Teresa Vidal-Calleja received her BSc in Mech Eng from the National Autonomous University of Mexico (UNAM), Mexico City, Mexico, her MSc in Electrical Eng (Mechatronics options) from CINVESTAV-IPN, Mexico City and her PhD in Automatic Control, Computer Vision and Robotics from the Technical University of Catalonia (UPC), Barcelona, Spain in 2007.
In 2008, she was Postdoctoral Fellow at LAAS-CNRS, Toulouse, France and research fellow at the Australian Centre for Field Robotics (ACFR), the University of Sydney, Australia from 2009 to 2011. Teresa was the highly prestigious UTS Chancellor's Research Fellow at the Centre for Autonomous Systems from 2014-2017. She has been Visiting Scholar at the Active Vision Lab, University of Oxford, U.K., ACFR and the Autonomous System Lab at ETH-Zurich Switzerland.
Teresa has been invited to present her research at leading international robotics laboratories such as ETHZ, Switzerland, IBEO Automotive, Germany, Virginia Tech in USA, AIST Japan; CCADET-UNAM, Mexico; Informatik Universität Bremen in Germany; KTH Royal Institute of Technology, Sweden; LAAS-CNRS, France.
She currently serves as Treasurer of the Australian Robotics and Autonomous Association (ARAA). She was program chair at ACRA 2017, local chair at International Conference on Social Robotics ICSR 2014, and co-organizer of IROS 2015 workshop on Alternative Sensing for Robot Perception: Beyond Laser and Vision and GraphBot 2010, the IROS Workshop on Probabilistic Graphical Models in Robotics.
Dr Vidal-Calleja is reviewer for ERA A*- and A-ranked journals such as IEEE Transactions on Robotics, International Journal of Robotics Research, Robots and Autonomous Systems, IEEE Transactions on Systems, Man and Cybernetics and Sensors. She has been Associate Editor for IROS since 2016. She has been a reviewer for leading robotics conferences, including ICRA, IROS and RSS, since 2006.
Can supervise: YES
Robotic perception, automatic recognition, alternative sensing, visual SLAM, aerial and ground robots cooperation, and autonomous navigation and manipulation.
Le Gentil, C, Vidal-Calleja, T & Huang, S 2020, 'Gaussian Process Preintegration for Inertial-Aided State Estimation', IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 2108-2114.View/Download from: Publisher's site
© 2020 IEEE. In this letter, we present Gaussian Process Preintegration, a preintegration theory based on continuous representations of inertial measurements. A novel use of linear operators on Gaussian Process kernels is employed to generate the proposed Gaussian Preintegrated Measurements (GPMs). This formulation allows the analytical integration of inertial signals on any time interval. Consequently, GPMs are especially suited for asynchronous inertial-aided estimation frameworks. Unlike discrete preintegration approaches, the proposed method does not rely on any explicit motion-model and does not suffer from numerical integration noise. Additionally, we provide the analytical derivation of the Jacobians involved in the first-order expansion for postintegration bias and inter-sensor time-shift correction. We benchmarked the proposed method against existing preintegration methods on simulated data. Our experiments show that GPMs produce the most accurate results and their computation time allows close-to-real-time operations. We validated the suitability of GPMs for inertial-aided estimation by integrating them into a lidar-inertial localisation and mapping framework.
IEEE In this article, we present inertial lidar localization autocalibration and mapping: an offline probabilistic framework for localization, mapping, and extrinsic calibration based on a 3-D lidar and a six-degree-of-freedom inertial measurement unit. Most of today’s lidars collect geometric information about the surrounding environment by sweeping lasers across their field of view. Consequently, 3-D points in one lidar scan are acquired at different timestamps. If the sensor trajectory is not accurately known, the scans are affected by the phenomenon known as motion distortion. The proposed method leverages preintegration with a continuous representation of the inertial measurements to characterize the system’s motion at any point in time. It enables precise correction of the motion distortion without relying on any explicit motion model. The system’s pose, velocity, biases, and time shift are estimated via a full batch optimization that includes automatically generated loop closure constraints. The autocalibration and the registration of lidar data rely on planar and edge features matched across pairs of scans. The performance of the framework is validated through simulated and real-data experiments.
Popović, M, Vidal-Calleja, T, Hitz, G, Chung, JJ, Sa, I, Siegwart, R & Nieto, J 2020, 'An informative path planning framework for UAV-based terrain monitoring', Autonomous Robots, vol. 44, no. 6, pp. 889-911.View/Download from: Publisher's site
© 2020, The Author(s). Unmanned aerial vehicles represent a new frontier in a wide range of monitoring and research applications. To fully leverage their potential, a key challenge is planning missions for efficient data acquisition in complex environments. To address this issue, this article introduces a general informative path planning framework for monitoring scenarios using an aerial robot, focusing on problems in which the value of sensor information is unevenly distributed in a target area and unknown a priori. The approach is capable of learning and focusing on regions of interest via adaptation to map either discrete or continuous variables on the terrain using variable-resolution data received from probabilistic sensors. During a mission, the terrain maps built online are used to plan information-rich trajectories in continuous 3-D space by optimizing initial solutions obtained by a coarse grid search. Extensive simulations show that our approach is more efficient than existing methods. We also demonstrate its real-time application on a photorealistic mapping scenario using a publicly available dataset and a proof of concept for an agricultural monitoring task.
© 2019, Springer Science+Business Media, LLC, part of Springer Nature. In this paper, we proposed an optimisation method to solve the problem of sound source localisation and calibration of an asynchronous microphone array. This method is based on the graph-based formulation of the simultaneous localisation and mapping problem. In this formulation, a moving sound source is considered to be observed from a static microphone array. Traditional approaches for sound source localisation rely on the well-known geometrical information of the array and synchronous readings of the audio signals. Recent work relaxed these two requirements by estimating the temporal offset between pair of microphones based on the assumption that the clock timing of each microphone is exactly the same. This assumption requires the sound cards to be identically manufactured, which in practice is not possible to achieve. Hereby an approach is proposed to jointly estimate the array geometrical information, time offset and clock difference/drift rate of each microphone together with the location of a moving sound source. In addition, an observability analysis of the system is performed to investigate the most suitable configuration for sound source localisation. Simulation and experimental results are presented, which prove the effectiveness of the proposed methodology.
Wu, L, Falque, R, Perez-Puchalt, V, Liu, L, Pietroni, N & Vidal-Calleja, T 2020, 'Skeleton-Based Conditionally Independent Gaussian Process Implicit Surfaces for Fusion in Sparse to Dense 3D Reconstruction', IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 1532-1539.View/Download from: Publisher's site
Zuo, X, Ye, W, Yang, Y, Zheng, R, Vidal‐Calleja, T, Huang, G & Liu, Y 2020, 'Multimodal localization: Stereo over LiDAR map', Journal of Field Robotics.View/Download from: Publisher's site
Woolfrey, J, Lu, W, Vidal-Calleja, T & Liu, D 2019, 'Clarifying clairvoyance: Analysis of forecasting models for near-sinusoidal periodic motion as applied to AUVs in shallow bathymetry', Ocean Engineering, vol. 190.View/Download from: Publisher's site
© 2019 Elsevier Ltd This paper shows that Gaussian Process Regression (GPR) with a periodic kernel has better mean prediction accuracy and uncertainty bounds than time series or Fourier series when forecasting motion data of underwater vehicles subject to wave excitation. Many robotic systems, such as autonomous underwater vehicles (AUVs), are required to operate in environments with disturbances and relative motion that make task performance difficult. This motion often exhibits periodic, near-sinusoidal behaviour. By predicting this motion, control strategies can be developed to improve accuracy. Moreover, factoring in uncertainty can aid the robustness of these predictive control methods. Time series and Fourier series have been applied to several predictive control problems in a variety of fields. However, there are contradictory results in performance based on parameters, assessment criteria, and application. This paper seeks to clarify these discrepancies using AUV motion as a case study. GPR is also introduced as a third candidate for prediction based on previous applications to time series forecasting in other fields of science. In addition to assessing mean prediction accuracy, the ability of each model to adequately bound prediction error is also considered as a key performance indicator.
