Distributed architecture which mobile robots follow to share useful information

For more information and documents related with the project, please use the following contact information:

URL: http://www.deec.uc.pt/~rprocha/research/research.html
Contact person: Rui Rocha
Email:
Mobile Robotics Laboratory
Institute of Systems and Robotics
Department of Electrical and Computer Engineering
Coimbra University
Pinhal de Marrocos, Pólo II
3030-290 COIMBRA – Portugal
Tel. +351 239 796 256 · Fax 351 239 406 672


Ph.D. Project

Vision-based Cooperative 3-D Mapping using Information Theory

Cooperative Multi-Robot Systems

Sep. 2002 – May 2006

http://www.deec.uc.pt/~rprocha/research/research.html

Aim

Ø  Take advantage from cooperation of multiple mobile robots, so as to build 3-D maps faster than a single mobile robot.

·  A method to share useful information among robots is a key point.

Research Issues

·  Grid-based probabilistic maps [1,3]

§  Compact representation of voxels’ coverage and explicit representation of uncertainty through the entropy concept.

§  Straightforward update of coverage beliefs through a Bayes Filter.

·  Entropy gradient-based exploration [1,3]

·  Distributed architecture model [1,2]

§  Each robot is capable of building a 3-D map, though it is altruistically committed to share useful measurements with its teammates, who also may provide it with useful data.

·  Entropy-based measure of information utility [1,2]

§  Supports efficient information sharing.

·  Coordinated exploration with minimization of mutual information [4]

§  Minimize robots’ interference.

Scientific Publications

·  [1] R. Rocha, J. Dias and A. Carvalho. “Cooperative Multi-Robot Systems: a study of Vision-based 3-D Mapping using Information Theory”. Robotics and Autonomous Systems, 53(3–4), Elsevier journals, ISSN: 0921-8890, pages 282-311, Dec. 31, 2005.

·  [2] R. Rocha, J. Dias and A. Carvalho. Cooperative multi-robot systems: a study of vision-based 3-D mapping using information theory. In Proc. of Int. Conf. on Robotics and Automation (ICRA’2005), Barcelona, Spain, pages 386-391, Apr. 2005.

·  [3] R. Rocha, J. Dias, and A. Carvalho. Exploring Information Theory for Vision-Based Volumetric Mapping. In Proc. of IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS’2005), Edmonton, Canada, pages 2409-2414, 2-6 Aug. 2005.

·  [4] R. Rocha, J. Dias and A. Carvalho. Entropy gradient-based exploration with cooperative robots in 3-D mapping missions. In Proc. of ICRA’2005 Workshop on Cooperative Robotics, IEEE Int. Conf. on Robotics and Automation, Barcelona, Spain, Apr. 2005.