Predation: an approach to improving the evolution of real robots with a distributed evolutionary controller

Abstract

This article describes the implementation of a strategy that selects, destroys, and replaces some individuals of a population of six real autonomous mobile robots. This strategy was called Predation. We introduce Predation as a methodology for improving the performance of an embedded evolutionary system developed for the automatic design of robotic controllers. The paper describes how the evolutionary system controls such a small robot population in Teal time and the effects of predation in avoiding local optimum. It is able to achieve obstacle avoidance behaviour with the robot population evolving while deployed in the field, instead of just using the evolving group to develop an optimum controller for a single robot.