A/Prof Robert Fitch is a leading research scientist in the area of autonomous field robotics. He is interested in systems of outdoor robots and their application to key problems in agriculture and environmental monitoring.
Robert received his PhD in computer science from Dartmouth (USA) and worked as a Senior Research Fellow with the Australian Centre for Field Robotics (ACFR) at The University of Sydney before joining UTS. He has led research in planning and collaborative decision-making for both ground and aerial robots in a variety of government and industry sponsored projects including those in broad-acre agriculture, horticulture, bird tracking, and commercial aviation.
Can supervise: YES
Best, G., Cliff, O.M., Patten, T., Mettu, R.R. & Fitch, R. 2018, 'Dec-MCTS: Decentralized planning for multi-robot active perception', International Journal of Robotics Research.View/Download from: Publisher's site
© 2018, The Author(s) 2018. We propose a decentralized variant of Monte Carlo tree search (MCTS) that is suitable for a variety of tasks in multi-robot active perception. Our algorithm allows each robot to optimize its own actions by maintaining a probability distribution over plans in the joint-action space. Robots periodically communicate a compressed form of their search trees, which are used to update the joint distribution using a distributed optimization approach inspired by variational methods. Our method admits any objective function defined over robot action sequences, assumes intermittent communication, is anytime, and is suitable for online replanning. Our algorithm features a new MCTS tree expansion policy that is designed for our planning scenario. We extend the theoretical analysis of standard MCTS to provide guarantees for convergence rates to the optimal payoff sequence. We evaluate the performance of our method for generalized team orienteering and online active object recognition using real data, and show that it compares favorably to centralized MCTS even with severely degraded communication. These examples demonstrate the suitability of our algorithm for real-world active perception with multiple robots.
Best, G., Faigl, J. & Fitch, R. 2018, 'Online planning for multi-robot active perception with self-organising maps', Autonomous Robots, vol. 42, no. 4, pp. 715-738.View/Download from: UTS OPUS or Publisher's site
© 2017, Springer Science+Business Media, LLC, part of Springer Nature. We propose a self-organising map (SOM) algorithm as a solution to a new multi-goal path planning problem for active perception and data collection tasks. We optimise paths for a multi-robot team that aims to maximally observe a set of nodes in the environment. The selected nodes are observed by visiting associated viewpoint regions defined by a sensor model. The key problem characteristics are that the viewpoint regions are overlapping polygonal continuous regions, each node has an observation reward, and the robots are constrained by travel budgets. The SOM algorithm jointly selects and allocates nodes to the robots and finds favourable sequences of sensing locations. The algorithm has a runtime complexity that is polynomial in the number of nodes to be observed and the magnitude of the relative weighting of rewards. We show empirically the runtime is sublinear in the number of robots. We demonstrate feasibility for the active perception task of observing a set of 3D objects. The viewpoint regions consider sensing ranges and self-occlusions, and the rewards are measured as discriminability in the ensemble of shape functions feature space. Exploration objectives for online tasks where the environment is only partially known in advance are modelled by introducing goal regions in unexplored space. Online replanning is performed efficiently by adapting previous solutions as new information becomes available. Simulations were performed using a 3D point-cloud dataset from a real robot in a large outdoor environment. Our results show the proposed methods enable multi-robot planning for online active perception tasks with continuous sets of candidate viewpoints and long planning horizons.
Cliff, O.M., Prokopenko, M. & Fitch, R. 2018, 'Minimising the Kullback–Leibler Divergence for Model Selection in Distributed Nonlinear Systems', Entropy, vol. 20, no. 2.View/Download from: UTS OPUS or Publisher's site
D'Urso, G., Smith, S.L., Mettu, R., Oksanen, T. & Fitch, R. 2018, 'Multi-vehicle refill scheduling with queueing', Computers and Electronics in Agriculture, vol. 144, pp. 44-57.View/Download from: Publisher's site
© 2017 We consider the problem of refill scheduling for a team of vehicles or robots that must contend for access to a single physical location for refilling. The objective is to minimise time spent in travelling to/from the refill station, and also time lost to queuing (waiting for access). In this paper, we present principled results for this problem in the context of agricultural operations. We first establish that the problem is NP-hard and prove that the maximum number of vehicles that can usefully work together is bounded. We then focus on the design of practical algorithms and present two solutions. The first is an exact algorithm based on dynamic programming that is suitable for small problem instances. The second is an approximate anytime algorithm based on the branch and bound approach that is suitable for large problem instances with many robots. We present simulated results of our algorithms for three classes of agricultural work that cover a range of operations: spot spraying, broadcast spraying and slurry application. We show that the algorithm is reasonably robust to inaccurate prediction of resource utilisation rate, which is difficult to estimate in cases such as spot application of herbicide for weed control, and validate its performance in simulation using realistic scenarios with up to 30 robots.
Classifying objects in complex unknown environments is a challenging problem in robotics and is fundamental in many applications. Modern sensors and sophisticated perception algorithms extract rich 3D textured information, but are limited to the data that are collected from a given location or path. We are interested in closing the loop around perception and planning, in particular to plan paths for better perceptual data, and focus on the problem of planning scanning sequences to improve object classification from range data. We formulate a novel time-constrained active classification problem and propose solution algorithms that employ a variation of Monte Carlo tree search to plan non-myopically. Our algorithms use a particle filter combined with Gaussian process regression to estimate joint distributions of object class and pose. This estimator is used in planning to generate a probabilistic belief about the state of objects in a scene, and also to generate beliefs for predicted sensor observations from future viewpoints. These predictions consider occlusions arising from predicted object positions and shapes. We evaluate our algorithms in simulation, in comparison to passive and greedy strategies. We also describe similar experiments where the algorithms are implemented online, using a mobile ground robot in a farm environment. Results indicate that our non-myopic approach outperforms both passive and myopic strategies, and clearly show the benefit of active perception for outdoor object classification.
Abdilla, A. & Fitch, R. 2017, 'FCJ-209 Indigenous Knowledge Systems and Pattern Thinking: An Expanded Analysis of the First Indigenous Robotics Prototype Workshop', The Fibreculture Journal.
Abdilla, A. & Fitch, R. 2017, 'FCJ-209 Indigenous Knowledge Systems and Pattern Thinking: An Expanded Analysis of the First Indigenous Robotics Prototype Workshop', Fibreculture Journal: internet theory criticism research, no. 28, pp. 1-14.View/Download from: UTS OPUS or Publisher's site
In November 2014, the lead researcher's interest in the conceptual development of digital
technology and her cultural connection to Indigenous Knowledge Systems created an opportunity to
explore a culturally relevant use of technology with urban Indigenous youth: the Indigenous Robotics
Prototype Workshop. The workshop achieved a sense of cultural pride and confidence in Indigenous
traditional knowledge while inspiring the youth to continue with their engagement in coding and
programming through building robots. Yet, the outcomes from the prototype workshop further revealed a
need to investigate how Indigenous Knowledge Systems, and particularly Pattern Thinking, might hint
toward a possible paradigm shift for the ethical and advanced design of new technologies. This article
examines the implications of such a hypothetical shift in autonomous systems in robotics and artificial
intelligence (AI), using the Indigenous Robotics Prototype Workshop as a case study and springboard.
The Technical Committee (TC) on Multirobot Systems (MRS) was founded in 2014 to create a focal point for the wide and diverse community of researchers interested in MRS. Researchers interested in MRS represent an inherently diverse community because several competences are needed in this field, including control systems, mechanical design, coordination, cooperation, estimation, perception, and interaction. MRS research comprises three broad research areas. These areas of interest are modeling and control of MRS, planning and decision making for MRS, and applications of MRS and technological and methodological issues. The MRS TC sponsors many activities that bring our members together, both in person and online. Our flagship achievement to date is the founding of a new conference dedicated to multirobot and multiagent systems, the International Symposium on Multirobot and Multiagent Systems.
Fitch, R., Best, G. & Martens, W. 2017, 'Path Planning With Spatiotemporal Optimal Stopping for Stochastic Mission Monitoring', IEEE Transactions on Robotics, vol. 33, no. 3, pp. 629-646.View/Download from: UTS OPUS or Publisher's site
We consider an optimal stopping formulation of the mission monitoring problem, in which a monitor vehicle must remain in close proximity to an autonomous robot that stochastically follows a predicted trajectory. This problem arises in a diverse range of scenarios, such as autonomous underwater vehicles supervised by surface vessels, pedestrians monitored by aerial vehicles, and animals monitored by agricultural robots. The key problem characteristics we consider are that the monitor must remain stationary while observing the robot, robot motion is modeled in general as a stochastic process, and observations are modeled as a spatial probability distribution. We propose a resolution-complete algorithm that runs in a polynomial time. The algorithm is based on a sweep-plane approach and generates a motion plan that maximizes the expected observation time and value. A variety of stochastic models may be used to represent the robot trajectory. We present results with data drawn from real AUV missions, a real pedestrian trajectory dataset and Monte Carlo simulations. Our results demonstrate the performance and behavior of our algorithm, and relevance to a variety of applications.