Bai, F, Vidal-Calleja, T & Huang, S 2018, 'Robust Incremental SLAM Under Constrained Optimization Formulation', IEEE ROBOTICS AND AUTOMATION LETTERS, vol. 3, no. 2, pp. 1207-1214.View/Download from: Publisher's site
Rahman, S, Quin, P, Walsh, T, Vidal-Calleja, T, McPhee, MJ, Toohey, E & Alempijevic, A 2018, 'Preliminary estimation of fat depth in the lamb short loin using a hyperspectral camera', Animal Production Science, vol. 58, no. 8, pp. 1488-1496.View/Download from: Publisher's site
© 2018 CSIRO. The objectives of the present study were to describe the approach used for classifying surface tissue, and for estimating fat depth in lamb short loins and validating the approach. Fat versus non-fat pixels were classified and then used to estimate the fat depth for each pixel in the hyperspectral image. Estimated reflectance, instead of image intensity or radiance, was used as the input feature for classification. The relationship between reflectance and the fat/non-fat classification label was learnt using support vector machines. Gaussian processes were used to learn regression for fat depth as a function of reflectance. Data to train and test the machine learning algorithms was collected by scanning 16 short loins. The near-infrared hyperspectral camera captured lines of data of the side of the short loin (i.e. with the subcutaneous fat facing the camera). Advanced single-lens reflex camera took photos of the same cuts from above, such that a ground truth of fat depth could be semi-automatically extracted and associated with the hyperspectral data. A subset of the data was used to train the machine learning model, and to test it. The results of classifying pixels as either fat or non-fat achieved a 96% accuracy. Fat depths of up to 12 mm were estimated, with an R 2 of 0.59, a mean absolute bias of 1.72 mm and root mean square error of 2.34 mm. The techniques developed and validated in the present study will be used to estimate fat coverage to predict total fat, and, subsequently, lean meat yield in the carcass.
Ulapane, N, Alempijevic, A, Valls Miro, J & Vidal-Calleja, T 2018, 'Non-destructive evaluation of ferromagnetic material thickness using Pulsed Eddy Current sensor detector coil voltage decay rate', NDT and E International, vol. 100, pp. 108-114.View/Download from: Publisher's site
© 2018 Elsevier Ltd A ferromagnetic material thickness quantification method based on the decay rate of the Pulsed Eddy Current sensor detector coil voltage is proposed. An expression for the decay rate is derived and the relationship between the decay rate and material thickness is established. Pipe wall thickness estimation is done with a developed circular sensor incorporating the proposed method, and results are evaluated through destructive testing. The decay rate feature has a unique attribute of being lowly dependent on properties such as sensor shape and size, and lift-off, enabling the method to be usable with any detector coil-based sensor. A case study on using the proposed method with a commercial sensor is also presented to demonstrate its versatility.
© 2016 Elsevier B.V.The existing methods for the registration of point clouds acquired by laser scanners have some limitations. Firstly, as some samples of surface, a point cloud acquired by the laser scanner, which normally works in a spherical fashion, has very limited density when the surface is far away from the laser scanner and the density varies a lot at different ranges. Current registration methods cannot accurately model the surface uncertainty for such kind of point clouds of limited and large varying density. Secondly, when the point cloud is acquired while the platform is simultaneously moving, the estimation error of the platform motion makes the acquired point cloud distorted. To deal with these problems, in this paper, we propose an uncertainty model based on the Gaussian Mixture Model (GMM) to represent the point cloud. Specifically, we construct the GMM piece-wisely on the underlying surface of point cloud, which will accurately model the surface uncertainty. Also a hierarchical structure is employed to increase the robustness of the registration. Furthermore, by assigning each Gaussian component with a pose, a probabilistic graph can be constructed to tackle the problem of registration when the platform is moving while scanning. In this way the distorted point cloud, caused by the estimation error of the platform's motion, can be corrected by performing graph optimization. Simulation and real world experimental results show that our method leads to better convergence than the state-of-the-art methods due to the accurate modeling of the surface uncertainty and the hierarchical structure, and it also enables us to correct the distorted point clouds.
Ulapane, N, Alempijevic, A, Vidal Calleja, T & Valls Miro, J 2017, 'Pulsed Eddy Current Sensing for Critical Pipe Condition Assessment.', Sensors (Basel, Switzerland), vol. 17, no. 10.View/Download from: Publisher's site
Pulsed Eddy Current (PEC) sensing is used for Non-Destructive Evaluation (NDE) of the structural integrity of metallic structures in the aircraft, railway, oil and gas sectors. Urban water utilities also have extensive large ferromagnetic structures in the form of critical pressure pipe systems made of grey cast iron, ductile cast iron and mild steel. The associated material properties render NDE of these pipes by means of electromagnetic sensing a necessity. In recent years PEC sensing has established itself as a state-of-the-art NDE technique in the critical water pipe sector. This paper presents advancements to PEC inspection in view of the specific information demanded from water utilities along with the challenges encountered in this sector. Operating principles of the sensor architecture suitable for application on critical pipes are presented with the associated sensor design and calibration strategy. A Gaussian process-based approach is applied to model a functional relationship between a PEC signal feature and critical pipe wall thickness. A case study demonstrates the sensor's behaviour on a grey cast iron pipe and discusses the implications of the observed results and challenges relating to this application.
Brunner, C, Peynot, T, Vidal Calleja, TA & Underwood, J 2013, 'Selective Combination of Visual and Thermal Imaging for Resilient Localization in Adverse Conditions: Day and Night, Smoke and Fire', Journal of Field Robotics, vol. 30, no. 4, pp. 641-666.View/Download from: Publisher's site
Long-term autonomy in robotics requires perception systems that are resilient to unusual but realistic conditions that will eventually occur during extended missions. For example, unmanned ground vehicles (UGVs) need to be capable of operating safely in adverse and low-visibility conditions, such as at night or in the presence of smoke. The key to a resilient UGV perception system lies in the use of multiple sensor modalities, e.g., operating at different frequencies of the electromagnetic spectrum, to compensate for the limitations of a single sensor type. In this paper, visual and infrared imaging are combined in a Visual-SLAM algorithm to achieve localization. We propose to evaluate the quality of data provided by each sensor modality prior to data combination. This evaluation is used to discard low-quality data, i.e., data most likely to induce large localization errors. In this way, perceptual failures are anticipated and mitigated. An extensive experimental evaluation is conducted on data sets collected with a UGV in a range of environments and adverse conditions, including the presence of smoke (obstructing the visual camera), fire, extreme heat (saturating the infrared camera), low-light conditions (dusk), and at night with sudden variations of artificial light. A total of 240 trajectory estimates are obtained using five different variations of data sources and data combination strategies in the localization method. In particular, the proposed approach for selective data combination is compared to methods using a single sensor type or combining both modalities without preselection. We show that the proposed framework allows for camera-based localization resilient to a large range of low-visibility conditions.
