A self-localization method based on omnidirectional vision and MTi for soccer robots

Self-Localization is the basis to realize mobile robot's autonomous ability such as motion planning, control decision and cooperation. Omnidirectional vision is one of the most important sensors for RoboCup Middle Size League soccer robots, and Motion Trackers instrument (MTi) is a kind of inertial sensors which can measure the attitude of the robot in real-time and accurately. In this paper we propose a self-localization method which is based on omnidirectional vision and MTi. By combining with matching optimization localization, global localization and localization tracking can be realized quickly for our soccer robots. The experimental results show that global localization can be realized effectively while highly accurate localization is achieved in real-time.