Martens, W., Poffet, Y., Soria, P.R., Fitch, R. & Sukkarieh, S. 2017, 'Geometric Priors for Gaussian Process Implicit Surfaces', IEEE Robotics and Automation Letters, vol. 2, no. 2, pp. 373-380.View/Download from: UTS OPUS or Publisher's site
This paper presents an extension of Gaussian process implicit surfaces (GPIS) by the introduction of geometric object priors. The proposed method enhances the probabilistic reconstruction of objects from three-dimensional (3-D) pointcloud data, providing a rigorous way of incorporating prior knowledge about objects expected in a scene. The key ideas, including the systematic use of surface normal information, are illustrated with one-dimensional and two-dimensional examples, and then applied to simulated and real pointcloud data for 3-D objects. The performance of our method is demonstrated in two different application scenarios, using complete and partial surface observations. Qualitative and quantitative analysis of the results reveals the superiority of the proposed approach over existing GPIS configurations that do not exploit prior knowledge.
Ball, D., Upcroft, B., Wyeth, G., Corke, P., English, A., Ross, P., Patten, T., Fitch, R., Sukkarieh, S. & Bate, A. 2016, 'Vision-based Obstacle Detection and Navigation for an Agricultural Robot', Journal of Field Robotics, vol. 33, no. 8, pp. 1107-1130.View/Download from: Publisher's site
This paper describes a vision-based obstacle detection and navigation system for use as part of a robotic solution for the sustainable intensification of broad-acre agriculture. To be cost-effective, the robotics solution must be competitive with current human-driven farm machinery. Significant costs are in high-end localization and obstacle detection sensors. Our system demonstrates a combination of an inexpensive global positioning system and inertial navigation system with vision for localization and a single stereo vision system for obstacle detection. The paper describes the design of the robot, including detailed descriptions of three key parts of the system: novelty-based obstacle detection, visually-aided guidance, and a navigation system that generates collision-free kinematically feasible paths. The robot has seen extensive testing over numerous weeks of field trials during the day and night. The results in this paper pertain to one particular 3 h nighttime experiment in which the robot performed a coverage task and avoided obstacles. Additional results during the day demonstrate that the robot is able to continue operating during 5 min GPS outages by visually following crop rows.
Cliff, O.M., Prokopenko, M. & Fitch, R.C. 2016, 'An Information Criterion for Inferring Coupling of Distributed Dynamical Systems', Frontiers in Robotics and AI, vol. 3, pp. 1-9.View/Download from: UTS OPUS or Publisher's site
The behavior of many real-world phenomena can be modeled by non-linear dynamical systems whereby a latent system state is observed through a filter. We are interested in interacting subsystems of this form, which we model by a set of coupled maps as a synchronous update graph dynamical system. Specifically, we study the structure learning problem for spatially distributed dynamical systems coupled via a directed acyclic graph. Unlike established structure learning procedures that find locally maximum posterior probabilities of a network structure containing latent variables, our work exploits the properties of dynamical systems to compute globally optimal approximations of these distributions. We arrive at this result by the use of time delay embedding theorems. Taking an information-theoretic perspective, we show that the log-likelihood has an intuitive interpretation in terms of information transfer.
Nguyen, J.L., Lawrance, N.R.J., Fitch, R. & Sukkarieh, S. 2016, 'Real-time path planning for long-term information gathering with an aerial glider', AUTONOMOUS ROBOTS, vol. 40, no. 6, pp. 1017-1039.View/Download from: UTS OPUS or Publisher's site
Patten, T., Zillich, M., Fitch, R., Vincze, M. & Sukkarieh, S. 2016, 'Viewpoint Evaluation for Online 3-D Active Object Classification', IEEE Robotics and Automation Letters, vol. 1, no. 1, pp. 73-81.View/Download from: UTS OPUS or Publisher's site
Yoo, C., Fitch, R. & Sukkarieh, S. 2016, 'Online task planning and control for fuel-constrained aerial robots in wind fields', INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, vol. 35, no. 5, pp. 438-453.View/Download from: Publisher's site
Fitch, R., Sukkarieh, S., Bergerman, M. & van Henten, E. 2015, '2015 IEEE RAS Summer School on Agricultural Robotics', IEEE ROBOTICS & AUTOMATION MAGAZINE, vol. 22, no. 2, pp. 96-98.View/Download from: UTS OPUS or Publisher's site
Kassir, A., Fitch, R. & Sukkarieh, S. 2015, 'Communication-aware information gathering with dynamic information flow', INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, vol. 34, no. 2, pp. 173-200.View/Download from: UTS OPUS or Publisher's site
Clements, D., Dugdale, T., Hunt, T., Fitch, R., Hung, C., Sukkarieh, S. & Xu, Z. 2014, 'Detection of alligator weed using an unmanned aerial vehicle', Plant Protection Quarterly, vol. 29, no. 3, pp. 84-89.View/Download from: UTS OPUS
A key impediment to the successful eradication
of high priority aquatic weeds
(State Prohibited Weeds in Victoria,
Australia) is the ability to detect infestations
so that control programs can be
enacted. Currently, the sole method used
to detect State Prohibited Weeds (SPWs)
is on-ground human surveillance.
Advances in unmanned aerial vehicle
(UAV) technology offer an opportunity to
detect SPWs using high resolution aerial
images of areas known, or suspected, to
contain SPWs. This proof of concept field
trial used a UAV coupled with a camera
to gain aerial imagery of an urban creek
and wetlands to detect alligator weed
(Alternanthera philoxeroides (Mart.)
Griseb.), a SPW that is currently being
targeted for eradication from Victoria.
The ability of three methods to detect
patches of alligator weed was compared:
intensive on-ground surveys; visual
assessment of images collected by the
UAV; and an automated algorithm to
scan images for the spectral signature of
Gan, S.K., Fitch, R. & Sukkarieh, S. 2014, 'Online decentralized information gathering with spatial-temporal constraints', AUTONOMOUS ROBOTS, vol. 37, no. 1, pp. 1-25.View/Download from: UTS OPUS or Publisher's site
Peynot, T., Lui, S.-.T., McAllister, R., Fitch, R. & Sukkarieh, S. 2014, 'Learned Stochastic Mobility Prediction for Planning with Control Uncertainty on Unstructured Terrain', JOURNAL OF FIELD ROBOTICS, vol. 31, no. 6, pp. 969-995.View/Download from: UTS OPUS or Publisher's site
Xu, Z., Fitch, R., Underwood, J. & Sukkarieh, S. 2013, 'Decentralized Coordinated Tracking with Mixed Discrete-Continuous Decisions', JOURNAL OF FIELD ROBOTICS, vol. 30, no. 5, pp. 717-740.View/Download from: UTS OPUS or Publisher's site
Singh, S.P.N., Fitch, R. & Williams, S.B. 2010, 'A research-driven approach to undergraduate robotics education', Computers in Education Journal, vol. 20, no. 4, pp. 21-27.
Robotics is a rapidly-progressing and applied subject. This paper advocates for a researchdriven model for modern robotics course design that, based on a principled approach, prepares students to consider and adopt recent results in their mechatronics applications. This view provides a rubric for defining a sufficient set of topics that give a broad overview of robotic technologies and provides a foundation for later (undergraduate) research experience. To address the inherently multidisciplinary nature of robotics, a modular co-teaching model is adopted in which separate sections are taught by different lecturers, who potentially span various academic departments. Evidence supporting this approach is illustrated from case studies of student projects in The University of Sydney's Experimental Robotics course, MTRX 4700. By providing an engaging topic, a research approach, extensive mentorship, and an open-ended problem, the course not only meets learning objectives, but also promotes a research foundation supporting later undergraduate research opportunities.
Sprinkle, J., Eklund, J.M., Gonzalez, H., Grotli, E.I., Upcroft, B., Makarenko, A., Uther, W., Moser, M., Fitch, R., Durrant-Whyte, H. & Sastry, S.S. 2009, 'Model-based design: a report from the trenches of the DARPA Urban Challenge', SOFTWARE AND SYSTEMS MODELING, vol. 8, no. 4, pp. 551-566.View/Download from: Publisher's site
Fitch, R. & Butler, Z. 2008, 'Million module march: Scalable locomotion for large self-reconfiguring robots', INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, vol. 27, no. 3-4, pp. 331-343.View/Download from: Publisher's site
Upcroft, B., Makarenko, A., Moser, M., Alempijevic, A., Donikian, A., Uther, W. & Fitch, R. 2007, 'Empirical Evaluation of an Autonomous Vehicle in an Urban Environment', Journal Of Aerospace Computing, Information, And Communication, vol. 4, no. 12, pp. 1086-1107.View/Download from: UTS OPUS or Publisher's site
Operation in urban environments creates unique challenges for research in autonomous ground vehicles. In this paper, we describe a novel autonomous platform developed by the Sydney-Berkeley Driving Team for entry into the 2007 DARPA Urban Challenge competition. We report empirical results analyzing the performance of the vehicle while navigating a 560-meter test loop multiple times in an actual urban setting with severe GPS outage. We show that our system is robust against failure of global position estimates and can reliably traverse standard two-lane road networks using vision for localization.
