AUTHOR=Tao Chongben , Xue Jie , Zhang Zufeng , Cao Feng , Li Chunguang , Gao Hanwen 
  
TITLE=Gait Optimization Method for Humanoid Robots Based on Parallel Comprehensive Learning Particle Swarm Optimizer Algorithm
  
JOURNAL=Frontiers in Neurorobotics
  
VOLUME=Volume 14 - 2020
  
YEAR=2021
  
URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2020.600885
  
DOI=10.3389/fnbot.2020.600885
  
ISSN=1662-5218
  
ABSTRACT=The speed, stability, and flexibility of humanoid robot walking in RoboCup3D competition are key factors. In this paper, a gait optimization method based on Parallel Comprehensive Learning Particle Swarm Optimizer (PCLPSO) is proposed. Firstly, the key parameters affecting the walking gait of humanoid robot are selected based on natural Zero Moment Point (ZMP) trajectory planning method. Secondly, a parallel and distributed multi robot gait training environment based on RoboCup3D is built, and PCLPSO algorithm is applied to automatically optimize the walking speed and stability of humanoid robot. Finally, a layered learning approach is used to optimize the turning ability of humanoid robot. The experimental results show that PCLPSO algorithm achieves quickly optimal solution, and the humanoid robot optimized possesses a fast and steady gait and excellent turnaround.