Robotic Control Using Hierarchical Genetic Programming

In this paper, we compare the performance of hierarchical GP methods (Automatically Defined Functions, Module Acquisition, Adaptive Representation through Learning) with the canonical GP Implementation and with a linear genome GP system in the domain of evolving robotic controllers for a simulated Khepera miniature robot. We successfully evolve robotic controllers to accomplish obstacle avoidance, wall following, and light avoidance tasks.

• Type: Conference
• Year: 2004
• Where: GECCO
• Authors: Marcin L. Pilat, Franz Oppacher
• Keywords: Canonical Gp Implementation, GECCO 2004, Hierarchical Gp Methods, Robotic Controllers