Multi-Agent Reinforcement Learning with Hybrid Action Space for Free Gait Motion Planning of Hexapod Robots
Abstract
Legged robots are able to overcome challenging terrains through diverse gaits formed by contact sequences. However, environments characterized by discrete footholds present significant challenges. In this paper, we tackle the problem of free gait motion planning for hexapod robots walking in randomly generated plum blossom pile environments. Specifically, we first address the complexity of multi-leg coordination in discrete environments by treating each leg of the hexapod robot as an individual agent. Then, we propose the Hybrid action space Multi-Agent Soft Actor Critic (Hybrid-MASAC) algorithm capable of handling both discrete and continuous actions. Finally, we present an integrated free gait motion planning method based on Hybrid-MASAC, streamlining gait, Center of Mass (COM), and foothold sequences planning into a single model. Comparative and ablation experiments in both of the simulated and real plum blossom pile environments demonstrate the feasibility and efficiency of our method.
Cite
Text
Fu et al. "Multi-Agent Reinforcement Learning with Hybrid Action Space for Free Gait Motion Planning of Hexapod Robots." Proceedings of The 8th Conference on Robot Learning, 2024.Markdown
[Fu et al. "Multi-Agent Reinforcement Learning with Hybrid Action Space for Free Gait Motion Planning of Hexapod Robots." Proceedings of The 8th Conference on Robot Learning, 2024.](https://mlanthology.org/corl/2024/fu2024corl-multiagent/)BibTeX
@inproceedings{fu2024corl-multiagent,
title = {{Multi-Agent Reinforcement Learning with Hybrid Action Space for Free Gait Motion Planning of Hexapod Robots}},
author = {Fu, Huiqiao and Tang, Kaiqiang and Li, Peng and Deng, Guizhou and Chen, Chunlin},
booktitle = {Proceedings of The 8th Conference on Robot Learning},
year = {2024},
pages = {5373-5388},
volume = {270},
url = {https://mlanthology.org/corl/2024/fu2024corl-multiagent/}
}