Hierarchical reinforcement learning for enhancing stability and adaptability of hexapod robots in complex terrains

IF 5.4
Shichang Huang , Zhihan Xiao , Minhua Zheng , Wen Shi
{"title":"Hierarchical reinforcement learning for enhancing stability and adaptability of hexapod robots in complex terrains","authors":"Shichang Huang ,&nbsp;Zhihan Xiao ,&nbsp;Minhua Zheng ,&nbsp;Wen Shi","doi":"10.1016/j.birob.2025.100231","DOIUrl":null,"url":null,"abstract":"<div><div>In the field of hexapod robot control, the application of central pattern generators (CPG) and deep reinforcement learning (DRL) is becoming increasingly common. Compared to traditional control methods that rely on dynamic models, both the CPG and the end-to-end DRL approaches significantly simplify the complexity of designing control models. However, relying solely on DRL for control also has its drawbacks, such as slow convergence speed and low exploration efficiency. Moreover, although the CPG can produce rhythmic gaits, its control strategy is relatively singular, limiting the robot’s ability to adapt to complex terrains. To overcome these limitations, this study proposes a three-layer DRL control architecture. The high-level reinforcement learning controller is responsible for learning the parameters of the middle-level CPG and the low-level mapping functions, while the middle and low level controllers coordinate the joint movements within and between legs. By integrating the learning capabilities of DRL with the gait generation characteristics of CPG, this method significantly enhances the stability and adaptability of hexapod robots in complex terrains. Experimental results show that, compared to pure DRL approaches, this method significantly improves learning efficiency and control performance, when dealing with complex terrains, it considerably enhances the robot’s stability and adaptability compared to pure CPG control.</div></div>","PeriodicalId":100184,"journal":{"name":"Biomimetic Intelligence and Robotics","volume":"5 3","pages":"Article 100231"},"PeriodicalIF":5.4000,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biomimetic Intelligence and Robotics","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2667379725000221","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

In the field of hexapod robot control, the application of central pattern generators (CPG) and deep reinforcement learning (DRL) is becoming increasingly common. Compared to traditional control methods that rely on dynamic models, both the CPG and the end-to-end DRL approaches significantly simplify the complexity of designing control models. However, relying solely on DRL for control also has its drawbacks, such as slow convergence speed and low exploration efficiency. Moreover, although the CPG can produce rhythmic gaits, its control strategy is relatively singular, limiting the robot’s ability to adapt to complex terrains. To overcome these limitations, this study proposes a three-layer DRL control architecture. The high-level reinforcement learning controller is responsible for learning the parameters of the middle-level CPG and the low-level mapping functions, while the middle and low level controllers coordinate the joint movements within and between legs. By integrating the learning capabilities of DRL with the gait generation characteristics of CPG, this method significantly enhances the stability and adaptability of hexapod robots in complex terrains. Experimental results show that, compared to pure DRL approaches, this method significantly improves learning efficiency and control performance, when dealing with complex terrains, it considerably enhances the robot’s stability and adaptability compared to pure CPG control.
层次强化学习提高六足机器人在复杂地形中的稳定性和适应性
在六足机器人控制领域,中心模式发生器(CPG)和深度强化学习(DRL)的应用越来越普遍。与依赖于动态模型的传统控制方法相比,CPG和端到端DRL方法都大大简化了控制模型设计的复杂性。但是,单纯依靠DRL进行控制也存在收敛速度慢、勘探效率低等缺点。此外,尽管CPG可以产生有节奏的步态,但其控制策略相对单一,限制了机器人适应复杂地形的能力。为了克服这些限制,本研究提出了一个三层DRL控制体系结构。高级强化学习控制器负责学习中级CPG的参数和低级映射函数,中低级控制器协调腿内和腿间的关节运动。该方法将DRL的学习能力与CPG的步态生成特性相结合,显著提高了六足机器人在复杂地形中的稳定性和适应性。实验结果表明,与纯DRL方法相比,该方法显著提高了学习效率和控制性能,在处理复杂地形时,与纯CPG控制相比,该方法显著增强了机器人的稳定性和自适应能力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
1.80
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信