Publications

Fitch, R, Butler, Z & Rus, D 2007, 'In-place distributed heterogeneous reconfiguration planning', SPRINGER, pp. 159-168.
View/Download from: Publisher's site

Herath, HD, Kodagoda, S & Dissanayake, G 2007, 'Stereo Vision Based SLAM: Issues and Solutions' in Obinata, G & Dutta, A (eds), Vision Systems, ITECH, Austria, pp. 555-582.

Kulatunga, AK, Skinner, BT, Liu, DK & Nguyen, HT 2007, 'Distributed simultaneous task allocation and motion coordination of autonomous vehicles using a parallel computing cluster' in Tarn, TJ, Chen, SB & Zhou, C (eds), Robotic Welding, Intelligence and Automation, Springer, Heidelberg, pp. 409-420.
View/Download from: Publisher's site
View description>>

Task allocation and motion coordination are the main factors that should be consi-dered in the coordination of multiple autonomous vehicles in material handling systems. Presently, these factors are handled in different stages, leading to a reduction in optimality and efficiency of the overall coordination. However, if these issues are solved simultaneously we can gain near optimal results. But, the simultaneous approach contains additional algorithmic complexities which increase computation time in the simulation environment. This work aims to reduce the computation time by adopting a parallel and distributed computation strategy for Simultaneous Task Allocation and Motion Coordination (STAMC). In the simulation experiments, each cluster node executes the motion coordination algorithm for each autonomous vehicle. This arrangement enables parallel computation of the expensive STAMC algorithm. Parallel and distributed computation is performed directly within the interpretive MATLAB environment. Results show the parallel and distributed approach provides sub-linear speedup compared to a single centralised computing node. © 2007 Springer-Verlag Berlin Heidelberg.

Kumar, MR & Sankaran, S 2007, 'Action research: Collecting insight and enduring organizational change' in Sankaran, G & Miller, P (eds), Exemplary practitioner research in management: ten studies from Southern Cross University's DBA prog, Southern Cross University Press, Lismore, pp. 31-49.

Liu, DK & Kulatunga, AK 2007, 'Simultaneous Planning and Scheduling for Multi-Autonomous Vehicles' in Dahal, KP, Tan, KC & Cowling, PI (eds), Studies in Computational Intelligence, Springer Berlin Heidelberg, Heidelberg, pp. 437-464.
View/Download from: Publisher's site
View description>>

With the increasing applications of autonomous vehicles in dynamic and strictly constrained environments such as automated container terminals, efficient task/resource allocation and motion coordination (i.e., path and speed planning) of multi-autonomous vehicles has become the critical problem and have therefore been recently recognized as the key research issues by both academics and industry. This chapter addresses a generic approach for integration of task allocation, path planning and collision avoidance, which has so far not attracted much attention in the academic literature. A Simultaneous Task Allocation and Motion Coordination (STAMC) approach is presented. Two metaheuristic algorithms, i.e. simulated annealing and ant colony, and an auction algorithm are investigated and applied. The proposed approach is able to solve the scheduling, planning and collision avoidance problems simultaneously; improve the usage of bottleneck areas; handle dynamic traffic conditions and avoid deadlock. Simulation results demonstrated the effectiveness and efficiency of this approach. © Springer-Verlag Berlin Heidelberg 2007.

Paul, G, Liu, DK & Kirchner, N 2007, 'An algorithm for surface growing from laser scan generated point clouds' in Tarn, TJ, Chen, SB & Zhou, C (eds), Robotic Welding, Intelligence and Automation, Springer, Heidelberg, pp. 481-491.
View/Download from: Publisher's site
View description>>

In robot applications requiring interaction with a partially/unknown environment, mapping is of paramount importance. This paper presents an effective surface growing algorithm for map building based on laser scan generated point clouds. The algorithm directly converts a point cloud into a surface and normals form which sees a significant reduction in data size and is in a desirable format for planning the interaction with surfaces. It can be used in applications such as robotic cleaning, painting and welding. © 2007 Springer-Verlag Berlin Heidelberg.

Phua, CW & Fitch, R 2007, 'Tracking value function dynamics to improve reinforcement learning with piecewise linear function approximation', ACM, pp. 751-758.
View/Download from: Publisher's site
View description>>

Reinforcement learning algorithms can become unstable when combined with linear function approximation. Algorithms that minimize the mean-square Bellman error are guaranteed to converge, but often do so slowly or are computationally expensive. In this paper, we propose to improve the convergence speed of piecewise linear function approximation by tracking the dynamics of the value function with the Kalman filter using a random-walk model. We cast this as a general framework in which we implement the TD, Q-Learning and MAXQ algorithms for different domains, and report empirical results demonstrating improved learning speed over previous methods.

Wong, P & Sankaran, S 2007, 'Critical incidents: Drilling down to core ethical issues' in Sankaran, G & Miller, P (eds), Exemplary practitioner research in management: ten studies from Southern Cross University's DBA prog, Southern Cross University Press, Lismore, pp. 191-210.

Xu, J, Liu, DK & Fang, G 2007, 'An Efficient Method for Collision Detection and Distance Queries in a Robotic Bridge Maintenance System' in Tarn, TJ, Chen, SB & Zhou, C (eds), Lecture Notes in Control and Information Sciences, Springer Berlin Heidelberg, Heidelberg, pp. 71-82.
View/Download from: Publisher's site
View description>>

When applying autonomous industrial robotic systems in an unknown/partially known or cluttered environment, mapping and representation of the environment as well as collision detection becomes crucial. Existing techniques in these areas are generally complex and computationally expensive to implement. In this paper an efficient sphere representation method is introduced for environment representation, collision detection and distance queries. In particular, this method is designed for the application in an autonomous bridge maintenance system. Simulation results show that this method is effective in environment representation and collision detection. Furthermore, the proposed method is also computationally efficient for real-time implementation. © 2007 Springer-Verlag Berlin Heidelberg.

Ellekilde, L-P, Huang, S, Miro, JV & Dissanayake, G 2007, 'Dense 3D map construction for indoor search and rescue', JOURNAL OF FIELD ROBOTICS, vol. 24, no. 1-2, pp. 71-89.
View/Download from: Publisher's site
View description>>

The main contribution of this paper is a new simultaneous localization and mapping (SLAM) algorithm for building dense three-dimensional maps using information acquired from a range imager and a conventional camera, for robotic search and rescue in unstructured indoor environments. A key challenge in this scenario is that the robot moves in 6D and no odometry information is available. An extended information filter (EIF) is used to estimate the state vector containing the sequence of camera poses and some selected 3D point features in the environment. Data association is performed using a combination of scale invariant feature transformation (SIFT) feature detection and matching, random sampling consensus (RANSAC), and least square 3D point sets fitting. Experimental results are provided to demonstrate the effectiveness of the techniques developed. © 2007 Wiley Periodicals, Inc.

