research

home contact publications cv
koan simra.net

My research explores problems in mobile robot localization and environment learning using vision and range sensors. In short, I'm looking to answer questions like: Given a map, and a sensor reading, what is the most plausible place I might be in? How can I move to improve my confidence about where I am? What are the best places to move to to build a map? What is the best representation for a map? How can attention be used to simplify the map-building process?

Recent happenings...

These days I work with the Windows Live Safety Platform as an Applied Researcher.

Previously I was a Senior Robotic Vision Scientist at Braintech, Inc.

For a while in 2006 I was a vision researcher at Microsoft adCenter Labs.

From Jan 2004-July 2006 I was at UBC, working as a postdoc with Jim Little and David Lowe.

In January, 2004, I defended my Ph.D. Thesis, entitled On Visual Maps and their Automatic Construction.

In the fall of 2003, I worked at UofT with Sven Dickinson.

In 2000, I submitted my Ph.D. Proposal on Bayesian Exploration under the supervision of Prof. Greg Dudek at the Centre for Intelligent Machines, McGill University.

My Master's thesis is entitled "Mobile Robot Localization from Learned Landmarks". You can browse my thesis online here.

Check out the mobile robotics lab (my former lab) for more info.

publications

journal publications patents theses and proposals conference and workshop publications invited publications abstracts technical reports

My complete BibTeX file is here.

refereed journal publications

A study of the Rao-Blackwellised particle filter for efficient and accurate vision-based SLAM, R. Sim, P. Elinas and J. J. Little, International Journal of Computer Vision/International Journal of Robotics Research Special Joint Issue on Vision in Robotics,vol 74, no 3, pp 303-318, Kluwer, Sept 2007

Landmark Selection for Vision-Based Navigation, P. L. Sala, R. Sim, A. Shokoufandeh and S. J. Dickinson. IEEE Transactions on Robotics, vol 22, no 2, pp 334-349. IEEE Press. April 2006.[preprint]

Learning generative models of scene features, R. Sim and G. Dudek, International Journal of Computer Vision vol 60, no 1, pp 45-61, Kluwer, 2004. Pre-press version: [pdf] [Kluwer on-line ]

Learning environmental features for pose estimation, R. Sim and G. Dudek, Image and Vision Computing, vol 19, num 11, pp 733-739, Elsevier Press, 2001. [Reprints available on request] [ postscript (650kb)]

In submission:

Autonomous vision-based robotic exploration and mapping using hybrid maps and particle filters, R. Sim and James J. Little, Image and Vision Computing, In review. Revised Jan 2008.

patents

Method and apparatus for Vision-based multiple object detection and position estimation., Robert Sim
U.S. Patent application filed with Braintech, Inc. July 2007.

Intelligent Information Display,Li Li, Robert A. Sim, Tarek Najm, Ying Li, Yi Chen.
U.S. Patent application filed with Microsoft. April 2007.

theses and proposals

On Visual Maps and their Automatic Construction, Robert Sim
Ph.D. Thesis, 170 pages. [ pdf (7.0Mb)]

Mobile robot localization from learned landmarks, Robert Sim
Master's Thesis, McGill University, 66 pages. July, 1998 [ postscript (2.5 MB)]

To Boldly Go: Bayesian Exploration for Mobile Robots, Robert Sim
Ph.D. Proposal, 24 pages. [ postscript (278kb)]

refereed conference and workshop publications

All papers included a presentation, unless otherwise indicated.
Page numbers for most of these papers are in my BibTeX file.

Autonomous vision-based exploration and mapping using hybrid maps and Rao-Blackwellised particle filters, Robert Sim and James J. Little.
Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), Beijing, 2006. [ pre-print: pdf ] Nominated for best paper.

Design and analysis of a framework for real-time vision-based SLAM using Rao-Blackwellised particle filters, Robert Sim, Pantelis Elinas, Matt Griffin, Alex Shyr, and James J. Little
Proceedings of the 3rd Canadian Conference on Computer and Robotic Vision (CRV 2006), Quebec City, QC, 9 pages, 2006. Best Robotics Paper [ pdf ]

σSLAM: Stereo Vision SLAM Using the Rao-Blackwellised Particle Filter and a Novel Mixture Proposal Distribution, Pantelis Elinas, Robert Sim, and James J. Little
Proceedings of the IEEE International Conference on Robotics and Automation, Orlando, FL, 7 pages, 2006. [ pdf ]

Scalable real-time vision-based SLAM for planetary rovers, Robert Sim, Matt Griffin, Alex Shyr, and James J. Little
Proceedings of the IEEE IROS Workshop on Robot Vision for Space Applications, Edmonton, AB, 6 pages, 2005. [ pdf ]

Stabilizing Information-Driven Exploration for Bearings-Only SLAM Using Range Gating, Robert Sim
Proceedings of Intelligent Robots and Systems (IROS), Edmonton, AB, 6 pages, 2005. [ pdf ]

Vision-based SLAM using the Rao-Blackwellised Particle Filter, Robert Sim, Pantelis Elinas, Matt Griffin, and James J. Little
IJCAI Workshop on Reasoning with Uncertainty in Robotics (RUR), Edinburgh, Scotland, 8 pages, 2005. [ pdf ]

Stable Exploration for Bearings-only SLAM, Robert Sim
Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Barcelona, Spain, 6 pages. 2005. [ pdf ]

Global A-Optimal Robot Exploration in SLAM, Robert Sim and Nicholas Roy
Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Barcelona, Spain, 6 pages. 2005. [ pdf ]

Learning Generative Models of Invariant Features, Robert Sim and Gregory Dudek
Proceedings of Intelligent Robots and Systems (IROS), Sendai, Japan. 8 pages. 2004. [ pdf ]

Landmark Selection for Vision-Based Navigation, Pablo Sala, Robert Sim, Ali Shokoufandeh and Sven J. Dickinson
Proceedings of Intelligent Robots and Systems (IROS), Sendai, Japan. 8 pages. 2004. [ pdf ]

AQUA: an aquatic walking robot, C. Georgiades, A. German, A. Hogue, H. Liu, C. Prahacs, A. Ripsman, R. Sim, L. A. Torres, P. Zhang, M. Buehler, G. Dudek, M. Jenkin and E. Milios
Proceedings of Intelligent Robots and Systems (IROS), Sendai, Japan. 8 pages. 2004.

