基于分布式教练的蛇形机器人运动强化学习控制器

Yuanyuan Jia, Shugen Ma
{"title":"基于分布式教练的蛇形机器人运动强化学习控制器","authors":"Yuanyuan Jia, Shugen Ma","doi":"10.1109/IROS47612.2022.9981749","DOIUrl":null,"url":null,"abstract":"Reinforcement learning commonly suffers from slow convergence speed and requires thousands of episodes, which makes it hard to be applied for physical robotic applications. Little research has been studied for snake robot control using RL because of the additional difficulty of high redundancy of freedom. Existing methods either adopts an asynchronous A3C structure or a joint state representation. We propose a distributed coach-based deep learning method for snake robot control, which can greatly expedite the training speed with less episodes. The major contributions include: 1) a completely distributed graphical formulation; 2) an explicit stochastic density propagation rule for each robot link; 3) various interaction models with uncertainty estimation. The preliminary results of both simulation and real-world experiments have demonstrated the promising performance in comparison with state-of-the-art.","PeriodicalId":431373,"journal":{"name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Distributed Coach-Based Reinforcement Learning Controller for Snake Robot Locomotion\",\"authors\":\"Yuanyuan Jia, Shugen Ma\",\"doi\":\"10.1109/IROS47612.2022.9981749\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Reinforcement learning commonly suffers from slow convergence speed and requires thousands of episodes, which makes it hard to be applied for physical robotic applications. Little research has been studied for snake robot control using RL because of the additional difficulty of high redundancy of freedom. Existing methods either adopts an asynchronous A3C structure or a joint state representation. We propose a distributed coach-based deep learning method for snake robot control, which can greatly expedite the training speed with less episodes. The major contributions include: 1) a completely distributed graphical formulation; 2) an explicit stochastic density propagation rule for each robot link; 3) various interaction models with uncertainty estimation. The preliminary results of both simulation and real-world experiments have demonstrated the promising performance in comparison with state-of-the-art.\",\"PeriodicalId\":431373,\"journal\":{\"name\":\"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)\",\"volume\":\"41 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-10-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IROS47612.2022.9981749\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IROS47612.2022.9981749","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

强化学习通常存在收敛速度慢、需要数千集的问题,这使得它很难应用于物理机器人应用。基于强化学习的蛇形机器人控制研究很少,主要是由于高度冗余的自由度带来了额外的困难。现有的方法要么采用异步A3C结构,要么采用联合状态表示。提出了一种基于分布式教练的蛇形机器人深度学习控制方法,该方法能够以较少的集数大大加快训练速度。主要贡献包括:1)一个完全分布的图形公式;2)机器人各环节的显式随机密度传播规则;3)具有不确定性估计的各种相互作用模型。仿真和实际实验的初步结果表明,该方法具有较好的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Distributed Coach-Based Reinforcement Learning Controller for Snake Robot Locomotion
Reinforcement learning commonly suffers from slow convergence speed and requires thousands of episodes, which makes it hard to be applied for physical robotic applications. Little research has been studied for snake robot control using RL because of the additional difficulty of high redundancy of freedom. Existing methods either adopts an asynchronous A3C structure or a joint state representation. We propose a distributed coach-based deep learning method for snake robot control, which can greatly expedite the training speed with less episodes. The major contributions include: 1) a completely distributed graphical formulation; 2) an explicit stochastic density propagation rule for each robot link; 3) various interaction models with uncertainty estimation. The preliminary results of both simulation and real-world experiments have demonstrated the promising performance in comparison with state-of-the-art.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
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