Publications

Waldron, KJ, Kinzel, GL & Agrawal, SK 2016, Kinematics, Dynamics, and Design of Machinery, 2nd, John Wiley & Sons, New York, USA.
View description>>

Kinematics, Dynamics, and Design of Machinery, Third Edition, presents a fresh approach to kinematic design and analysis and is an ideal textbook for senior undergraduates and graduates in mechanical, automotive and production engineering ...

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: Publisher's site
View description>>

© Springer International Publishing Switzerland 2016. 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 decentralised and assumes local (neighbour-toneighbour) 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 standardmesh networks in implementing decentralised algorithms.

Huang, S & Dissanayake, G 2016, 'Robot Localization: An Introduction' in Wiley Encyclopedia of Electrical and Electronics Engineering, Wiley, USA, pp. 1-10.
View/Download from: Publisher's site
View description>>

Robot localization is the process of determining where a mobile robot is located with respect to its environment. Localization is one of the most fundamental competencies required by an autonomous robot as the knowledge of the robot's own location is an essential precursor to making decisions about future actions. In a typical robot localization scenario, a map of the environment is available and the robot is equipped with sensors that observe the environment as well as monitor its own motion. The localization problem then becomes one of estimating the robot position and orientation within the map using information gathered from these sensors. Robot localization techniques need to be able to deal with noisy observations and generate not only an estimate of the robot location but also a measure of the uncertainty of the location estimate. This article provides an introduction to estimation of theoretic solutions to the robot localization problem. It begins by discussing the mathematical models used to describe the robot motion and observations from the sensors. Two of the most common probabilistic techniques, the extended Kalman filter and the particle filter, that can be used to combine information from sensors to compute an estimate of the robot location are then discussed in detail and illustrated by simple examples. A brief summary of the large body of literature on robot localization is presented next. Appendices that present the essential mathematical background and alternative techniques are provided. The MATLAB code of the localization algorithms is also available.

Lui, ST, Peynot, T, Fitch, R & Sukkarieh, S 2016, 'Enhanced Stochastic Mobility Prediction on Unstructured Terrain Using Multi-output Gaussian Processes', Springer, pp. 173-190.
View/Download from: Publisher's site
View description>>

© 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.

Waldron, KJ & Schmiedeler, J 2016, 'Kinematics' in Springer Handbooks, Springer International Publishing, pp. 11-36.
View/Download from: Publisher's site
View description>>

Kinematics pertains to the motion of bodies in a robotic mechanism without regard to the forces/torques that cause the motion. Since robotic mechanisms are by their very essence designed for motion, kinematics is the most fundamental aspect of robot design, analysis, control, and simulation. The robotics community has focused on efficiently applying different representations of position and orientation and their derivatives with respect to time to solve foundational kinematics problems. This chapter will present the most useful representations of the position and orientation of a body in space, the kinematics of the joints most commonly found in robotic mechanisms, and a convenient convention for representing the geometry of robotic mechanisms. These representational tools will be applied to compute the workspace, the forward and inverse kinematics, the forward and inverse instantaneous kinematics, and the static wrench transmission of a robotic mechanism. For brevity, the focus will be on algorithms applicable to open-chain mechanisms. The goal of this chapter is to provide the reader with general tools in tabulated form and a broader overview of algorithms that can be applied together to solve kinematics problems pertaining to a particular robotic mechanism.

Ang, KCS, Sankaran, S & Killen, CP 2016, '‘Value for Whom, by Whom’: Investigating Value Constructs in Non-Profit Project Portfolios', Project Management Research and Practice, vol. 3, no. July-Dec, pp. 5038-5038.
View/Download from: Publisher's site
View description>>

In most non-profit organisations (NPOs), there are multiple programs, projects or initiatives running simultaneously. The management of multiple projects in organisations can be coined as project portfolio management (PPM) (Archer & Ghasemzadeh 1999; Pennypacker & Dye 2002).  In any project-based organisation, it is critical that selected projects align with and deliver the organisation’s strategy or mission. Decisions about project funding are strategic decisions, particularly when there are resource limitations. In PPM decision making, the allocation of resources to projects requires a clear judgement of value across multiple perspectives. Value has often been expressed in financial terms, however increasingly research indicates that non-financial considerations are equally important in evaluating value.A key task in project portfolio management is to maximise value across the portfolio.  However, value can be a subjective notion, as each person may have different expectations of what is valuable. The involvement of diverse stakeholder interests could create complexities in decision making in non-profit organisations due to value being interpreted in different ways by the stakeholders. Furthermore in order to achieve its purpose, non-profits depend heavily on donors, patrons and sponsors - stakeholders who contribute to the portfolio but are often not the direct recipients of the services provided by the non-profit organisation (Kaplan 2012). Non-profit portfolios often compete with other initiatives for resources and attention from the same donors and sponsors, and may need to constantly justify the value they provide to these stakeholders.Most research about value in PPM has been conducted in the ‘for-profit’ sector. Recent value-based studies in the project portfolio field stress the importance of considering both commercial and non-commercial value in portfolio decision making (Killen, du Plessis & Young 2012; Kopman 2013; Mart...

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
View description>>

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.

Cheng, J, Kim, J, Jiang, Z & Che, W 2016, 'Dual quaternion-based graphical SLAM', Robotics and Autonomous Systems, vol. 77, pp. 15-24.
View/Download from: Publisher's site

Cliff, OM, Prokopenko, M & Fitch, R 2016, 'An Information Criterion for Inferring Coupling in Distributed Dynamical Systems', Front. Robot. AI 3(71), 2016, vol. 3, no. NOV, pp. 1-9.
View/Download from: Publisher's site
View description>>

The behaviour of many real-world phenomena can be modelled by nonlineardynamical systems whereby a latent system state is observed through a filter.We are interested in interacting subsystems of this form, which we model by aset of coupled maps as a synchronous update graph dynamical systems.Specifically, we study the structure learning problem for spatially distributeddynamical systems coupled via a directed acyclic graph. Unlike establishedstructure learning procedures that find locally maximum posterior probabilitiesof a network structure containing latent variables, our work exploits theproperties of dynamical systems to compute globally optimal approximations ofthese distributions. We arrive at this result by the use of time delayembedding theorems. Taking an information-theoretic perspective, we show thatthe log-likelihood has an intuitive interpretation in terms of informationtransfer.

Dantanarayana, L, Dissanayake, G & Ranasinghe, R 2016, 'C-LOG: A Chamfer distance based algorithm for localisation in occupancy grid-maps.', CAAI Trans. Intell. Technol., vol. 1, no. 3, pp. 272-284.
View/Download from: Publisher's site

Huang, S & Dissanayake, G 2016, 'A critique of current developments in simultaneous localization and mapping', International Journal of Advanced Robotic Systems, vol. 13, no. 5, pp. 172988141666948-172988141666948.
View/Download from: Publisher's site
View description>>

The number of research publications dealing with the simultaneous localization and mapping problem has grown significantly over the past 15 years. Many fundamental and practical aspects of simultaneous localization and mapping have been addressed, and some efficient algorithms and practical solutions have been demonstrated. The aim of this paper is to provide a critical review of current theoretical understanding of the fundamental properties of the SLAM problem, such as observability, convergence, achievable accuracy and consistency. Recent research outcomes associated with these topics are briefly discussed together with potential future research directions.