Huang, S & Dissanayake, G 2007, 'Convergence and consistency analysis for extended Kalman filter based SLAM', IEEE TRANSACTIONS ON ROBOTICS, vol. 23, no. 5, pp. 1036-1049.
View/Download from: Publisher's site
View description>>

This paper investigates the convergence properties and consistency of Extended Kalman Filter (EKF) based simultaneous localization and mapping (SLAM) algorithms. Proofs of convergence are provided for the nonlinear two-dimensional SLAM problem with point landmarks observed using a range-and- bearing sensor. It is shown that the robot orientation uncertainty at the instant when landmarks are first observed has a significant effect on the limit and/or the lower bound of the uncertainties of the landmark position estimates. This paper also provides some insights to the inconsistencies of EKF based SLAM that have been recently observed. The fundamental cause of EKF SLAM inconsistency for two basic scenarios are clearly stated and associated theoretical proofs are provided. © 2007 IEEE.

Kim, J & Sukkarieh, S 2007, 'Real-time implementation of airborne inertial-SLAM', Robotics and Autonomous Systems, vol. 55, no. 1, pp. 62-71.
View/Download from: Publisher's site

Kodagoda, KRS, Ge, SS, Wijesoma, WS & Balasuriya, AP 2007, 'IMMPDAF Approach for Road-Boundary Tracking', IEEE Transactions on Vehicular Technology, vol. 56, no. 2, pp. 478-486.
View/Download from: Publisher's site
View description>>

Robust road-boundary extraction/tracking is one of the main problems in autonomous roadway navigation. Although the road boundary can be defined by various means including lane markings, curbs, and borders of vegetation, this paper focuses on road-boundary tracking using curbs. A vehicle-mounted (downward tilted) 2-D laser-measurement system is utilized to detect the curbs. The tracking problem is difficult because both the vehicle is moving and the target is disappearing, reappearing, and maneuvering in clutter. The interacting-multiple-model probabilistic-data-association filter (IMMPDAF) is proposed to solve the problems after detailed analysis. Track initiation, confirmation, and deletion are performed using the sequential-probability-ratio test. Extensive simulations followed by experiments in a campus environment show that the road-boundary tracking utilizing curbs is possible and robust through IMMPDAF. © 2007 IEEE.

Kwok, NM, Ha, QP, Huang, S, Dissanayake, G & Fang, G 2007, 'Mobile robot localization and mapping using a Gaussian sum filter', INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS, vol. 5, no. 3, pp. 251-268.
View description>>

A Gaussian sum filter (GSF) is proposed in this paper on simultaneous localization and mapping (SLAM) for mobile robot navigation. In particular, the SLAM problem is tackled here for cases when only bearing measurements are available. Within the stochastic mapping framework using an extended Kalman filter (EKF), a Gaussian probability density function (pdf) is assumed to describe the range-and-bearing sensor noise. In the case of a bearing-only sensor, a sum of weighted Gaussians is used to represent the non-Gaussian robot-landmark range uncertainty, resulting in a bank of EKFs for estimation of the robot and landmark locations. In our approach, the Gaussian parameters are designed on the basis of minimizing the representation error. The computational complexity of the GSF is reduced by applying the sequential probability ratio test (SPRT) to remove under-performing EKFs. Extensive experimental results are included to demonstrate the effectiveness and efficiency of the proposed techniques.

Lam, J & Huang, S 2007, 'Decentralized H∞ control and reliability analysis for symmetric composite systems: Dynamic output feedback case', Dynamics of Continuous, Discrete and Impulsive Systems Series B: Applications and Algorithms, vol. 14, no. 3, pp. 445-462.
View description>>

The dynamic output feedback decentralized H∞ control and the reliability of the designed system (the maximal number of control-channel outages when the performance is still acceptable) is studied for symmetric composite systems. It is shown that the decentralized H∞ control problem can be simplified to a simultaneous H∞ control problem for two modified subsystems. A design method based on the simultaneous H∞ control method is given. Simple methods for testing the reliablity are presented using the special structure of symmetric composite systems. Copyright © 2007 Watam Press.

Orr, M & Sankaran, S 2007, 'Mutual empathy, ambiguity, and the implementation of electronic knowledge management within the complex health system', E:CO Emergence: Complexity and Organization, vol. 9, no. 1-2, pp. 44-55.
View description>>

Healthcare can be characterized as a complex adaptive system. New Zealand is recognized as having one of the highest rates of enmeshed clinical information and communication technology within this complex system. This paper describes the implementation of an integrated series of electronic clinical health knowledge management systems in a large New Zealand District Health Board. In combination with standard project management, the core implementation team utilized an action research reflective learning approach to enhance their capability to cope with emergent issues, and plan for each subsequent project stage. The emergent focus on 'process' issues of connectedness, competency, and control were not the 'technical' concerns the principal author was initially expecting, but can be understood through an appreciation of individual and group dynamics, system and complexity theories. In particular, mutual empathy for both self and others was identified as a core capability requirement to cope with the inherent ambiguity within complex systems.

Ranjan Kumar, M & Sankaran, S 2007, 'Indian culture and the culture for TQM: a comparison', The TQM Magazine, vol. 19, no. 2, pp. 176-188.
View/Download from: Publisher's site
View description>>

PurposeThis paper seeks to argue against the conventional wisdom in the current TQM literature that hierarchy is not conducive for TQM. It aims to identify the cultural dynamics that can aid TQM implementation in a hierarchical country like India.Design/methodology/approachThe paper reflects on the existing literature on culture and TQM and develops a mechanism that explains why hierarchy hinders TQM implementation in Western culture and how it can support TQM implementation in Indian culture.FindingsIn a people oriented culture like those of Japan and India, nurturance is the juice that sustains hierarchy that finally morphs into collectivism. In these social systems, there need not be conflicting impact of hierarchy and collectivism on TQM implementation if the nurturance aspect of hierarchy is understood. Thus, in the Indian context, hierarchy, operationalised through the guru‐shishya (teacher‐student) relationship between the boss and the subordinate can develop a learning orientation among the organisational members and facilitate TQM implementation. Similarly, by superimposing the element of “equity” on the “personalised relationship” dimension of hierarchy, in a collectivistic society like India, it is possible to elevate the aspect of “personalised relationship” between superior and subordinate to the status of “individualised consideration” dimension of transformational leadership provided it is bestowed only upon the satisfactory completion of “task” by the subordinate.Practical implicationsThis paper shows how the cultural aspect of TQM implementation should be h...

