GA-based learning in behaviour based robotics

Abstract

This paper presents a genetic algorithm (GA) approach to evolving robot behaviors. We use fuzzy logic controllers (FLCs) to design robot behaviors. The antecedents of the FLCs are pre-designed, while their consequences are learned using a GA. The Sony quadruped robots are used to evaluate proposed approaches in the robotic football domain. Two behaviors, ball-chasing and position-reaching, are studied and implemented. An embodied evolution scheme is adopted, by which the robot autonomously evolves its behaviors based on a layered control architecture. The results show that the robot behaviors can be automatically acquired through the GA-based learning of FLCs.