Khosoussi, K, Huang, S & Dissanayake, G 2016, 'A Sparse Separable SLAM Back-End', IEEE Transactions on Robotics, vol. 32, no. 6, pp. 1536-1549.
View/Download from: Publisher's site
View description>>

© 2004-2012 IEEE. We propose a scalable algorithm to take advantage of the separable structure of simultaneous localization and mapping (SLAM). Separability is an overlooked structure of SLAM that distinguishes it from a generic nonlinear least-squares problem. The standard relative-pose and relative-position measurement models in SLAM are affine with respect to robot and features' positions. Therefore, given an estimate for robot orientation, the conditionally optimal estimate for the rest of the state variables can be easily computed by solving a sparse linear least-squares problem. We propose an algorithm to exploit this intrinsic property of SLAM by stripping the problem down to its nonlinear core, while maintaining its natural sparsity. Our algorithm can be used in conjunction with any Newton-based solver and is applicable to 2-D/3-D pose-graph and feature-based SLAM. Our results suggest that iteratively solving the nonlinear core of SLAM leads to a fast and reliable convergence as compared to the state-of-the-art sparse back-ends.

Khushaba, RN, Al-Timemy, A, Kodagoda, S & Nazarpour, K 2016, 'Combined influence of forearm orientation and muscular contraction on EMG pattern recognition', EXPERT SYSTEMS WITH APPLICATIONS, vol. 61, pp. 154-161.
View/Download from: Publisher's site

Kodagoda, S, Sehestedt, S & Dissanayake, G 2016, 'Socially aware path planning for mobile robots', Robotica, vol. 34, no. 3, pp. 513-526.
View/Download from: Publisher's site
View description>>

SUMMARYHuman–robot interaction is an emerging area of research where a robot may need to be working in human-populated environments. Human trajectories are generally not random and can belong to gross patterns. Knowledge about these patterns can be learned through observation. In this paper, we address the problem of a robot's social awareness by learning human motion patterns and integrating them in path planning. The gross motion patterns are learned using a novel Sampled Hidden Markov Model, which allows the integration of partial observations in dynamic model building. This model is used in the modified A* path planning algorithm to achieve socially aware trajectories. Novelty of the proposed method is that it can be used on a mobile robot for simultaneous online learning and path planning. The experiments carried out in an office environment show that the paths can be planned seamlessly, avoiding personal spaces of occupants.

Kodikara, J, Valls Miro, J & Melchers, R 2016, 'Failure Prediction of Critical Cast Iron Pipes', Advances in Water Research, vol. 26, no. 3, pp. 6-11.
View description>>

In 2011, a consortium of Australian water utilities led by Sydney Water (SW) joined forces with WRF and UK Water Industry Research (UKWIR) to initiate a five-year research program, Advanced Condition Assessment and Pipe Failure Prediction Project (ACAPFP).

Nguyen, JL, Lawrance, NRJ, 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: Publisher's site
View description>>

© 2015, Springer Science+Business Media New York. Autonomous thermal soaring offers an opportunity to extend the flight duration of unmanned aerial vehicles (UAVs). In this work, we introduce the informative soaring problem, where a gliding UAV performs an information gathering mission while simultaneously replenishing energy from known thermal energy sources. We pose this problem in a way that combines convex optimisation with graph search and present four path planning algorithms with complementary characteristics. Using a target-search task as a motivating example, finite-horizon and Monte Carlo tree search methods are shown to be appropriate for situations with little prior knowledge, but suffer from either myopic planning or high computation cost in more complex scenarios. These issues are addressed by two novel tree search algorithms based on creating clusters that associate high uncertainty regions with nearby thermals. The cluster subproblems are solved independently to generate local plans, which are then linked together. Numerical simulations show that these methods find high-quality nonmyopic plans quickly. The more promising cluster-based method, which uses dynamic programming to compute a total ordering over clusters, is demonstrated in hardware tests on a UAV. Fifteen-minute plans are generated in less than four seconds, facilitating online replanning when simulated thermals are added or removed in-flight.

Nguyen, LV, Kodagoda, S & Ranasinghe, R 2016, 'Spatial Sensor Selection via Gaussian Markov Random Fields', IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 46, no. 9, pp. 1226-1239.
View/Download from: Publisher's site

Nguyen, LV, Kodagoda, S, Ranasinghe, R & Dissanayake, G 2016, 'Information-Driven Adaptive Sampling Strategy for Mobile Robotic Wireless Sensor Network', IEEE Transactions on Control Systems Technology, vol. 24, no. 1, pp. 372-379.
View/Download from: Publisher's site
View description>>

This brief addresses the issue of monitoring physical spatial phenomena of interest using information collected by a resource-constrained network of mobile, wireless, and noisy sensors that can take discrete measurements as they navigate through the environment. We first propose an efficient novel optimality criterion for designing a sampling strategy to find the most informative locations in taking future observations to minimize the uncertainty at all unobserved locations of interest. This solution is proven to be within bounds. The computational complexity of this proposition is shown to be practically feasible. We then prove that under a certain condition of monotonicity property, the approximate entropy at resulting locations obtained by our proposed algorithm is within 1-(1/e) of the optimum, which is then utilized as a stopping criterion for the sampling algorithm. The criterion enables the prediction results to be within user-defined accuracies by controlling the number of mobile sensors. The effectiveness of the proposed method is illustrated using a prepublished data set.

Norouzi, M, Valls Miro, J & Dissanayake, G 2016, 'Probabilistic stable motion planning with stability uncertainty for articulated vehicles on challenging terrains', Autonomous Robots, vol. 40, no. 2, pp. 361-381.
View/Download from: Publisher's site
View description>>

© 2015, Springer Science+Business Media New York. A probabilistic stable motion planning strategy applicable to reconfigurable robots is presented in this paper. The methodology derives a novel statistical stability criterion from the cumulative distribution of a tip-over metric. The measure is dynamically updated with imprecise terrain information, localization and robot kinematics to plan safety-constrained paths which simultaneously allow the widest possible visibility of the surroundings by simultaneously assuming highest feasible vantage robot configurations. The proposed probabilistic stability metric allows more conservative poses through areas with higher levels of uncertainty, while avoiding unnecessary caution in poses assumed at well-known terrain sections. The implementation with the well known grid based A* algorithm and also a sampling based RRT planner are presented. The validity of the proposed approach is evaluated with a multi-tracked robot fitted with a manipulator arm and a range camera using two challenging elevation terrains data sets: one obtained whilst operating the robot in a mock-up urban search and rescue arena, and the other from a publicly available dataset of a quasi-outdoor rover testing facility.

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: Publisher's site
View description>>

© 2015 IEEE. We present an end-to-end method for active object classification in cluttered scenes from RGB-D data. Our algorithms predict the quality of future viewpoints in the form of entropy using both class and pose. Occlusions are explicitly modeled in predicting the visible regions of objects, which modulates the corresponding discriminatory value of a given view. We implement a one-step greedy planner and demonstrate our method online using a mobile robot. We also analyze the performance of our method compared to similar strategies in simulated execution using the Willow Garage dataset. Results show that our active method usefully reduces the number of views required to accurately classify objects in clutter as compared to traditional passive perception.

Ryu, K, Dantanarayana, L, Furukawa, T & Dissanayake, G 2016, 'Grid-based scan-to-map matching for accurate 2D map building.', Adv. Robotics, vol. 30, no. 7, pp. 431-448.
View/Download from: Publisher's site
View description>>

This paper presents a grid-based scan-to-map matching technique for accurate 2D map building. At every acquisition of a new scan, the proposed technique matches the new scan to the previous scan similarly to the conventional techniques, but further corrects the error by matching the new scan to the globally defined map. In order to achieve best scan-to-map matching at each acquisition, the map is represented as a grid map with multiple normal distributions (NDs) in each cell, which is one contribution of this paper. Additionally, the new scan is also represented by NDs, developing a novel ND-to-ND matching technique. This ND-to-ND matching technique has significant potential in the enhancement of the global matching as well as the computational efficiency. Experimental results first show that the proposed technique accumulates very small errors after consecutive matchings and identifies that the scans are matched better to the map with the multi-ND representation than one ND representation. The proposed t...

