An On-Line Method to Evolve Behavior and to Control a Miniature Robot in Real Time with Genetic Programming

Abstract

We present a novel evolutionary approach to robotic control of a real robot based on genetic programming (GP). Our approach uses GP techniques that manipulate machine code to evolve control programs for robots. This variant of GP has several advantages over a conventional GP system, such as higher speed, lower memory requirements, and better real-time properties. Previous attempts to apply GP in robotics use simulations to evaluate control programs and have difficulties with learning tasks involving a real robot. We present an on-line control method that is evaluated in two different physical environments and applied to two tasks—obstacle avoidance and object following—using the Khepera robot platform. The results show fast learning and good generalization.