Rozyn, M, Zhang, N & Dissanayake, G 2007, 'Identification of Inertial Parameters of an On-Road Vehicle', SAE Technical Paper Series, vol. 116, no. 6, pp. 1680-1687.
View/Download from: Publisher's site
View description>>

During normal use vehicles are loaded in multiple configurations that directly alter their inertial properties. A method of accurately identifying and tracking these changes would benefit the many vehicle subsystems that rely on the accuracy of these parameters. In this paper a novel method is presented to determine the inertial properties of a vehicle from the measured sprung mass vibration responses, without the need of sophisticated measuring devices or specialized test rigs. After a brief description of the theoretical basis of the method, experimental results are presented which show estimation of the inertial properties is possible. The results validate the accuracy and applicability of the method and illustrate that the vehicle inertial properties can be obtained even when certain system parameters, such as damping coefficients, are assumed unknown.

Sankaran, S, Hase, S, Dick, B & Davies, A 2007, 'Singing different tunes from the same song sheet', Action Research, vol. 5, no. 3, pp. 293-305.
View/Download from: Publisher's site
View description>>

In a move consistent with co-generated learning, this article is co-written by teachers of action research and a former student. Before we present the content and structure of the actual course, we write about the vital issues in teaching action research. We then describe the course and finally hear a former student (himself now supervising doctoral students) on the merits of this particular approach to learning AR as a doctoral student. This article represents the combined experience of the authors in teaching action research together for several years at Southern Cross University in New South Wales, Australia. While involved in the same general activity our focus and experiences have, naturally, been quite different and we have tried to communicate them in this article. Hopefully, our learning will be of some value to the readers. What follows, then, are the thoughts of: Bob, the master action research craftsman and educator; Alan, who sees the bigger picture no matter what he is looking at; Shankar, the implementer and coordinator of projects; and Stewart, who struggles and is at peace with a world full of contradictions.

Upcroft, B, Makarenko, A, Moser, M, Alempijevic, A, Donikian, A, Uther, W & Fitch, R 2007, 'Empirical Evaluation of an Autonomous Vehicle in an Urban Environment', Journal of Aerospace Computing, Information, and Communication, vol. 4, no. 12, pp. 1086-1107.
View/Download from: Publisher's site
View description>>

Operation in urban environments creates unique challenges for research in autonomous ground vehicles. Due to the presence of tall trees and buildings in close proximity to traversable areas, GPS outage is likely to be frequent and physical hazards pose real threats to autonomous systems. In this paper, we describe a novel autonomous platform developed by the Sydney-Berkeley Driving Team for entry into the 2007 DARPA Urban Challenge competition. We report empirical results analyzing the performance of the vehicle while navigating a 560-meter test loop multiple times in an actual urban setting with severe GPS outage. We show that our system is robust against failure of global position estimates and can reliably traverse standard two-lane road networks using vision for localization. Copyright © 2007 by the American Institute of Aeronautics and Astronautics, Inc. All rights reserved.

Waldron, KJ & Abdallah, ME 2007, 'An Optimal Traction Control Scheme for Off-Road Operation of Robotic Vehicles', IEEE/ASME Transactions on Mechatronics, vol. 12, no. 2, pp. 126-133.
View/Download from: Publisher's site
View description>>

Active degrees of freedom provide a robotic vehicle the ability to enhance its performance in all terrain conditions. While active suspension systems are now commonplace in on-road vehicles, their application to off-road terrains has been little investigated. A fundamental component of such an application is a need to translate desired body motion commands into actuator values through the use of proprioceptive algorithms. The diverse nature of the terrains that might be encountered places variable demands upon the operation of the vehicle. This entails the potential use of a diverse set of algorithms designed to optimize mobility and performance. This paper presents a cohesive control scheme designed for the operation of an autonomous vehicle under all conditions. The ideas presented have been tested in simulation, and some have been used extensivly in the field. © 2007 IEEE.

Wang, Z, Huang, S & Dissanayake, G 2007, 'D-SLAM: A decoupled solution to simultaneous localization and mapping', INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, vol. 26, no. 2, pp. 187-204.
View/Download from: Publisher's site
View description>>

The main contribution of this paper is the reformulation of the simultaneous localization and mapping (SLAM) problem for mobile robots such that the mapping and localization can be treated as two concurrent yet separated processes: D-SLAM (decoupled SLAM). It is shown that SLAM with a range and bearing sensor in an environment populated with point features can be decoupled into solving a nonlinear static estimation problem for mapping and a low-dimensional dynamic estimation problem for localization. This is achieved by transforming the measurement vector into two parts: one containing information relating features in the map and another with information relating the map and robot. It is shown that the new formulation results in an exactly sparse information matrix for mapping when it is solved using an Extended Information Filter (EIF).Thus a significant saving in the computational effort can be achieved for large-scale problems by exploiting the special properties of sparse matrices. An important feature of D-SLAM is that the correlation among features in the map are still kept and it is demonstrated that the uncertainty of the feature estimates monotonically decreases. The algorithm is illustrated and evaluated through computer simulations and experiments. © 2007 SAGE Publications.

Cheong, CY, Lin, CJ, Tan, KC & Liu, DK 1970, 'A multi-objective evolutionary algorithm for berth allocation in a container port', 2007 IEEE Congress on Evolutionary Computation, 2007 IEEE Congress on Evolutionary Computation, IEEE, Singapore, pp. 927-934.
View/Download from: Publisher's site
View description>>

This paper considers a berth allocation problem (BAP) which requires the determination of exact berthing times and positions of incoming ships in a container port. The problem is solved by optimizing the berth schedule so as to minimize concurrently the three objectives of make span, number of crossings, and waiting time. These objectives represent the interests of both port and ship operators. A multi-objective evolutionary algorithm (MOEA) that incorporates the concept of Pareto optimality is proposed for solving the multi-objective BAP. The MOEA is equipped with a novel solution decoding scheme which is specifically designed to optimize the use of berth space. The MOEA is also able to function in a dynamic context which is of more relevance to a real-world situation. © 2007 IEEE.

