EVOLUTION OF HOMING NAVIGATION IN A REAL MOBILE ROBOT

In this paper we describe the evolution of a discrete-time recurrent n eural network to control a real mobile robot. In all our experiments t he evolutionary procedure is carried out entirely on the physical robo t without human intervention, We show that the autonomous development of a set of behaviors for locating a battery charger and periodically returning to it can be achieved by lifting constraints in the design o f the robot/environment interactions that were employed in a prelimina ry experiment, The emergent homing behavior is based on the autonomous development of an internal neural topographic map (which is not pre-d esigned) that allows the robot to choose the appropriate trajectory as function of location and remaining energy.