Fitch, R 2005, 'Immigrants, Unions, and the New U.S. Labor Market', NEW POLITICAL SCIENCE, vol. 27, no. 4, pp. 548-549.
Ha, QP, Tran, TH & Dissanayake, G 2005, 'A wavelet- and neural network-based voice interface system for wheelchair control', International Journal of Intelligent Systems Technologies and Applications, vol. 1, no. 1/2, pp. 49-49.
View/Download from: Publisher's site
View description>>
Voice control has long been considered as a natural mechanism to assist powered wheelchair users. However, one implementation difficulty is that a voice input system may fail to recognise a user’s voice. Indeed, speech activated interface between human and autonomous/semi-autonomous systems requires accurate detection and recognition. In this area pitch and end-point detection is of vital importance. This paper presents a new method for pitch detection based on the continuous wavelet transform phase. The proposed technique can serve as an accurate pitch detector, and also can offer an efficient solution to the end-point detection problem. The extracted features from a user’s speech are then used to train a neural network for speech recognition. Experimental results are provided for the detection of pitch periods and end points and the recognition of a number of commands of male and female users. Laboratory tests are reported for the proposed voice control wheelchair system. © 2005 Inderscience Enterprises Ltd.
Huang, S, James, MR & Jiang, ZP 2005, '-bounded robust control of nonlinear cascade systems', Systems & Control Letters, vol. 54, no. 3, pp. 215-224.
View/Download from: Publisher's site
View description>>
In this paper, we consider the L-infinity-bounded robust control problem for a class of nonlinear cascade systems with disturbances. Sufficient conditions are provided under which a hard bound is imposed on the system performance measure. The backsteppin
Huang, S, James, MR, Nešić, D & Dower, PM 2005, 'Analysis of input-to-state stability for discrete time nonlinear systems via dynamic programming', Automatica, vol. 41, no. 12, pp. 2055-2065.
View/Download from: Publisher's site
View description>>
The input-to-state stability (ISS) property for systems with disturbances has received considerable attention over the past decade or so, with many applications and characterizations reported in the literature. The main purpose of this paper is to present analysis results for ISS that utilize dynamic programming techniques to characterize minimal ISS gains and transient bounds. These characterizations naturally lead to computable necessary and sufficient conditions for ISS. Our results make a connection between ISS and optimization problems in nonlinear dissipative systems theory (including L2-gain analysis and nonlinear H∞ theory). As such, the results presented address an obvious gap in the literature. © 2005 Elsevier Ltd. All rights reserved.
Kim, J & Sukkarieh, S 2005, '6DoF SLAM aided GNSS/INS navigation in GNSS denied and unknown environments', Positioning, vol. 1, pp. 0-0.
Kim, JH & Sukkarieh, S 2005, 'Recasting SLAM - Towards Improving Efficiency and Platform Independency', Springer Tracts in Advanced Robotics, vol. 15, pp. 399-408.
View/Download from: Publisher's site
View description>>
This paper provides an alternative solution to solving SLAM's computational complexity in Inertial Navigation System (INS) application, not from the perspective of map management techniques, but by focusing on the filter's structure and model, and recasting the SLAM algorithm into what is known as an "indirect" implementation. In doing so we provide a navigation structure which is computationally efficient in even for highly non-linear, highly dynamic systems. The problem is solved by separating the SLAM filter from the main navigation loop and, instead of estimating the states of the vehicle and landmarks, the filter estimates the errors in these states. This is accomplished by perturbing the dynamic equations which govern the platform and map models, and hence linearising an otherwise highly non-linear system. The error behaviour of INS is well known and can be predicted precisely using the linearised model. The result is a SLAM linearized error model which provides four main benefits: 1) since the model is linearised, the estimation filter itself is linear during sample interval, providing both significant advantages in computation and in filter tuning; 2) the error model represents the error dynamics, which drift slowly with time, hence the sampling rate required for the prediction cycle of the filter is significantly lower; 3) since the navigation loop and map are decoupled from the time-consuming filter structure, the navigation loop can provide the navigation outputs within fixed deadline without disturbed from the filter; and 4) as the error model is in piecewisely linear form, the observability of SLAM system can be directly analysed. Furthermore, in this paper the navigation structure makes use of an INS as the driver for the platform model, thus providing a navigation solution which is totally separated and independent of the vehicle implemented (however the structure implemented here can also be used when given a vehicle kinematic representation cast ...