Chotiprayanakul, P, Liu, D, Wang, D & Dissanayake, G 1970, 'Collision-Free Trajectory Planning for Manipulator Using Virtual Force based Approach', Proceedings of the International Conference on Engineering, Applied Sciences, and Technology (ICEAST 2007), International Conference on Engineering, Applied Sciences, and Technology, KMITL, Bangkok, Thailand, pp. 351-354.

Chotiprayanakul, P, Liu, DK, Wang, D & Dissanayake, G 1970, 'A 3-dimensional force field method for robot collision avoidance in complex environments', Automation and Robotics in Construction - Proceedings of the 24th International Symposium on Automation and Robotics in Construction, International Symposium on Automation and Robotics in Construction, Indian Institute of Technology Madras, Kochi, Kerala, India, pp. 139-145.
View description>>

This paper proposes a three-dimensional force field (3D-F 2) method for efficient motion planning and collision avoidance of a 6DOF manipulator in complex and dynamic environments while keeping the planned end-effector's path and speed unchanged. The 3D-F 2 is defined as ellipsoid shapes covering selected links of a manipulator. When the manipulator moves and its ellipsoid force field approaches to an obstacle in a tolerant range, a repulsive force will be generated and considered in the robot kinematic and dynamic analyses. In infrastructure maintenance, spray-painting and sand-blasting operations require that the operating spot 'moves' smoothly and continuously along planned path on a work surface at a constant speed, and allow changes in length and orientation of the spray/blasting stream. Thus, the stream is supposed to be another link and the end of stream performs as a spherical joint fixed on the target surface. Various simulations in a construction area show that the 3D-F 2 can retain the operating path and effectively avoid potential collisions.

D. Wang, N. M. Kwok, D. K. Liu, H. Lau & G. Dissanayake 1970, 'PSO-Tuned F² method for multi-robot navigation', 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, San Diego, California, USA, pp. 3765-3770.
View/Download from: Publisher's site
View description>>

The F2 (Force Field) method is a novel approach for multi-robot motion planning and collision avoidance. The setting of parameters is however vital to its performance. This paper presents an approach using Particle Swarm Optimization (PSO) to properly determine the control parameters for the F 2 method. The goal of the optimization is to minimize the resultant path lengths. The approach presented in this paper can be used as a tool to obtain optimal parameters for various tasks before their execution. Simulations are carried out in various environments to show the feasibility of this approach. ©2007 IEEE.

Euston, M & Kim, J 1970, 'Rao-blackwellised Inertial-SLAM with partitioned vehicle subspace', Proceedings of the 2007 Australasian Conference on Robotics and Automation, ACRA 2007.
View description>>

This paper presents methods which enable the Rao-Blackwellised (R-B) particle filtering technique to be applicable for the airborne simultaneous localisation and mapping problem. Although R-B filter has been successfully applied to mobile/ground vehicles, its extension to flying vehicles has been impractical due to the high dimensionality involved in inertial navigation system (INS). To overcome this problem, the full INS state is further partitioned into an external state (vehicle pose) and an internal state (navigation and sensor calibration), with a particle filter being applied only to the external state. The computational complexity is further reduced by developing a hybrid R-B Inertial-SLAM. Simulation results will be presented with simulated flight data, showing reliable performances during loop-closures.

Fitch, R, Butler, Z & IEEE 1970, 'Scalable locomotion for large self-reconfiguring robots', PROCEEDINGS OF THE 2007 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-10, IEEE International Conference on Robotics and Automation, IEEE, Rome, ITALY, pp. 2248-2253.
View/Download from: Publisher's site

Guo, Y, Zhu, J, Liu, D, Lu, H & Wang, S 1970, 'Application of Multi-level Multi-domain Modeling in the Design and Analysis of a PM Transverse Flux Motor with SMC Core', 2007 7th International Conference on Power Electronics and Drive Systems, 2007 7th International Conference on Power Electronics and Drive Systems, IEEE, Bangkok, Thailand, pp. 27-31.
View/Download from: Publisher's site
View description>>

This paper presents the design and analysis of a permanent magnet (PM) transverse flux motor with soft magnetic composite (SMC) core by applying multi-level multi-domain modeling. The design is conducted in two levels. The upper level is composed of a group of equations which describe the electrical and mechanical characteristics of the motor. The lower level consists of two domains: electromagnetic analysis and thermal calculation. The initial design, including structure, materials and major dimensions, is determined according to existing experience and empirical formulae. Then, optimization is carried out at the system level (the upper level) for the best motor performance by optimizing the structural dimensions. To successfully deal with such a multi-level multi-domain optimization problem, an effective modeling with both high computational accuracy and speed is required. For accurately computing the key motor parameters, such as back electromotive force, winding inductance and core loss, magnetic field finite element analysis is performed. The core loss in each element is stored for effective thermal calculation, and the winding inductance and back EMF are stored as a look-up table for effective analysis of the motor's dynamic performance. The presented approach is effective with good accuracy and reasonable computational speed. © 2007 IEEE.

Guo, Y, Zhu, J, Liu, D, Lu, H & Wang, S 1970, 'Application of multi-level multi-domain modeling in the design and analysis of a PM transverse flux motor with SMC core', 2007 INTERNATIONAL CONFERENCE ON POWER ELECTRONICS AND DRIVE SYSTEMS, VOLS 1-4, 7th International Conference on Power Electronics and Drive Systems (PEDS 2007), IEEE, Bangkok, THAILAND, pp. 275-+.

Kim, J & Brambley, G 1970, 'Dual optic-flow integrated navigation for small-scale flying robots', Proceedings of the 2007 Australasian Conference on Robotics and Automation, ACRA 2007.
View description>>

This paper addresses the recent development of real-time visual odometry system based on a dual optical-flow system and its integration to an inertial navigation system aiming for small-scale flying robots. To overcome the unknown depth information in optic-flow, a dual optic-flow system is developed and tested. The flow measurements are fused with a low-cost inertial sensor using an extended Kalman filter. The experimental results in indoor environment will be presented showing improved navigational performances constraining errors in height, velocity and attitude.

Kirchner, NG, Liu, D, Taha, T & Paul, G 1970, 'Capacitive Object Ranging and Material Type Classifying Sensor', Proceedings of the 8th International Conference on Intelligent Technologies (InTech), International Conference on Intelligent Technologies, University of Technology, Sydney, Sydney, Australia, pp. 130-135.