Arora, A., Furlong, P.M., Fitch, R., Fong, T., Sukkarieh, S. & Elphic, R. 2018, 'Online Multi-modal Learning and Adaptive Informative Trajectory Planning for Autonomous Exploration' in Hutter, M. & Siegwart, R. (eds), Field and Service Robotics, Springer International Publishing, pp. 239-254.
Ramon Soria, P., Sukkar, F., Martens, W., Arrue, B.C. & Fitch, R. 2018, 'Multi-view Probabilistic Segmentation of Pome Fruit with a Low-Cost RGB-D Camera' in Ollero, A., Sanfeliu, A., Montano, L., Lau, N. & Cardeira, C. (eds), ROBOT 2017: Third Iberian Robotics Conference, Springer International Publishing, pp. 320-331.
Fitch, R., Alempijevic, A. & Peynot, T. 2016, 'Global reconfiguration of a team of networked mobile robots among obstacles', Springer, Berlin, Germany, pp. 639-656.View/Download from: UTS OPUS or Publisher's site
This paper presents a full system demonstration of dynamic sensor-based reconfiguration of a networked robot team. Robots sense obstacles in their environment locally and dynamically adapt their global geometric configuration to conform to an abstract goal shape.We present a novel two-layer planning and control algorithm for team reconfiguration that is decentralized and assumes local (neighbour-to-neighbour) communication only. The approach is designed to be resource-efficient and we show experiments using a team of nine mobile robots with modest computation, communication, and sensing. The robots use acoustic beacons for localisation and can sense obstacles in their local neighbourhood using IR sensors. Our results demonstrate globally-specified reconfiguration
from local information in a real robot network, and highlight limitations
of standard mesh networks in implementing decentralised algorithms.
Ball, D., Ross, P., English, A., Patten, T., Upcroft, B., Fitch, R., Sukkarieh, S., Wyeth, G. & Corke, P. 2015, 'Robotics for sustainable broad-acre agriculture', Springer, Germany, pp. 439-453.View/Download from: UTS OPUS or Publisher's site
This paper describes the development of small low-cost cooperative robots for sustainable broad-acre agriculture to increase broad-acre crop production and reduce environmental impact. The current focus of the project is to use robotics to deal with resistant weeds, a critical problem for Australian farmers. To keep the overall system affordable our robot uses low-cost cameras and positioning sensors to perform a large scale coverage task while also avoiding obstacles. A multi-robot coordinator assigns parts of a given field to individual robots. The paper describes the modification of an electric vehicle for autonomy and experimental results from one real robot and twelve simulated robots working in coordination for approximately two hours on a 55 hectare field in Emerald Australia. Over this time the real robot 'sprayed' 6 hectares missing 2.6% and overlapping 9.7% within its assigned field partition, and successfully avoided three obstacles.
Lui, S.T., Peynot, T., Fitch, R. & Sukkarieh, S. 2015, 'Enhanced stochastic mobility prediction with multi-output Gaussian processes', Springer, pp. 173-190.View/Download from: UTS OPUS or Publisher's site
© Springer International Publishing Switzerland 2016.Outdoor robots such as planetary rovers must be able to navigate safely and reliably in order to successfully perform missions in remote or hostile environments. Mobility prediction is critical to achieving this goal due to the inherent control uncertainty faced by robots traversing natural terrain. We propose a novel algorithm for stochastic mobility prediction based on multi-output Gaussian process regression. Our algorithm considers the correlation between heading and distance uncertainty and provides a predictive model that can easily be exploited by motion planning algorithms. We evaluate our method experimentally and report results from over 30 trials in a Mars-analogue environment that demonstrate the effectiveness of our method and illustrate the importance of mobility prediction in navigating challenging terrain.
Yoo, C., Fitch, R. & Sukkarieh, S. 2015, 'Online task planning and control for aerial robots with fuel constraints in winds' in Algorithmic Foundations of Robotics XI, Springer, 42, pp. 711-727.View/Download from: Publisher's site
© Springer International Publishing Switzerland 2015. Real-world applications of aerial robots must consider operational constraints such as fuel level during task planning. This paper presents an algorithm for automatically synthesizing a continuous non-linear flight controller given a complex temporal logic task specification that can include contingency planning rules. Our method is a hybrid controller where fuel level is treated continuously in the low-level and symbolically in the high-level. The low-level controller assumes the availability of a set of point-estimates of wind velocity and builds a continuous interpolation using Gaussian process regression. Fuel burn and aircraft dynamics are modelled under physically realistic assumptions.Our algorithm is efficient and we showempirically that it is feasible for online execution and replanning. We present simulation examples of navigation in a wind field and surveillance with fuel constraints.
Reconfiguration allows a self-reconfiguring modular robot to adapt to its environment. The reconfiguration planning problem is one of the key algorithmic challenges in realizing self-reconfiguration. Many existing successful approaches rely on grouping modules together to act as meta-modules. However, we are interested in reconfiguration planning that does not impose fixed meta-module relationships but instead forms cooperative relationships between modules dynamically. This approach avoids the need to hand-code meta-module motions and potentially allows reconfiguration with fewer modules. In this paper we present a general two level reconfiguration framework. The top level plans in module-connector space using distributed dynamic programming. The lower level accepts a transition function for the kinematic model of the chosen module type as input. As an example, we implement such a transition function for the 3R, SuperBot-style module. Although not explored in this paper, this general approach is naturally extended to consider power use, clock time, or other quantities of interest. © 2013 Springer-Verlag.
Peynot, T., Fitch, R., McAllister, R. & Alempijevic, A. 2013, 'Resilient Navigation through Probabilistic Modality Reconfiguration', Springer Verlag, Berlin, Germany, pp. 75-88.View/Download from: UTS OPUS or Publisher's site
This paper proposes an approach to achieve resilient navigation for indoor mobile robots. Resilient navigation seeks to mitigate the impact of control, localisation, or map errors on the safety of the platform while enforcing the robots ability to achieve its goal. We show that resilience to unpredictable errors can be achieved by combining the benefits of independent and complementary algorithmic approaches to navigation, or modalities, each tuned to a particular type of environment or situation. In this paper, the modalities comprise a path planning method and a reactive motion strategy. While the robot navigates, a Hidden Markov Model continually estimates the most appropriate modality based on two types of information: context (information known a priori) and monitoring (evaluating unpredictable aspects of the current situation). The robot then uses the recommended modality, switching between one and another dynamically. Experimental validation with a SegwayRMPbased platform in an office environment shows that our approach enables failure mitigation while maintaining the safety of the platform. The robot is shown to reach its goal in the presence of: 1) unpredicted control errors, 2) unexpected map errors and 3) a large injected localisation fault
Yoo, C., Fitch, R. & Sukkarieh, S. 2013, 'Probabilistic temporal logic for motion planning with resource threshold constraints' in Roy, N., Newman, P. & Srinivasa, S. (eds), Robotics: Science and Systems VIII, MIT Press - Journals, UK, pp. 457-464.View/Download from: UTS OPUS
© 2013 Massachusetts Institute of Technology. Temporal logic and model-checking are useful theoretical tools for specifying complex goals at the task level and formally verifying the performance of control policies. We are interested in tasks that involve constraints on real-valued energy resources. In particular, autonomous gliding aircraft gain energy in the form of altitude by exploiting wind currents and must maintain altitude within some range during motion planning. We propose an extension to probabilistic computation tree logic that expresses such real-valued resource threshold constraints, and present model-checking algorithms that evaluate a piecewise control policy with respect to a formal specification and hard or soft performance guarantees. We validate this approach through simulated examples of motion planning among obstacles for an autonomous thermal glider. Our results demonstrate probabilistic performance guarantees on the ability of the glider to complete its task, following a given piecewise control policy, without knowing the exact path of the glider in advance.