Orr, M, Sankaran, S & James, P 2005, 'The implementation of electronic health knowledge management systems in a district health board: Respect and Protect', International Journal of Knowledge Culture and Change Management, vol. 5, no. 2005/6, pp. 113-124.
View description>>
This paper describes the implementation of a suite of Electronic Clinical Health Knowledge Management Systems in a New Zealand District Health Board. The implementation team utilized an action research framework, actively reflecting on each sub-stage of the project, and then utilising key learnings from these reflections, in combination with available related literature, to plan for the next implementation stage. A brief overview of key implementation issues/learning and ethical challenges will be presented. The paper will highlight the importance of a systemic shared culture that 'Respects and Protects' Health Knowledge. The Use of I-Mail as a reflection tool, and perceived links between Action Research and individual and group psychological processes will also be discussed.
Sankaran, S 2005, 'Notes from the field', Action Research, vol. 3, no. 4, pp. 341-352.
View/Download from: Publisher's site
View description>>
I had the pleasure of meeting several action researchers across the USA during my sabbatical late last year. The multiple purposes for my visit to the USA were to meet doctoral students doing their research in organizational change and development in Hawaii; interview prominent action researchers in the US about examining action research dissertations; and to have discussions with action researchers on ways to increase conversations among action researchers around the world. I thought it would be good to share some insights from my visit with fellow action researchers as a letter to Action Research.
Sankaran, S, Swepson, P & Hill, G 2005, 'Do Research Thesis Examiners Need Training?: Practitioner Stories', QUALITATIVE REPORT, vol. 10, no. 4, pp. 817-835.
View description>>
We are thesis examiners within the Australian academic system who formed a community of practice to try to resolve some of the issues we were facing. Stories of examiners reflecting on and examining their own practice are a notable silence in the higher degree research literature. In this study we have adopted a storytelling inquiry method that involved telling our practitioner stories, firstly to each other and then to a wider audience through this paper. We then identified issues that we believe are relevant to other thesis examiners. We have also found that engaging in a community of practice is itself a valuable form of examiner professional development.
Sankaran, S, Walker, S, James, P, Mau, M & Orr, M 2005, 'Real experiences in knowledge management implementation: Using action research', International Journal of Knowledge Culture and Change Management, vol. 5, no. 2005/6, pp. 99-106.
View description>>
This session will descibe real experiences of four managers who are using action research to study/ implement knowledge management strategies in private and public sector organisations as part of their Doctor of Business Administration at Southern Cross University. An overview of how action research approaches are being used to conduct research into knowledge management will be descibed by their supervisor from Southern Cross University. The session is expected to be conducted in an interactive 'knowledge cafe' format introduced by David Gurteen at the Fourth knowledge, Culture and Change at Greenwich and the participants will be expected to take an active part in discussing practitioner's research into knowledge management. 'Action Research Models in Knowledge Management' The following four presenters are all DBA students of the Graduate College of Management, Southern Cross University, Australia. Simon Walker (UK) 'What are the Major Barriers to the Successful Deployment of Knowledge Management Programs in the Telecommunications Industry: A Participatory Action Research Study' Paul James (Canberra, Australia) 'Knowledge Asset Management: A Study of the Lifecyle of Knowledge Assets' Michelle Mau (Brisbane, Australia) 'Knowledge Management: Connecting Knowledge in a Public Sector Organisation' Martin Orr (Auckland, New Zealand) 'The Implementation fo Electronic Health Knowledge Management Systems at a Divisional Health Board'
Shoudong Huang, James, MR, Nesic, D & Dower, PM 2005, 'A unified approach to controller design for achieving ISS and related properties', IEEE Transactions on Automatic Control, vol. 50, no. 11, pp. 1681-1697.
View/Download from: Publisher's site
View description>>
A unified approach to the design of controllers achieving various specified input-to-state stability (ISS) like properties is presented. Both full state and measurement feedback cases are considered. Synthesis procedures based on dynamic programming are given using the recently developed results on controller synthesis to achieve uniform l∞ bound. Our results provide a link between the ISS literature and the nonlinear H∞ design literature. © 2005 IEEE.