Kirchner, NG, Taha, T, Liu, D & Paul, G 1970, 'Simultaneous Material Type Classification And Mapping Data Acquisition Using A Laser Range Finder', Proceedings of the 8th International Conference on Intelligent Technologies (InTech), International Conference on Intelligent Technologies, University of Technology, Sydney, Sydney, Australia, pp. 124-129.
View description>>

This paper presents a method for single sensor simultaneous derivation of three-dimensional mapping data and material type data for use in an autonomous sandblasting system. A Hokuyo laser range finder’s firmware has been modified so that it returns intensity data. A range error and return intensity analyzing algorithm allows the material type of the sensed object to be determined from a set of known materials. Empirical results have demonstrated the system’s ability to classify material type (under alignment and orientation constraints) from a set of known materials common to sandblasting environments (wood, concrete, metals with different finishes and cloth/fabric) and to successfully classify objects both when static and when fitted to an in-motion 6-DOF anthropomorphic robotic arm.

Kodagoda, S, Alempijevic, A, Sehestedt, S & Dissanayake, G 1970, 'Towards improving driver situation awareness at intersections', 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, San Diego, California, pp. 3739-3744.
View/Download from: Publisher's site
View description>>

Providing safety critical information to the driver is vital in reducing road accidents, especially at intersections. Intersections are complex to deal with due to the presence of large number of vehicle and pedestrian activities, and possible occlusions. Information available from only the sensors onboard a vehicle has limited value in this scenario. In this paper, we propose to utilize sensors on-board the vehicle of interest as well as the sensors that are mounted on nearby vehicles to enhance the driver situation awareness. The resulting major research challenge of sensor registration with moving observers is solved using a mutual information based technique. The response of the sensors to common causes are identified and exploited for computing their unknown relative locations. Experimental results, for a mock up traffic intersection in which mobile robots equipped with laser range finders are used, are presented to demonstrate the efficacy of the proposed technique. ©2007 IEEE.

Kodagoda, S, Sehestedt, S, Alempijevic, A, Zhang, Z, Donikian, A & Dissanayake, G 1970, 'Towards an enhanced driver situation awareness system', 2007 International Conference on Industrial and Information Systems, 2007 International Conference on Industrial and Information Systems, IEEE, Sri Lanka, pp. 295-300.
View/Download from: Publisher's site
View description>>

This paper outlines our current research agenda to achieve enhanced driver situation awareness. A novel approach that incorporates information gathered from sensors mounted on the neighboring vehicles, in the road infrastructure as well as onboard sensory information is proposed. A solution to the fundamental issue of registering data into a common reference frame when the relative locations of the sensors themselves are changing is outlined. A description of the vehicle test bed, experimental results from information gathered from various onboard sensors, and preliminary results from the sensor registration algorithm are presented. ©2007 IEEE.

Kwok, N, Carmichael, MG, Ha, QP & Tan, K 1970, 'Statistical decision based gray-level image feature matching', Proceedings of the 8th International Conference on Intelligent Technologies (InTech'07), International Conference on Intelligent Technologies, University of Technology Sydney, Sydney, Australia, pp. 269-274.
View description>>

Na

Kwok, NM, Fang, G, Ha, QP & Liu, DK 1970, 'An enhanced particle swarm optimization algorithm for multi-modal functions', 2007 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION, VOLS I-V, CONFERENCE PROCEEDINGS, IEEE International Conference on Mechatronics and Automation, IEEE, Harbin, Heilongjiang, China, pp. 457-462.
View/Download from: Publisher's site
View description>>

The particle swarm optimization algorithm has been frequently employed to solve various optimization problems. Although the algorithm is performing satisfactorily while tackling unit-modal optimizations, enhancements in dealing with multi-modal functions are indeed desirable. Convergence of particles to the optimum solution is a primary and traditional requirement, however, this is achieved only after all the solutions space has been covered and evaluated. In this work, the focus is directed towards maintaining sufficient divergence of particles in multi-modal problems, by developing an alternative social interaction scheme among the swarm members. Particularly, a multiple-leaders strategy is employed in the new PSO algorithm to prevent pre-mature convergence. Results from benchmark problems are included to illustrate the effectiveness of the proposed method. © 2007 IEEE.

Kwok, NM, Ha, QP, Liu, DK, Fang, G, Tan, KC & IEEE 1970, 'Efficient particle swarm optimization: A termination condition based on the decision-making approach', 2007 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1-10, PROCEEDINGS, IEEE Congress on Evolutionary Computation, IEEE, Singapore, pp. 3353-3360.
View/Download from: Publisher's site
View description>>

Evolutionary computation algorithms, such as the particle swarm optimization (PSO), have been widely applied in numerical optimizations and real-world product design, not only for their satisfactory performances but also in their relaxing the need for detailed mathematical modelling of complex systems. However, as iterative heuristic searching methods, they often suffer from difficulties in obtaining high quality solutions in an efficient manner. Since unnecessary resources used in computation iterations should be avoided, the determination of a proper termination condition for the algorithms is desirable. In this work, termination is cast as a decision-making process to end the algorithm. Specifically, the non-parametric sign-test is incorporated as a hypothetical test method such that a quantifiable termination in regard to specifiable decision-errors can be assured. Benchmark optimization problems are tackled using the PSO as an illustrative optimizer to demonstrate the effectiveness of the proposed termination condition. © 2007 IEEE.

Lau, H, Huang, S & Dissanayake, G 1970, 'Multi-agent search with interim positive information', 2007 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-9, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, San Diego, CA, pp. 3797-3802.

Lau, H, Huang, S & Dissanayake, G 1970, 'Multi-agent search with interim positive information', 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, San Diego, USA, pp. 3791-3796.
View/Download from: Publisher's site
View description>>

A problem of searching with multiple searchers and scouts is presented. Unlike most search problems that terminate as soon as the target is found, successful detection by scouts only improve on the current knowledge of the moving target's location, such that the searchers can more effectively find and service the target in the future. The team must correspondingly plan not only to maximize the probability of the searchers directly finding the target, but also give them the best chance of exploiting any new information from potential scout detections. It is shown that this need to plan for replanning can be addressed by equivalently solving a series of simpler detection search problems that always do terminate on detection. Optimal and heuristic solution methods for this Searcher/Scout problem are derived, such that the capabilities of all the sensing platforms in a search task are harnessed even when only a subset are capable of actually servicing the target. ©2007 IEEE.