Upcroft, B., Makarenko, A., Brooks, A., Moser, M., Alempijevic, A., Donikian, A., Sprinkle, J., Uther, W. & Fitch, R. 2012, 'Empirical Evaluation Of An Autonomous Vehicle In An Urban Environment' in Experience From The Darpa Urban Challenge, Springer-Verlag Berlin, Berlin, pp. 273-301.View/Download from: UTS OPUS or Publisher's site
Operation in urban environments creates unique challenges for research in autonomous ground vehicles. Due to the presence of tall trees and buildings in close proximity to traversable areas, GPS outage is likely to be frequent and physical hazards pose r
Upcroft, B., Makarenko, A., Brooks, A., Moser, M., Alempijevic, A., Donikian, A., Sprinkle, J., Uther, W. & Fitch, R. 2012, 'Empirical Evaluation Of An Autonomous Vehicle In An Urban Environment' in Experience From The Darpa Urban Challenge, Springer-Verlag Berlin, Berlin, pp. 273-301.View/Download from: Publisher's site
Operation in urban environments creates unique challenges for research in autonomous ground vehicles. Due to the presence of tall trees and buildings in close proximity to traversable areas, GPS outage is likely to be frequent and physical hazards pose r
Reinforcement learning algorithms can become unstable when combined with linear function approximation. Algorithms that minimize the mean-square Bellman error are guaranteed to converge, but often do so slowly or are computationally expensive. In this paper, we propose to improve the convergence speed of piecewise linear function approximation by tracking the dynamics of the value function with the Kalman filter using a random-walk model. We cast this as a general framework in which we implement the TD, Q-Learning and MAXQ algorithms for different domains, and report empirical results demonstrating improved learning speed over previous methods.
Fitch, R., Hengst, B., Suc, D., Calbert, G. & Scholz, J. 2005, 'Structural abstraction experiments in reinforcement learning', pp. 164-175.
Butler, Z., Fitch, R. & Rus, D. 2003, 'Experiments in distributed control for modular robots', pp. 307-316.
Fitch, R., Rus, D. & Vona, M. 2000, 'A basis for self-repair robots using self-reconfiguring crystal modules', pp. 903-910.
Arora, A., Fitch, R. & Sukkarieh, S. 2017, 'An Approach to Autonomous Science by Modeling Geological Knowledge in a Bayesian Framework', Proc. of IEEE/RSJ IROS.
Collart, J., Fitch, R. & Alempijevic, A. 2017, 'Motion States Inference through 3D Shoulder Gait Analysis and Hierarchical Hidden Markov Models', Proc. of ARAA ACRA.
Best, G. & Fitch, R. 2016, 'Probabilistic Maximum Set Cover with Path Constraints for Informative Path Planning', Website Proceedings of Australasian Conference on Robotics and Automation 2016, Australasian Conference on Robotics and Automation, ARAA, Brisbane, Australia, pp. 1-10.View/Download from: UTS OPUS
We pose a new formulation for informative path
planning problems as a generalisation of the
well-known maximum set cover problem. This
new formulation adds path constraints and
travel costs, as well as a probabilistic observation
model, to the maximum set cover problem.
Our motivation is informative path planning
applications where the observation model can
be naturally encoded as overlapping subsets
of a set of discrete elements. These elements
may include features, landmarks, regions, targets
or more abstract quantities, that the robot
aims to observe while moving through the environment
with a given travel budget. This
formulation allows directly modelling the dependencies
of observations from different viewpoints.
We show this problem is NP-hard and
propose a branch and bound tree search algorithm.
Simulated experiments empirically evaluate
the bounding heuristics, several tree expansion
policies and convergence rate towards
optimal. The tree pruning allows finding optimal
or bounded-approximate solutions in a reasonable
amount of time, and therefore indicates
our work is suitable for practical applications.
Best, G., Cliff, O., Patten, T., Mettu, R. & Fitch, R. 2016, 'Decentralised Monte Carlo Tree Search for Active Perception', Workshop on the Algorithmic Foundations of Robotics (WAFR), Workshop on the Algorithmic Foundations of Robotics (WAFR), International Workshop on the Algorithmic Foundations of Robotics, San Francisco, USA.View/Download from: UTS OPUS
We propose a decentralised variant of Monte Carlo tree search
(MCTS) that is suitable for a variety of tasks in multi-robot active perception.
Our algorithm allows each robot to optimise its own individual
action space by maintaining a probability distribution over plans in
the joint-action space. Robots periodically communicate a compressed
form of these search trees, which are used to update the locally-stored
joint distributions using an optimisation approach inspired by variational
methods. Our method admits any objective function defined over robot
actions, assumes intermittent communication, and is anytime. We extend
the analysis of the standard MCTS for our algorithm and characterise
asymptotic convergence under reasonable assumptions. We evaluate the
practical performance of our method for generalised team orienteering
and active object recognition using real data, and show that it compares
favourably to centralised MCTS even with severely degraded communication.
These examples support the relevance of our algorithm for
real-world active perception with multi-robot systems.
Best, G., Faigl, J. & Fitch, R. 2016, 'Multi-Robot Path Planning for Budgeted Active Perception with Self-Organising Maps', Proceedings of the 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Daejeon, Korea, pp. 3164-3171.View/Download from: UTS OPUS or Publisher's site
We propose a self-organising map (SOM) algorithm
as a solution to a new multi-goal path planning problem
for active perception and data collection tasks. We optimise
paths for a multi-robot team that aims to maximally observe a
set of nodes in the environment. The selected nodes are observed
by visiting associated viewpoint regions defined by a sensor
model. The key problem characteristics are that the viewpoint
regions are overlapping polygonal continuous regions, each
node has an observation reward, and the robots are constrained
by travel budgets. The SOM algorithm jointly selects and
allocates nodes to the robots and finds favourable sequences
of sensing locations. The algorithm has polynomial-bounded
runtime independent of the number of robots. We demonstrate
feasibility for the active perception task of observing a set of 3D
objects. The viewpoint regions consider sensing ranges and selfocclusions,
and the rewards are measured as discriminability in
the ensemble of shape functions feature space. Simulations were
performed using a 3D point cloud dataset from a real robot in
a large outdoor environment. Our results show the proposed
methods enable multi-robot planning for budgeted active perception
tasks with continuous sets of candidate viewpoints and
long planning horizons.
Hefferan, B., Cliff, O. & Fitch, R. 2016, 'Adversarial Patrolling with Reactive Point Processes', Proceedings of the Australasian Conference on Robotics & Automation (ACRA), Australasian Conference on Robotics and Automation, ARAA, Brisbane, Australia.View/Download from: UTS OPUS
Kassir, A., Fitch, R. & Sukkarieh, S. 2016, 'Communication-Efficient Motion Coordination and Data Fusion in Information Gathering Teams', Proceedings of the 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Daejeon, Korea, pp. 5258-5265.View/Download from: Publisher's site
Multi-robot information gathering teams typically require communication for data fusion and cooperative decision making. However, when communication takes place over wireless networks, stringent bandwidth limits apply. These limits raise the need for efficient utilisation of available communication resources in a manner that balances information gathering utility with communication costs or limits. In our previous work, we introduced the dynamic information flow (DIF) problem as a general formulation of this trade-off. We introduced two variants of the problem addressing the issue of communication efficiency for data fusion only. In this paper, we extend one of the variants to address communication efficiency for both data fusion and cooperative decision making in a synergistic manner. We present a solution to this new variant that integrates a multi-cast routing algorithm with information structure optimisation. This solution allows teams that involve high-data-rate sensors and tight coordination to respect bandwidth limits. Through several simulations we verify that our solution significantly reduces bandwidth usage of such teams while maintaining information gathering performance.
Nguyen, J.L., Lawrance, N.R.J., Fitch, R. & Sukkarieh, S. 2016, 'Informative soaring with drifting thermals', Proceedings - IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Stockholm, Sweden, pp. 1522-1529.View/Download from: UTS OPUS or Publisher's site
© 2016 IEEE.The informative soaring (IFS) problem involves a gliding unmanned aerial vehicle (UAV) exploiting energy from thermals to extend its information gathering capability. In this paper, we address the realistic situation of detecting new thermals drifting with the wind in the search environment. We consider complex target-search scenarios characterised by information clusters and propose a new set of algorithms designed to both explore for and exploit high-value thermals to maximise information gain. Our algorithms: 1) compute a thermal exploration map to detect useful thermals that eventually intercept clusters, 2) solve a boundary value problem for interthermal path segment (ITP) generation with moving thermals, 3) compute thermal time windows to gather information from clusters and form a cluster service schedule, and 4) use branch and bound (BnB) tree search for global planning, considering high-utility-rate ITPs to maximise information gain. Our solution is compared against a greedy method that neither considers the thermal exploration map nor cluster schedule and a full knowledge method that has access to all thermals. Numerical simulations show that on average, our solution outperforms the greedy method in one-third of 2400 Monte Carlo trials, and achieves similar performance to the full knowledge method when environmental conditions are favourable.