Self-Organizing Visual Maps, Robert Sim and Gregory Dudek
Proceedings of the National Conference on Artificial Intelligence (AAAI), San Jose, CA. 6 pages. 2004. [ pdf ]

Online Control Policy Optimization for Minimizing Map Uncertainty during Exploration, Robert Sim, Gregory Dudek and Nicholas Roy
Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), New Orleans, LA. 6 pages. 2004. [ pdf ]

Effective Exploration Strategies for the Construction of Visual Maps, Robert Sim and Gregory Dudek
Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV. 8 pages. 2003. [ pdf ]

Examining Exploratory Trajectories for Minimizing Map Uncertainty, Robert Sim and Gregory Dudek
Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI) workshop on Reasoning with Uncertainty in Robotics (RUR), Acapulco, Mexico. pp 69--76. 2003. [ pdf ]

Comparing image-based localization methods, Robert Sim and Gregory Dudek
Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI), Acapulco, Mexico, 2003, 3 pages. [ pdf ]

Self-Organizing Visual Maps, Robert Sim and Gregory Dudek
Workshop on Advances in Machine Learning (presentation, no published proceedings) Montreal, Quebec. 6 pages. 2003. [ pdf ]

RoboDaemon - A device independent, network-oriented, modular mobile robot controller, Gregory Dudek and Robert Sim
Proceedings of the IEEE Conference on Robotics and Automation (ICRA), Taipei, Taiwan, 2003, 7 pages. [ pdf (485kb)]

Learning Generative Models of Scene Features, Robert Sim and Gregory Dudek
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Hawaii, 2001, 7 pages. [ postscript (915kb)] [ pdf (525kb)]

Collaborative Exploration for the Construction of Visual Maps, Ioannis Rekleitis, Robert Sim, Gregory Dudek and Evangelos Milios
Proceedings of IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), Hawaii, 2001, 6 pages. [ postscript (1060kb)] [ pdf (575kb)]

Collaborative Exploration for Map Construction, Ioannis Rekleitis, Robert Sim, Gregory Dudek and Evangelos Milios
International Symposium on Computational Intelligence in Robotics and Automation (CIRA), Banff, Alberta, 2001, 6 pages. [ postscript (829kb)]

Learning Landmarks for Robot Localization, Robert Sim and Gregory Dudek
AAAI-2000 Doctoral Consortium, Austin, Texas, July 2000, 2 pages. [ postscript (82kb)]

Learning and Evaluating Visual Features for Pose Estimation, Robert Sim and Gregory Dudek
Proceedings of International Conference on Computer Vision, Kerkyra, Greece, September 1999, 6 pages. Paper and Poster. [ postscript (450kb)]

Learning Environmental Features for Pose Estimation, Robert Sim and Gregory Dudek
CVPR Workshop on Perception for Mobile Agents, Ft. Collins, CO, June 1999, 8 pages. [ postscript (669kb)]

Learning Visual Landmarks for Pose Estimation, Robert Sim and Gregory Dudek
Proceedings of International Conference on Robotics and Automation (ICRA), Detroit, MI, May 1999, 7 pages. [ postscript (433kb)]

Mobile robot localization from learned landmarks, Robert Sim and Gregory Dudek
Proceedings of IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), Victoria, BC, Oct 1998, 6 pages. [ postscript (223 kB)]

invited publications

Visual Landmarks for Pose Estimation, Robert Sim and Gregory Dudek
Canadian Artificial Intelligence, No. 43, Spring 1999 pp13-17

abstracts

On Visual Maps and their Automatic Construction, Robert Sim and Gregory Dudek
Precarn/IRIS Conference, June 2003.

Position Estimation from Learned Landmarks, Robert Sim and Gregory Dudek
Second Prize Poster, Precarn/IRIS Conference, June 1998.

Navigating by the Stars: A landmark-based method for Mobile Robot Localization, Robert Sim and Gregory Dudek
Poster. Precarn/IRIS Conference, June 1997.

Autonomous Exploration: An integrated Systems Approach, Bolduc, M. Bourque, E. Dudek, G. Roy, N. and Sim, R.
Proc. National Conference on Artificial Intelligence, July 1996, pp.779-780, MIT Press.

technical reports

Self-Organizing Visual Maps, Robert Sim and Gregory Dudek
Technical Report, Centre for Intelligent Machines, McGill University, 16 pages. June, 2003 [ pdf ]

Comparing Attention Operators for Learning Landmarks, Robert Sim, Sandra Polifroni and Gregory Dudek
Technical Report, Centre for Intelligent Machines, McGill University, 16 pages. October, 2001 [ pdf (315 kB)]

Bayesian Exploration for Mobile Robots, Robert Sim
Technical Report, CIM-03-02, Centre for Intelligent Machines, McGill University, 23 pages. June, 2000 [ pdf (330 kB)]

Mobile robot localization from learned landmarks, Robert Sim
Technical Report, CIM-98-03, Centre for Intelligent Machines, McGill University, 66 pages. November, 1998 [ postscript (2.5 MB)]

Robert Sim, Last modified: 18 Nov 2010