TAKEZAWA, S, GULREZ, T, HERATH, DC & DISSANAYAKE, G 2005, 'Environmental Recognition for Autonomous Robot using Simultaneous Localization and Map Building (SLAM) (Real Time Path Planning with Dynamical Localized Voronoi Division)', TRANSACTIONS OF THE JAPAN SOCIETY OF MECHANICAL ENGINEERS Series C, vol. 71, no. 703, pp. 904-911.
View/Download from: Publisher's site
View description>>
The Goal of this work is to provide a more in depth understanding of the navigation in the autonomous robot using stable visual points derived from the repeated experimentation by the stereo vision in a natural featured environment. In order to identify the position of the robot as well as to establish the 3 D obstacle map under the unknown environment, we discuss the simultaneous stereo type localization and map building (SLAM) problem. The design of the planning algorithm for a vision guided mobile robot depends upon the two main characteristics of visual environmental recognition i.e. Uncertainty and Efficiency. The uncertainty is reduced by the Extended Kalman Filter algorithm based on the process and observation model of the mobile robot. Regarding the efficiency, the optimal path planning algorithm which uses the dynamical localized Voronoi division is a new concept in our proposal. This method has the ability to make the path for mobile robot with only suitable number of natural features.
Tan, KC, Chen, YJ, Wang, LF & Liu, DK 2005, 'INTELLIGENT SENSOR FUSION AND LEARNING FOR AUTONOMOUS ROBOT NAVIGATION', Applied Artificial Intelligence, vol. 19, no. 5, pp. 433-456.
View/Download from: Publisher's site
View description>>
This paper presents the design and implementation of an autonomous robot navigation system for intelligent target collection in dynamic environments. A feature-based multi-stage fuzzy logic (MSFL) sensor fusion system is developed for target recognition, which is capable of mapping noisy sensor inputs into reliable decisions. The robot exploration and path planning are based on a grid map oriented reinforcement path learning system (GMRPL), which allows for long-term predictions and path adaptation via dynamic interactions with physical environments. In our implementation, the MSFL and GMRPL are integrated into subsumption architecture for intelligent target-collecting applications. The subsumption architecture is a layered reactive agent structure that enables the robot to implement higher-layer functions including path learning and target recognition regardless of lower-layer functions such as obstacle detection and avoidance. The real-world application using a Khepera robot shows the robustness and flexibility of the developed system in dealing with robotic behaviors such as target collecting in the ever-changing physical environment. Copyright © 2005 Taylor & Francis Inc.
Tan, YG, Liu, DK, Liu, F & Zhou, ZD 2005, 'Digital robust preview control of path tracking', Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, vol. 219, no. 1, pp. 111-116.
View/Download from: Publisher's site
View description>>
A robust optimal preview control method is presented in this paper for path tracking control problems to improve robustness and tracking precision of path tracking control systems. The known path information is used as reference input signals. Simulation results show that this method is valid not only for improving the performance of highly accurate trajectory control but also for improving system stabilization.
Wijesoma, WS, Kodagoda, KRS & Balasuriya, AP 2005, 'Laser-camera composite sensing for road detection and tracking', International Journal of Robotics and Automation, vol. 20, no. 3, pp. 145-157.
View description>>
An important feature in most urban roads and similar environments, such as in theme parks, campus sites, industrial estates, science parks, and the like, is the existence of pavements or curbs on either side defining the road boundaries. These curbs, which are mostly parallel to the road, can be harnessed to extract useful features of the road for implementing autonomous navigation or driver assistance systems. However, vision-alone methods for extraction of such curbs or road edge features with accurate depth information is a formidable task, as the curb is not conspicuous in the vision image and also requires the use of stereo images. Further, bad lighting, adverse weather conditions, nonlinear lens aberrations, or lens glare due to sun and other bright light sources can severely impair the road image quality and thus the operation of vision-alone methods. In this paper an alternative and novel approach involving the fusion of 2D laser range and monochrome vision image data is proposed to improve the robustness and reliability. Experimental results are presented to demonstrate the viability and effectiveness of the proposed methodology and its robustness to different road configurations and shadows.
