Adaptive Evolutionary Neural Network Gait Generation for Humanoid Robot Optimized with Modified Differential Evolution Algorithm

Abstract

This paper introduces a novel approach for the biped robot gait generation which aims to control humanoid robot to walk more naturally and stably on a flat platform. The dynamic biped gait generator created by the novel adaptive evolutionary neural model (AENM) that is optimally identified with the proposed modified differential evolution (MDE) optimization algorithm. The comparison results with genetic algorithm (GA) and particle swarm optimisation (PSO) demonstrated the effectiveness of proposed MDE method. The prototype small sized humanoid robot is used to test the performance of the proposed MDE algorithm and other algorithms. The comparison results demonstrate that the new proposed neural AENM model proves an effective approach for a robust and precise biped gait generation.