Sun, Y, Zhao, L, Zhou, G & Yan, L 2016, 'Absolute Orientation Based on Distance Kernel Functions', Remote Sensing, vol. 8, no. 3, pp. 213-213.
View/Download from: Publisher's site
View description>>

The classical absolute orientation method is capable of transforming tie points (TPs) from a local coordinate system to a global (geodetic) coordinate system. The method is based only on a unique set of similarity transformation parameters estimated by minimizing the total difference between all ground control points (GCPs) and the fitted points. Nevertheless, it often yields a transformation with poor accuracy, especially in large-scale study cases. To address this problem, this study proposes a novel absolute orientation method based on distance kernel functions, in which various sets of similarity transformation parameters instead of only one set are calculated. When estimating the similarity transformation parameters for TPs using the iterative solution of a non-linear least squares problem, we assigned larger weighting matrices for the GCPs for which the distances from the point are short. The weighting matrices can be evaluated using the distance kernel function as a function of the distances between the GCPs and the TPs. Furthermore, we used the exponential function and the Gaussian function to describe distance kernel functions in this study. To validate and verify the proposed method, six synthetic and two real datasets were tested. The accuracy was significantly improved by the proposed method when compared to the classical method, although a higher computational complexity is experienced.

Takami, K, Furukawa, T, Kumon, M, Kimoto, D & Dissanayake, G 2016, 'Estimation of a nonvisible field-of-view mobile target incorporating optical and acoustic sensors', Autonomous Robots, vol. 40, no. 2, pp. 343-359.
View/Download from: Publisher's site

To, AWK, Paul, G & Liu, D 2016, 'An approach for identifying classifiable regions of an image captured by autonomous robots in structural environments', Robotics and Computer-Integrated Manufacturing, vol. 37, pp. 90-102.
View/Download from: Publisher's site
View description>>

© 2015 Elsevier Ltd. Abstract When an autonomous robot is deployed in a structural environment to visually inspect surfaces, the capture conditions of images (e.g. camera's viewing distance and angle to surfaces) may vary due to un-ideal robot poses selected to position the camera in a collision-free manner. Given that surface inspection is conducted by using a classifier trained with surface samples captured with limited changes to the viewing distance and angle, the inspection performance can be affected if the capture conditions are changed. This paper presents an approach to calculate a value that represents the likelihood of a pixel being classifiable by a classifier trained with a limited dataset. The likelihood value is calculated for each pixel in an image to form a likelihood map that can be used to identify classifiable regions of the image. The information necessary for calculating the likelihood values is obtained by collecting additional depth data that maps to each pixel in an image (collectively referred to as a RGB-D image). Experiments to test the approach are conducted in a laboratory environment using a RGB-D sensor package mounted onto the end-effector of a robot manipulator. A naive Bayes classifier trained with texture features extracted from Gray Level Co-occurrence Matrices is used to demonstrate the effect of image capture conditions on surface classification accuracy. Experimental results show that the classifiable regions identified using a likelihood map are up to 99.0% accurate, and the identified region has up to 19.9% higher classification accuracy when compared against the overall accuracy of the same image.

Valls Miro, J & Shi, L 2016, 'Aiming for the Holy Grail: Pipe Condition Assessment Along Critical Mains from Limited Inspections', Utility Magazine, vol. 10, pp. 90-92.
View description>>

The Advanced Condition Assessment and Pipe Failure Prediction Project is coming up with a novel condition assessment research concept: exploiting data-driven research to improve large critical water mains condition prediction, over extended sections of pipeline, from limitedcondition assessment inspection data.

Vander Poorten, E, Tran, P, Devreker, A, Gruijthuijsen, C, Portoles-Diez, S, Smoljkic, G, Strbac, V, Famaey, N, Reynaerts, D, Vander Sloten, J, Tibebu, A, Yu, B, Rauch, C, Bernard, F, Kassahun, Y, Metzen, JH, Giannarou, S, Zhao, L, Lee, S, Yang, G, Mazomenos, E, Chang, P, Stoyanov, D, Kvasnytsia, M, Van Deun, J, Verhoelst, E, Sette, M, Di Iasio, A, Leo, G, Hertner, F, Scherly, D, Chelini, L, Häni, N, Seatovic, D, Rosa, B, De Praetere, H & Herijgers, P 2016, 'Cognitive AutonomouS CAtheters Operating in Dynamic Environments', Journal of Medical Robotics Research, vol. 01, no. 03, pp. 1640011-1640011.
View/Download from: Publisher's site
View description>>

Advances in miniaturized surgical instrumentation are key to less demanding and safer medical interventions. In cardiovascular procedures interventionalists turn towards catheter-based interventions, treating patients considered unfit for more invasive approaches. A positive outcome is not guaranteed. The risk for calcium dislodgement, tissue damage or even vessel rupture cannot be eliminated when instruments are maneuvered through fragile and diseased vessels. This paper reports on the progress made in terms of catheter design, vessel reconstruction, catheter shape modeling, surgical skill analysis, decision making and control. These efforts are geared towards the development of the necessary technology to autonomously steer catheters through the vasculature, a target of the EU-funded project Cognitive AutonomouS CAtheters operating in Dynamic Environments (CASCADE). Whereas autonomous placement of an aortic valve implant forms the ultimate and concrete goal, the technology of individual building blocks to reach such ambitious goal is expected to be much sooner impacting and assisting interventionalists in their daily clinical practice.

Wang, Y, Huang, S, Xiong, R & Wu, J 2016, 'A framework for multi-session RGBD SLAM in low dynamic workspace environment', CAAI Transactions on Intelligence Technology, vol. 1, no. 1, pp. 90-103.
View/Download from: 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

Zhao, L, Giannarou, S, Lee, S-L & Yang, G-Z 2016, 'SCEM+: Real-Time Robust Simultaneous Catheter and Environment Modeling for Endovascular Navigation', IEEE Robotics and Automation Letters, vol. 1, no. 2, pp. 961-968.
View/Download from: Publisher's site
View description>>

Endovascular procedures are characterised by significant challenges mainly due to the complexity in catheter control and navigation. Real-time recovery of the 3-D structure of the vasculature is necessary to visualise the interaction between the catheter and its surrounding environment to facilitate catheter manipulations. State-of-the-art intraoperative vessel reconstruction approaches are increasingly relying on nonionising imaging techniques such as optical coherence tomography (OCT) and intravascular ultrasound (IVUS). To enable accurate recovery of vessel structures and to deal with sensing errors and abrupt catheter motions, this letter presents a robust and real-time vessel reconstruction scheme for endovascular navigation based on IVUS and electromagnetic (EM) tracking. It is formulated as a nonlinear optimisation problem, which considers the uncertainty in both the IVUS contour and the EM pose, as well as vessel morphology provided by preoperative data. Detailed phantom validation is performed and the results demonstrate the potential clinical value of the technique.

Abeywardena, D, Huang, S, Barnes, B, Dissanayake, G & Kodagoda, S 1970, 'Fast, On-board, Model-aided Visual-Inertial Odometry System for Quadrotor Micro Aerial Vehicles', Published in 2016 IEEE International Conference on Robotics and Automation (ICRA), 2016 IEEE International Conference on Robotics and Automation (ICRA), IEEE, Stockholm, Sweden, pp. 1530-1537.
View/Download from: Publisher's site
View description>>

The main contribution of this paper is a high frequency, low-complexity,on-board visual-inertial odometry system for quadrotor micro air vehicles. Thesystem consists of an extended Kalman filter (EKF) based state estimationalgorithm that fuses information from a low cost MEMS inertial measurement unitacquired at 200Hz and VGA resolution images from a monocular camera at 50Hz.The dynamic model describing the quadrotor motion is employed in the estimationalgorithm as a third source of information. Visual information is incorporatedinto the EKF by enforcing the epipolar constraint on features tracked betweenimage pairs, avoiding the need to explicitly estimate the location of thetracked environmental features. Combined use of the dynamic model and epipolarconstraints makes it possible to obtain drift free velocity and attitudeestimates in the presence of both accelerometer and gyroscope biases. Astrategy to deal with the unobservability that arises when the quadrotor is inhover is also provided. Experimental data from a real-time implementation ofthe system on a 50 gram embedded computer are presented in addition to thesimulations to demonstrate the efficacy of the proposed system.