Patten, T., Fitch, R. & Sukkarieh, S. 2014, 'Multi-Robot Coverage Planning with Resource Constraints for Horticulture Applications', Acta Horticulturae, International Horticultural Congress on Horticulture, International Society for Horticultural Science, Brisbane, Australia, pp. 655-662.View/Download from: UTS OPUS or Publisher's site
A multi-robot system is a team of autonomous robots that work together to perform a given task. Multi-robot systems have great potential for use in horticulture applications. Robots have the potential to perform crop surveillance, efficiently apply fertiliser and chemical inputs, and perform weeding and harvesting. In all of these tasks, robots must visit many trees or plants over a large area in a time-sensitive manner. Multi-robot systems are appropriate because many robots can work efficiently in parallel. However, a fundamental challenge to be addressed is how to coordinate the motion of many robots while also respecting resource constraints such as limited energy storage, liquid payload, and harvested product storage. The algorithmic problem of multi-robot coverage planning with resource constraints is similar to the NP-hard vehicle routing problem, but the computational complexity of general resource-constrained coverage remains unknown. We show that one variant of this problem, coverage with fixed replenishment stations and zero queuing time, can be solved in polynomial time using area partitioning and graph search. We present algorithms and analysis for this variant, and demonstrate the behaviour of our algorithms in simulation experiments with up to 100 robots. The robots cover a large area organised as a collection of sub-areas with defined boundaries and row orientations. Robots plan to visit one of several possible replenishment stations in order to satisfy resource constraints. Each robot may replenish itself multiple times throughout its mission. This work is practically applicable to systems where refill time is short relative to working time
Reid, W., Fitch, R., Goktogan, A.H. & Sukkarieh, S. 2016, 'Motion Planning for ReconfigurableMobile Robots Using Hierarchical FastMarching Trees', Website proceedings of the 12th Workshop on the Algorithmic Foundations of Robotics, Workshop on the Algorithmic Foundations of Robotics (WAFR), WAFR, San Francisco, USA, pp. 1-16.View/Download from: UTS OPUS
Reconfigurable mobile robots are versatile platforms that
may safely traverse cluttered environments by morphing their physical
geometry. However, planning paths for these robots is challenging due to
their many degrees of freedom. We propose a novel hierarchical variant
of the Fast Marching Tree (FMT*) algorithm. Our algorithm assumes a
decomposition of the full state space into multiple sub-spaces, and begins
by rapidly finding a set of paths through one such sub-space. This set
of solutions is used to generate a biased sampling distribution, which is
then explored to find a solution in the full state space. This technique
provides a novel way to incorporate prior knowledge of sub-spaces to ef-
ficiently bias search within the existing FMT* framework. Importantly,
probabilistic completeness and asymptotic optimality are preserved. Experimental
results are provided for a reconfigurable wheel-on-leg platform
that benchmark the algorithm against state-of-the-art samplingbased
planners. In minimizing an energy objective that combines the
mechanical work required for platform locomotion with that required
for reconfiguration, the planner produces intuitive behaviors where the
robot dynamically adjusts its footprint, varies its height, and clambers
over obstacles using legged locomotion. These results illustrate the generality
of the planner in exploiting the platform's mechanical ability to
fluidly transition between various physical geometric configurations, and
wheeled/legged locomotion modes.
Best, G. & Fitch, R. 2015, 'Bayesian Intention Inference for Trajectory Prediction with an Unknown Goal Destination', Proceedings of the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Hamburg, Germany, pp. 5817-5823.View/Download from: UTS OPUS or Publisher's site
Contextual cues can provide a rich source of information for robots that operate in the presence of other agents such as people, animals, vehicles and fellow robots. We are interested in context, in the form of the behavioural intent of an agent, for enhanced trajectory prediction. We present a Bayesian framework that estimates both the intended goal destination and future trajectory of a mobile agent moving among multiple static obstacles. Our method is based on multi-modal hypotheses of the intended goal, and is focused primarily on the long-term trajectory of the agent. We propose a computationally efficient solution and demonstrate its behaviour in a pedestrian scenario with a real-world data set. Results show the benefits of our method in comparison to traditional trajectory prediction methods and illustrate the feasibility of integration with higher-level planning algorithms.
Best, G., Martens, W. & Fitch, R. 2015, 'A spatiotemporal optimal stopping problem for mission monitoring with stationary viewpoints', Robotics: Science and Systems, Robotics: Systems and Science, MIT Press, Rome, Italy, pp. 1-10.View/Download from: UTS OPUS or Publisher's site
© 2015, MIT Press Journals. All rights reserved. We consider an optimal stopping formulation of the mission monitoring problem, where a monitor vehicle must remain in close proximity to an autonomous robot that stochastically follows a pre-planned trajectory. This problem arises when autonomous underwater vehicles are monitored by surface vessels, and in a diverse range of other scenarios. The key problem characteristics we consider are that the monitor must remain stationary while observing the robot, and that the robot motion is modelled in general as a stochastic process. We propose a resolution-complete algorithm for this problem that runs in polynomial time. The algorithm is based on a sweep-plane approach and generates a motion plan that maximises the expected observation time. A variety of stochastic models may be used to represent the expected robot trajectory. We present results drawn from real AUV trajectories and Monte Carlo simulations that validate the correctness of our algorithm and its feasibility in practice.
Cliff, O.M., Fitch, R., Sukkarieh, S., Saunders, D.L. & Heinsohn, R. 2015, 'Online localization of radio-tagged wildlife with an autonomous aerial robot system', Robotics: Science and Systems, Robotics: Systems and Science, MIT Press, Rome, Italy, pp. 1-9.View/Download from: UTS OPUS or Publisher's site
© 2015, MIT Press Journals. All rights reserved. The application of autonomous robots to efficiently locate small wildlife species has the potential to provide significant ecological insights not previously possible using traditional land-based survey techniques, and a basis for improved conservation policy and management. We present an approach for autonomously localizing radio-tagged wildlife using a small aerial robot. We present a novel two-point phased array antenna system that yields unambiguous bearing measurements and an associated uncertainty measure. Our estimation and information-based planning algorithms incorporate this bearing uncertainty to choose observation points that improve confidence in the location estimate. These algorithms run online in real time and we report experimental results that show successful autonomous localization of stationary radio tags and live radio-tagged birds.
Gerardo-Castro, M.P., Peynot, T., Ramos, F. & Fitch, R. 2015, 'Non-parametric consistency test for multiple-sensing-modality data fusion', Proceedings of the 2015 18th International Conference on Information Fusion, Fusion 2015, International Conference on Information Fusion, IEEE, Washington, DC, USA, pp. 443-451.View/Download from: UTS OPUS
© 2015 IEEE. Fusing data from multiple sensing modalities, e.g. laser and radar, is a promising approach to achieve resilient perception in challenging environmental conditions. However, this may lead to catastrophic fusion in the presence of inconsistent data, i.e. when the sensors do not detect the same target due to distinct attenuation properties. It is often difficult to discriminate consistent from inconsistent data across sensing modalities using local spatial information alone. In this paper we present a novel consistency test based on the log marginal likelihood of a Gaussian process model that evaluates data from range sensors in a relative manner. A new data point is deemed to be consistent if the model statistically improves as a result of its fusion. This approach avoids the need for absolute spatial distance threshold parameters as required by previous work. We report results from object reconstruction with both synthetic and experimental data that demonstrate an improvement in reconstruction quality, particularly in cases where data points are inconsistent yet spatially proximal.
Patten, T., Kassir, A., Martens, W., Douillard, B., Fitch, R. & Sukkarieh, S. 2015, 'A Bayesian Approach for Time-Constrained 3D Outdoor Object Recognition [Extended Abstract]', IEEE International Conference on Robotics and Automation, Seattle, USA.View/Download from: UTS OPUS
Richards, D., Patten, T., Fitch, R., Ball, D. & Sukkarieh, S. 2015, 'User interface and coverage planner for agricultural robotics', ARAA ACRA, Australasian Conference on Robotics and Automation, ARAA, Canberra, Australia.View/Download from: UTS OPUS
Farmers are under growing pressure to increase
production, a challenge that robotics has the
potential to address. A possible solution is to
replace large farm machinery with numerous
smaller robots. However, with a large number of
robots it will become increasingly time
consuming for the farmer to monitor and control
them all, hence the need for an effective user
interface and automatic multi-robot coordination.
This paper describes the design of a user interface
and coverage planner suitable for controlling
multiple robots for typical coverage style farm
operations. The cross-platform user interface
allows the farmer to specify their farm including
fields, roads and docking stations. The coverage
planner splits the workload between the robots
and plans periodic docking. The results for the
different multi-robot coverage strategies
demonstrate the advantage of the robots
sequentially moving between fields rather than
freely moving between them. The multi-robot
system has been used for a coverage task on a real
farm for controlling two real robots and four
simulated robots operating for two days.
