Sensor resetting localization for poorly modelled mobile robots

We present a new localization algorithm, called sensor resetting localization, which is an extension of Monte Carlo localization. The algorithm adds sensor based re-sampling to Monte Carlo localization when the robot is lost. Sensor resetting localization (SRL) is robust to modelling errors including unmodelled movements and systematic errors. It can be used in real time on systems with limited computational power. The algorithm has been successfully used on autonomous legged robots in the Sony legged league of the robotic soccer competition RoboCup'99. We present results from the real robots demonstrating the success of the algorithm and results from simulation comparing SRL to Monte Carlo localization.

[1]  Reid G. Simmons,et al.  Probabilistic Robot Navigation in Partially Observable Environments , 1995, IJCAI.

[2]  Wolfram Burgard,et al.  Estimating the Absolute Position of a Mobile Robot Using Position Probability Grids , 1996, AAAI/IAAI, Vol. 2.

[3]  Wolfram Burgard,et al.  An experimental comparison of localization methods , 1998, Proceedings. 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems. Innovations in Theory, Practice and Applications (Cat. No.98CH36190).

[4]  Manuela M. Veloso,et al.  The CMTrio-98 Sony-Legged Robot Team , 1998, RoboCup.

[5]  Wolfram Burgard,et al.  Active Markov localization for mobile robots , 1998, Robotics Auton. Syst..

[6]  Wolfram Burgard,et al.  Monte Carlo Localization: Efficient Position Estimation for Mobile Robots , 1999, AAAI/IAAI.

[7]  Wolfram Burgard,et al.  Monte Carlo localization for mobile robots , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[8]  Hiroaki Kitano,et al.  Vision, Strategy, and Localization Using the Sony Robots at RoboCup-98 , 2000, AI Mag..

[9]  Vision , Strategy , and Localization Using the Sony Legged Robots at RoboCup-98 , 2000 .