Bai, F, Huang, S, Vidal-Calleja, T & Zhang, Q 1970, 'Incremental SQP method for constrained optimization formulation in SLAM', 2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV), 2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV), IEEE, Phuket, Thailand, pp. 1-6.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. 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.

Best, G & Fitch, R 1970, 'Probabilistic maximum set cover with path constraints for informative path planning', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, ARAA, Brisbane, Australia, pp. 97-106.
View description>>

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, Faigl, J & Fitch, R 1970, 'Multi-robot path planning for budgeted active perception with self-organising maps', 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Daejeon, Korea, pp. 3164-3171.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. 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 self-occlusions, 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.

Bykerk, L, Liu, D & Waldron, K 1970, 'A topology optimisation based design of a compliant gripper for grasping objects with irregular shapes', 2016 IEEE International Conference on Advanced Intelligent Mechatronics (AIM), 2016 IEEE International Conference on Advanced Intelligent Mechatronics (AIM), IEEE, Banff, Canada, pp. 383-388.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. Complex steel structures such as power transmission towers require regular inspection and maintenance during their lifetime. This work is currently completed by teams of human workers who climb the live structures. The exposure of these workers to the risks of climbing and completing work on towers provides motivation for developing a robotic substitute. There are many complex elements of climbing power transmission towers, such as the variation in beam shapes, sizes and orientations. To the best of our knowledge, there is no existing robotic grasping solution that can be directly used in this complex environment. This paper presents a topology optimisation based design of a compliant gripper for grasping objects with irregular shapes such as the beam members found in power transmission towers. The structure of the gripper is obtained through the use of a modified topology optimisation model where stiffness constraints are implemented in the optimisation to increase the strength of the gripper in desired areas. The stiffness constrained topology optimisation produces a novel gripper design which is validated through both simulations and physical testing of the manufactured gripper on a variety of physical objects.

Cui, Y, Poon, J, Matsubara, T, Miro, JV, Sugimoto, K & Yamazaki, K 1970, 'Environment-adaptive interaction primitives for human-robot motor skill learning', 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids), 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids), IEEE, Cancun, Mexico, pp. 711-717.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. In complex environments where robots are expected to co-operate with human partners, it is vital for the robot to consider properties of their collaborative activity in addition to the behavior of its partner. In this paper, we propose to learn such complex interactive skills by observing the demonstrations of a human-robot team with additional external attributes. We propose Environment-adaptive Interaction Primitives (EalPs) as an extension of Interaction Primitives. In cooperation tasks between human and robot with different environmental conditions, EalPs not only improve the predicted motor skills of robot within a brief observed human motion, but also obtain the generalization ability to adapt to new environmental conditions by learning the relationships between each condition and the corresponding motor skills from training samples. Our method is validated in the collaborative task of covering objects by plastic bag with a humanoid Baxter robot. To achieve the task successfully, the robot needs to coordinate itself to its partner while also considering information about the object to be covered.

Cui, Y, Poon, JT, Valls Miro, J, Matsubara, T & Sugimoto, K 1970, 'Optimal Control Approach for Active Local Driving Assistance in Mobility Aids', 34th annual conference of the Robotics Society of Japan (RSJ), 34th annual conference of the Robotics Society of Japan (RSJ), Japan.

Emery, BM, Jadidi, MG, Nakamura, K & Miro, JV 1970, 'An audio-visual solution to sound source localization and tracking with applications to HRI', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, ARAA, Brisbane, pp. 268-277.
View description>>

Robot audition is an emerging and growing branch in the robotic community and is necessary for a natural Human-Robot Interaction (HRI). In this paper, we propose a framework that integrates advances from Simultaneous Localization And Mapping (SLAM), bearing-only target tracking, and robot audition techniques into a unified system for sound source identification, localization, and tracking. In indoors, acoustic observations are often highly noisy and corrupted due to reverberations, the robot egomotion and background noise, and the possible discontinuous nature of them. Therefore, in everyday interaction scenarios, the system requires accommodating for outliers, robust data association, and appropriate management of the landmarks, i.e. sound sources. We solve the robot self-localization and environment representation problems using an RGB-D SLAM algorithm, and sound source localization and tracking using recursive Bayesian estimation in the form of the extended Kalman filter with unknown data associations and an unknown number of landmarks. The experimental results show that the proposed system performs well in the medium-sized cluttered indoor environment.

Faigl, J, Penicka, R & Best, G 1970, 'Self-organizing map-based solution for the Orienteering problem with neighborhoods', 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC), IEEE, pp. 001315-001321.
View/Download from: Publisher's site

Falque, R, Vidal-Calleja, T, Dissanayake, G & Miro, JV 1970, 'From the Skin-Depth Equation to the Inverse RFEC Sensor Model', 2016 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016, International Conference on Control, Automation, Robotics and Vision, IEEE, Phuket, Thailand.
View/Download from: Publisher's site
View description>>

In this paper, we tackle the direct and inverse problems for the Remote-FieldEddy-Current (RFEC) technology. The direct problem is the sensor model, wheregiven the geometry the measurements are obtained. Conversely, the inverseproblem is where the geometry needs to be estimated given the fieldmeasurements. These problems are particularly important in the field ofNon-Destructive Testing (NDT) because they allow assessing the quality of thestructure monitored. We solve the direct problem in a parametric fashion usingLeast Absolute Shrinkage and Selection Operation (LASSO). The proposed inversemodel uses the parameters from the direct model to recover the thickness usingleast squares producing the optimal solution given the direct model. This studyis restricted to the 2D axisymmetric scenario. Both, direct and inverse models,are validated using a Finite Element Analysis (FEA) environment with realisticpipe profiles.

Hassan, M, Liu, D & Paul, G 1970, 'Modeling and stochastic optimization of complete coverage under uncertainties in multi-robot base placements', 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Daejeon, Korea, pp. 2978-2984.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. Uncertainties in base placements of mobile, autonomous industrial robots can cause incomplete coverage in tasks such as grit-blasting and spray painting. Sensing and localization errors can cause such uncertainties in robot base placements. This paper addresses the problem of collaborative complete coverage under uncertainties through appropriate base placements of multiple mobile and autonomous industrial robots while aiming to optimize the performance of the robot team. A mathematical model for complete coverage under uncertainties is proposed and then solved using a stochastic multi-objective optimization algorithm. The approach aims to concurrently find an optimal number and sequence of base placements for each robot such that the robot team's objectives are optimized whilst uncertainties are accounted for. Several case studies based on a real-world application using a realworld object and a complex simulated object are provided to demonstrate the effectiveness of the approach for different conditions and scenarios, e.g. various levels of uncertainties, different numbers of robots, and robots with different capabilities.

Hefferan, BN, Cliff, OM & Fitch, R 1970, 'Adversarial patrolling with reactive point processes', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, ARAA, Brisbane, Australia, pp. 39-46.
View description>>

Adversarial patrolling is an algorithmic problem where a robot visits sites within a given area so as to detect the presence of an adversary. We formulate and solve a new variant of this problem where intrusion events occur at discrete locations and are assumed to be clustered in time. Unlike related formulations, we model the behaviour of the adversary using a stochastic point process known as the reactive point process, which naturally models temporally self-exciting events such as pest intrusion and weed growth in agriculture. We present an asymptotically optimal, anytime algorithm based on Monte Carlo tree search that plans the motion of a robot given a separate event detection system in order to regulate event propagation at the sites it visits. We illustrate the behaviour of our algorithm in simulation using several scenarios, and compare its performance to a lawnmower planning algorithm. Our results indicate that our formulation and solution are promising in enabling practical applications and further theoretical extensions.

