Building Integrated Robots for Soccer Competition

Middle-sized robot soccer competition provides an excellent opportunity for distributed robotic systems. In particular, a team of dog-sized robot players must perform real-time visual recognition, navigate in a dynamic field, track moving objects, collaborate with teammates, and hit a FIFA size-4 ball in the correct direction. All these tasks demand integrated robots that are autonomous (on-board sensing, thinking, and acting as living creatures), efficient (functioning under time and resource constraints), cooperative (collaborating with each other to accomplish tasks that are beyond individual's capabilities), and intelligent (reasoning and planing actions and perhaps learning from experience). Building such robots may require techniques that are different from those employed in separate research disciplines. This paper describes our experience in building these soccer robots and highlights problems and solutions that are unique to such multi-agent robotic systems in general. These problems include a framework for multi-agent programming, agent modeling and architecture, evaluation of multi-agent systems, and decentralized skill composition. Our robots share the same general architecture and basic hardware, but they have integrated abilities to play different roles (goalkeeper, defender or forward) and utilize different strategies in their team behavior. In the 1997 RoboCup competition, these integrated robots played well and our "Dreamteam" won the world championship in the middlesized robot league.