Behavior learning and group evolution for autonomous multi-agent robot

In this research, the evolutionary algorithm is applied to behavior learning of an individual agent in multi-agent robots. Each robot which is an agent is given two behavior duties both collision avoidance from the other agent and target (food point) reaching for recovering self-energy. In the problem for two conflicting behaviors, collision avoidance and target reaching motion, of multi-agent robots the learning method of behavior based on the self-energy and the behavior gain of each agent was discussed in the author's previous paper (1996). In this paper, he performs the simulation with the additional algorithm of the group evolution which the parameters of the most excellent agent are copied to a dead agent, that is, an agent lost its energy. It was confirmed in the simulation that each agent has abilities of both behavior learning and group evolution.