Wijesoma, WS, Kodagoda, KRS & Balasuriya, AP 2005, 'Laser-camera composite sensing for road detection and tracking', International Journal of Robotics and Automation, vol. 20, no. 3, pp. 145-157.
View description>>
An important feature in most urban roads and similar environments, such as in theme parks, campus sites, industrial estates, science parks, and the like, is the existence of pavements or curbs on either side defining the road boundaries. These curbs, which are mostly parallel to the road, can be harnessed to extract useful features of the road for implementing autonomous navigation or driver assistance systems. However, vision-alone methods for extraction of such curbs or road edge features with accurate depth information is a formidable task, as the curb is not conspicuous in the vision image and also requires the use of stereo images. Further, bad lighting, adverse weather conditions, nonlinear lens aberrations, or lens glare due to sun and other bright light sources can severely impair the road image quality and thus the operation of vision-alone methods. In this paper an alternative and novel approach involving the fusion of 2D laser range and monochrome vision image data is proposed to improve the robustness and reliability. Experimental results are presented to demonstrate the viability and effectiveness of the proposed methodology and its robustness to different road configurations and shadows.
Zhang, N, Kirpitchenko, I & Liu, DK 2005, 'Dynamic model of the grinding process', Journal of Sound and Vibration, vol. 280, no. 1-2, pp. 425-432.
View/Download from: Publisher's site
View description>>
Grinding is one of the most versatile methods of removing material from machine parts to provide precise geometry. Dynamic analysis of the grinding process is necessary to reduce the surface waviness and roughness induced by vibrations, and to offer a machining accuracy in the order of nanometers. This research is to investigate the dynamic function of the grinding process. A new approach to determination of cutting factors in dynamic grinding is proposed. Attention is paid to the mechanisms of dynamic grinding from the kinematics viewpoint. A non-linear dynamic model is developed to investigate the dynamic characteristics of the grinding process. The model demonstrates that different vibration frequencies result in qualitatively different behavior of the grinding machine. The relationship between grinding force variations and vibration frequency is revealed. The formulas to calculate cutting force variations are given. A comparison of the theoretical transfer function of dynamic grinding and experimental one shows good matching. As a result, the paper significantly expands the opportunities of vibration control of grinding machines. © 2004 Elsevier Ltd. All rights reserved.
Andrade-Cetto, J, Vidal-Calleja, T & Sanfeliu, A 1970, 'Unscented Transformation of Vehicle States in SLAM', Proceedings of the 2005 IEEE International Conference on Robotics and Automation, 2005 IEEE International Conference on Robotics and Automation, IEEE, Barcelona, SPAIN, pp. 323-328.
View/Download from: Publisher's site
View description>>
In this article we propose an algorithm to reduce the effects caused by linearization in the typical EKF approach to SLAM. The technique consists in computing the vehicle prior using an Unscented Transformation. The UT allows a better nonlinear mean and
Bryson, M, Kim, J & Sukkarieh, S 1970, 'Information and observability metrics of inertial SLAM for on-line path-planning on an aerial vehicle', IEEE international conference on robotics and automation, Spain.
Crawford, L, Sankaran, S & Butler, Y 1970, 'Project Management in Complex Times', PMOZ 2005 - Projects: Making it Happen, PMOZ 2005 - Projects: Making it Happen, PM Oz, Brisbane, Australia, pp. 1-15.
Fang, G, Dissanayake, G, Kwok, NM, Huang, SD & IEEE 1970, 'Near minimum time path planning for bearing-only localisation and mapping', 2005 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-4, IEEE/RSJ International Conference on Intelligent Robots and Systems, The Institute of Electrical and Electronic Engineers Inc, Edmonton, Canada, pp. 2763-2768.
