Multi-Agent Robot Simulation for Evolutionary Learning of Cooperative Behavior

May 1999

Proceedings of the Twelfth International Florida Artificial Intelligence Research Society Conference (FLAIRS 1999)

Volume

Proceedings of the Twelfth International Florida Artificial Intelligence Research Society Conference (FLAIRS 1999)

All Papers

In this research, the evolutionary algorithm is applied to behavior learning of an individual agent in the multi-agent robot system. Each agent robot is given two behavior duties both collision avoidance from the other agent and target (food point) reaching for recovering self-energy. In this paper, we carried out the evolutionary simulation of the cooperative behavior creating an environmentla map for the above-mentioned multi-agent robots. Each agent robot has two confliced tasks, that is, local individual behaviors for self preservation or self-protection and global group behaviors for the cooperative task, and has the additional algorithm of the group evolution which the parameters of the best agent are copies to a dead agent, that is, an agent lost its energy. we also report simulation results performed with the evolutionary behavior learning simulator which we developed for multi-agent robots with the map creation task.