A reinforcement learning-based method is applied to realize the cooperation of mobile robots. According to the reinforcement learning rule, the agents are encouraged when they happen to do a desirable action. Therefore if the robot as a decision-making agent is made to receive a positive reward signal when playing a role in achieving the global goal, the strategy of actions that each robot learned individually will turn out to be a cooperative algorithm in the viewpoint of the entire system.
This paper proposes methods for the cooperative control of multiple mobile robots and constructs a robotic soccer system in which the cooperation will be implemented as a pass play of two robots. To play a soccer game, elementary actions such as shooting and moving have been designed, and Q-learning, which is one of the popular methods for reinforcement learning, is used to determine what actions to take. Through simulation, learning is successful in case of deliberate initial arrangements of ball and robots, thereby cooperative work can be accomplished. Building other components comprising a real robotic soccer system, such as computer vision system and micro mobile robot, is also described briefly.
