanced Robotics, vol. 15, no. 5, pp. 533-550.
View/Download from: Publisher's site
Williams, S.B., Newman, P., Rosenblatt, J.K., Dissanayake, G. & Durrant-Whyte, H. 2001, 'Autonomous Underwater Navigation and Control', Robotica, vol. 19, no. 5, pp. 481-496.
Dissanayake, G., Sukkarieh, S., Nebot, E. & Durrant-Whyte, H. 2001, 'The aiding of a low-cost strapdown inertial measurement unit using vehicle model constraints for land vehicle applications', IEEE Transactions on Robotics and Automation, vol. 17, no. 5, pp. 731-747.
View/Download from: Publisher's site
This paper presents a new method for improving the accuracy of inertial measurement units (IMUs) mounted on land vehicles. In contrast to the typical techniques used for IMUs mounted on flight vehicles, the algorithm exploits nonholonomic constraints that govern the motion of a vehicle on a surface to obtain velocity observation measurements which aid in the estimation of the alignment of the IMU as well as the forward velocity of the vehicle. It is shown that this can be achieved without any external sensing provided that certain observability conditions are met. A theoretical analysis is provided together with a comparison of experimental results between a nonlinear implementation of the algorithm and an IMU/GPS navigation system. This comparison demonstrates the effectiveness of the algorithm. The real time implementation is also addressed through a multiple observation inertial aiding algorithm based on the information filter. The observations used in the information filter include position and velocity of the vehicle from a GPS unit, speed from a wheel encoder, and virtual observations due to the constraints on the motion of the vehicle. The results show that the use of these constraints and vehicle speed guarantees the observability of the velocity and the attitude of the inertial unit, and hence bounds the errors associated with these states. The observations from the GPS unit adds extra information to the estimate of these states as well as providing observability of position. The strategies proposed in this paper provides for a tighter navigation loop which can sustain outages of GPS for a greater amount of time as compared to when the inertial unit is used with standard integration algorithms.
Scheding, S., Dissanayake, G., Nebot, E. & Durrant-Whyte, H. 1999, 'An Experiment In Autonomous Navigation Of An Underground Mining Vehicle', IEEE Transactions On Robotics And Automation, vol. 15, no. 1, pp. 85-95.
View/Download from: Publisher's site
This paper describes the theoretical development and experimental evaluation of a navigation system for an autonomous load, haul, and dump truck (LHD) based on the results obtained during extensive in-situ field trials. The particular contributions of th
Clark, S. & Dissanayake, G. 1999, 'Simultaneous localisation and map building using millimetre wave radar to extract natural features', Proceedings - IEEE International Conference on Robotics and Automation, vol. 2, pp. 1316-1321.
This paper discusses the use of a 77GHz millimetre wave radar as a guidance sensor for autonomous land vehicle navigation. An extended Kalman filter (EKF) maintains an estimate of map features in addition to vehicle state. This map augmented EKF is implemented with radar reflectors, designed for high visibility from all orientations. An improvement on this approach enables natural features to be identified, using the polarisation of returned radar signals. Those that are suitable as navigational markers are used to update estimates of vehicle and feature locations. This method requires no a priori knowledge of the environment and no target infrastructure.
Dissanayake, G., Sukkarieh, S., Nebot, E. & Durrant-Whyte, H. 1999, 'New algorithm for the alignment of inertial measurement units without external observation for land vehicle applications', Proceedings - IEEE International Conference on Robotics and Automation, vol. 3, pp. 2274-2279.
This paper describes a real time, on-the-fly, Roll and Pitch alignment algorithm for Inertial Measurement Units (IMUs) mounted on land vehicles. Unlike conventional strategies, the alignment is achieved without external observations. This is achieved by exploiting the non-holonomic constraints that govern the motion of a vehicle on a surface to obtain the Roll and Pitch of the IMU. The position of the vehicle along its path is still unobservable and the algorithm is effective only when there is sufficient excitation in all degrees of freedom. However, with the proposed alignment algorithm, the IMU is able to provide sufficiently accurate position information for substantially longer periods of time compared with conventional methods. Experimental results are provided along with a comparison of an IMU/GPS navigation loop showing the effectiveness of the algorithm.
Madhavan, R., Dissanayake, G., Durrant-Whyte, H., Roberts, J., Corke, P. & Cunningham, J. 1999, 'Issues in autonomous navigation of underground vehicles', Mineral Resources Engineering, vol. 8, no. 3, pp. 313-324.
This paper describes current research at the Australian Centre for Field Robotics (ACFR) in collaboration with the Commonwealth Scientific and Industrial Research Organisation (CSIRO) within the Cooperative Research Centre (CRC) for Mining Technology and Equipment (CMTE) towards achieving autonomous navigation of underground vehicles, like a Load-Haul-Dump (LHD) truck. This work is being sponsored by the mining industry through the Australian Mineral Industries Research Association Limited (AMIRA). Robust and reliable autonomous navigation can only be realised by achieving high level tasks such as path-planning and obstacle avoidance. This requires determining the pose (position and orientation) of the vehicle at all times. A minimal infrastructure localisation algorithm that has been developed for this purpose is outlined and the corresponding results are presented. Further research issues that are under investigation are also outlined briefly.
Madhavan, R., Nettleton, E., Nebot, E., Dissanayake, G., Cunningham, J., Durrant-Whyte, H., Corke, P. & Roberts, J. 1999, 'Evaluation of internal navigation sensor suites for underground mining vehicle navigation', Proceedings - IEEE International Conference on Robotics and Automation, vol. 2, pp. 999-1004.
This paper describes a series of trials that were done at an underground mine in New South Wales, Australia. Experimental results are presented from the data obtained during the field trials and suitable sensor suites are evaluated.