Evolutionary self-organization of an artificial potential field map with a group of autonomous robots

This paper is concerned with two issues: (1) how to enable distributed robots to dynamically acquire their goal-directed collective behaviors, and (2) how to apply the methodology of collective behavioral learning to solve the world modeling problems in mobile robot navigation. We have developed an evolutionary self-organization approach to collective task handling, and furthermore, demonstrated the implemented approach in tackling the specific problem of collectively constructing a global spatial representation, i.e., an artificial potential field map, in an unknown environment