Kassir, A, Fitch, R & Sukkarieh, S 1970, 'Communication-efficient motion coordination and data fusion in information gathering teams', 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Daejeon, Korea, pp. 5258-5265.
View/Download from: Publisher's site
View description>>

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.

Khosoussi, K, Shoudong Huang & Dissanayake, G 1970, 'Tree-connectivity: Evaluating the graphical structure of SLAM', 2016 IEEE International Conference on Robotics and Automation (ICRA), 2016 IEEE International Conference on Robotics and Automation (ICRA), IEEE, Stockholm, Sweden, pp. 1316-1322.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. Simultaneous localization and mapping (SLAM) in robotics, and a number of related problems that arise in sensor networks are instances of estimation problems over weighted graphs. This paper studies the relation between the graphical representation of such problems and estimationtheoretic concepts such as the Cramér-Rao lower bound (CRLB) and D-optimality. We prove that the weighted number of spanning trees, as a graph connectivity metric, is closely related to the determinant of CRLB. This metric can be efficiently computed for large graphs by exploiting the sparse structure of underlying estimation problems. Our analysis is validated using experiments with publicly available pose-graph SLAM datasets.

Kim, J, Cheng, J & Guivant, J 1970, 'Tightly-coupled integration of GPS/INS and simultaneous localisation and mapping', Australasian Conference on Robotics and Automation, ACRA, pp. 194-199.
View description>>

This paper presents a tightly integrated navigation system combining global positioning system (GPS) and inertial-based simultaneous localization and mapping (SLAM) for UAV platforms. GPS raw measurements, called pseudorange and pseudorange rate, are directly fused to an inertial SLAM filter. A compressed form of unscented filtering is implemented by partitioning the map into a local and global one. The performance of the proposed method is analysed using a high-fidelity 6-degrees-of-freedom simulator, demonstrating accurate and robust navigation even under a single satellite observation. The information gain of bearing and elevation angles is further analysed offering effective sensing strategies.

Ma, H, Shi, L, Kodagoda, S & Xiong, R 1970, 'A semantic labeling strategy to reject unknown objects in large scale 3D point clouds', 2016 35th Chinese Control Conference (CCC), 2016 35th Chinese Control Conference (CCC), IEEE, Chengdu, Sichuan, China, pp. 7070-7075.
View/Download from: Publisher's site
View description>>

In recent years, there has been a growing interest in the research of semantic labeling of indoor scenes represented by 3D point clouds. A fundamental problem that has largely been oversighted in the current research is the way of dealing with the unknown class which collectively includes all the objects that are of no interest to the application developer. In the training stage, these objects are either completely removed or labeled as unknown, resulting in a trained model which is not fully and fairly exposed to the actual sample space. In the test stage, the unknown objects are naturally present and provided to the classifier, causing a significant drop of the classification accuracy-usually 20%~30%. Simply improving the features or the classifier will not address the root cause problem. In this paper, we propose a labeling framework combining both Conditional Random Field (CRF) and PI-SVM to specifically solve the problem caused by the unknown class. First, we use a CRF to model the contextual relations in the 3D space, for which the parameters for both node potential and edge potential are learned from training data. Then, we make use of the rejection strategy of the PI-SVM, which estimates an unnormalized probability for each class. Finally, we reinforce the result of CRF with the belief provided by the PI-SVM, and the labeling result is based on the agreement of the two classifiers. The proposed method takes advantage of the global optimization of CRF and the advantage of unknown rejection of PI-SVM. Experimental results on publicly available data set show that this method has improved the classification accuracy by 10.7% given the accuracy drop of 19.23% caused by the unknown.

Muller, R, Nikolova, N, Sankaran, S, Hase, S, Zhu, F, Xu, X, Vaagaasar, AL & Drouin, N 1970, 'Leading projects by balancing vertical and horizontal leadership – International case studies', Manageable Cooperation?, EURAM, Paris.
View description>>

Leadership has become a central theme in the project management literature. Two majorstreams of research have emerged in studies on project leadership: the person-centered orvertical leadership stream, which focuses on the leadership role and skills of project managers;and the team-centered or horizontal leadership stream, which recognizes the distributed form ofleadership in projects. Previous research in project leadership has focused mostly on verticalleadership while in recent studies horizontal leadership has begun to emerge as an importantarea. While some view these two forms of leadership as separate, in reality, projects have toinclude both forms of leadership simultaneously. Studies on new product development teamshave shown that horizontal leadership supplements, but does not replace, vertical leadership.We investigate the interrelationship between vertical and horizontal leadership in projects andargue that projects are characterized by vertical leadership which provides a socio-cognitivespace in form of structures, processes and shared frameworks that enable the team to engage inhorizontal leadership. Based on a study of projects in different organizational contexts inAustralia and China, we provide insights about the characteristics of these socio-cognitive spacesand how they contribute to a balance between vertical and horizontal leadership in projectmanagement.

Nguyen, JL, Lawrance, NRJ, Fitch, R & Sukkarieh, S 1970, 'Informative Soaring with Drifting Thermals', 2016 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), IEEE International Conference on Robotics and Automation, IEEE, Stockholm, Sweden, pp. 1522-1529.
View/Download from: Publisher's site
View description>>

© 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.

Nguyen, L & Kodagoda, S 1970, 'Soil organic matter estimation in precision agriculture using wireless sensor networks', 2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV), 2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV), IEEE, Thailand, pp. 1-6.
View/Download from: Publisher's site

Patten, T, Fitch, R & Sukkarieh, S 1970, 'Multi-robot coverage planning with resource constraints for horticulture applications', Acta Horticulturae, International Horticultural Congress on Horticulture, International Society for Horticultural Science (ISHS), Brisbane, Australia, pp. 655-662.
View/Download from: Publisher's site
View description>>

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.

Paul, G, Liu, L & Liu, D 1970, 'A novel approach to steel rivet detection in poorly illuminated steel structural environments', 2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV), 2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV), IEEE, Phuket, Thailand, pp. 1-7.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. It is becoming increasingly achievable for steel bridge structures, which are normally both inaccessible and hazardous for humans, to be inspected and maintained by autonomous robots. Steel bridges have been traditionally constructed by securing plate members together with rivets. However, rivets present a challenge for robots both in terms of cleaning and surface traversal. This paper presents a novel approach to RGB-D image and point cloud analysis that enables rivets to be rapidly and robustly located using low cost, non-contact sensing devices that can be easily affixed to a robot. The approach performs classification based on: (a) high-intensity blobs in color images, (b) the non-linear perturbations in depth images, and (c) surface normal clusters in 3D point clouds. The predicted rivet locations from the three classifiers are combined using a probabilistic occupancy mapping technique. Experiments are conducted in several different lab and real-world steel bridge environments, where there is no external lighting infrastructure, and the sensors are attached to a mobile platform, i.e. a climbing inspection robot. The location of rivets within 2m of the robot can be robustly located within 10mm of their correct location. The state of voxels can be predicted with above 95% accuracy, in approximately 1 second per frame.

Quin, P, Paul, G, Alempijevic, A & Liu, D 1970, 'Exploring in 3D with a climbing robot: Selecting the next best base position on arbitrarily-oriented surfaces.', IROS, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Daejeon, Korea, pp. 5770-5775.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. This paper presents an approach for selecting the next best base position for a climbing robot so as to observe the highest information gain about the environment. The robot is capable of adhering to and moving along and transitioning to surfaces with arbitrary orientations. This approach samples known surfaces, and takes into account the robot kinematics, to generate a graph of valid attachment points from which the robot can either move to other positions or make observations of the environment. The information value of nodes in this graph are estimated and a variant of A∗ is used to traverse the graph and discover the most worthwhile node that is reachable by the robot. This approach is demonstrated in simulation and shown to allow a 7 degree-of-freedom inchworm-inspired climbing robot to move to positions in the environment from which new information can be gathered about the environment.