Lindsay, E, Liu, D, Murray, SJ & Lowe, DB 1970, 'Remote Laboratories in Engineering Education: Trends in Students' Perceptions', Proceedings of the 18th Conference of the Australasian Association of Engineering Education, Annual Conference of Australasian Association for Engineering Education, Australasian Association for Engineering Education, University of Melbourne, Australia, pp. 1-6.

Mufti, F, Mahony, R & Kim, J 1970, 'Super-Resolution of Speed Signs in Video Sequences', 9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications (DICTA 2007), 9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications (DICTA 2007), IEEE, IEEE, pp. 278-285.
View/Download from: Publisher's site

Paul, G, Liu, DK, Kirchner, N & Webb, S 1970, 'Safe and Efficient Autonomous Exploration Technique for 3D Mapping of a Complex Bridge Maintenance Environment', Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC), 24th International Symposium on Automation and Robotics in Construction, International Association for Automation and Robotics in Construction (IAARC), Kochi, Kerala, India, pp. 99-104.
View/Download from: Publisher's site
View description>>

This paper describes a technique for autonomously exploring a complex steel bridge environment using a 6DOF anthropomorphic robotic arm, instrumented with a laser range scanner. Potential knowledge ained from a 3D range scan at an end-effector position and orientation (pose) is estimated, then arm configurations which avoid obstacles and unknown areas are computed using an optimisation approach. Safe pose solutions are compared in terms of potential gain of new weighted-information and minimal joint movement. Both simulations and robotic platform results show exploration of unknown areas occurs in a consistent and timely manner - taking an average of 4.5secs to calculate the next safe valid robot arm poses. Complex environments, typical in bridge maintenance, can be explored using an anthropomorphic arm equipped with this technique.

Pedraza, L, Dissanayake, G, Valls Miro, J, Rodriguez-Losada, D & Matia, F 1970, 'BS-SLAM: Shaping the World', Robotics: Science and Systems III, Robotics: Science and Systems 2007, Robotics: Science and Systems Foundation, Atlanta, GA, USA, pp. 1-8.
View/Download from: Publisher's site
View description>>

This paper presents BS-SLAM, a simultaneous localization and mapping algorithm for use in unstructured environments that is effective regardless of whether features correspond to simple geometric primitives such as points and lines or not. The coordinates of the control points defining a set of B-splines are used to form a complete and compact description of the environment, thus making it feasible to use an extended Kalman filter based SLAM algorithm. The proposed method is the first known EKF-SLAM implementation capable of describing both straight and curve features in a parametric way. Appropriate observation equation that allows the exploitation of virtually all observations from a range sensor such as the ubiquitous laser range finder is developed. Efficient strategies for computing the relevant Jacobians, perform data association, initialization and expanding the map are presented. The effectiveness of the algorithms is demonstrated using experimental data.

Sankaran, S & Tay, BH 1970, 'Are interpretive and critical research methods useful for research in project management?', Setting the Standard: Proceedings of the AIPM National Conference 2007, Project Management conference, AIPM, Hobart, Australia, pp. 1-13.
View description>>

This paper proposes that the project management discipline would benefit from the findings of practitioners who conduct research into their own practice. Project management researchers associated with a UK government-funded research project [1] have recently suggested that the project management field requires more research into ‘project actuality’, focusing on social processes of how project managers think in action and that such research could contribute to more satisfactory outcomes of contemporary projects. This paper describes a hypothetical dilemma faced by a project manager and briefly describes four doctoral research projects carried out by practitioners who used action research, case research and systems thinking methodologies to address real problems they faced in their projects. It discusses their findings and some common features of these projects and argues that practitioner research using interpretative and critical research methods into actual problems faced by project managers could contribute to useful knowledge for project managers.

Sehestedt, S, Kodagoda, S, Alempijevic, A, Dissanayake, G & IEEE 1970, 'Robust lane detection in urban environments', 2007 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-9, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, USA, pp. 123-128.
View/Download from: Publisher's site
View description>>

Most of the lane marking detection algorithms reported in the literature are suitable for highway scenarios. This paper presents a novel clustered particle filter based approach to lane detection, which is suitable for urban streets in normal traffic conditions. Furthermore, a quality measure for the detection is calculated as a measure of reliability. The core of this approach is the usage of weak models, i.e. the avoidance of strong assumptions about the road geometry. Experiments were carried out in Sydney urban areas with a vehicle mounted laser range scanner and a ccd camera. Through experimentations, we have shown that a clustered particle filter can be used to efficiently extract lane markings. ©2007 IEEE.

Sehestedt, SA, Kodagoda, S, Alempijevic, A & Dissanayake, G 1970, 'Efficient Lane Detection and Tracking in Urban Environments', third European Conference on Mobile Robots, European Conference on Mobile Robots, ECMR, Germany, pp. 78-83.

Singh, SPN & Waldron, KJ 1970, 'A Hybrid Motion Model for Aiding State Estimation in Dynamic Quadrupedal Locomotion', Proceedings 2007 IEEE International Conference on Robotics and Automation, 2007 IEEE International Conference on Robotics and Automation, IEEE, Rome, ITALY, pp. 4337-+.
View/Download from: Publisher's site

Singh, SPN, Csonka, PJ & Waldron, KJ 1970, 'Robotic harness for the field assessment of galloping gaits', 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, pp. 4247-4252.
View/Download from: Publisher's site
View description>>

An important tool in clarifying various theories governing the dynamics of rapid quadrupedal gaits, such as the trot and gallop, is the measurement of body attitude. Such measurements are complicated in open field environments because of the large ranges and high data rates needed due to the speeds (7 m/s) and rapid shifts in dynamics present. To address this a lightweight inertial sensing harness is introduced with sensing design based on the KOLT robot. Its mass center is collocated with the subject so as to reduce dynamic bias. This work combines dynamic gait system identification and motion estimation and is demonstrated on a Labrador retriever (Cams lupus familiaris) through measurements of the gallop over long spans (20 m) and at data rates comparable with gait laboratories (400 Hz). The results are consistent with laboratory measurements, but seem to suggest a roll and yaw cross-coupling during gallop. ©2007 IEEE.