Sola, J, Vidal Calleja, TA, Civera, J & Montiel, J 2012, 'Impact of Landmark Parametrization on Monocular EKF-SLAM with Points and Lines', International journal of computer vision, vol. 97, no. 3, pp. 339-368.View/Download from: Publisher's site
This paper explores the impact that landmark parametrization has in the performance of monocular, EKF-based, 6-DOF simultaneous localization and mapping (SLAM) in the context of undelayed landmark initialization. Undelayed initialization in monocular SLA
Vidal Calleja, TA, Berger, C, Sola, J & Lacroix, S 2011, 'Large Scale Multiple Robot Visual Mapping With Heterogeneous Landmarks In Semi-structured Terrain', Robotics And Autonomous Systems, vol. 59, no. 9, pp. 654-674.View/Download from: Publisher's site
This paper addresses the cooperative localization and visual mapping problem with multiple heterogeneous robots. The approach is designed to deal with the challenging large semi-structured outdoors environments in which aerial/ground ensembles are to evo
Vidal Calleja, TA, Sanfeliu, A & Andrade-cetto, J 2010, 'Action Selection For Single-camera Slam', IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, vol. 40, no. 6, pp. 1567-1581.View/Download from: Publisher's site
A method for evaluating, at video rate, the quality of actions for a single camera while mapping unknown indoor environments is presented. The strategy maximizes mutual information between measurements and states to help the camera avoid making ill-condi
Sola, J, Monin, A, Devy, M & Vidal Calleja, TA 2008, 'Fusing Monocular Information In Multicamera Slam', IEEE TRANSACTIONS ON ROBOTICS, vol. 24, no. 5, pp. 958-968.View/Download from: Publisher's site
This paper explores the possibilities of using monocular simultaneous localization and mapping (SLAM) algorithms in systems with more than one camera. The idea is to combine in a single system the advantages of both monocular vision (bearings-only, infin
Vidal-Calleja, T, Andrade-Cetto, J & Sanfeliu, A 2004, 'Estimator stability analysis in SLAM', IFAC Proceedings Volumes (IFAC-PapersOnline), vol. 37, no. 8, pp. 346-351.
Copyright © 2004 IFAC This work presents an analysis of the state estimation error dynamics for a linear system within the Kalman filter based approach to Simultaneous Localization and Map Building. Our objective is to demonstrate that such dynamics is marginally stable. The paper also presents the necessary modifications required in the observation model, in order to guarantee zero mean stable error dynamics. Simulations for a one-dimensional robot and a planar vehicle are presented.
Maleki, B, Alempijevic, A & Vidal Calleja, T 2018, 'Continuous Optimization Framework for Depth Sensor Viewpoint Selection', Algorithmic Foundations of Robotics XIII, Workshop on the Algorithmic Foundations of Robotics, Springer, Merida, Mexico, pp. 357-372.View/Download from: Publisher's site
Distinguishing differences between areas represented with point cloud data is generally approached by choosing a optimal viewpoint. The most informative view of a scene ultimately enables to have the optimal coverage over distinct points both locally and globally while accounting for the distance to the foci of attention. Measures of surface saliency, related to curvature inconsistency, extenuate differences in shape and are coupled with viewpoint selection approaches. As there is no analytical solution for optimal viewpoint selection, candidate viewpoints are generally discretely sampled and evaluated for information and require (near) exhaustive combinatorial searches. We present a consolidated optimization framework for optimal viewpoint selection with a continuous cost function and analytically derived Jacobian that incorporates view angle, vertex normals and measures of task related surface information relative to viewpoint. We provide a mechanism in the cost function to incorporate sensor attributes such as operating range, field of view and angular resolution. The framework is evaluated as competing favorably with the state-of-the-art approaches to viewpoint selection while significantly reducing the number of viewpoints to be evaluated in the process.
Nguyen, L, Miro, JV, Shi, L & Vidal-Calleja, T 2019, 'Gaussian Mixture Marginal Distributions for Modelling Remaining Pipe Wall Thickness of Critical Water Mains in Non-Destructive Evaluation', 2019 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM), IEEE International Conference on Cybernetics and Intelligent Systems, and Robotics, Automation and Mechatronics, IEEE, Bangkok, Thailand.View/Download from: Publisher's site
Rapidly estimating the remaining wall thickness (RWT) is paramount for the non-destructive condition assessment evaluation of large critical metallic pipelines. A robotic vehicle with embedded magnetism-based sensors has been developed to traverse the inside of a pipeline and conduct inspections at the location of a break. However its sensing speed is constrained by the magnetic principle of operation, thus slowing down the overall operation in seeking dense RWT mapping. To ameliorate this drawback, this work proposes the partial scanning of the pipe and then employing Gaussian Processes (GPs) to infer RWT at the unseen pipe sections. Since GP prediction assumes to have normally distributed input data - which does correspond with real RWT measurements - Gaussian mixture (GM) models are proven in this work as fitting marginal distributions to effectively capture the probability of any RWT value in the inspected data. The effectiveness of the proposed approach is extensively validated from real-world data collected in collaboration with a water utility from a cast iron water main pipeline in Sydney, Australia.
Popovic, M, Vidal-Calleja, T, Chung, JJ, Nieto, J & Siegwart, R 2020, 'Informative Path Planning for Active Field Mapping under Localization Uncertainty', Proceedings - IEEE International Conference on Robotics and Automation, pp. 10751-10757.View/Download from: Publisher's site
© 2020 IEEE. Information gathering algorithms play a key role in unlocking the potential of robots for efficient data collection in a wide range of applications. However, most existing strategies neglect the fundamental problem of the robot pose uncertainty, which is an implicit requirement for creating robust, high-quality maps. To address this issue, we introduce an informative planning framework for active mapping that explicitly accounts for the pose uncertainty in both the mapping and planning tasks. Our strategy exploits a Gaussian Process (GP) model to capture a target environmental field given the uncertainty on its inputs. For planning, we formulate a new utility function that couples the localization and field mapping objectives in GP-based mapping scenarios in a principled way, without relying on manually-tuned parameters. Extensive simulations show that our approach outperforms existing strategies, reducing mean pose uncertainty and map error. We present a proof of concept in an indoor temperature mapping scenario.
Bai, F, Vidal-Calleja, T, Huang, S & Xiong, R 2018, 'Predicting Objective Function Change in Pose-Graph Optimization', IEEE International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Madrid, Spain, pp. 145-152.View/Download from: Publisher's site
© 2018 IEEE. Robust online incremental SLAM applications require metrics to evaluate the impact of current measurements. Despite its prevalence in graph pruning, information-theoretic metrics solely are insufficient to detect outliers. The optimal value of the objective function is a better choice to detect outliers but cannot be computed unless the problem is solved. In this paper, we show how the objective function change can be predicted in an incremental pose-graph optimization scheme, without actually solving the problem. The predicted objective function change can be used to guide online decisions or detect outliers. Experiments validate the accuracy of the predicted objective function, and an application to outlier detection is also provided, showing its advantages over M-estimators.
Fryc, S, Liu, L & Vidal Calleja, T 2019, 'Efficient Pipeline for Mobile Brick Picking', https://ssl.linklings.net/conferences/acra/acra2019_proceedings/views/b…, Australasian Conference on Robotics and Automation, ARAA, Adelaide, pp. 1-8.
Autonomous mobile manipulation is gaining more and more attention for a range of application including disaster response, logistics, manufacturing and construction because removes work space limitation and allows object handling. A key challenge in mobile manipulation is the interaction between motion planning and perception that will deliver stable and efficient solutions. In this work, we are interested in the problem of picking a single brick shaped object from an unstructured pile using a mo- bile manipulator and a 3D camera system. We propose a robust multi-stage pipeline for a efficient, collision-free brick picking given the object pose. The key contribution of this work is a scoring function used to find the most suitable configuration considering the integrated kinematic chain of mobile base and manipulator arm. Realistic simulation results show the proposed pipeline has 100% success rate as opposed to a standard off-the-shelf solution, which has high-failure rates.
Fryc, S, Liu, L & Vidal-Calleja, T 2019, 'Robust pipeline for mobile brick picking', Australasian Conference on Robotics and Automation, ACRA.