Gerardo-Castro, M.P., Peynot, T., Ramos, F. & Fitch, R. 2014, 'Robust multiple-sensing-modality data fusion using Gaussian Process Implicit Surfaces', FUSION 2014 - 17th International Conference on Information Fusion, International Conference on Information Fusion, IEEE, Salamanca, Spain.View/Download from: UTS OPUS or Publisher's site
© 2014 International Society of Information Fusion. The ability to build high-fidelity 3D representations of the environment from sensor data is critical for autonomous robots. Multi-sensor data fusion allows for more complete and accurate representations. Furthermore, using distinct sensing modalities (i.e. sensors using a different physical process and/or operating at different electromagnetic frequencies) usually leads to more reliable perception, especially in challenging environments, as modalities may complement each other. However, they may react differently to certain materials or environmental conditions, leading to catastrophic fusion. In this paper, we propose a new method to reliably fuse data from multiple sensing modalities, including in situations where they detect different targets. We first compute distinct continuous surface representations for each sensing modality, with uncertainty, using Gaussian Process Implicit Surfaces (GPIS). Second, we perform a local consistency test between these representations, to separate consistent data (i.e. data corresponding to the detection of the same target by the sensors) from inconsistent data. The consistent data can then be fused together, using another GPIS process, and the rest of the data can be combined as appropriate. The approach is first validated using synthetic data. We then demonstrate its benefit using a mobile robot, equipped with a laser scanner and a radar, which operates in an outdoor environment in the presence of large clouds of airborne dust and smoke.
Lee, J.J.H., Frey, K., Fitch, R. & Sukkarieh, S. 2014, 'Fast path planning for precision weeding', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, ARAA, Melbourne, Australia.View/Download from: UTS OPUS
Agricultural robots have the potential to reduce herbicide use in agriculture and horticulture through autonomous precision weeding. One of the main challenges is how to efficiently plan paths for a robot arm such that many individual weeds can be processed quickly. This paper considers an abstract weeding task among obstacles and proposes an efficient online path planning algorithm for an industrial manipulator mounted to a mobile robot chassis. The algorithm is based on a multi-query approach, inspired by industrial bin-picking, where a database of high-quality paths is computed offline and paths are then selected and adapted online. We present a preliminary implementation using a 6-DOF arm and report results from simulation experiments designed to evaluate system performance with varying database and obstacle sizes. We also validate the approach using a Universal Robots UR5 manipulator and ROS interface.
Alempijevic, A., Fitch, R. & Kirchner, N.G. 2013, 'Bootstrapping Navigation and Path Planning Using Human Positional Traces', IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Karlsruhe, Germany, pp. 1234-1239.View/Download from: UTS OPUS or Publisher's site
Navigating and path planning in environments with limited a priori knowledge is a fundamental challenge for mobile robots. Robots operating in human-occupied environments must also respect sociocontextual boundaries such as personal workspaces. There is a need for robots to be able to navigate in such environments without having to explore and build an intricate representation of the world. In this paper, a method for supplementing directly observed environmental information with indirect observations of occupied space is presented. The proposed approach enables the online inclusion of novel human positional traces and environment information into a probabilistic framework for path planning. Encapsulation of sociocontextual information, such as identifying areas that people tend to use to move through the environment, is inherently achieved without supervised learning or labelling. Our method bootstraps navigation with indirectly observed sensor data, and leverages the flexibility of the Gaussian process (GP) for producing a navigational map that sampling based path planers such as Probabilistic Roadmaps (PRM) can effectively utilise. Empirical results on a mobile platform demonstrate that a robot can efficiently and socially-appropriately reach a desired goal by exploiting the navigational map in our Bayesian statistical framework.
Alempijevic, A., Fitch, R., Kirchner, N. & IEEE 2013, 'Bootstrapping Navigation and Path Planning Using Human Positional Traces', 2013 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), pp. 1242-1247.
Kuo, V. & Fitch, R. 2013, 'Zero mutual interference network for intelligent vehicle communication', IEEE Intelligent Vehicles Symposium, Proceedings, Intelligent Vehicles Symposium Workshops, IEEE, Gold Coast, QLD, Australia, pp. 121-126.View/Download from: UTS OPUS or Publisher's site
We propose to enable high-throughput, scalable communication for cooperative autonomous vehicles through zero mutual interference (ZMI) networks. Cooperation in complex environments relies on wireless communication, but conventional wireless networks are not designed for cooperative autonomous vehicles and are fundamentally limited by mutual interference. Our approach is to avoid mutual interference by design; ZMI networks provide wired network properties using wireless radio links. In this paper, we present the initial instantiation of a ZMI network based on a multi-radio, multi-channel architecture. The network is constructed such that each vehicle communicates with topological neighbours using a dedicated radio and channel. We also present experimental results that compare the performance of a ZMI network to a conventional inter-vehicle communication network in a cooperative perception and control task. © 2013 IEEE.
We propose to enable high-throughput, scalable communication for cooperative autonomous vehicles through zero mutual interference (ZMI) networks. Cooperation in complex environments relies on wireless communication, but conventional wireless networks are not designed for cooperative autonomous vehicles and are fundamentally limited by mutual interference. Our approach is to avoid mutual interference by design; ZMI networks provide wired network properties using wireless radio links. In this paper, we present the initial instantiation of a ZMI network based on a multi-radio, multichannel architecture. The network is constructed such that each vehicle communicates with topological neighbours using a dedicated radio and channel. We also present experimental results that compare the performance of a ZMI network to a conventional inter-vehicle communication network in a cooperative perception and control task. © 2013 IEEE.
Nguyen, J., Lawrance, N., Fitch, R. & Sukkarieh, S. 2013, 'Energy-constrained motion planning for information gathering with autonomous aerial soaring', Proceedings - IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Karlsruhe, Germany, pp. 3825-3831.View/Download from: UTS OPUS or Publisher's site
Autonomous aerial soaring presents a unique opportunity to extend the flight duration of Unmanned Aerial Vehicles (UAVs). In this paper, we examine the problem of a gliding UAV searching for a ground target while simultaneously collecting energy from known thermal energy sources. The problem is posed as a tree search problem by noting that a long-duration mission can be divided into similar segments of flying between and climbing in thermals. The algorithm attempts to maximise the probability of detecting a target by exploring a tree of the possible thermal-to-thermal transitions to a fixed search depth and executing the highest utility plan. The sensitivity of the algorithm to different search depths is explored, and the method is compared against a locally-optimal myopic search algorithm. In larger, more complicated problems, the suggested method outperforms myopic search by sacrificing short-term utility to reach more valuable exploration areas later in the mission. © 2013 IEEE.
Patten, T., Fitch, R. & Sukkarieh, S. 2013, 'Large-scale near-optimal decentralised information gathering with multiple mobile robots', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, ARAA, Sydney, New South Wales.View/Download from: UTS OPUS
Information gathering at large spatial scales can be addressed with teams of decentralised robots. Many existing methods search over a limited time horizon and do not provide strong performance guarantees. Near-optimal methods that exploit submodular objective functions have been proposed, given a fixed time budget. We propose a revised problem formulation that seeks to near-optimally maximise information gain quickly. We present a novel, near-optimal polynomial-time decentralised algorithm for multiple robots and analyse the expected path length with respect to the number of robots, the size of the area, and the number of observations. Our approach is based on area partitioning and is practically beneficial in that it allows for superlinear speedup in the time required to maximise the submodular objective function, is decentralised, and is easy to implement. We show extensive simulation results that compare the performance of our algorithm to existing sequential allocation methods.
Xu, Z., Fitch, R. & Sukkarieh, S. 2013, 'Decentralised coordination of mobile robots for target tracking with learnt utility models', Proceedings - IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Karlsruhe, Germany, pp. 2014-2020.View/Download from: UTS OPUS or Publisher's site
This paper addresses the coordination of a decentralised robot team for target tracking. In many approaches to coordination, robots jointly plan their actions through negotiation, which incurs communication costs. Previous work examined the use of learning to reduce the need for negotiations in a network of static robots. Robots incrementally learn how each team member impacts the team utility and can thus make coordinated, team-wide decisions. In this paper, we extend the concept of learning utility models to a team of mobile robots. We also propose a mechanism by which robots switch between negotiating and using the learnt model. This mechanism reduces the communications required for coordination whilst maintaining the same level of tracking performance. Hardware experiments demonstrated that our approach resulted in coordinated behaviours while only negotiating intermittently. Simulation results show that our approach reduced the data communicated for negotiations by up to 70%, without making a statistically significant impact on the tracking performance. © 2013 IEEE.
Yoo, C., Fitch, R. & Sukkarieh, S. 2013, 'Provably-correct stochastic motion planning with safety constraints', 2013 IEEE International Conference on Robotics and Automation (ICRA), IEEE International Conference on Robotics and Automation, IEEE, Karlsruhe, Germany, pp. 981-986.View/Download from: UTS OPUS or Publisher's site
Formal methods based on the Markov decision process formalism, such as probabilistic computation tree logic (PCTL), can be used to analyse and synthesise control policies that maximise the probability of mission success. In this paper, we consider a different objective. We wish to minimise time-to-completion while satisfying a given probabilistic threshold of success. This important problem naturally arises in motion planning for outdoor robots, where high quality mobility prediction methods are available but stochastic path planning typically relies on an arbitrary weighted cost function that attempts to balance the opposing goals of finding safe paths (minimising risk) while making progress towards the goal (maximising reward). We propose novel algorithms for model checking and policy synthesis in PCTL that 1) provide a quantitative measure of safety and completion time for a given policy, and 2) synthesise policies that minimise completion time with respect to a given safety threshold. We provide simulation results in a stochastic outdoor navigation domain that illustrate policies with varying levels of risk. © 2013 IEEE.