Ranasinghe, R & Kodagoda, S 1970, 'Spatial prediction in mobile robotic wireless sensor networks with network constraints', 2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV), 2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV), IEEE, Phuket, Thailand, pp. 1-6.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. In recent years mobile robotic wireless sensor networks have been a popular choice for modelling spatial phenomena. This research is highly demanding and non-trivial due to challenges from both network and robotic aspects. In this paper, we address the spatial modelling of a physical phenomena with the network connectivity constraints while the mobile robots are striving to achieve the minimum modelling mismatch in terms of root mean square error (RMSE). We have resolved it through Gauss markov random field based approach which is a computationally efficient implementation of Gaussian processes. In this strategy, the Mobile Robotic Wireless Sensor Node (MRWSN) are centrally controlled to maintain the connectivity while minimizing the RMSE. Once the number of MRWSNs reach their maximum coverage, a new MRWSN is requested at the most informative location. The experimental results are convincing and they show the effectiveness of the algorithm.

Reeks, C, Carmichael, MG, Dikai Liu & Waldron, KJ 1970, 'Angled sensor configuration capable of measuring tri-axial forces for pHRI', 2016 IEEE International Conference on Robotics and Automation (ICRA), 2016 IEEE International Conference on Robotics and Automation (ICRA), IEEE, Stockholm, Sweden, pp. 3089-3094.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. This paper presents a new configuration for single axis tactile sensor arrays molded in rubber to enable tri-axial force measurement. The configuration requires the sensing axis of each sensor in the array to be rotated out of alignment with respect to external forces. This angled sensor array measures shear forces along axes in a way that is different to a planar sensor array. Three sensors using the angled configuration (22.5°, 45° and 67.5°) and a fourth sensor using the planar configuration (0°) have been fabricated for experimental comparison. Artificial neural networks were trained to interpret the external force applied along each axis (X, Y and Z) from raw pressure sensor values. The results show that the angled sensor configuration is capable of measuring tri-axial external forces with a root mean squared error of 1.79N, less error in comparison to the equivalent sensor utilizing the planar configuration (4.52N). The sensors are then implemented to control a robotic arm. Preliminary findings show angled sensor arrays to be a viable alternative to planar sensor arrays for shear force measurement; this has wide applications in physical Human Robot Interaction (pHRI).

Reid, W, Fitch, R, Goktogan, AH & Sukkarieh, S 1970, '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 description>>

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 sampling based 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.

Shi, L, Miro, JV, Zhang, T, Vidal-Calleja, T, Sun, L & Dissanayake, G 1970, 'Constrained sampling of 2.5D probabilistic maps for augmented inference', 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Daejeon, Korea, pp. 3131-3136.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. This work exploits modeling spatial correlation in 2.5D data using Gaussian Processes (GPs), and produces constrained sampling realizations on these models to improve certainty in the predictions by means of integrating additional sparse information. Data organized in 2.5D such as elevation and thickness maps has been extensively studied in the fields of robotics and geostatistics. These maps are typically represented as a probabilistic 2D grid that stores an estimated value (height or thickness) for each cell. With the increasing popularity and deployment of robotic devices for infrastructure inspection, 2.5D data becomes a common interpretation of the condition of the target being inspected. Modeling the spatial dependencies and making inferences on new grid locations is a common task that has been addressed using GPs, but inference results on locations which are weakly correlated with the training data are generally not sufficiently informative and distinctly uncertain. The predictive capability of the proposed framework, which is applicable to any 2.5D data, is demonstrated with field inspection data from pipelines. Specifically, sparse and complementary measurements from alternative sensing modalities have been incorporated into the model to predict in more detail local thickness conditions where GP training data is limited. The output of this work aims to probabilistically present variations of the target in the case that both accuracy and reasonable diversity are of significant interest.

Song, J, Wang, J, Zhao, L, Huang, S & Dissanayake, G 1970, '3D shape recovery of deformable soft-tissue with computed tomography and depth scan', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, ARAA, Queensland, Australia, pp. 11-19.
View description>>

Knowing the tissue environment accurately is very important in minimal invasive surgery (MIS). While, as the soft-tissues is deformable, reconstruction of the soft-tissues environment is challenging. This paper proposes a new framework for recovering the deformation of the soft-tissues by using a single depth sensor. This framework makes use of the morphology information of the soft-tissues from Xray computed tomography, and deforms it by the embedded deformation method. Here, the key is to build a distance field function of the scan from the depth sensor, which can be used to perform accurate model-to-scan deformation together with robust non-rigid shape registration in the same go. Simulations show that soft-tissue shape in the previous step can be efficiently deformed to fit the partially observed scan in the current step by using the proposed method. And the results from the simulated sequential deformation of three different softtissues demonstrate the potential clinical value for MIS.

Su, D, Nakamura, K, Nakadai, K & Miro, JV 1970, 'Robust sound source mapping using three-layered selective audio rays for mobile robots', 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Daejeon, Korea, pp. 2771-2777.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. This paper investigates sound source mapping in a real environment using a mobile robot. Our approach is based on audio ray tracing which integrates occupancy grids and sound source localization using a laser range finder and a microphone array. Previous audio ray tracing approaches rely on all observed rays and grids. As such observation errors caused by sound reflection, sound occlusion, wall occlusion, sounds at misdetected grids, etc. can significantly degrade the ability to locate sound sources in a map. A three-layered selective audio ray tracing mechanism is proposed in this work. The first layer conducts frame-based unreliable ray rejection (sensory rejection) considering sound reflection and wall occlusion. The second layer introduces triangulation and audio tracing to detect falsely detected sound sources, rejecting audio rays associated to these misdetected sounds sources (short-term rejection). A third layer is tasked with rejecting rays using the whole history (long-term rejection) to disambiguate sound occlusion. Experimental results under various situations are presented, which proves the effectiveness of our method.

Su, D, Vidal-Calleja, T & Miro, JV 1970, 'Split conditional independent mapping for sound source localisation with Inverse-Depth Parametrisation', 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Daejeon, Korea, pp. 2000-2006.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. 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, 1) a proprioceptive sensor only (such as wheel odometry) or 2) 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, T & Miro, JV 1970, 'Gaussian Markov Random Fields for fusion in information form', 2016 IEEE International Conference on Robotics and Automation (ICRA), 2016 IEEE International Conference on Robotics and Automation (ICRA), IEEE, Stockholm, Sweden, pp. 1840-1845.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. 2.5D maps are preferable for representing the environment owing to their compactness. When noisy observations from multiple 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 sparse structure of the information matrix. Gaussian Markov Random Fields are employed to learn a prior map, which uses the conditional independence property between spatial location to obtain a representation of the state with a sparse information matrix. This prior map encoded in information form can then be updated with other sources of sensor data in constant time. Later, mean state vector and variances can be also efficiently recovered using sparse matrices techniques. The proposed approach allows accurate estimation of 2.5D maps at arbitrary resolution, while incorporating sensor noise and spatial dependency in a statistically sound 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 methods, 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 computationally expensive optimal fusion method in covariance form with a Gaussian Process prior.

