Evaluating GA and PSO evolutionary algorithms for humanoid walk pattern planning

Abstract

Biped robot locomotion is one of the most challenging fields in humanoid robots. Many gait generation models are introduced to have stable walking similar to human. One of the gait generation models is Central Pattern Generator (CPG) which can produce complex nonlinear oscillation as a pattern for walking. In this paper joints trajectories are calculated by using polynomial equations for the support leg's joints and Truncated Fourier Series (TFS) equation for the swing leg's joints in sagittal plane and also to keep robot stability TFS is used for both leg in frontal plan. PSO algorithm and Genetic Algorithm (GA) are used and compared as evolutionary algorithms to find the best optimization algorithm for TFS and polynomial equation parameters to achieve the best speed and performance in walking.