oru.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Duckett, Tom
Publications (10 of 36) Show all publications
Cielniak, G., Duckett, T. & Lilienthal, A. J. (2007). Improved data association and occlusion handling for vision-based people tracking by mobile robots. In: 2007 IEEE/RSJ international conference on intelligent robots and systems: . Paper presented at IEEE/RSJ international conference on intelligent robots and systems, 2007, IROS 2007, San Diego, CA, USA, 29 Oct.-2 Nov., 2007 (pp. 3436-3441). New York, NY, USA: IEEE
Open this publication in new window or tab >>Improved data association and occlusion handling for vision-based people tracking by mobile robots
2007 (English)In: 2007 IEEE/RSJ international conference on intelligent robots and systems, New York, NY, USA: IEEE, 2007, p. 3436-3441Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents an approach for tracking multiple persons using a combination of colour and thermal vision sensors on a mobile robot. First, an adaptive colour model is incorporated into the measurement model of the tracker. Second, a new approach for detecting occlusions is introduced, using a machine learning classifier for pairwise comparison of persons (classifying which one is in front of the other). Third, explicit occlusion handling is then incorporated into the tracker.

Place, publisher, year, edition, pages
New York, NY, USA: IEEE, 2007
Keywords
Person tracking, robot vision, occlusion handling
National Category
Engineering and Technology Computer and Information Sciences
Research subject
Computer and Systems Science
Identifiers
urn:nbn:se:oru:diva-3271 (URN)10.1109/IROS.2007.4399507 (DOI)000254073202089 ()2-s2.0-51349163493 (Scopus ID)978-1-4244-0912-9 (ISBN)
Conference
IEEE/RSJ international conference on intelligent robots and systems, 2007, IROS 2007, San Diego, CA, USA, 29 Oct.-2 Nov., 2007
Available from: 2008-11-28 Created: 2008-11-28 Last updated: 2018-06-12Bibliographically approved
Andreasson, H., Treptow, A. & Duckett, T. (2007). Self-localization in non-stationary environments using omni-directional vision. Robotics and Autonomous Systems, 55(7), 541-551
Open this publication in new window or tab >>Self-localization in non-stationary environments using omni-directional vision
2007 (English)In: Robotics and Autonomous Systems, ISSN 0921-8890, E-ISSN 1872-793X, Vol. 55, no 7, p. 541-551Article in journal (Refereed) Published
Abstract [en]

This paper presents an image-based approach for localization in non-static environments using local feature descriptors, and its experimental evaluation in a large, dynamic, populated environment where the time interval between the collected data sets is up to two months. By using local features together with panoramic images, robustness and invariance to large changes in the environment can be handled. Results from global place recognition with no evidence accumulation and a Monte Carlo localization method are shown. To test the approach even further, experiments were conducted with up to 90% virtual occlusion in addition to the dynamic changes in the environment

Place, publisher, year, edition, pages
Amsterdam: Elsevier, 2007
National Category
Engineering and Technology Computer and Information Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-5185 (URN)10.1016/j.robot.2007.02.002 (DOI)
Available from: 2009-01-30 Created: 2009-01-30 Last updated: 2018-01-13Bibliographically approved
Li, J. & Duckett, T. (2006). Growing RBF networks for learning reactive behaviours in mobile robotics. International journal of vehicle autonomous systems, 4(2/3/4), 285-307
Open this publication in new window or tab >>Growing RBF networks for learning reactive behaviours in mobile robotics
2006 (English)In: International journal of vehicle autonomous systems, ISSN 1471-0226, Vol. 4, no 2/3/4, p. 285-307Article in journal (Refereed) Published
Abstract [en]

This paper investigates a learning system based on growing Radial Basis Function (RBF) networks for acquiring reactive behaviours in mobile robotics. The learning algorithm integrates unsupervised and supervised learning, directly mapping the sensor information to the required motor action. The learning system is evaluated through a number of experiments on a real robot. The experimental results show that our learning system can learn a wide range of robot behaviours from simple tasks to complex tasks and demonstrate that the task need not be known at the programming time. This means that many different behaviours could potentially be acquired by the same learning architecture, thus dramatically reducing the development cost of autonomous robotic systems

National Category
Computer Sciences
Research subject
Computer and Systems Science
Identifiers
urn:nbn:se:oru:diva-3453 (URN)10.1504/IJVAS.2006.012213 (DOI)
Available from: 2007-08-01 Created: 2007-08-01 Last updated: 2018-01-13Bibliographically approved
Lilienthal, A. J., Duckett, T., Ishida, H. & Werner, F. (2006). Indicators of gas source proximity using metal oxide sensors in a turbulent environment. In: The First IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, 2006, BioRob 2006: . Paper presented at IEEE/RAS-EMBS International conference on biomedical robotics and biomechatronics, Biorob - 2006, 20-22 Feb. 2006, Pisa, Tuscany, Italy (pp. 733-738). New York, NY, USA: IEEE, Article ID 1639177.
Open this publication in new window or tab >>Indicators of gas source proximity using metal oxide sensors in a turbulent environment
2006 (English)In: The First IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, 2006, BioRob 2006, New York, NY, USA: IEEE, 2006, p. 733-738, article id 1639177Conference paper, Published paper (Refereed)
Abstract [en]