© 2019 Australasian Robotics and Automation Association. All rights reserved. In this work, we are interested in the problem of picking a single brick shaped object from an unstructured pile using a mobile manipulator and a 3D camera system. We propose a robust multi-stage pipeline for efficient, collision-free brick picking given the pose of a target object. The key contribution of this work is a scoring function used to find the most suitable configuration considering the integrated kinematic chain of a mobile base and manipulator arm. Realistic simulation results show the proposed pipeline has 100% success rate as opposed to a standard off-the-shelf solution, which has high-failure rates.
Galea, M & Vidal Calleja, T 2019, 'Point Cloud Edge Detection and Template Matching with 1D Gradient Descent for Wall Pose Estimation', https://ssl.linklings.net/conferences/acra/acra2019_proceedings/views/b…, Australasian Conference on Robotics and Automation, ARAA, Adelaide, Australia, pp. 1-10.
Mobile manipulation in unstructured construction environments involves a range of complex robotic problems. We address a perception requirement for autonomous brick placement; estimating the pose of a partially built wall to
facilitate the placement of the subsequent brick. Our method uses RGB-D data to extract the surface edge points of the wall and classify them as horizontally or vertically aligned. The contribution of this paper encompasses a wall template that encapsulates its surface edge features and a novel 1D gradient descent template matching algorithm for pose estimation. We apply our method in mobile manipulator brick placement, demonstrating its robotic applications. Evaluation methods prove the efficacy of the proposed framework, both quantitatively and qualitatively and using both simulated and real data.
Le Gentil, C, Vidal Calleja, T & Huang, S 2019, 'IN2LAMA: INertial Lidar Localisation And Mapping', 2019 International Conference on Robotics and Automation (ICRA), International Conference on Robotics and Automation, IEEE, Montreal.View/Download from: Publisher's site
In this paper, we introduce a probabilistic framework for INertial Lidar Localisation And MApping (IN2LAMA). Most of today's lidars are based on spinning mechanisms that do not capture snapshots of the environment. As a result, movement of the sensor can occur while scanning. Without a good estimation of this motion, the resulting point clouds might be distorted. In the lidar mapping literature, a constant velocity motion model is commonly assumed. This is an approximation that does not necessarily always hold. The key idea of the proposed framework is to exploit preintegrated measurements over upsampled inertial data to handle motion distortion without the need for any explicit motion-model. It tightly integrates inertial and lidar data in a batch on-manifold optimisation formulation. Using temporally precise upsampled preintegrated measurement allows frame-to-frame planar and edge features association. Moreover, features are re-computed when the estimate of the state changes, consolidating front-end and back-end interaction. We validate the effectiveness of the approach through simulated and real data.
Sutjipto, S, Tish, D, Paul, G, Vidal Calleja, T & Schork, T 2018, 'Towards Visual Feedback Loops for Robot-Controlled Additive Manufacturing', Robotic Fabrication in Architecture, Art and Design 2018, Robotic Fabrication in Architecture, Art and Design, Springer, Zurich, pp. 85-97.View/Download from: Publisher's site
Robotic additive manufacturing methods have enabled the design and fabrication of novel forms and material systems that represent an important step forward for architectural fabrication. However, a common problem in additive manufacturing is to predict and incorporate the dynamic behavior of the material that is the result of the complex confluence of forces and material properties that occur during fabrication. While there have been some approaches towards verification systems, to date most robotic additive manufacturing processes lack verification to ensure deposition accuracy. Inaccuracies, or in some instances critical errors, can occur due to robot dynamics, material self-deflection, material coiling, or timing shifts in the case of multi-material prints. This paper addresses that gap by presenting an approach that uses vision-based sensing systems to assist robotic additive manufacturing processes. Using online image analysis techniques, occupancy maps can be created and updated during the fabrication process to document the actual position of the previously deposited material. This development is an intermediary step towards closed-loop robotic control systems that combine workspace sensing capabilities with decision-making algorithms to adjust toolpaths to correct for errors or inaccuracies if necessary. The occupancy grid map provides a complete representation of the print that can be analyzed to determine various key aspects, such as, print quality, extrusion diameter, adhesion between printed parts, and intersections within the meshes. This valuable quantitative information regarding system robustness can be used to influence the system's future actions. This approach will help ensure consistent print quality and sound tectonics in robotic additive manufacturing processes, improving on current techniques and extending the possibilities of robotic fabrication in architecture.
Vu, TL, Liu, L, Paul, G & Vidal Calleja, T 2019, 'Rectangular-shaped object recognition and pose estimation', ACRA 2019 Proceedings, Australian Conference on Robotics and Automation, ARAA, Adelaide, pp. 1-9.
This paper presents a novel solution for rectangular-shaped object pose estimation in the robotic bin-picking problem, using data from a single RGB-D camera collecting point cloud data from a fixed position. The key benefit of the presented framework is its ability to accurately and robustly locate an object position and orientation, which allows for high precision robotic grasping and placing of such objects in an open-loop motion execution system. Firstly, intelligent grasping surface selection is performed, then Principal Component Analysis is used for pose estimation and finally, rotation averaging is integrated to significantly
improve noise-reduction over time. Comparisons between the resulting poses and ones estimated by a traditional Iterative Closest Point
technique, have demonstrated the framework's advantages for pose estimation tasks.
Caruana, A & Vidal Calleja, T 2018, 'Very Low Complexity Convolutional Neural Network for Generating Quadtree Structures', ACRA 2018 Website Proceedings, Australian Robotics and Automation Association, ARAA, Lincoln, New Zealand, pp. 1-8.
In this paper, we present a Very Low Complexity Convolutional Neural Network (VLC-CNN)
for the purpose of generating quadtree data
structures for image segmentation. The use of
quadtrees to encode images has applications including video encoding and robotic perception,
with examples including the Coding Tree Unit
in the High Efficiency Video Coding (HEVC)
standard and Occupancy Grid Maps (OGM)
as environment representations with variable
grid-size. While some methods for determining quadtree structures include brute-force algorithms or heuristics, this paper describes the
use of a Convolutional Neural Network (CNN)
to predict the quadtree structure. CNNs traditionally require substantial computational and
memory resources to operate, however, VLCCNN exploits downsampling and integer-only
quantised arithmetic to achieve minimal complexity. Therefore, VLC-CNN's minimal design
makes it feasible for implementation in realtime or memory-constrained processing applications.
Le Gentil, C, Vidal-Calleja, T & Huang, S 2018, '3D Lidar-IMU Calibration based on Upsampled Preintegrated Measurements for Motion Distortion Correction', International Conference on Robotics and Automation, Brisbane.
In this paper, we present a probabilistic framework to recover the extrinsic calibration parameters of a lidar-IMU sensing system. Unlike global-shutter cameras, lidars do not take single snapshots of the environment. Instead, lidars collect a succession of 3D-points generally grouped in scans. If these points are assumed to be expressed in a common frame, this becomes an issue when the sensor moves rapidly in the environment causing motion distortion. The fundamental idea of our proposed framework is to use preintegration over interpolated inertial measurements to characterise the motion distortion in each lidar scan. Moreover, by using a set of planes as a calibration target, the proposed method makes use of lidar point-to-plane distances to jointly calibrate and localise the system using on-manifold optimisation. The calibration does not rely on a predefined target as arbitrary planes are detected and modelled in the first lidar scan. Simulated and real data are used to show the effectiveness of the proposed method.
Virgona, A, Alempijevic, A & Vidal-Calleja, T 2018, 'Socially constrained tracking in crowded environments using shoulder pose estimates', Proceedings - IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Brisbane, QLD, Australia, pp. 4555-4562.View/Download from: Publisher's site
© 2018 IEEE. Detecting and tracking people is a key requirement in the development of robotic technologies intended to operate in human environments. In crowded environments such as train stations this task is particularly challenging due the high numbers of targets and frequent occlusions. In this paper we present a framework for detecting and tracking humans in such crowded environments in terms of 2D pose (x, y, θ). The main contributions are a method for extracting pose from the most visible parts of the body in a crowd, the head and shoulders, and a tracker which leverages social constraints regarding peoples orientation, movement and proximity to one another, to improve robustness in this challenging environment. The framework is evaluated on two datasets: one captured in a lab environment with ground truth obtained using a motion capture system, and the other captured in a busy inner city train station. Pose errors are reported against the ground truth and the tracking results are then compared with a state-of-the-art person tracking framework.
