A New Humanoid Robot Gait Generation Based on Multiobjective Optimization

Abstract

Up to now, the optimization algorithms are applied for humanoid robot gait generation, where a single fitness function drives the optimization process. But often, the humanoid robot gait generation problem is subject to several objectives. In order to deal with this problem, in this paper, we propose a new method based on multiobjective evolutionary algorithm. In order to verify the effectiveness of our proposed method, we considered two important conflicting objectives: minimum energy and minimum torque change, simultaneously. The angle trajectories are generated without neglecting the stability of humanoid robot. Results using the Bonten-Maru humanoid robot show a good performance of the proposed method.