View/Download from: Publisher's site
View description>>
The main contribution of this paper is an algorithm for integrating motion planning and simultaneous localisation and mapping (SLAM). Accuracy of the maps and the robot locations computed using SLAM is strongly dependent on the characteristics of the environment, for example feature density, as well as the speed and direction of motion of the robot. Appropriate control of the robot motion is particularly important in bearing-only SLAM, where the information from a moving sensor is essential. In this paper a near minimum time path planning algorithm with a finite planning horizon is proposed for bearing-only SLAM. The objective of the algorithm is to achieve a predefined mapping precision while maintaining acceptable vehicle location uncertainty in the minimum time. Simulation results have shown the effectiveness of the proposed method. © 2005 IEEE.
Fitch, R, Butler, Z, Rus, D & IEEE 1970, 'Reconfiguration planning among obstacles for heterogeneous self-reconfiguring robots', 2005 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), VOLS 1-4, IEEE International Conference on Robotics and Automation (ICRA), IEEE, Barcelona, SPAIN, pp. 117-124.
Ha, QP, Tran, TH, Scheding, S, Dissanayake, G & Durrant-Whyte, HF 1970, 'Control Issues of an Autonomous Vehicle', Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC), 22nd International Symposium on Automation and Robotics in Construction, International Association for Automation and Robotics in Construction (IAARC).
View/Download from: Publisher's site
View description>>
This paper addresses some control issues of a robotic amphibious vehicle that can serve as a general framework for automation of tractors used in construction. These include the vehicle's low-level dynamic equations, the development of its braking control system, kinematics in interactions with ground and the slip problem. Simulation and real-time results to date are presented.
Ha, QP, Tran, TH, Scheding, S, Dissanayake, G & Durrant-Whyte, HF 1970, 'Control issues of an autonomous vehicle', 22nd International Symposium on Automation and Robotics in Construction, ISARC 2005, International Symposium of Automation and Robotics in Construction, Faculty of Architecture and Engineering, University of Ferrara, Farrara, Italy, pp. 1-7.
View description>>
This paper addresses some control issues of a robotic amphibious vehicle that can serve as a general framework for automation of tractors used in construction. These include the vehicle's low-level dynamic equations, the development of its braking control system, kinematics in interactions with ground and the slip problem. Simulation and real-time results to date are presented.
Ha, QP, Trinh, HM & Dissanayake, G 1970, 'A Distributed Approach to Global Feedback Control of Multi-Agent Systems', Proceedings of the 6th International Symposium on Intelligent Technologies, International Symposium on Intelligent Technologies in Tech '05, Faculty of Science and Technology, Assumption University, Phuket, Thailand, pp. 67-72.
Huang, S, Kwok, N, Dissanayake, G, Ha, QP & Fang, G 1970, 'Multi-Step Look-Ahead Trajectory Planning in SLAM: Possibility and Necessity', Proceedings of 2005 IEEE International Conference on Robotics and Automation, IEEE International Conference on Robots and Automation, The Institute of Electrical and Electronic Engineers Inc, Barcelona, Spain, pp. 1103-1108.
View description>>
In this paper, the possibility and necessity of multistep trajectory planning in Extended Kalman Filter (EKF) based SLAM is investigated. The objective of the trajectory planning here is to minimize the estimation error of the robot and landmark locations subject to a given time horizon. We show that the problem can be regarded as an optimization problem for a gradually identified model. A numerical method is proposed for trajectory planning using a variant of the nonlinear Model Predictive Control (MPC). The proposed method is optimal in the sense that the control action is computed using all the information available at the time of decision making. Simulation results are included to compare the results from the one-step look-ahead trajectory planning and the proposed multi-step lookahead technique
Huang, SD, James, MR & Jiang, ZP 1970, 'L-infinity-bounded robust control of nonlinear cascade systems', SYSTEMS & CONTROL LETTERS, ELSEVIER, Las Vegas, Nevada,USA, pp. 215-224.
View/Download from: Publisher's site
Kim, J & Brambley, G 1970, 'Dual Optic-flow Integrated Inertial Navigation', Australasian Conference on Robotics and Automation.
Kim, J & Sukkarieh, S 1970, 'Towards robust airborne slam in unknown wind environments', Proceedings of the 2005 Australasian Conference on Robotics and Automation, ACRA 2005, pp. 15-19.
