Case-Based Reasoning for Planning and World Modeling in the RoboCup Small Size League

This paper presents three case-based reasoning (CBR) prototypes developed for the RoboCats, a team of five soccer playing robots in the RoboCup small size league. CBR is used to help the RoboCats plan individual moves and team strategies, as well as to model the world of the playing field. More specifically, the case-based reasoners position the goalie, select team formations, and recognize game states for the RoboCats. This paper also discusses issues and opportunities for CBR in RoboCup and other endeavors in which physical agents must operate in dynamic, real-time environments.