Takami, K, Liu, H, Furukawa, T, Kumon, M & Dissanayake, G 1970, 'Non-field-of-view sound source localization using diffraction and reflection signals', 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Daejeon, Korea, pp. 157-162.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. This paper describes a non-field-of-view (NFOV) localization approach for a mobile robot in an unknown environment based on an acoustic signal combined with the geometrical information from an optical sensor. The approach estimates the location of a target through the mobile robot's sensor observation frame, which consists of a combination of diffraction and reflection acoustic signals and a 3-D environment geometrical description. This fusion of audio-visual sensor observation likelihoods allows the robot to estimate the NFOV target. The diffraction and reflection observations from the microphone array generate the acoustic joint observation likelihood. The observed geometry also determines far-field or near-field acoustic conditions to improve the estimation of the sound direction of arrival. A mobile robot equipped with a microphone array and an RGB-D sensor was tested in a controlled environment, an anechoic chamber, to demonstrate the NFOV localization capabilities. This resulted in +/-18 degrees, and less than 0.75 m error in angle and distance estimation, respectively.

Thiyagarajan, K, Kodagoda, S & Alvarez, JK 1970, 'An instrumentation system for smart monitoring of surface temperature', 2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV), 2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV), IEEE, Phuket, Thailand, pp. 1-6.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. Reliable sensing is a crucial factor for assessing the structural health conditions of civil infrastructure such as sewerage networks, which are susceptible to hydrogen sulfide induced concrete corrosion. In this context, this paper reports the work on the development and characterization of an instrumentation system using an infrared radiometer for monitoring surface temperature variations of the concrete through non-contact measurements. The surface temperature measurements are gathered by positioning the sensor at different distance and angles from the surface of interest. The effects of ambient lighting conditions during measurements are investigated. Furthermore, the sensing performance of the sensor is evaluated by performing statistical error analysis, and the efficacy of a custom-made signal processing board is tested by comparing the electrical signal with reference measures.

Thiyagarajan, K, Kodagoda, S, Ulapane, N & IEEE 1970, 'Data-driven Machine Learning Approach for Predicting Volumetric Moisture Content of Concrete Using Resistance Sensor Measurements', PROCEEDINGS OF THE 2016 IEEE 11TH CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA), IEEE Conference on Industrial Electronics and Applications, IEEE, Hefei, China, pp. 1288-1293.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. In sewerage industry, hydrogen sulphide induced corrosion of reinforced concretes is a global problem. To achieve a comprehensive knowledge of the propagation of concrete corrosion, it is vital to monitor the critical factors such as moisture. In this context, this paper investigates the use of resistance measuring and processing for estimating the concrete moisture content. The behavior of concrete moisture with resistance and surface temperature are studied and the effects of pH concentration on concrete are analyzed. Gaussian Process regression modeling is carried out to predict volumetric moisture content of concrete, where the results from experimental data are used to train the prediction model.

Wijerathna, B, Falque, R, Kodagoda, S & Dissanayake, G 1970, 'Linear approximation for mapping remaining wall thickness using a magnetic flux leakage sensor', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, ACRA, The University of Queensland, pp. 240-247.
View description>>

Use of an unconventional sensor for mapping the remaining wall thickness of a pipe is presented in this paper. This is achieved through the development of a sensor model relating the measurements from a Magnetic Flux Leakage (MFL) sensor to the environment geometry. Conventional sensors, such as laser-range finders commonly used in the robotic community are not able to infer thickness profiles of ferromagnetic structures such as water pipes when the surface is covered with corrosion products. Sensors based on electromagnetic principles or ultrasound are the methods of choice in such situations to estimate the extent of corrosion and predict eventual failure. The general relationship between readings from electromagnetic sensors and the environment geometry is governed by a set of partial differential equations (Maxwells equations). However, in the case of an MFL sensor, it is demonstrated that a linear combination of the thickness profiles can be used to adequately model the sensor signal. Parameters associated with the sensor model are obtained using a two-dimensional finite element simulations. Extensive simulation results are presented to validate the proposed method by estimating a remaining wall thickness map of a realistic pipe.

Woolfrey, J, Liu, D & Carmichael, M 1970, 'Kinematic control of an Autonomous Underwater Vehicle-Manipulator System (AUVMS) using autoregressive prediction of vehicle motion and Model Predictive Control', 2016 IEEE International Conference on Robotics and Automation (ICRA), 2016 IEEE International Conference on Robotics and Automation (ICRA), IEEE, Stockholm, Sweden, pp. 4591-4596.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. Autonomous Underwater Vehicle-Manipulator Systems (AUVMS) operating in shallow waters or near-surface environments may be exposed to wave disturbances which will cause undesired motion of the end effector. This paper presents a method to maneuver the manipulator joints and counteract undesired motion of the vehicle body, in order to maintain a steady end-effector position in the inertial frame. An Autoregressive (AR) model is used to predict vehicle motion, and then combined with Model Predictive Control (MPC) to optimize joint motion. Simulation was conducted using real data to verify the efficacy of this method.

Yang, C-HJ, Paul, G, Ward, P & Liu, D 1970, 'A path planning approach via task-objective pose selection with application to an inchworm-inspired climbing robot', 2016 IEEE International Conference on Advanced Intelligent Mechatronics (AIM), 2016 IEEE International Conference on Advanced Intelligent Mechatronics (AIM), IEEE, Banff, Canada, pp. 401-406.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. This paper presents a stepping path planning approach for a climbing robot inspired kinematically from an inchworm caterpillar's looping locomotion. This approach generates an optimised multi-step path to traverse through space and to land a specific footpad onto a selected point on a surface with a specific footpad orientation. The candidate landing joint configuration for each step is generated by a pose selection process, using an optimisation technique with task-objective functions based on the constraints of the robot. Then another technique is used to obtain a new set of poses satisfying strict constraints of the landing motion. The set of candidate landing poses is used to compute the subsequent steps. A valid motion trajectory, which avoids all obstacles, can be generated by a point-to-point planner for each of the landing poses from the current pose. This single step planning technique is then expanded to multi-step path planning by building a search tree, where a combination of steps is evaluated and optimised by a cost function, which includes objectives related to robot movement. This approach is implemented and validated on the climbing robot in real-world steel bridge environments. The planner successfully finds multi-step paths in these field trials enabling the robot to traverse through several complex structures inside the bridge steel box girders.

Yiyi Liao, Kodagoda, S, Yue Wang, Lei Shi & Yong Liu 1970, 'Understand scene categories by objects: A semantic regularized scene classifier using Convolutional Neural Networks', 2016 IEEE International Conference on Robotics and Automation (ICRA), 2016 IEEE International Conference on Robotics and Automation (ICRA), IEEE, Stockholm, Sweden, pp. 2318-2325.
View/Download from: Publisher's site
View description>>

Scene classification is a fundamental perception task for environmental understanding in today's robotics. In this paper, we have attempted to exploit the use of popular machine learning technique of deep learning to enhance scene understanding, particularly in robotics applications. As scene images have larger diversity than the iconic object images, it is more challenging for deep learning methods to automatically learn features from scene images with less samples. Inspired by human scene understanding based on object knowledge, we address the problem of scene classification by encouraging deep neural networks to incorporate object-level information. This is implemented with a regularization of semantic segmentation. With only 5 thousand training images, as opposed to 2.5 million images, we show the proposed deep architecture achieves superior scene classification results to the state-of-the-art on a publicly available SUN RGB-D dataset. In addition, performance of semantic segmentation, the regularizer, also reaches a new record with refinement derived from predicted scene labels. Finally, we apply our model trained on SUN RGB-D dataset to a set of images captured in our university using a mobile robot, demonstrating the generalization ability of the proposed algorithm.