This paper addresses the problem of estimating proximity to a gas source using concentration measurements. In particular, we consider the problem of gas source declaration by a mobile robot equipped with metal oxide sensors in a turbulent indoor environment. While previous work has shown that machine learning classifiers can be trained to detect close proximity to a gas source, it is difficult to interpret the learned models. This paper investigates possible underlying indicators of gas source proximity, comparing three different statistics derived from the sensor measurements of the robot. A correlation analysis of 1056 trials showed that response variance (measured as standard deviation) was a better indicator than average response. An improved result was obtained when the standard deviation was normalized to the average response for each trial, a strategy that also reduces calibration problems.

Place, publisher, year, edition, pages
New York, NY, USA: IEEE, 2006
Series
Proceedings of the IEEE RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, ISSN 2155-1782
Keywords
Mobile nose, gas source localisation, turbulent gas distribution
National Category
Computer and Information Sciences
Research subject
Computer and Systems Science
Identifiers
urn:nbn:se:oru:diva-3959 (URN)10.1109/BIOROB.2006.1639177 (DOI)000244445100066 ()2-s2.0-33845562422 (Scopus ID)978-1-4244-0039-3 (ISBN)
Conference
IEEE/RAS-EMBS International conference on biomedical robotics and biomechatronics, Biorob - 2006, 20-22 Feb. 2006, Pisa, Tuscany, Italy
Available from: 2007-08-27 Created: 2007-08-27 Last updated: 2018-06-11Bibliographically approved
Jun, L., Lilienthal, A. J., Martìnez-Marìn, T. & Duckett, T. (2006). Q-RAN: a constructive reinforcement learning approach for robot behavior learning. In: 2006 IEEE/RSJ international conference on intelligent robots and systems: . Paper presented at IEEE/RSJ International Conference on Intelligent Robots and Systems, Beijing, China, 9-15 Oct, 2006 (pp. 2656-2662). New York, NY, USA: IEEE, Article ID 4058792.
Open this publication in new window or tab >>Q-RAN: a constructive reinforcement learning approach for robot behavior learning
2006 (English)In: 2006 IEEE/RSJ international conference on intelligent robots and systems, New York, NY, USA: IEEE, 2006, p. 2656-2662, article id 4058792Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents a learning system that uses Q-learning with a resource allocating network (RAN) for behavior learning in mobile robotics. The RAN is used as a function approximator, and Q-learning is used to learn the control policy in `off-policy' fashion that enables learning to be bootstrapped by a prior knowledge controller, thus speeding up the reinforcement learning. Our approach is verified on a PeopleBot robot executing a visual servoing based docking behavior in which the robot is required to reach a goal pose. Further experiments show that the RAN network can also be used for supervised learning prior to reinforcement learning in a layered architecture, thus further improving the performance of the docking behavior.

Place, publisher, year, edition, pages
New York, NY, USA: IEEE, 2006
National Category
Computer and Information Sciences
Research subject
Computer and Systems Science
Identifiers
urn:nbn:se:oru:diva-3957 (URN)10.1109/IROS.2006.281986 (DOI)000245452402127 ()2-s2.0-34250630005 (Scopus ID)978-1-4244-0258-8 (ISBN)
Conference
IEEE/RSJ International Conference on Intelligent Robots and Systems, Beijing, China, 9-15 Oct, 2006
Available from: 2007-08-27 Created: 2007-08-27 Last updated: 2018-06-12Bibliographically approved
Munkevik, P., Hall, G. & Duckett, T. (2006). Quality control of meal components by appearance-based novelty detection. Industries Alimentaires et Agricoles, 123(3), 11-15
Open this publication in new window or tab >>Quality control of meal components by appearance-based novelty detection
2006 (English)In: Industries Alimentaires et Agricoles, ISSN 0019-9311, Vol. 123, no 3, p. 11-15Article in journal (Refereed) Published
Keywords
Spermatophyta, Angiospermae, Dicotyledones, Leguminosae, Color, Vegetables, Image analysis, Filing, Article, Control method, Analysis method, Detection, Novelty, Appearance, Pisum sativum, Chemical composition, Ready meal, Quality control
National Category
Computer Sciences
Research subject
Computer and Systems Science
Identifiers
urn:nbn:se:oru:diva-3464 (URN)
Available from: 2007-07-19 Created: 2007-07-19 Last updated: 2018-01-13Bibliographically approved
Skoglund, A., Duckett, T., Iliev, B., Lilienthal, A. J. & Palm, R. (2006). Teaching by demonstration of robotic manipulators in non-stationary environments. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) ,2006: . Paper presented at IEEE International Conference on Robotics and Automation, 2006, Orlando, Florida, May, 15-19, 2006 (pp. 4339-4341). IEEE
Open this publication in new window or tab >>Teaching by demonstration of robotic manipulators in non-stationary environments
Show others...
2006 (English)In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) ,2006, IEEE, 2006, p. 4339-4341Conference paper, Published paper (Refereed)
Abstract [en]