Virgona, A, Alempijevic, A & Vidal-Calleja, T 2018, 'Socially Constrained Tracking in Crowded Environments Using Shoulder Pose Estimates', 2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), IEEE International Conference on Robotics and Automation (ICRA), IEEE COMPUTER SOC, Brisbane, AUSTRALIA, pp. 4555-4562.
Popovic, M, Vidal Calleja, TA, Hitz, G, Sa, I, Siegwart, R & Nieto, J 2017, 'Multiresolution Mapping and Informative Path Planning for UAV-based Terrain Monitoring', 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Vancouver, Canada.View/Download from: Publisher's site
Unmanned aerial vehicles (UAVs) can offer timely and cost-effective delivery of high-quality sensing data. However, deciding when and where to take measurements in complex environments remains an open challenge. To address this issue, we introduce a new multiresolution mapping approach for informative path planning in terrain monitoring using UAVs. Our strategy exploits the spatial correlation encoded in a Gaussian Process model as a prior for Bayesian data fusion with probabilistic sensors. This allows us to incorporate altitude-dependent sensor models for aerial imaging and perform constant-time measurement updates. The resulting maps are used to plan information-rich trajectories in continuous 3-D space through a combination of grid search and evolutionary optimization. We evaluate our framework on the application of agricultural biomass monitoring. Extensive simulations show that our planner performs better than existing methods, with mean error reductions of up to 45% compared to traditional "lawnmower" coverage. We demonstrate proof of concept using a multi rotor to map color in different environments.
Shi, L, Valls Miro, J, Vidal Calleja, T, Vitanage, D & Rajalingam, J 2017, 'Innovative Data-driven "along-the-pipe" Condition Assessment for Critical Water Mains', OZWATER'17 Australia's International Water Conference & Exhibition, OZWATER'17 Australia's International Water Conference & Exhibition, Australian Water Association, Sydney, pp. 1-8.
Recent research findings on remaining life prediction for older Cast Iron critical water mains suggest increasing reliability by calculating stress concentration factors from the corrosion patch geometries expected to be present in the asset, not just extreme pitting as is generally carried out within the industry. This study proposes an innovative data-driven "along-the-pipe" framework able to utilise local inspection results further by capturing data correlations present in the remaining wall thickness measurement. This knowledge can in turn be utilised to produce estimates for "along-the-pipe" patch geometry predictions, hence remaining life. Results from inspections in a real pipeline in the Sydney Water network are compared to conventional Extreme Value Analysis (EVA) to validate the improvements of the proposed strategy.
Su, D, Vidal Calleja, TA & Valls Miro, J 2017, 'Towards Real-Time 3D Sound Sources Mapping with Linear Microphone Arrays', Proceedings of the 2017 IEEE International Conference on Robotics and Automation (ICRA), 2017 IEEE International Conference on Robotics and Automation, IEEE, Singapore, Singapore.View/Download from: Publisher's site
In this paper, we present a method for real-time 3D sound sources mapping using an off-the-shelf robotic perception sensor equipped with a linear microphone array. Conventional approaches to map sound sources in 3D scenarios use dedicated 3D microphone arrays, as this type of arrays provide two degrees of freedom (DOF) observations. Our method addresses the problem of 3D sound sources mapping using a linear microphone array, which only provides one DOF observations making the estimation of the sound sources location more challenging. In the proposed method, multi hypotheses tracking is combined with a new sound source parametrisation to provide with a good initial guess for an online optimisation strategy. A joint optimisation is carried out to estimate 6 DOF sensor poses and 3 DOF landmarks together with the sound sources locations. Additionally, a dedicated sensor model is proposed to accurately model the noise of the Direction of Arrival (DOA) observation when using a linear microphone array. Comprehensive simulation and experimental results show the effectiveness of the proposed method. In addition, a real-time implementation of our method has been made available as open source software for the benefit of the community.
Sun, L, Vidal Calleja, TA & Valls Miro, JAIME 2017, 'Coupling Conditionally Independent Submaps for Large-Scale 2.5D Mapping with Gaussian Markov Random Fields', IEEE International Conference on Robotics and Automation : ICRA : [proceedings] IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Singapore, Singapore, pp. 3131-3137.View/Download from: Publisher's site
Building large-scale 2.5D maps when spatial correlations are considered can be quite expensive, but there are clear advantages when fusing data. While optimal submapping strategies have been explored previously in covariance-form using Gaussian Process for large-scale mapping, this paper focuses on transferring such concepts into information form. By exploiting the conditional independence property of the Gaussian Markov Random Field (GMRF) models, we propose a submapping approach to build a nearly optimal global 2.5D map. In the proposed approach data is fused by first fitting a GMRF to one sensor dataset; then conditional independent submaps are inferred using this model and updated individually with new data arrives. Finally, the information is propagated from submap to submap to later recover the fully updated map. This is efficiently achieved by exploiting the inherent structure of the GMRF, fusion and propagation all in information form. The key contribution of this paper is the derivation of the algorithm to optimally propagate information through submaps by only updating the common parts between submaps. Our results show the proposed method reduces the computational complexity of the full mapping process while maintaining the accuracy. The performance is evaluated on synthetic data from the Canadian Digital Elevation Data.
Bai, F, Huang, S, Vidal Calleja, TA & Zhang, Q 2016, 'Incremental SQP Method for Constrained Optimization Formulation in SLAM', Proceedings of the 14th International Conference on Control, Automation, Robotics and Vision (ICARCV), International Conference on Control, Automation, Robotics and Vision, IEEE, Phuket, Thailand.View/Download from: Publisher's site
The simultaneous localization and mapping (SLAM) problem has been a research focus for many years and have reached a mature state. However, more robust solutions to the SLAM problem are still required, especially in large noise level scenarios. Because of the strong non-linearity of the SLAM problem, it is vital to start from a good initial value to avoid being trapped in local minima. In this paper, we propose a new SLAM formulation transforming the unconstrained Least Squares formulation into a constrained optimization problem. Algorithms based on this new formulation can naturally start from good initial value. Different from other constrained optimization problem, this new formulation can be efficiently solved with Sequential Quadratic Programming (SQP) methods. Based on SQP, we propose an incremental SQP algorithm to solve SLAM, which shows great advantage over Gauss Newton (g2o implementation) when working in large noise level scenarios. Experimental results show the validity of the proposed approach.
Falque, R, Vidal Calleja, TA, Dissanayake, G & Valls Miro, J 2016, 'From the skin-depth equation to the inverse RFEC sensor model', 2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV), International Conference on Control, Automation, Robotics and Vision, IEEE, Phuket, Thailand.