Zhang, T, Huang, S, Liu, D, Shi, L, Zhou, C & Xiong, R 1970, 'A method of state estimation for underwater vehicle navigation around a cylindrical structure', 2016 IEEE 11th Conference on Industrial Electronics and Applications (ICIEA), 2016 IEEE 11th Conference on Industrial Electronics and Applications (ICIEA), IEEE, Hefei, China, pp. 101-106.
View/Download from: Publisher's site
View description>>

© 2016 IEEE. Recently, increasing efforts have been focused on the development and adoption of autonomous underwater vehicles (AUVs) for various applications. However, the GPS signals are usually unavailable, the vehicle dynamics is very uncertain, and the complicated vision based localization algorithms may not work well in the underwater environments. Hence, accurate and timely state estimation using low-cost sensors remains a challenge for the control and navigation of AUVs. This paper considers the state estimation problem for underwater vehicle navigation around a cylindrical structure. The vehicle is assumed to be equipped with only low-cost sensors: an inertia measurement unit (IMU), a pressure sensor and a monocular camera. By exploiting the prior knowledge on the size and shape of the structure, an efficient algorithm for estimating the state of the AUV is developed without using any dynamic model. Firstly, a state observer is proposed under the condition that the localization result (rotational and translational position) is available. Next, we present a method for localization based on the IMU readings, pressure sensor readings and the image of the cylindrical structure, which uses the geometry of the structure and only requires simple image processing (line extraction). Then we prove that the proposed observer is globally stable. Preliminary experimental results and simulation results are reasonable and promising, which implies the proposed method has potential to be used in the real AUV navigation applications.

Zhao, L, Giannarou, S, Lee, S-L & Yang, G-Z 1970, 'Registration-Free Simultaneous Catheter and Environment Modelling', Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016 (LNCS), Medical Image Computing and Computer-Assisted Intervention, Springer International Publishing, Athens, Greece, pp. 525-533.
View/Download from: Publisher's site
View description>>

Endovascular procedures are challenging to perform due to the complexity and difficulty in catheter manipulation. The simultaneous recovery of the 3D structure of the vasculature and the catheter position and orientation intra-operatively is necessary in catheter control and navigation. State-of-art Simultaneous Catheter and Environment Modelling provides robust and real-time 3D vessel reconstruction based on real-time intravascular ultrasound (IVUS) imaging and electromagnetic (EM) sensing, but still relies on accurate registration between EM and pre-operative data. In this paper, a registration-free vessel reconstruction method is proposed for endovascular navigation. In the optimisation framework, the EM-CT registration is estimated and updated intra-operatively together with the 3D vessel reconstruction from IVUS, EM and pre-operative data, and thus does not require explicit registration. The proposed algorithm can also deal with global (patient) motion and periodic deformation caused by cardiac motion. Phantom and in-vivo experiments validate the accuracy of the algorithm and the results demonstrate the potential clinical value of the technique.

Zhao, L, Giannarou, S, Lee, S-L, Merrifield, R & Yang, GZ 1970, 'Intra-operative Simultaneous Catheter and Environment Modelling for Endovascular Navigation Based on Intravascular Ultrasound, Electromagnetic Tracking and Pre-operative Data', Proceedings of The Hamlyn Symposium on Medical Robotics, The Hamlyn Symposium on Medical Robotics, Imperial College London and the Royal Geographical Society, London, UK, pp. 76-77.
View description>>

Cardiovascular diseases (CVD) form the single mostcommon cause of death. Catheter procedures are amongthe most common surgical interventions used to treatCVD. Due to their minimal access trauma, theseprocedures extend the range of patients able to receiveinterventional CVD treatment to age groups dominatedby co-morbidity and unacceptable risks for open surgery[1]. The downside associated with minimising accessincisions lies at the increased complexity and difficultmanipulation of the instruments and anatomical targets,which is mainly caused by the loss of direct access tothe anatomy and the poor visualisation of the surgicalsite. The current clinical approaches to endovascularprocedures mainly rely on 2D guidance based on X-rayfluoroscopy, which uses ionising radiation anddangerous contrast agents [2].In this paper, a Simultaneous Catheter and EnvironmentModelling (SCEM) method is presented forendovascular navigation based on intravascularultrasound (IVUS) imaging, electromagnetic (EM)sensing as well as the vessel structure informationprovided from the pre-operative CT/MR imaging (seeFig. 1). Thus, radiation dose and contrast agents areavoided. The proposed SCEM intra-operatively recoversthe 3D structure of the vasculature together with thepose of the catheter tip, which the knowledge of theinteraction between the catheter and its surroundingscan be provided. The corresponding uncertainties ofboth vessel reconstruction and catheter pose can also becomputed which is necessary for autonomous roboticcatheter navigation. Experimental results using threedifferent phantoms, with different catheter motions andcardiac motions simulated by using a periodic pumpdemonstrated the accuracy of the vessel reconstructionand the potential clinical value of the proposed SCEMmethod.

Cliff, OM, Prokopenko, M & Fitch, R 2016, An Information Criterion for Inferring Coupling in Complex Networks.

Cliff, OM, Prokopenko, M & Fitch, R 2016, Inferring Coupling of Distributed Dynamical Systems via Transfer Entropy.
View description>>

In this work, we are interested in structure learning for a set of spatiallydistributed dynamical systems, where individual subsystems are coupled vialatent variables and observed through a filter. We represent this model as adirected acyclic graph (DAG) that characterises the unidirectional couplingbetween subsystems. Standard approaches to structure learning are notapplicable in this framework due to the hidden variables, however we canexploit the properties of certain dynamical systems to formulate exact methodsbased on state space reconstruction. We approach the problem by usingreconstruction theorems to analytically derive a tractable expression for theKL-divergence of a candidate DAG from the observed dataset. We show thismeasure can be decomposed as a function of two information-theoretic measures,transfer entropy and stochastic interaction. We then present two mathematicallyrobust scoring functions based on transfer entropy and statistical independencetests. These results support the previously held conjecture that transferentropy can be used to infer effective connectivity in complex networks.

Abeywardena, D, Huang, S, Barnes, B, Dissanayake, G & Kodagoda, S 2016, 'Fast, On-board, Model-aided Visual-Inertial Odometry System for Quadrotor Micro Aerial Vehicles'.

Dissanayake, G 2016, 'INFRASTRUCTURE ROBOTICS: OPPORTUNITIES AND CHALLENGES', WORLD SCIENTIFIC PUBL CO PTE LTD, pp. 3-3.

Khosoussi, K, Sukhatme, GS, Huang, S & Dissanayake, G 2016, 'Designing Sparse Reliable Pose-Graph SLAM: A Graph-Theoretic Approach'.
View description>>

In this paper, we aim to design sparse D-optimal (determinantoptimal)pose-graph SLAM problems through the synthesis of sparse graphs with themaximum weighted number of spanning trees. Characterizing graphs with themaximum number of spanning trees is an open problem in general. To tackle thisproblem, several new theoretical results are established in this paper,including the monotone log-submodularity of the weighted number of spanningtrees. By exploiting these structures, we design a complementary pair ofnear-optimal efficient approximation algorithms with provable guarantees. Ourtheoretical results are validated using random graphs and a publicly availablepose-graph SLAM dataset.

Khosoussi, K, Sukhatme, GS, Huang, S & Dissanayake, G 2016, 'Maximizing the Weighted Number of Spanning Trees: Near-$t$-Optimal Graphs'.
View description>>

Designing well-connected graphs is a fundamental problem that frequentlyarises in various contexts across science and engineering. The weighted numberof spanning trees, as a connectivity measure, emerges in numerous problems andplays a key role in, e.g., network reliability under random edge failure,estimation over networks and D-optimal experimental designs. This paper tacklesthe open problem of designing graphs with the maximum weighted number ofspanning trees under various constraints. We reveal several new structures,such as the log-submodularity of the weighted number of spanning trees inconnected graphs. We then exploit these structures and design a pair ofefficient approximation algorithms with performance guarantees andnear-optimality certificates. Our results can be readily applied to a wideverity of applications involving graph synthesis and graph sparsificationscenarios.

Liao, Y, Huang, L, Wang, Y, Kodagoda, S, Yu, Y & Liu, Y 2016, 'Parse Geometry from a Line: Monocular Depth Estimation with Partial Laser Observation'.