Cooperative behavior acquisition of multiple autonomous mobile robots by an objective-based reinforcement learning system

The present paper proposes an objective-based reinforcement learning system for multiple autonomous mobile robots to acquire cooperative behavior. The proposed system employs profit sharing (PS) as a learning method. A major characteristic of the system is using two kinds of PS tables. One is to learn cooperative behavior using information on other agents´ positions and the other is to learn how to control basic movements. Through computer simulation and real robot experiment using a garbage-collection problem, the performance of the proposed system is evaluated. As a result, it is verified that agents select the most available garbage for cooperative behavior using visual information in an unknown environment and move to the target avoiding obstacles.