Shi, L, Valls Miro, J, Zhang, T, Vidal Calleja, T, Sun, L & Dissanayake, G 2016, 'Constrained Sampling of 2.5D Probabilistic Maps for Augmented Inference', IEEE International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Daejeon, Korea.View/Download from: Publisher's site
Su, D, Vidal Calleja, TA & Valls Miro, J 2016, 'Split Conditional Independent Mapping for Sound Source Localisation with Inverse-Depth Parametrisation', IEEE International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Daejeon, Korea, pp. 2000-2006.View/Download from: Publisher's site
In this paper, we propose a framework to map stationary sound sources while simultaneously localise a moving robot. Conventional methods for localisation and sound source mapping rely on a microphone array and either, a proprioceptive sensor only (such as wheel odometry) or an additional exteroceptive sensor (such as cameras or lasers) to get accurately
the robot locations. Since odometry drifts over time and sound observations are bearing-only, sparse and extremely noisy, the former can only deal with relatively short trajectories before the whole map drifts. In comparison, the latter can get more accurate trajectory estimation over long distances and a better estimation of the sound source map as a result. However, in most of the work in the literature, trajectory estimation and sound source mapping are treated as uncorrelated, which means an update on the robot trajectory does not propagate properly to the sound source map. In this paper, we proposed an efficient method to correlate robot trajectory with sound source mapping by exploiting the conditional independence property between
two maps estimated by two different Simultaneous Localisation and Mapping (SLAM) algorithms running in parallel. In our approach, the first map has the flexibility that can be built with any SLAM algorithm (filtering or optimisation) to estimate robot poses with an exteroceptive sensor. The second map
is built by using a filtering-based SLAM algorithm locating all stationary sound sources parametrised with Inverse Depth Parametrisation (IDP). Robot locations used during IDP initialisation are the common features shared between the two SLAM maps, which allow to propagate information accordingly. Comprehensive simulations and experimental results show the
effectiveness of the proposed method.
Sun, L, Vidal Calleja, TA & Valls Miro, J 2016, 'Gaussian Markov Random Fields for Fusion in Information Form', Proceedings - IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, Institute of Electrical and Electronics Engineers (IEEE), Stockholm, Sweden, pp. 1840-1845.View/Download from: Publisher's site
2.5D maps are preferable for representing the environment owing to compactness. When noisy observations from diverse sensors at different resolutions are available, the problem of 2.5D mapping turns to how to compound the information in an effective and efficient manner. This paper proposes a generic probabilistic framework for fusing efficiently multiple sources of sensor data to generate amendable, high-resolution 2.5D maps. The key idea is to exploit the sparsity of the information matrix. Gaussian Markov Random Fields are employed to learn a prior map, using the conditional independence property between location to obtain a representation of the state. This prior map encoded in information form can then be updated with other sources of data in constant time. Later, mean state vector and variances can be efficiently recovered using numerical methods. The proposed approach allows accurate estimation of 2.5D maps at arbitrary resolution, while incorporating sensor noise and spatial dependency in a statistically reasonable way. We apply the proposed framework to pipe wall thickness mapping and fuse data from two diverse sensors that have different resolutions. Experimental results are compared with three other approaches, showing that, while greatly reducing computation time, the proposed framework is able to capture in large extend the spatial correlation to generate equivalent results to the expensive optimal fusion method in covariance form with a Gaussian Process prior.
Falque, R, Vidal Calleja, TA & Valls Miro, J 2015, 'Kidnapped Laser-Scanner for Evaluation of RFEC Tool', IEEE International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Hamburg, Germany, pp. 313-318.View/Download from: Publisher's site
An algorithm is proposed for matching data from
different sensing modalities. The problem is formalised as a
kidnapped robot problem, where Bayesian fusion is used to
find the most likely location where both modalities agree. The
key idea of our algorithm is to model the correlation between
the two modalities as a likelihood used to update a location
prior. Data, in this case, is represented as 2.5D thickness maps
from a laser scanner and a Remote Field Eddy Current (RFEC)
tool, used in non-destructive testing to assess the condition of
infrastructures. The laser data is limited, while RFEC data is
continuous. Given some prior in location, the aim is to find
the 2.5D thickness map from the laser that corresponds to the
RFEC data, which should be noted is highly noisy. Real data
from CCTV inspections of water pipes are used to validate the
Shi, L, Sun, L, Vidal Calleja, T & Miro, JV 2015, 'Kernel-Specific Gaussian Process for Predicting Pipe Wall Thickness Maps', Website Proceedings of the Australasian Conference on Robotics and Automation 2015, Australasian Conference on Robotics and Automation, AARA, Canberra, pp. 1-8.
Data organised in 2.5D such as elevation and
thickness maps has been extensively studied in
the fields of robotics and geostatistics. These
maps are typically a probabilistic 2D grid that
stores an estimated value (height or thickness)
for each cell. Modelling the spatial dependencies
and making inference on new grid locations
is a common task that has been addressed using
Gaussian random fields. However, inference
faraway from the training areas results quite
uncertain, therefore not informative enough for
some applications. The objective of this research
is to model the status of a pipeline based
on limited and sparse local assessments, predicting
the likely condition on pipes that have
not been inspected. A customised kernel for
Gaussian Processes (GP) is proposed to capture
the spatial correlation of the pipe wall
thickness data. An estimate of the likely condition
of non-inspected pipes is achieved by concretising
GP to a multivariate Gaussian distribution
and generating realisations from the distribution.
The performance of this approach is
evaluated on various thickness maps from the
same pipeline, where data have been obtained
by measuring the actual remaining wall thickness.
The output of this work aims to serve as
the input of
Su, D, Valls Miro, J & Vidal Calleja, T 2015, 'Graph-SLAM based calibration of an embedded asynchronousmicrophone array for outdoor robotic target tracking', Assistive Robotics: Proceedings of the International Conference on CLAWAR 2015, International Conference on Climbing and Walking Robots (CLAWAR), World Scientific, Hangzhou, Zhejiang Province, China, pp. 641-648.View/Download from: Publisher's site
This paper presents a strategy for sound source localisation using an embedded asynchronous microphone array for robotic target tracking application. Conventional microphone array technologies require a multi-channel A/D converter for inter-microphone synchronization making the technology relatively expensive. In our method, a synchronization free embedded asynchronous microphone array has released this requirement. The microphone array needs self calibration using graph-based SLAM method, which estimates starting time offset and clock difference/drift of each microphone channel using Gauss-Newton least square optimization. Once calibrated, the asynchronous microphone array can be used to find the sound source direction using various Direction Of Arrival (DOA) estimation algorithms just like a synchronized one. The proposed method is suitable for target tracking applications. Specifically, this method is used for tracking a person with an outdoor service robot: Garden Utility Transportation System. Comprehensive simulations and experimental results are presented to show the validity of the algorithm.
Su, D, Valls Miro, J & Vidal Calleja, T 2015, 'Modelling In-Pipe Acoustic Signal Propagation for Condition Assessment of Multi-Layer Water Pipelines', Proceedings of the 10th IEEE Conference on Industrial Electronics and Applications, IEEE Conference on Industrial Electronics and Applications, IEEE, Auckland, New Zealand, pp. 545-550.View/Download from: Publisher's site
A solution to the condition assessment of fluid-filled conduits based on the analysis of in-pipe acoustic signal propagation is presented in this paper. The sensor arrangement consists of an acoustic emitter from which a known sonic pulse is generated, and a collocated hydrophone receiver that records the arrival acoustic wave at a high sampling rate. The proposed method exploits the influence of the surrounding environment on the propagation of an acoustic wave to estimate the condition of the pipeline. Specifically, the propagation speed of an acoustic wave is influenced by the hoop stiffness of the surrounding materials, a fact that has been exploited in the analysis of boreholes in the literature. In this work, this finding is extended to validate the analytical expression derived to infer the condition of uniform, axis-symmetric lined waterworks, a first step to ultimately be able to predict the remaining active life (time- to-failure) of pipelines with arbitrary geometries through finite element analysis (FEA). An investigation of the various aspects of the proposed methodology with typical pipe material and structures is presented to appreciate the advantages of modelling acoustic waves behaviours in fluid-filled cylindrical cavities for condition assessment of water pipelines.
