基于人工势场DDPG算法的移动机械臂协同避障轨迹规划

TP241%TP18; 为了提高移动机械臂在狭窄通道和障碍物约束情况的避障轨迹规划能力,提出一种人工势场法(APF)和深度确定性策略梯度算法(DDPG)结合的改进算法(APF-DDPG).首先,对机械臂设计了 APF规划得到近似姿态,再将研究问题表示为马尔科夫决策过程,设计了状态空间、动作空间和奖惩函数,对规划过程进行阶段性分析处理,设计了一种引导机制来过渡各控制阶段,即避障阶段由DDPG主导训练,目标规划阶段由近似姿态引导DDPG训练,最终获得用于规划的策略模型.最后,建立并设计了固定和随机状态场景的仿真实验,验证了所提算法的有效性.实验结果表明,相较于传统DDPG算法,APF-DDPG算法...

Full description

Saved in:
Bibliographic Details
Published in计算机集成制造系统 Vol. 30; no. 12; pp. 4282 - 4291
Main Authors 李勇, 张朝兴, 柴燎宁
Format Journal Article
LanguageChinese
Published 重庆邮电大学工业物联网与网络化控制教育部重点实验室,重庆 400065 31.12.2024
Subjects
deep deterministic policy gradient
深度确定性策略梯度
避障轨迹规划
人工势场法
mobile robotic arm
artificial potential field
guided training
引导训练
移动机械臂
obstacle avoidance trajectory planning
Online AccessGet full text
ISSN1006-5911
DOI10.13196/j.cims.2023.0369