Skinner, BT, Nguyen, HT & Liu, DK 1970, 'Classification of EEG Signals Using a Genetic-Based Machine Learning Classifier', 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Lyon, France, pp. 3120-3123.
View/Download from: Publisher's site
View description>>

This paper investigates the efficacy of the genetic-based learning classifier system XCS, for the classification of noisy, artefact-inclusive human electroencephalogram (EEG) signals represented using large condition strings (108bits). EEG signals from three participants were recorded while they performed four mental tasks designed to elicit hemispheric responses. Autoregressive (AR) models and Fast Fourier Transform (FFT) methods were used to form feature vectors with which mental tasks can be discriminated. XCS achieved a maximum classification accuracy of 99.3% and a best average of 88.9%. The relative classification performance of XCS was then compared against four non-evolutionary classifier systems originating from different learning techniques. The experimental results will be used as part of our larger research effort investigating the feasibility of using EEG signals as an interface to allow paralysed persons to control a powered wheelchair or other devices. © 2007 IEEE.

Skinner, BT, Nguyen, HT & Liu, DK 1970, 'Distributed classifier migration in xcs for classification of electroencephalographic signals', 2007 IEEE Congress on Evolutionary Computation, 2007 IEEE Congress on Evolutionary Computation, IEEE, Singapore, pp. 2829-2836.
View/Download from: Publisher's site
View description>>

This paper presents an investigation into combining migration strategies inspired by multi-deme Parallel Genetic Algorithms with the XCS Learning Classifier System to provide parallel and distributed classifier migration. Migrations occur between distributed XCS classifier sub-populations using classifiers ranked according to numerosity, fitness or randomly selected. The influence of the degree-of-connectivity introduced by Fully-Connected, Bi-directional Ring and Uni-directional Ring topologies is examined. Results indicate that classifier migration is an effective method for improving classification accuracy, improving learning speed and reducing final classifier population size, in the single-step classification of noisy, artefact-inclusive human electroencephalographic signals. The experimental results will be used as part of our larger research effort investigating the feasibility of using EEG signals as an interface to allow paralysed persons to control a powered wheelchair or other devices. © 2007 IEEE.

Skinner, BT, Nguyen, HT & Liu, DK 1970, 'Hybrid Optimisation Method Using PGA and SQP Algorithm', 2007 IEEE Symposium on Foundations of Computational Intelligence, 2007 IEEE Symposium on Foundations of Computational Intelligence, IEEE, Honolulu, Hawaii, USA, pp. 73-80.
View/Download from: Publisher's site
View description>>

This paper investigates the hybridisation of two very different optimisation methods, namely the Parallel Genetic Algorithm (PGA) and Sequential Quadratic Programming (SQP) Algorithm. The different characteristics of genetic-based and traditional quadratic programming-based methods are discussed and to what extent the hybrid method can benefit the solving of optimisation problems with nonlinear complex objective and constraint functions. Experiments show the hybrid method effectively combines the robust and global search property of Parallel Genetic Algorithms with the high convergence velocity of the Sequential Quadratic Programming Algorithm, thereby reducing computation time, maintaining robustness and increasing solution quality. © 2007 IEEE.

Su, SW, Huang, S, Wang, L, Celler, BG, Savkin, AV, Guo, Y, Cheng, T & IEEE 1970, 'Nonparametric Hammerstein model based model predictive control for heart rate regulation', 2007 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-16, IEEE Engineering in Medicine and Biology Society Annual Conference, Medicine and Biology Society, Lyon, France, pp. 2984-2987.
View/Download from: Publisher's site
View description>>

This paper proposed a novel nonparametric model based model predictive control approach for the regulation of heart rate during treadmill exercise. As the model structure of human cardiovascular system is often hard to determine, nonparametric modelling is a more realistic manner to describe complex behaviours of cardiovascular system. This paper presents a new nonparametric Hammerstein model identification approach for heart rate response modelling. Based on the pseudo-random binary sequence experiment data, we decouple the identification of linear dynamic part and input nonlinearity of the Hammerstein system. Correlation analysis is applied to acquire step response of linear dynamic component. Support Vector Regression is adopted to obtain a nonparametric description of the inverse of input static nonlinearity that is utilized to form an approximate linear model of the Hammerstein system. Based on the established model, a model predictive controller under predefined speed and acceleration constraints is designed to achieve safer treadmill exercise. Simulation results show that the proposed control algorithm can achieve optimal heart rate tracking performance under predefined constraints.

Su, SW, Nguyen, J, Jarman, R, Huang, S, Chen, W, Celler, BG, Bao, J, Lee, P & Weng, K 1970, 'A new decentralized fault tolerant control strategy and the fault accommodation of coupled drives', Proceedings of the 8th International Conference on Intelligent Technologies (InTech'07), International Conference on Intelligent Technologies, University of Technology, Sydney, Sydney, Australia, pp. 313-317.

Taha, T, Miro, JV & Dissanayake, G 1970, 'Wheelchair driver assistance and intention prediction using POMDPs', PROCEEDINGS OF THE 2007 INTERNATIONAL CONFERENCE ON INTELLIGENT SENSORS, SENSOR NETWORKS AND INFORMATION PROCESSING, International Conference on Intelligent Sensors, Sensor Networks and Information Processing, IEEE Computer Society, Melbourne, Victoria, pp. 449-454.
View/Download from: Publisher's site
View description>>

Electric wheelchairs give otherwise immobile people the free-dom of movement, they significantly increase independence and dramatically increase quality of life. However the physical control systems of such wheelchair can be prohibitive for some users; for example, people with severe tremors. Several assisted wheelchair platforms have been developed in the past to assist such users. Algorithms that assist specific behaviors such as door - passing, follow - corridor, or avoid - obstacles have been successful. Recent research has seen a move towards systems that predict the users intentions, based on the users input. These predictions have been typically limited to locations immediately surrounding the wheelchair. This paper presents a new assisted wheelchair driving system with large scale intelligent intention recognition based on POMDPs (Partially Observable Markov Decision Processes). The systems acts as an intelligent agent/decision-maker, it relies on minimal user input; to predict the users intention and then autonomously drives the user to his destination. The prediction is constantly being updated as new user input is received allowing for true user/system integration. This shifts the users focus from fine motor-skilled control to coarse control intended to convey intention. © 2007 IEEE.

Tan, KC, Goh, CK, Teoh, EJ & Liu, D 1970, 'A hybrid evolutionary approach for heterogeneous multiprocessor scheduling', Proceedings of the 8th International Conference on Intelligent Technologies (InTech), International Conference on Intelligent Technologies, University of Technology, Sdyney, Sydney, Australia, pp. 261-268.

Valls Miro, J, Taha, T, Wang, D, Dissanayake, G & Liu, D 1970, 'An efficient strategy for robot navigation in cluttered environments in the presence of dynamic obstacles', Proceedings of the 8th International Conference on Intelligent Technologies (InTech), International Conference on Intelligent Technologies, University of Technology, Sydney, Sydney, Australia, pp. 74-81.