Su, D, Valls Miro, J & Vidal Calleja, T 2015, 'Real-time Sound Source Localisation for Target Tracking Applications using an Asynchronous Microphone Array', 2015 IEEE 10th Conference on Industrial Electronics and Applications (ICIEA), IEEE Conference on Industrial Electronics and Applications, IEEE, Auckland, New Zealand.View/Download from: Publisher's site
Su, D, Vidal Calleja, TA & Valls Miro, J 2015, 'Simultaneous asynchronous microphone array calibration and sound source localisation', IEEE International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Hamburg, Germany, pp. 5561-5567.View/Download from: Publisher's site
In this paper, an approach for sound source
localisation and calibration of an asynchronous microphone
array is proposed to be solved simultaneously. A graph-based
Simultaneous Localisation and Mapping (SLAM) method is
used for this purpose. Traditional sound source localisation
using a microphone array has two main requirements. Firstly,
geometrical information of microphone array is needed. Secondly,
a multichannel analog-to-digital converter is required
to obtain synchronous readings of the audio signal. Recent
works aim at releasing these two requirements by estimating
the time offset between each pair of microphones. However, it
was assumed that the clock timing in each microphone sound
card is exactly the same, which requires the clocks in the sound
cards to be identically manufactured. A methodology is hereby
proposed to calibrate an asynchronous microphone array using
a graph-based optimisation method borrowed from the SLAM
literature, effectively estimating the array geometry, time offset
and clock difference/drift rate of each microphone together with
the sound source locations. Simulation and experimental results
are presented, which prove the effectiveness of the proposed
methodology in achieving accurate estimates of the microphone
array characteristics needed to be used on realistic settings with
asynchronous sound devices.
Sun, L, Vidal Calleja, TA & Valls Miro, J 2015, 'Bayesian Fusion using Conditionally Independent Submaps for High Resolution 2.5D Mapping', Proceedings of 2015 IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Seattle, Washington, United States, pp. 3394-3400.View/Download from: Publisher's site
— Typically 2.5D maps provide a compact and effi- cient representation of the environment. When sensor data is obtained from multiple sets of noisy measurements at differing resolutions, the problem of compounding this information together to provide an effective and efficient means of mapping is not trivial, particularly as the size of the environment increases. In this paper, we propose a general framework for integrating heterogeneous sensor data to obtain largescale 2.5D probabilistic maps. Gaussian Processes are used to generate a prior map that learns the spatial correlation between nearby points. Bayesian data fusion is then employed to update these prior maps with new measurements from distinct sensor modalities. In order to deal with large scale data, a novel submapping strategy is introduced to perform the fusion step efficiently in dealing with large covariance matrices. Submaps are first marginalised from the learned correlated prior and then updated based on the property of conditional independence. Most notably, the technique lends itself to generate accurate estimates at arbitrary resolutions and is able to handle varying noise from disparate sensor sources. The framework is applied to pipeline thickness mapping, with experimental results in fusing a high-resolution sensor and a low-resolution sensor showing the ability of the proposed technique to capture spatial correlations to come up with more accurate results when compared with a na¨ıve fusion approach.
Falque, R, Vidal-Calleja, T, Valls Miro, J, Lingnau, DC & Russel, DE 2014, 'Background Segmentation to Enhance Remote Field Eddy Current Signals', https://ssl.linklings.net/conferences/acra/acra2014_proceedings/views/a…, Australasian Conference on Robotics and Automation, ARAA, Melbourne University.
Pipe condition assessment is critical to avoid breakages. Remote Field Eddy Current (RFEC) is a commonly used technology to assess the condition of pipes. The nature of this technology induces some particular noise into its measurements. In this paper, we develop a 3D simulation based on the Finite Element Analysis to study the properties of this noise. Moreover, we propose filtering process based on a modified version of graph-cuts segmentation method to remove the influence of this noise. Simulated data together with an experimental data-set obtained from a real RFEC inspection show the validity of the proposed approach.
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, IEEE/RSJ International Conference on Intelligent Robots and Systems, Institute of Electrical and Electronics Engineers Inc., Chicago, IL, pp. 1748-1753.View/Download from: 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.
Skinner, B, Vidal Calleja, T, Valls Miro, J, de Bruijn, F & Falque, R 2014, '3D Point Cloud Upsampling for Accurate Reconstruction of Dense 2.5D Thickness Maps.', https://ssl.linklings.net/conferences/acra/acra2014_proceedings/views/a…, Australasian Conference on Robotics and Automation, ARAA, Melbourne University.
This paper presents a novel robust processing methodology for computing 2.5D thickness maps from dense 3D collocated surfaces. The proposed pipeline is suitable to faithfully adjust data representation detailing as required, from preserving fine surface features to coarse interpretations. The foundations of the proposed technique exploit spatial point-based filtering, ray tracing techniques and the Robust Implicit Moving Least Squares (RIMLS) algorithm applied to dense 3D datasets, such as those acquired from laser scanners. The effectiveness of the proposed technique in overcoming traditional angular aliasing and corruption artifacts is validated with 3D ranging data acquired from internal and external surfaces of exhumed water pipes. It is shown that the resulting 2.5D maps can be more accurately and completely computed to higher resolutions, while significantly reducing the number of raytracing errors when compared with 2.5D thickness maps derived from our current approach.
Ulapane, N, Alempijevic, A, Vidal-Calleja, T, Valls Miro, J, Rudd, J & Roubal, M 2014, 'Gaussian process for interpreting pulsed eddy current signals for ferromagnetic pipe profiling', Industrial Electronics and Applications (ICIEA), 2014 IEEE 9th Conference on, IEEE Conference on Industrial Electronics and Applications, IEEE, Hangzhou, PEOPLES R CHINA, pp. 1762-1767.View/Download from: Publisher's site
Vidal Calleja, TA, Su, D, De Bruijn, F & Valls Miro, J 2014, 'Learning Spatial Correlations for Bayesian fusion in Pipe Thickness Mapping', 2014 IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Hong Kong, pp. 1-8.View/Download from: Publisher's site
Vidal Calleja, TA, Valls Miro, J, Martin, F, Lingnau, D & Russell, D 2014, 'Automatic Detection and Verification of Pipeline Construction Featureswith Multi-modal data', IEEE International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Chicago, IL, USA, pp. 3116-3122.View/Download from: Publisher's site
Assessment of the condition of underground pipelines is crucial to avoid breakages. Autonomous in-line inspection tools provided with Non-destructive Technology (NDT) sensors to assess large sections of the pipeline are commonly used for these purposes. An example of such sensors based on Eddy currents is the Remote Field Technology (RFT). A crucial step during in-line inspections is the detection of construction features, such as joints and elbows, to accurately locate and size specific defects within pipe sections. This step is often performed manually with the aid of visual data, which results in slow data processing. In this paper, we propose a generic framework to automate the detection and verification of these construction
features using both NDT sensor data and visual images. Firstly, supervised learning is used to identify the construction features in the NDT sensor signals. Then, image processing is employed to verify the selection. Results are presented with data from a
RFT tool, for which a specialised descriptor has been designed to characterise and classify its signal features. Furthermore, the construction feature is displayed in the image, once it is identified in the RFT data and detected in the visual data. A visual odometry algorithm has been implemented to locate the visual data with respect to the RFT data. About 800 meters of these multi-modal data are evaluated to test the validity of the proposed approach.
Wijerathna, BS, Vidal Calleja, TA, Kodagoda, S, Zhang, Q & Valls Miro, J 2013, 'Multiple defect interpretation based on Gaussian processes for MFL technology', Proceedings of SPIE - The International Society for Optical Engineering vol 8694 - Nondestructive Characterization for Composite Materials, Aerospace Engineering, Civil Infrastructure, and Homeland Security 2013, Conference on Nondestructive Characterization for Composite Materials, Aerospace Engineering, Civil Infrastructure, and Homeland Security, SPIE, San Diego, USA, pp. 1-12.View/Download from: Publisher's site
Magnetic Flux Leakage (MFL) technology has been used in non-destructive testing for more than three decades. There have been several publications in detecting and sizing defects on metal pipes using machine learning techniques. Most of these literature focus on isolated defects, which is far from the real scenario.