Gan, S.K., Fitch, R. & Sukkarieh, S. 2012, 'Real-time decentralized search with inter-agent collision avoidance', 2012 IEEE International Conference on Robotics and Automation (ICRA), IEEE International Conference on Robotics and Automation, IEEE, Saint Paul, MN, USA, pp. 504-510.View/Download from: UTS OPUS or Publisher's site
This paper addresses the problem of coordinating a team of mobile autonomous sensor agents performing a cooperative mission while explicitly avoiding inter-agent collisions in a team negotiation process. Many multi-agent cooperative approaches disregard the potential hazards between agents, which are an important aspect to many systems and especially for airborne systems. In this work, team negotiation is performed using a decentralized gradient-based optimization approach whereas safety distance constraints are specifically designed and handled using Lagrangian multiplier methods. The novelty of our work is the demonstration of a decentralized form of inter-agent collision avoidance in the loop of the agents' real-time group mission optimization process, where the algorithm inherits the properties of performing its original mission while minimizing the probability of inter-agent collisions. Explicit constraint gradient formulation is derived and used to enhance computational advantage and solution accuracy. The effectiveness and robustness of our algorithm has been verified in a simulated environment by coordinating a team of UAVs searching for targets in a large-scale environment. © 2012 IEEE.
Kassir, A., Fitch, R. & Sukkarieh, S. 2012, 'Decentralised information gathering with communication costs', 2012 IEEE International Conference on Robotics and Automation (ICRA), IEEE International Conference on Robotics and Automation, IEEE, Saint Paul, MN, USA, pp. 2427-2432.View/Download from: Publisher's site
Advantages of decentralised decision making systems for multi-agent robotic tasks are limited by the heavy demand they impose on communication. This paper presents an approach to control communication for the LQ team problem, namely a team of agents with linear dynamics and quadratic team cost. Communication costs are added to the objective of the LQ optimal control linear matrix inequality formulation, allowing for a well-defined balancing of communication costs and team performance. Results show a reduction in communication consistent with the specified cost and in a manner that upholds team performance relative to the reduced communication footprint. The applicability of the approach has also been extended to information gathering tasks through local LQ approximations along the agents' paths. Simulation testing on a sample two-agent problem shows a 40% reduction in communication with negligible impact on performance. © 2012 IEEE.
McAllister, R., Peynot, T., Fitch, R. & Sukkarieh, S. 2012, 'Motion planning and stochastic control with experimental validation on a planetary rover', IEEE International Conference on Intelligent Robots and Systems 2012, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Vilamoura, Portugal, pp. 4716-4723.View/Download from: UTS OPUS or Publisher's site
Motion planning for planetary rovers must consider control uncertainty in order to maintain the safety of the platform during navigation. Modelling such control uncertainty is difficult due to the complex interaction between the platform and its environment. In this paper, we propose a motion planning approach whereby the outcome of control actions is learned from experience and represented statistically using a Gaussian process regression model. This model is used to construct a control policy for navigation to a goal region in a terrain map built using an on-board RGB-D camera. The terrain includes flat ground, small rocks, and non-traversable rocks. We report the results of 200 simulated and 35 experimental trials that validate the approach and demonstrate the value of considering control uncertainty in maintaining platform safety. © 2012 IEEE.
Xu, Z., Fitch, R. & Sukkarieh, S. 2012, 'Learning utility models for decentralised coordinated target tracking', 2012 IEEE International Conference on Robotics and Automation (ICRA), IEEE International Conference on Robotics and Automation, IEEE, Saint Paul, MN, USA, pp. 1753-1759.View/Download from: UTS OPUS or Publisher's site
In decentralised target tracking, a set of sensors observes moving targets. When the sensors are static but steerable, each sensor must dynamically choose which target to observe in a decentralised manner. We show that the information exchanged by the sensors to synchronise their beliefs can be exploited to learn a model of the utility function that drives each others' decisions. Instead of communicating utilities to enable negotiation, each sensor regresses on the learnt model to predict the utilities of other team members. This approach bridges the gap between coordinating implicitly, a locally-greedy solution, and negotiating explicitly. We validated our approach in both hardware and simulations, and found that it out-performed implicit coordination by a statistically significant margin with both ideal and limited communications. © 2012 IEEE.
Cong, J.J. & Fitch, R. 2011, 'The X-CLAW Self-Aligning Connector for Self-Reconfiguring Modular Robots', IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, San Francisco, California.View/Download from: UTS OPUS
Kuo, V. & Fitch, R. 2011, 'A multi-radio architecture for neighbor-to-neighbor communication in modular robots', Proceedings - IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Shanghai, China, pp. 5387-5394.View/Download from: UTS OPUS or Publisher's site
Decentralized control of modular robots requires reliable inter-module communication. Communication links must tolerate module misalignment and implement the neighbor-to-neighbor communication model. We propose a wireless system based on multiple radios per module that addresses these challenges. Our system scales to large robots because available bandwidth is independent of the number of modules. In this paper, we present our multi-radio singlechannel architecture and validate its performance through hardware experiments. Results show that radios can provide reliable neighbor-to-neighbor communication suitable for modular robots. © 2011 IEEE.
Peynot, T., Fitch, R., McAllister, R. & Alempijevic, A. 2011, 'Autonomous Reconfiguration of a Multi-Modal Mobile Robot', Workshop on Automated Diagnosis, Repair and Re-Configuration of Robot Systems, IEEE International Conference on Robotics and Automation (ICRA), IEEE International Conference on Robotics and Automation, IEEE, Shanghai, China.
Fitch, R., Alempijevic, A. & Lal, R. 2010, 'A self-reconfiguring team of mobile robots', Proc. of IEEE ICRA, Workshop on Network Science and Systems in Multi-Robot Autonomy.
Kirchner, N.G., Alempijevic, A., Caraian, S.A., Fitch, R., Hordern, D.L., Hu, G., Paul, G., Richards, D., Singh, S.P. & Webb, S.S. 2010, 'RobotAssist - a Platform for Human Robot Interaction Research', 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, pp. 1-10.View/Download from: UTS OPUS
This paper presents RobotAssist, a robotic platform designed for use in human robot interaction research and for entry into Robocup@Home competition. The core autonomy of the system is implemented as a component based software framework that allows for integration of operating system independent components, is designed to be expandable and integrates several layers of reasoning. The approaches taken to develop the core capabilities of the platform are described, namely: path planning in a social context, Simultaneous Localisation and Mapping (SLAM), human cue sensing and perception, manipulatable object detection and manipulation.
Kuo, V. & Fitch, R. 2010, 'A concentric network algorithm for spatial reuse in networked robotics', Proceedings of the 2010 Australasian Conference on Robotics and Automation, ACRA 2010.
Existing wireless network architectures are often poorly suited to the growing diversity of up-coming networked robot systems. As networked robots depend on reliable wireless communication to operate effectively as a team of networked robots, it is important that the communication system is scalable. One of the existing challenges in wireless communication is maintaining the bandwidth throughput of the network as the system size scales upward. In this paper we demonstrate a new method of applying spatial reuse to improve bandwidth in our proposed network architecture and topology. We also successfully demonstrate experimental evidence of our network architecture in both static and mobile scenarios using custom hardware and off-the-shelf radios.
Kuo, V. & Fitch, R. 2010, 'A parallel wireless radio communication architecture for modular robots,', Proc. of IEEE ICRA, Workshop on Modular Robots, pp. 69-76.
Fitch, R. & Lal, R. 2009, 'Experiments with a ZigBee wireless communication system for self-reconfiguring modular robots', Proceedings - IEEE International Conference on Robotics and Automation, pp. 1947-1952.View/Download from: Publisher's site
The problem of designing reliable low-cost communications systems to support decentralized algorithms is a major research challenge in self-reconfiguring modular robotics. In this paper we evaluate a communication system based on ZigBee, a wireless ad-hoc mesh networking standard. We present a 15-node system prototype and results from an experiment of 300 trials that measures system performance on a benchmark task. The benchmark we chose is the connectivity problem - how to maintain connectivity in the module graph during the disconnections and reconnections that occur during reconfiguration. We also provide full implementation detailsi n pseudocode for our connectivity algorithm. Our results show that, despite its inherent scalability limitations, a ZigBee wireless system is feasible as a simple, low-cost communicationsystem for self-reconfiguring modular robots. © 2009 IEEE.
