A Monte-Carlo based stochastic approach of soccer robot self-localization

Abstract

The self-localization problem of mobile robot is considered as one of the most difficult problems in robotics, and is generally handled through stochastic methods. This paper discusses a stochastic approach of soccer robot self-localization using Monte-Carlo localization (MCL) method. In MCL, environment information of lines, goals, balls, etc. is first retrieved and processed; such information is used to deal with state uncertainty of robot self-localization. Experiments show that MCL is a fast and robust way in discovering position and pose of soccer robot.