Adaptive behavior acquisition of collision avoidance among multiple autonomous mobile robots

Abstract

We discuss adaptive behavior acquisition for collision avoidance among multiple autonomous mobile robots which are equipped with the locally communicable infrared sensory system (LOCISS). The LOCISS is a local sensing device for collision avoidance by which robots can detect other robots and obstacles and discriminate them by exchanging relevant information. We (1996) reported previously a collision avoidance method between two robots based on the predetermined rules using LOCISS. It is, however, difficult to realize collision avoidance among three or more robots by the predetermined rules only because situations around the robots become more complicated as the number of robots increases. Thus, it is desirable for the robots to have an adaptive capability for acquisition of the behaviors to avoid collision with other robots and obstacles. To acquire the adaptive behavior, the reinforcement learning is introduced in this paper. It is shown that appropriate behaviors for collision avoidance can be successfully acquired through the proposed learning process.