View description>>
This paper presents a robust multi-loop air- borne SLAM structure which augments wind information into the state of 6DoF Simultane- ous Localisation and Mapping (SLAM). The relative air velocity observation from an air data system can be used to estimate the error of the vehicle state. However due to a priori unknown wind information, it cannot directly be used for that purpose. This can be tack- led by augmenting this information into SLAM and estimating it simultaneously with the ve- hicle state. This can significantly increase the consistency of airborne SLAM at the time of loop closure. The air velocity based SLAM loop limits the error growth of the velocity and at- titude effectively and the feature based SLAM loop bounds the position error growth. Simu- lation results show that wind information can be estimated consistently and the robustness of airborne SLAM improves significantly.
Kodagoda, S, Wang, C & Dissanayake, G 1970, 'Laser Based Sensing on Roads', Proceedings of the Intelligent Vehicles and Road Infrastructure Conference, Intelligent Vehicles & Road Infrastructure Conference, Society of Automotive Engineers, Australia, Melbourne, Australia, pp. 1-8.
Kwok, NM, Dissanayake, G & Ha, QP 1970, 'Bearing-only SLAM Using a SPRT Based Gaussian Sum Filter', Proceedings of the 2005 IEEE International Conference on Robotics and Automation, 2005 IEEE International Conference on Robotics and Automation, IEEE, Barcelona, SPAIN, pp. 1109-1114.
View/Download from: Publisher's site
Lasky, V, Liu, D, Murray, SJ & Choy, KK 1970, 'A Remote PLC System for e-Learning', Proc of the 4th ASEE/AAEE Global Colloquium on Engineering Education, ASEE Global Colloquium of Engineering Education, AAEE, Sydney, Australia, pp. 1-10.
Lau, HY, Huang, SD, Dissanayake, G & IEEE 1970, 'Optimal search for multiple targets in a built environment', 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, Vols 1-4, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE Press, Edmonton, Canada, pp. 228-233.
View/Download from: Publisher's site
View description>>
The main contribution of this paper is an algorithm for autonomous search that minimizes the expected time for detecting multiple targets present in a known built environment. The proposed technique makes use of the probability distribution of the target(s) in the environment, thereby making it feasible to incorporate any additional information, known a-priori or acquired while the search is taking place, into the search strategy. The environment is divided into a set of distinct regions and an adjacency matrix is used to describe the connections between them. The costs of searching any of the regions as well as the cost of travel between them can be arbitrarily specified. The search strategy is derived using a dynamic programming algorithm. The effectiveness of the algorithm is illustrated using an example based on the search of an office environment. An analysis of the computational complexity is also presented. © 2005 IEEE.
Leung, C, Huang, SD, Dissanayake, G, Furukawa, T & IEEE 1970, 'Trajectory planning for multiple robots in bearing-only target localisation', 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, Vols 1-4, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Edmonton, Canada, pp. 2312-2317.
View/Download from: Publisher's site
View description>>
This paper provides a solution to the optimal trajectory planning problem in target localisation for multiple heterogeneous robots with bearing-only sensors. The objective here is to find robot trajectories that maximise the accuracy of the locations of the targets at a prescribed terminal time. The trajectory planning is formulated as an optimal control problem for a nonlinear system with a gradually identified model and then solved using nonlinear Model Predictive Control (MPC). The solution to the MPC optimisation problem is computed through Exhaustive Expansion Tree Search (EETS) plus Sequential Quadratic Programming (SQP). Simulations were conducted using the proposed methods. Results show that EETS alone performs considerably faster than EETS+SQP with only minor differences in information gain, and that a centralised approach outperforms a decentralised one in terms of information gain. We show that a centralised EETS provides a near optimal solution. We also demonstrate the significance of using a matrix to represent the information gathered. © 2005 IEEE.
McLachlan, S, Arblaster, J, Liu, DK, Miro, JV & Chenoweth, L 1970, 'A Multi-Stage Shared Control Method for an Intelligent Mobility Assistant', 9th International Conference on Rehabilitation Robotics, 2005. ICORR 2005., 9th International Conference on Rehabilitation Robotics, 2005. ICORR 2005., IEEE, Chicago, USA, pp. 426-429.