Vidal Calleja, TA & Agammenoni, G 2012, 'Integrated Probabilistic Generative Model For Detecting Smoke On Visual Images', Robotics and Automation (ICRA), 2012 IEEE International Conference on, IEEE International Conference on Robotics and Automation, IEEE, St Paul, MN, pp. 2183-2188.View/Download from: Publisher's site
Early fire detection is crucial to minimise damage and save lives. Video surveillance smoke detectors do not suffer from transport delays and can cover large areas. The smoke detection on images is, however, a difficult problem due the variability of smo
Brunner, C, Peynot, T & Vidal Calleja, TA 2011, 'Combining Multiple Sensor Modalities For A Localisation Robust To Smoke', Intelligent Robots and Systems (IROS), 2011 IEEE/RSJ International Conference on, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, San Francisco, CA, pp. 0-0.View/Download from: Publisher's site
This paper proposes an approach to obtain a localisation that is robust to smoke by exploiting multiple sensing modalities: visual and infrared (IR) cameras. This localisation is based on a state-of-the-art visual SLAM algorithm. First, we show that a re
Brunner, C, Peynot, T & Vidal-Calleja, T 2011, 'Combining multiple sensor modalities for a localisation robust to smoke', 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011), IEEE.View/Download from: Publisher's site
Nieto, J, Agamennoni, G & Vidal Calleja, TA 2011, 'Loop-closure Candidates Selection By Exploiting Structure In Vehicle Trajectory', 2011 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, San Francisco, CA, pp. 92-97.View/Download from: Publisher's site
One of the most important problems in robot localisation is the detection of previously visited places (loops). When a robot closes a loop, the association between observed features and present ones can be used to update its position. The computational c
Nieto, JI, Agamennoni, G & Vidal-Calleja, T 2011, 'Loop-closure candidates selection by exploiting structure in vehicle trajectory', 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011), IEEE.View/Download from: Publisher's site
Hernandez-Gutierrez, A, Nieto, JI, Vidal-Calleja, T & Nebot, E 2009, 'Large scale visual odometry using stereo vision', Proceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009.
This paper presents a system for egomotion estimation using a stereo head camera. The camera motion estimation is based on features tracked along a video sequence. The system also estimates the tridimensional geometry of the environment by fusing the visual information from multiple views. Furthermore, the paper presents comparisons between two different algorithms. The first one is by applying triangulation to 3D points. Motion estimation using 3D points suffers from the problem of nonisotropic noise due to the large uncertainty in depth estimation. To deal with this problem we present results with a second approach that works directly in the disparity space. Experimental results using a mobile platform are presented. The experiments cover long distances in urban-like environments with the presence of dynamic objects. The system presented is part of a bigger project involving autonomous navigation using vision only.
Sola, J, Vidal Calleja, TA & Devy, M 2009, 'Undelayed Initialization Of Line Segments In Monocular Slam', Intelligent Robots and Systems, 2009. IROS 2009. IEEE/RSJ International Conference on, IEEE RSJ International Conference on Intelligent Robots and Systems, IEEE, St. Louis, MO, pp. 1553-1558.View/Download from: Publisher's site
This paper presents 6-DOF monocular EKF-SLAM with undelayed initialization using linear landmarks with extensible endpoints, based on the Plucker parametrization. A careful analysis of the properties of the Plucker coordinates, defined in the projective
Vidal Calleja, TA, Berger, C & Lacroix, S 2009, 'Event-driven Loop Closure In Multi-robot Mapping', elligent Robots and Systems, 2009. IROS 2009. IEEE/RSJ International Conference on, IEEE RSJ International Conference on Intelligent Robots and Systems, IEEE, St Louis, MO, pp. 1535-1540.View/Download from: Publisher's site
A large-scale mapping approach is combined with multiple robots events to achieve cooperative mapping. The mapping approach used is based on hierarchical SLAM global level and local maps, which is generalized for the multi-robot case. In particular, the
Neubert, P, Protzel, P, Vidal Calleja, TA & Lacroix, S 2008, 'A Fast Visual Line Segment Tracker', 2008 IEEE INTERNATIONAL CONFERENCE ON EMERGING TECHNOLOGIES AND FACTORY AUTOMATION, PROCEEDINGS, 13th IEEE International Conference on Emerging Technologies and Factory Automation, IEEE, Hamburg, GERMANY, pp. 353-360.View/Download from: Publisher's site
We present a fast line segment tracker which does not require any knowledge about the motion of the camera nor he structure of the observed scene. It runs on 320 x 240 pixel images at 30 Hz. We adapted the RAPiD tracker with a new way of handling multipl
Vidal Calleja, TA, Bryson, M, Sukkarieh, S, Sanfeliu, A & Andrade-cetto, J 2007, 'On, On The Observability Of Bearing-only Slam', PROCEEDINGS OF THE 2007 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-10, IEEE International Conference on Robotics and Automation, IEEE, Rome, ITALY, pp. 4114-4119.View/Download from: Publisher's site
In this paper we present an observability analysis for a mobile robot performing SLAM with a single monocular camera. The aim is to get a better understanding of the well known intuitive behavior of these systems, such as the need for triangulation to fe
Vidal-Calleja, T, Sanfeliu, A & Juan, AC 2007, 'Guiding and localising in real-time a mobile robot with a monocular camera in non-flat terrains', IFAC Proceedings Volumes (IFAC-PapersOnline), pp. 560-565.View/Download from: Publisher's site
In this paper we present a real-time active motion strategy for a mobile robot navigating in a non-flat terrain and its 3D constrained motion model. The aim is to control the robot with measurements from only one camera that autonomously builds a visual feature map while at the same time optimises its localisation within this map. The technique chooses the most appropriate commands maximising the expected information gain between prior states and measurements, while performing 6DOF bearing-only SLAM at real-time. The constrained 3D motion model presented here is used to infer the position of the vehicle in order to evaluate the mutual information for all possible actions at the same time. To validate the approach, not only simulations over uneven terrain have been performed, but also experimental results are shown for the technique being tested with a synchro-drive mobile robot platform with a wide-angle camera.
Vidal Calleja, TA, Davison, A, Andrade-cetto, J & Murray, D 2006, 'Active Control For Single Camera Slam', 2006 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), VOLS 1-10, IEEE International Conference on Robotics and Automation (ICRA), IEEE, Orlando, FL, pp. 1930-1936.
In this paper we consider a single hand-held camera performing SLAM at video rate with generic 6DOF motion. The aim is to optimise both the localisation of the sensor and building of the feature map by computing the most appropriate control actions or mo
Andrade-cetto, J, Vidal Calleja, TA & Sanfeliu, A 2005, 'Unscented Transformation Of Vehicle States In Slam', 2005 IEEE International Conference on Robotics and Automation (ICRA), Vols 1-4, IEEE International Conference on Robotics and Automation (ICRA), IEEE, Barcelona, SPAIN, pp. 323-328.
In this article we propose an algorithm to reduce the effects caused by linearization in the typical EKF approach to SLAM. The technique consists in computing the vehicle prior using an Unscented Transformation. The UT allows a better nonlinear mean and
Vidal-Calleja, T, Andrade-Cetto, J & Sanfeliu, A 2004, 'Conditions for suboptimal filter stability in SLAM', 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 27-32.
In this article, we show marginal stability in SLAM, guaranteeing convergence to a non-zero mean state error estimate bounded by a constant value. Moreover, marginal stability guarantees also convergence of the Riccati equation of the one-step ahead state error covariance to at least one psd steady state solution. In the search for real-time implementations of SLAM, covariance inflation methods produce a suboptimal filter that eventually may lead to the computation of an unbounded state error covariance. We provide tight constraints in the amount of decorrelation possible, to guarantee convergence of the state error covariance, and at the same time, a linear-time implementation of SLAM.