Obstacle avoidance learning for a multi-agent linked robot in the real world

In order to achieve an autonomous system which can adaptively behave through learning in the real world, we constructed a distributed autonomous swimming robot that consisted of mechanically linked multi-agent and adopted adaptive oscillator method that was developed as a general decision making for distributed autonomous systems (DASs). One of the our aims by using this system is to verify whether the robot could complete a target approaching including obstacle avoidance. For this purpose, we introduced a modified Q-learning in which plural Q-tables are used alternately according to dead-lock situations. By using this system, as a result, the robot acquired stable target approaching and obstacle avoiding behavior.