Cover

Abstract TP241%TP18; 为了提高移动机械臂在狭窄通道和障碍物约束情况的避障轨迹规划能力,提出一种人工势场法(APF)和深度确定性策略梯度算法(DDPG)结合的改进算法(APF-DDPG).首先,对机械臂设计了 APF规划得到近似姿态,再将研究问题表示为马尔科夫决策过程,设计了状态空间、动作空间和奖惩函数,对规划过程进行阶段性分析处理,设计了一种引导机制来过渡各控制阶段,即避障阶段由DDPG主导训练,目标规划阶段由近似姿态引导DDPG训练,最终获得用于规划的策略模型.最后,建立并设计了固定和随机状态场景的仿真实验,验证了所提算法的有效性.实验结果表明,相较于传统DDPG算法,APF-DDPG算法能够以更高收敛效率训练得到具有更高效控制性能的策略模型.
AbstractList TP241%TP18; 为了提高移动机械臂在狭窄通道和障碍物约束情况的避障轨迹规划能力,提出一种人工势场法(APF)和深度确定性策略梯度算法(DDPG)结合的改进算法(APF-DDPG).首先,对机械臂设计了 APF规划得到近似姿态,再将研究问题表示为马尔科夫决策过程,设计了状态空间、动作空间和奖惩函数,对规划过程进行阶段性分析处理,设计了一种引导机制来过渡各控制阶段,即避障阶段由DDPG主导训练,目标规划阶段由近似姿态引导DDPG训练,最终获得用于规划的策略模型.最后,建立并设计了固定和随机状态场景的仿真实验,验证了所提算法的有效性.实验结果表明,相较于传统DDPG算法,APF-DDPG算法能够以更高收敛效率训练得到具有更高效控制性能的策略模型.
Abstract_FL To improve the obstacle avoidance trajectory planning ability of mobile robotic arm in narrow channel and obstacle constraint situations,by combining Artificial Potential Field method(APF)and Deep Deterministic Policy Gradient algorithm(DDPG),an improved algorithm named APF-DDPG was proposed.The APF planning was de-signed for the robotic arm to get the approximate pose,and the research problem was represented as a Markov deci-sion process.The state space,action space and reward and punishment functions were designed,and the planning process was analyzed and processed in phases.A mechanism for guiding was designed to transition the various con-trol phases,which the obstacle avoidance phase of the training was dominated by DDPG,and the approximate pose dominated the goal planning phase to guide the DDPG for the training.Thus the strategy model for planning was ob-tained from the training.Finally,simulation experiments of fixed and random state scenarios were established and designed to verify the effectiveness of the proposed algorithm.The experimental results showed that APF-DDPG al-gorithm could be trained with higher convergence efficiency to obtain a policy model with more efficient control per-formance by comparing with the traditional DDPG algorithm.
Author 李勇
张朝兴
柴燎宁
AuthorAffiliation 重庆邮电大学工业物联网与网络化控制教育部重点实验室,重庆 400065
AuthorAffiliation_xml – name: 重庆邮电大学工业物联网与网络化控制教育部重点实验室,重庆 400065
Author_FL ZHANG Chaoxing
CHAI Liaoning
LI Yong
Author_FL_xml – sequence: 1
  fullname: LI Yong
– sequence: 2
  fullname: ZHANG Chaoxing
– sequence: 3
  fullname: CHAI Liaoning
Author_xml – sequence: 1
  fullname: 李勇
– sequence: 2
  fullname: 张朝兴
– sequence: 3
  fullname: 柴燎宁
BookMark eNotj8tKw0AYRmdRwVr7AL6CkDj_3NIspbVVKOhC12WSTKRBUzCK0p1SUIo3BBFKQRCkXYngQoxIXqaTpG9hQFcfZ3MO3xIqhb1QIbQC2AQKtlgLTLd7GJkEE2piKuwSKgPGwuA2wCKqRlHXKZALanFeRk39HM_i21kc689XPUz0OG40dlrZ21P68ZiNBtnkWw-n6ThOX97zywt9c6fvr-fnyXw0zn-mefKVTwb66mEZLfjyIFLV_62gvebGbn3TaG-3turrbSMCzMGgvsU95fiCKkokltQRnrBqQBhYjLnMYtx2nRpWnmBYcgwOowQ7nictX7hK0Qpa_fOeytCX4X4n6J0chUWxE0RB4Pb7Z8fFcQYEA9BfLbVomQ
ClassificationCodes TP241%TP18
ContentType Journal Article
Copyright Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 2B.
4A8
92I
93N
PSX
TCJ
DOI 10.13196/j.cims.2023.0369
DatabaseName Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
DocumentTitle_FL Collaborative obstacle avoidance trajectory planning for mobile robotic arms based on artificial potential field DDPG algorithm
EndPage 4291
ExternalDocumentID jsjjczzxt202412011
GroupedDBID 2B.
4A8
92I
93N
ALMA_UNASSIGNED_HOLDINGS
CDYEO
PSX
TCJ
ID FETCH-LOGICAL-s1051-3f75debf63e32a0a3b6d6781241744c47459cb80ed640a501b4320bdda7f6cee3
ISSN 1006-5911