Fitch, R., Lal, R. & IEEE 2009, 'Experiments with a ZigBee Wireless Communication System for Self-Reconfiguring Modular Robots', ICRA: 2009 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-7, pp. 3965-3970.
Kuo, V. & Fitch, R. 2009, 'Towards a parallel wireless radio communication architecture for modular robots', Proceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009.
Provisioning a scalable communication architecture in self-reconfiguring (SR) modular robots is one of the major challenges in their large-scale implementation in hardware. The infrared and hardwired communication systems usually employed are complex, are unreliable, and can lead to unrecoverable errors. Wireless mesh networks offer a robust and versatile solution but do not scale in terms of bandwidth and latency. By exploiting the unique properties of modular robots, we address the scalability problem in this paper. We propose a novel multi-radio, multi-channel mesh network architecture that guarantees fixed bandwidth and latency for inter-module communication, independent of the robot size. We present experimental results using modified ZigBee radios in a well-controlled setup that is free from unpredictable properties of radio propagation such as multi-path interference. By eliminating variables that would otherwise be present in a practical environment, we are able to precisely validate the principles and assumptions of our architecture. Using results from our experiments as a baseline we also qualitatively show that our approach has in-built protection from multi-path interference.
Lal, R. & Fitch, R. 2009, 'A hardware-in-the-loop simulator for distributed robotics', Proceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009.
Developing planning and control algorithms for distributed robotic systems involves implementing complex asynchronous algorithms on embedded hardware platforms with limited computational resources. The ability to efficiently validate such algorithms in hardware is critical, yet challenging due to their decentralised nature. We propose the use of hardware-in-the-loop simulation as an intermediate step to improve the process of performing such validation. We present the design and implementation of a custom hardware-in-the-loop simulator consisting of 27 embedded units with wireless communication and a special gateway device for interfacing with a desktop computer. We also present two case studies that illustrate the use and benefits of this system.
Fitch, R., Butler, Z. & IEEE 2007, 'Scalable locomotion for large self-reconfiguring robots', PROCEEDINGS OF THE 2007 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-10, pp. 2248-2253.View/Download from: Publisher's site
Butler, Z. & Fitch, R. 2006, 'Internally specified heterogeneous self-reconfiguration', 3rd Conference on Foundations of Nanoscience: Self-Assembled Architectures and Devices, FNANO 2006, pp. 196-202.
Self-reconfiguring robots are systems built from a large number of modules (which can be homogeneous or heterogeneous) that have the ability to change shape to fit the task at hand. Previous algorithms for shape formation have generally used a data structure common to all modules and passed in from an external user. In this work, we show how some of our previous algorithms can be easily adapted to an on-demand situation, so that the system can form the correct (heterogeneous) shape with a small amount of communication and state. We can also use this adapted algorithm to generate locomotion among the modules with little additional overhead.© 2006 by ScienceTechnica, Inc.
Fitch, R., Butler, Z., Rus, D. & IEEE 2005, 'Reconfiguration planning among obstacles for heterogeneous self-reconfiguring robots', 2005 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), VOLS 1-4, pp. 117-124.
Fitch, R., Butler, Z., Rus, D., IEEE & IEEE 2003, 'Reconfiguration planning for heterogeneous self-reconfiguring robots', IROS 2003: PROCEEDINGS OF THE 2003 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-4, pp. 2460-2467.
Butler, Z., Fitch, R., Kotay, K. & Rus, D. 2002, 'Distributed systems of self-reconfiguring robots', ACM SIGGRAPH 2002 Conference Abstracts and Applications, SIGGRAPH 2002, p. 69.View/Download from: Publisher's site
A robot designed for a single purpose can perform a specific task very well, but it may perform poorly on a different task, or in a different environment. This is acceptable if the environment is structured; however, if the task is in an unknown environment, then a robot with the ability to change shape to suit the environment and the required functionality will be more likely to succeed. We wish to create more versatile robots by using self-reconfiguration: hundreds of small modules will autonomously organize and reorganize as geometric structures to best fit the terrain on which the robot has to move, the shape of the object the robot has to manipulate, or the sensing needs for the given task. For example, a robot could synthesize a snake shape to travel through a narrow tunnel, and then morph into a six-legged insect to navigate on rough terrain upon exit. Self-reconfiguring robots are well-suited for tasks in hazardous and remote environments, especially when the environmental model and the task specifications are uncertain. A collection of simple, modular robots endowed with self-reconfiguration capabilities can conform to the shape of the terrain for locomotion by implementing "water-flow" like locomotion gaits which allow the robots to move by conforming to the shape of the terrain. To create autonomous robot systems capable of such applications, our research agenda is focused on two directions of work: (1) new designs for modular robots that can support self-assembly and self-reconfiguration and (2) new distributed planners that support parallelism, are efficient, and correctly direct units to change shape.
Butler, Z., Fitch, R., Rus, D., IEEE & IEEE 2002, 'Experiments in distributed locomotion with a unit-compressible modular robot', 2002 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-3, PROCEEDINGS, pp. 2813-2818.
Butler, Z., Fitch, R., Rus, D., Wang, Y.H., IEEE, IEEE & IEEE 2002, 'Distributed goal recognition algorithms for modular robots', 2002 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS I-IV, PROCEEDINGS, pp. 110-116.
Fitch, R., Butler, Z., Rus, D., IEEE & IEEE 2001, '3D rectilinear motion planning with minimum bend paths', IROS 2001: PROCEEDINGS OF THE 2001 IEEE/RJS INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-4, pp. 1491-1498.
© 2017 IEEE. Autonomous Science is a field of study which aims to extend the autonomy of exploration robots from low level functionality, such as on-board perception and obstacle avoidance, to science autonomy, which allows scientists to specify missions at task level. This will enable more remote and extreme environments such as deep ocean and other planets to be studied, leading to significant science discoveries. This paper presents an approach to extend the high level autonomy of robots by enabling them to model and reason about scientific knowledge on-board. We achieve this by using Bayesian networks to encode scientific knowledge and adapting Monte Carlo Tree Search techniques to reason about the network and plan informative sensing actions. The resulting knowledge representation and reasoning framework is anytime, handles large state spaces and robust to uncertainty making it highly applicable to field robotics. We apply the approach to a Mars exploration mission in which the robot is required to plan paths and decide when to use its sensing modalities to study a scientific latent variable of interest. Extensive simulation results show that our approach has significant performance benefits over alternative methods. We also demonstrate the practicality of our approach in an analog Martian environment where our experimental rover, Continuum, plans and executes a science mission autonomously.
Cliff, O.M., Prokopenko, M. & Fitch, R. 2016, An Information Criterion for Inferring Coupling in Complex Networks.
Chung, J.J., Lawrance, N.R.J., Gan, S.K., Xu, Z., Fitch, R. & Sukkarieh, S. 2015, Variable Density PRM Waypoint Generation and Connection Radii for Energy-Efficient Flight through Wind Fields.
Underwood, J.P., Calleija, M., Taylor, Z., Hung, C., Nieto, J., Fitch, R. & Sukkarieh, S. 2015, Real-time target detection and steerable spray for vegetable crops.
Upcroft, B., Moser, M., Makarenko, A., Johnson, D., Donikian, A., Alempijevic, A., Fitch, R., Uther, W., Grøtli, E.I., Biermeyer, J. & others 2007, Darpa urban challenge technical paper: Sydney-Berkeley driving team.
Fitch, R., Butler, Z. & Rus, D. 2002, The Crystal Robot: Implementation and Demonstration, pp. 65-71.
Arora, A., Fitch, R. & Sukkarieh, S. Extending Autonomy of Planetary Rovers by Encoding Geological Knowledge in a Bayesian Framework.
In this work, we are interested in structure learning for a set of spatially
distributed dynamical systems, where individual subsystems are coupled via
latent variables and observed through a filter. We represent this model as a
directed acyclic graph (DAG) that characterises the unidirectional coupling
between subsystems. Standard approaches to structure learning are not
applicable in this framework due to the hidden variables, however we can
exploit the properties of certain dynamical systems to formulate exact methods
based on state space reconstruction. We approach the problem by using
reconstruction theorems to analytically derive a tractable expression for the
KL-divergence of a candidate DAG from the observed dataset. We show this
measure can be decomposed as a function of two information-theoretic measures,
transfer entropy and stochastic interaction. We then present two mathematically
robust scoring functions based on transfer entropy and statistical independence
tests. These results support the previously held conjecture that transfer
entropy can be used to infer effective connectivity in complex networks.
Peynot, T., Ho, K., Lui, A., McAllister, R., Fitch, R. & Sukkarieh, S. Experimental Learning for Traversability Estimation and Stochastic Motion Planning on a Planetary Rover.
Fitch, R.C. & others 2004, 'Heterogeneous self-reconfiguring robotics'.