14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services

Research Article

Gait Optimization for Multiple Humanoid Robots Based on Parallel Multi-swarm Particle Swarm Algorithm

Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.4108/eai.7-11-2017.2274577,
    author={Chunguang li and Rongyi He and Lina Yao and Chongben Tao},
    title={Gait Optimization for Multiple Humanoid Robots Based on Parallel Multi-swarm Particle Swarm Algorithm},
    proceedings={14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services},
    publisher={ACM},
    proceedings_a={MOBIQUITOUS},
    year={2018},
    month={4},
    keywords={humaniod robot multi-swarm particle swarm optimization gait optimization distributed system robocup},
    doi={10.4108/eai.7-11-2017.2274577}
}
  • Chunguang li
    Rongyi He
    Lina Yao
    Chongben Tao
    Year: 2018
    Gait Optimization for Multiple Humanoid Robots Based on Parallel Multi-swarm Particle Swarm Algorithm
    MOBIQUITOUS
    ACM
    DOI: 10.4108/eai.7-11-2017.2274577
Chunguang li1,*, Rongyi He2, Lina Yao3, Chongben Tao4
  • 1: School of Computer and Information Engineering, Changzhou Institute of Technology
  • 2: Institute of Intelligence Science and Technology, School of Computer and Information, Hohai university
  • 3: School of Computer Science and Engineering, University of New South Wales
  • 4: School of Electronic and Information Engineering, Suzhou University of Science and Technology
*Contact email: leechunguang76@163.com

Abstract

In the RoboCup 3D simulation competition, how to find a flexible and stable gait pattern is one of the keys to win the match. To achieve such walking gait, a machine learning method of optimizing the vertical Center of Mass(CoM) trajectory is presented. The vertical CoM trajectory is planned by multiple polynomial function. Inverted Pendulum Model(IPM) and a numerical method are utilized to control the Zero Moment Point(ZMP). Then the key parameters are extracted from the gait pattern, a distributed multi-robot training environment based on RoboCup 3D simulated platform is constructed, and the parallel multi-swarm particle swarm algorithm is applied to optimize the parameters. The results of experiment and competition demonstrate that the effectiveness of the proposed method.

Keywords
humaniod robot multi-swarm particle swarm optimization gait optimization distributed system robocup
Published
2018-04-18
Publisher
ACM
http://dx.doi.org/10.4108/eai.7-11-2017.2274577
Copyright © 2017–2024 EAI