Physical Model Based Multi-objects Tracking and Prediction in RoboSoccer

RoboSoccer is a multi-agent framework in which multiple robots collaborate in an adversarial environment. RoboSoccer can be built with robots and elds of different sizes. In the smallest version of the game, robots cannot incorporate on-board full autonomous capabilities. In particular, vision processing is oo-board, centralized, and connected to the individual clients that control the robots. The vision system needs to overview the complete eld and to compute in real time positioning information for the moving ball and players. This paper describes our ongoing work on developing a multi-object tracking and prediction in this challenging setup. This paper presents our preliminary work applying an extended Kalman lter to follow the trajectory of multiple moving colored objects. We present empirical results that show the effectiveness of the method both in position tracking and prediction. We conclude with a discussion of the approach, results and future work.