Vidal-Calleja, T, Bryson, M, Sukkarieh, S, Sanfeliu, A & Andrade-Cetto, J 1970, 'On the Observability of Bearing-only SLAM', Proceedings 2007 IEEE International Conference on Robotics and Automation, 2007 IEEE International Conference on Robotics and Automation, IEEE, Rome, ITALY, pp. 4114-4119.
View/Download from: Publisher's site
View description>>

In this paper we present an observability analysis for a mobile robot performing SLAM with a single monocular camera. The aim is to get a better understanding of the well known intuitive behavior of these systems, such as the need for triangulation to fe

Vidal-Calleja, T, Sanfeliu, A & Andrade-Cetto, J 1970, 'GUIDING AND LOCALISING IN REAL-TIME A MOBILE ROBOT WITH A MONOCULAR CAMERA IN NON-FLAT TERRAINS', IFAC Proceedings Volumes, Elsevier BV, pp. 560-565.
View/Download from: Publisher's site
View description>>

In this paper we present a real-time active motion strategy for a mobile robot navigating in a non-flat terrain and its 3D constrained motion model. The aim is to control the robot with measurements from only one camera that autonomously builds a visual feature map while at the same time optimises its localisation within this map. The technique chooses the most appropriate commands maximising the expected information gain between prior states and measurements, while performing 6DOF bearing-only SLAM at real-time. The constrained 3D motion model presented here is used to infer the position of the vehicle in order to evaluate the mutual information for all possible actions at the same time. To validate the approach, not only simulations over uneven terrain have been performed, but also experimental results are shown for the technique being tested with a synchro-drive mobile robot platform with a wide-angle camera.

Wan, SH, Kodagoda, S & Sehestedt, SA 1970, 'Multiple Cue Based Vehicle Detection and Tracking for Road Safety', Proceedings of the 8th International Conference on Intelligent Technologies (InTech-07), International Conference on Intelligent Technologies, University of Technology, Sydney, Sydney, Australia, pp. 340-345.
View description>>

With the rise in accident related fatalities on roads, the researchers around the world are looking for solutions including integrating intelligence to vehicles. One cruicial aspects of it is the robust detection and tracking of other vehicles in the visinity. In this paper, we have proposed a probabilistic way of incorporation of several visual cues in vehicle detection and a particle filter based tracking strategy. Visual cues used are, lane markings, symmetry, entropy and shadows. Combination of visual cues provided us with robust results when compared with their individual counterparts. The definition of a region of interest lowers the computational requirements with improved robustness. Experimental results of the algorithm in Sydney urban areas are presented

Wang, D, Kwok, NM, Liu, DK, Lau, H, Dissanayake, G & IEEE 1970, 'PSO-Tuned F-2 method for multi-robot navigation', 2007 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-9, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, San Diego, CA, pp. 3771-3776.

Wang, Z, Huang, S & Dissanayake, G 1970, 'D-SLAM: Decoupled localization.and mapping for autonomous robots', Robotics Research, International Symposium on Robotics Research, Springer, San Francisco, USA, pp. 203-213.
View/Download from: Publisher's site
View description>>

The main contribution of this paper is the reformulation of the simultaneous localization and mapping (SLAM) problem for mobile robots such that the mapping and localization can be treated as two concurrent yet separated processes: D-SLAM (decoupled SLAM). It is shown that SLAM can be decoupled into solving a non-linear static estimation problem for mapping and a low-dimensional dynamic estimation problem for localization. The mapping problem can be solved using an Extended Information Filter where the information matrix is shown to be exactly sparse. A significant saving in the computational effort can be achieved for large scale problems by exploiting the special properties of sparse matrices. An important feature of D-SLAM is that the correlation among landmarks are still kept and it is demonstrated that the uncertainty of the map landmarks monotonically decrease. The algorithm is illustrated through computer simulations and experiments.

Wang, Z, Huang, S & Dissanayake, G 1970, 'Multi-robot simultaneous localization and mapping using D-SLAM framework', PROCEEDINGS OF THE 2007 INTERNATIONAL CONFERENCE ON INTELLIGENT SENSORS, SENSOR NETWORKS AND INFORMATION PROCESSING, International Conference on Intelligent Sensors, Sensor Networks and Information Processing, ARC Research Network on Sensor Networks, Melbourne, pp. 317-322.
View/Download from: Publisher's site
View description>>

This paper presents an algorithm for the multi-robot simultaneous localization and mapping (SLAM) problem with the robot initial locations completely unknown. Each robot builds its own local map using the traditional Extended Kalman Filter (EKF) SLAM algorithm. We provide a new method to fuse the local maps into a jointly maintained global map by first transforming the local map state estimate into relative location information and then conducting the fusion using the decoupled SLAM (D-SLAM) framework [1O]. An efficient algorithm to find the map overlap and corresponding beacons across the maps is developed from a point feature based medical image registration method and the joint compatibility test. By adding the robot initial pose of each local map into the global map state, the algorithm shows valuable properties. Simulation results are provided to illustrate the effectiveness of the algorithm. ©2007 IEEE.

Zhou, W, Miro, JV & Dissanayake, G 1970, 'Information efficient 3D visual SLAM in unstructured domains', PROCEEDINGS OF THE 2007 INTERNATIONAL CONFERENCE ON INTELLIGENT SENSORS, SENSOR NETWORKS AND INFORMATION PROCESSING, International Conference on Intelligent Sensors, Sensor Networks and Information Processing, IEEE, Melbourne, Victoria, pp. 323-328.
View/Download from: Publisher's site
View description>>

This paper presents a strategy for increasing the efficiency of simultaneous localisation and mapping (SLAM) in unknown and unstructured environments using a vision-based sensory package. Traditional feature-based SLAM, using either the Extended Kalman Filter (EKF) or its dual, the Extended Information Filter (EIF), leads to heavy computational costs while the environment expands and the number of features increases. In this paper we propose an algorithm to reduce computational cost for real-time systems by giving robots the 'intelligence' to select, out of the steadily collected data, the maximally informative observations to be used in the estimation process. We show that, although the actual evaluation of information gain for each frame introduces an additional computational cost, the overall efficiency is significantly increased by keeping the matrix compact. The noticeable advantage of this strategy is that the continuously gathered data is not heuristically segmented prior to be input to the filter. Quite the opposite, the scheme lends itself to be statistically optimal. © 2007 IEEE.