In this paper we propose a system consisting of a manipulator equipped with range sensors, that is instructed to follow a trajectory demonstrated by a human teacher wearing a motion capturing device. During the demonstration a three dimensional occupancy grid of the environment is built using the range sensor information and the trajectory. The demonstration is followed by an exploration phase, where the robot undergoes self-improvement of the task, during which the occupancy grid is used to avoid collisions. In parallel a reinforcement learning (RL) agent, biased by the demonstration, learns a point-to-point task policy. When changes occur in the workspace, both the occupancy grid and the learned policy will be updated online by the system.

Place, publisher, year, edition, pages
IEEE, 2006
National Category
Computer Sciences
Research subject
Computer and Systems Science
Identifiers
urn:nbn:se:oru:diva-4091 (URN)
Conference
IEEE International Conference on Robotics and Automation, 2006, Orlando, Florida, May, 15-19, 2006
Available from: 2007-11-01 Created: 2007-11-01 Last updated: 2018-06-11Bibliographically approved
Magnusson, M., Duckett, T., Elsrud, R. & Skagerlund, L.-E. (2005). 3D modelling for underground mining vehicles. Paper presented at The Conference on Modeling and Simulation for Public Safety, SimSafe, 2005 Linköping, Sweden.
Open this publication in new window or tab >>3D modelling for underground mining vehicles
2005 (English)Conference paper, Oral presentation only (Refereed)
Abstract [en]

This paper presents the basis of a new system for making detailed 3D models of underground tunnels. The system is to be used for automated control of mining vehicles. We describe some alternative methods for matching several partial scans, and their applicability for making a complete model of a mine environment

National Category
Mechanical Engineering
Research subject
Mechanical Engineering
Identifiers
urn:nbn:se:oru:diva-3996 (URN)
Conference
The Conference on Modeling and Simulation for Public Safety, SimSafe, 2005 Linköping, Sweden
Available from: 2007-09-03 Created: 2007-09-03 Last updated: 2017-10-18Bibliographically approved
Magnusson, M. & Duckett, T. (2005). A comparison of 3D registration algorithms for autonomous underground mining vehicles. Paper presented at 2nd European Conference on Mobile Robots, ECMR 2005, Ancona, Italy, September 7-10.
Open this publication in new window or tab >>A comparison of 3D registration algorithms for autonomous underground mining vehicles
2005 (English)Conference paper, Oral presentation only (Refereed)
Abstract [en]

The ICP algorithm and its derivatives is the de facto standard for registration of 3D range-finder scans today. This paper presents a quantitative comparison between ICP and 3D NDT, a novel approach based on the normal distributions transform. The new method ad- dresses two of the main problems of ICP: the fact that it does not make use of the local surface shape and the computationally demanding nearest-neighbour search. The results show that 3D NDT produces accurate results much faster, though it is more sensitive to error in the initial pose estimate.

National Category
Mechanical Engineering
Research subject
Mechanical Engineering
Identifiers
urn:nbn:se:oru:diva-3964 (URN)
Conference
2nd European Conference on Mobile Robots, ECMR 2005, Ancona, Italy, September 7-10
Available from: 2007-08-27 Created: 2007-08-27 Last updated: 2017-10-18Bibliographically approved
Frese, U., Larsson, P. & Duckett, T. (2005). A multilevel relaxation algorithm for simultaneous localisation and mapping. IEEE Transactions on robotics, 21(2), 196-207
Open this publication in new window or tab >>A multilevel relaxation algorithm for simultaneous localisation and mapping
2005 (English)In: IEEE Transactions on robotics, ISSN 1552-3098, E-ISSN 1941-0468, Vol. 21, no 2, p. 196-207Article in journal (Refereed) Published
Abstract [en]

This paper addresses the problem of simultaneous localisation and mapping (SLAM) by a mobile robot. An incremental SLAM algorithm is introduced that is derived from multigrid methods used for solving partial differential equations. The approach improves on the performance of previous relaxation methods for robot mapping because it optimizes the map at multiple levels of resolution. The resulting algorithm has an update time that is linear in the number of estimated features for typical indoor environments, even when closing very large loops, and offers advantages in handling non-linearities compared to other SLAM algorithms. Experimental comparisons with alternative algorithms using two well-known data sets and mapping results on a real robot are also presented

Keywords
Termsómobile robot navigation, SLAM, metrictopological maps, Gauss-Seidel relaxation, Galerkin multigrid
National Category
Robotics
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-3497 (URN)10.1109/TRO.2004.839220 (DOI)
Available from: 2007-07-22 Created: 2007-07-22 Last updated: 2017-12-14Bibliographically approved
Organisations

Search in DiVA

Show all publications