View/Download from: Publisher's site
View description>>
This paper presents a multi-stage shared control method (MSSC) which can be used to control the movement of a robotic mobility assistant designed to facilitate safe mobilization for people with unstable gait. The multi-stage control module consists of user intent, obstacle avoidance and fuzzy logic components. The user intent represents the person's commands. The obstacle avoidance component reads data representing any obstacles in the vicinity of the assistant and uses the Vector Field Histogram (VFH) algorithm to select a suitable path to avoid any obstacles in the path of travel. The fuzzy logic component is responsible for merging the user intent and obstacle avoidance information such that the user's request is satisfied to the highest extent possible. When an unsafe situation presents itself the user's request(s) will be partially or wholly overridden so the assistant can return to a safe state. The system has been designed to be dynamically configurable so as to suit different users in terms of gait stability and strength, preferred speed of travel and level of control over the system. It has been tested both in a simulated environment and real-world operating conditions and has been shown to effectively avoid obstacles with minimal disruption to the user and their intent. ©2005 IEEE.
Miro, JV, Dissanayake, G, Zhou, WZ & IEEE 1970, 'Vision-based SLAM using natural features in indoor environments', Proceedings of the 2005 Intelligent Sensors, Sensor Networks & Information Processing Conference, International Conference on Intelligent Sensors, Sensor Networks and Information Processing, IEEE Publications, Melbourne, Australia, pp. 151-156.
View description>>
This paper presents a practical approach to solve the simultaneous localization and mapping (SLAM) problem for autonomous mobile platforms by using natural visual landmarks obtained from an stereoscopic camera. It is an attempt to depart from traditional sensors such as laser rangefinders in order to gain the many benefits of nature-inspired information-rich 3D vision sensors. Whilst this makes the system fully observable in that the sensor provide enough information (range and bearing) to compute the full 2D estate of the observed landmarks from a single position, it is also true that depth information is difficult to rely on, particularly on measurements beyond a few meters (in fact the full 3D estate is observable, but here robot motion is constrained to 2D and only the 2D problem is considered). The work presented here is an attempt to overcome such a drawback by tackling the problem from a partially measurable SLAM perspective in that only landmark bearing from one of the cameras is employed in the fusion estimation. Range information estimates from the stereo pair is only used during map building in the landmark initialization phase in order to provide a reasonably accurate initial estimate. An additional benefit of the approach presented here lies in the data association aspect of SLAM. The availability of powerful feature extraction algorithms from the vision community, such as SIFT, permits a more flexible SLAM implementation separated from feature representation, extraction and matching, essentially carrying out matching with minimal recourse to geometry. Simulation results on real data illustrate the validity of the approach. © 2005 IEEE.
Shoudong Huang, Kwok, NM, Dissanayake, G, Ha, QP & Gu Fang 1970, 'Multi-Step Look-Ahead Trajectory Planning in SLAM: Possibility and Necessity', Proceedings of the 2005 IEEE International Conference on Robotics and Automation, 2005 IEEE International Conference on Robotics and Automation, IEEE, Barcelona, SPAIN, pp. 1091-1096.
View/Download from: Publisher's site
Singh, SPN & Waldron, KJ 1970, 'Attitude Estimation for Dynamic Legged Locomotion Using Range and Inertial Sensors', Proceedings of the 2005 IEEE International Conference on Robotics and Automation, 2005 IEEE International Conference on Robotics and Automation, IEEE, Barcelona, Spain, pp. 1663-1668.
View/Download from: Publisher's site
View description>>
Legged robots offer exceptional mobility in uncharted terrains. Their dynamic nature yields unrivaled mobility, but serves to destabilize the motion estimation process that underlies legged operations. In particular, the discontinuous foot fall patterns and flight phases result in severe impulses, which, in turn, result in excessive accumulation of drift by inertial sensors. Ground range measurements, amongst several others, are robust to this drift yet are limited in application due to their low-bandwidth and sensitivity to ground conditions. In considering the attitude estimation problem for this dynamic legged locomotion, this paper develops a pose calculation method based on ground range measurements. This is used in conjunction with a hybrid Extended Kalman Filter that takes advantage of the ballistic nature of the flight phases. Results indicate that this combination provides rapid, robust estimates of attitude necessary for extended dynamic legged operations. In single leg experiments, which were conducted using low-cost sensing hardware, this method had an RMS error of < 1 °, half that of a non-hybrid EKF approach.