IngestDate Thu May 29 04:00:06 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 12
Keywords deep deterministic policy gradient
深度确定性策略梯度
避障轨迹规划
人工势场法
mobile robotic arm
artificial potential field
guided training
引导训练
移动机械臂
obstacle avoidance trajectory planning
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-s1051-3f75debf63e32a0a3b6d6781241744c47459cb80ed640a501b4320bdda7f6cee3
PageCount 10
ParticipantIDs wanfang_journals_jsjjczzxt202412011
PublicationCentury 2000
PublicationDate 2024-12-31
PublicationDateYYYYMMDD 2024-12-31
PublicationDate_xml – month: 12
  year: 2024
  text: 2024-12-31
  day: 31
PublicationDecade 2020
PublicationTitle 计算机集成制造系统
PublicationTitle_FL Computer Integrated Manufacturing Systems
PublicationYear 2024
Publisher 重庆邮电大学工业物联网与网络化控制教育部重点实验室,重庆 400065
Publisher_xml – name: 重庆邮电大学工业物联网与网络化控制教育部重点实验室,重庆 400065
SSID ssib006563755
ssib023646381
ssib001102950
ssib051375755
ssib023167363
ssib036438063
ssib000459500
ssib002258428
Score 2.4511452
Snippet TP241%TP18; 为了提高移动机械臂在狭窄通道和障碍物约束情况的避障轨迹规划能力,提出一种人工势场法(APF)和深度确定性策略梯度算法(DDPG)结合的改进算法(APF-DDPG).首先,对机械臂设计了...
SourceID wanfang
SourceType Aggregation Database
StartPage 4282
Title 基于人工势场DDPG算法的移动机械臂协同避障轨迹规划
URI https://d.wanfangdata.com.cn/periodical/jsjjczzxt202412011
Volume 30
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LaxRBEB5ichFEFBXfBLRPsnGmZ7qn-zizO2sQI4IJ5BZ2XsaAK5gNyN6UgBJ8IYgQAoIgyUkED-KK5M9kks2_sKq2MzsxOUQvQ6e6qrqqvt2u6s10t2Vdt3nLbrmZrOG1DjWPZ6KmcqFqPod8kviZnUncnDx1V07OeLdnxezI6InKW0tLnXgi6R66r-R_UAUa4Iq7ZP8B2VIpEKAN-MITEIbnkTBmkWC6ycKARR4-VWQaSBEs9FkgsKGA0iTmOnQ1GvdusQj6IqZ9FkkWukwLpGhQ4VGXz8LQSAYKeUgSGwFnoc0ixZTPFCeeBlMD7TZTdRZpqE5pPI0KQRCYwwbpUUgPNTZgCBwLxBUb3FO3VyNTb8QCZ5-RxgDQGTIlkYKCttEQShrXZoGNUuAR2k9e6PLdZVLToCiBEKjxhz0QrToJ00jAhSxA9PYJg_EUH_SdtIB5g7tg9n454eX5jOazTnb5GCQcIyDbNUYORDHkgBdhFHgYEmxAqGQFPmBQGEgcVrOAggcB1mQIxFU7hkdFFcrA9Tq5Af4MAhaZIUzAJMKuBwoBVU6GuQRUaTOBjIiRrzrCriAgnIkCZvP6QR9veFR2VlIe_qYktEl5Jiea_5WZ7z6vZDhYrvJKtQTljHNoJsapnVJx8vARHovP3QkolvSw7ChfBl1YXFhIut2nHcTIwYL0mDXGYdUHeXYsaEzduV9df2hROU8SaleuRXUjN9TTlfU0LFZcf7jxmuOxD5Xz5vDyBMg_ZYKDP11lD_uFA9I-3ZxcRsm8GYHu3fzbOdr4185b7QeVGnX6lHXSLC7Hg8FMcdoa6c6fsZrFp95W781Wr1f8-FKsbBZrPZwBdr5-3P7-YWd1eWf9V7Gysb3W2_78rf_iefH6bfHu1e6zzd3Vtf7vjf7mz_76cvHy_VlrphlN1ydr5vaU2iKsmZyam_sizeJcuplLE3IsU6hMoZ53fM9LPB9imcTKzlLp2S1hO7HncjtO05afSyid3XPWaPtxOztvjac6SUUuhVa57WW5VJlWyhFJmjtSKTe_YF0zfs-Z2XFx7iCqF4_Edck6PvyuXrZGO0-WsitQ93fiq-bT8Acair4_
linkProvider EBSCOhost
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8E%E4%BA%BA%E5%B7%A5%E5%8A%BF%E5%9C%BADDPG%E7%AE%97%E6%B3%95%E7%9A%84%E7%A7%BB%E5%8A%A8%E6%9C%BA%E6%A2%B0%E8%87%82%E5%8D%8F%E5%90%8C%E9%81%BF%E9%9A%9C%E8%BD%A8%E8%BF%B9%E8%A7%84%E5%88%92&rft.jtitle=%E8%AE%A1%E7%AE%97%E6%9C%BA%E9%9B%86%E6%88%90%E5%88%B6%E9%80%A0%E7%B3%BB%E7%BB%9F&rft.au=%E6%9D%8E%E5%8B%87&rft.au=%E5%BC%A0%E6%9C%9D%E5%85%B4&rft.au=%E6%9F%B4%E7%87%8E%E5%AE%81&rft.date=2024-12-31&rft.pub=%E9%87%8D%E5%BA%86%E9%82%AE%E7%94%B5%E5%A4%A7%E5%AD%A6%E5%B7%A5%E4%B8%9A%E7%89%A9%E8%81%94%E7%BD%91%E4%B8%8E%E7%BD%91%E7%BB%9C%E5%8C%96%E6%8E%A7%E5%88%B6%E6%95%99%E8%82%B2%E9%83%A8%E9%87%8D%E7%82%B9%E5%AE%9E%E9%AA%8C%E5%AE%A4%2C%E9%87%8D%E5%BA%86+400065&rft.issn=1006-5911&rft.volume=30&rft.issue=12&rft.spage=4282&rft.epage=4291&rft_id=info:doi/10.13196%2Fj.cims.2023.0369&rft.externalDocID=jsjjczzxt202412011
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fjsjjczzxt%2Fjsjjczzxt.jpg