Takezawa, S & Dissanayake, G 1970, 'Simultaneous localisation and mapping problems in indoor environments with stereovision', 31st Annual Conference of IEEE Industrial Electronics Society, 2005. IECON 2005., 31st Annual Conference of IEEE Industrial Electronics Society, 2005. IECON 2005., IEEE, Raleigh, NC, pp. 1896-1901.
View/Download from: Publisher's site
Waldron, KJ, Enedah, C & Gladstone, H 1970, 'Stiffness and texture perception for teledermatology.', Stud Health Technol Inform, Medicine Meets Virtual Reality, IOS Press Fairfax, Netherlands, pp. 579-585.
View description>>
The goal of the teledermatology project currently being carried out at Stanford University is to deliver tactile images of the human skin to a dermatologist at a remote location, in real time. In order to make a diagnosis, dermatologists typically need to obtain data regarding the skin texture and the mechanical properties of any lesions on a patient's skin. For example, pre-cancerous or weather-damaged skin typically feels rougher than normal skin and the profile and stiffness of the underlying tissue may shed light on the nature of a skin disease.
Wang, D, Liu, D, Wu, X & Tan, K 1970, 'A Force Field Method for Robot Navigation', Proceedings of the 3rd International Conference on Computational Intelligence, Robotics and Autonomous Systems, International Conference on Computational Intelligence, Robotics and Autonomous Systems, CIRAS & FIRA Organising Committee 2005, Singapore, pp. 1-6.
Wang, Z, Huang, SD, Dissanayake, G & IEEE 1970, 'Decoupling localization and mapping in SLAM using compact relative maps', 2005 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-4, IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Edmonton, Canada, pp. 1041-1046.
View/Download from: Publisher's site
View description>>
In this paper, we propose a new algorithm for SLAM that makes use of a state vector consisting of quantities that describes the relative locations among features. In contrast to previous relative map strategies, the new state vector is compact and always consists of 2n - 3 elements (in a 2-D environment) where n is the number of features in the map. It is also shown that the information from observations can be transformed and grouped into two parts: first one containing the information about the map and the second one containing the information about the robot location relative to the features in the map. Therefore the SLAM can be decoupled into two processes where mapping uses the first part of the transformed observation vector and localization becomes a 3-dimensional estimation problem. It is also shown that the information matrix of the map is exactly sparse, resulting in potential computational savings when an information filter is used for mapping. The new decoupled SLAM algorithm is called D-SLAM and is illustrated using simulation. © 2005 IEEE.
Zhang, Z & Kodagoda, KRS 1970, 'A monocular vision based localizer', Proceedings of the 2005 Australasian Conference on Robotics and Automation, ACRA 2005, Australasian Conference on Robotics and Automation, Australian Robotics and Automation Association, Sydney, Australia, pp. 1-6.
View description>>
Utilization of low cost sensing is feasible in office like environments due to the regular man made structures. In this paper, we presented an algorithm, which exploits floor boundaries as a feature for robot localization. A colour based floor detection technique along with laser-like scan generation algorithm is proposed for feature extraction. Then an AMCL based localizer is used for robot localization. Experimental results in an office like environment shows the feasibility of the monocular vision based localization.
Zhengzhi, Z & Kodagoda, KRS 1970, 'Multi-sensor approach for people detection', Proceedings of the 2005 Intelligent Sensors, Sensor Networks and Information Processing Conference, International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Casual Productions, Melbourne, Australia, pp. 355-360.
View description>>
Human detection is an important research topic for many researchers who are working with surveillance, safe driving, military and security applications. It is now becoming more and more appropriate with the global increase in the terrorism related activities. This paper presents an algorithm for people detection using information gathered from a composite moving sensor incorporating a camera and a laser range finder. Laser range finder is used to identify a region of interest (ROI) where a moving object is likely to be present. Corresponding ROI in the visual image is then analyzed and a hierarchical template matching strategy is used to confirm the presence of a moving human. This approach improves the robustness of the template matching and the computational efficiency as the matching is only done in the resized ROI. The proposed strategy is evaluated through experimentation. © 2005 IEEE.
