安全约束和干扰下的最优控制:一种多步、非策略自适应动态规划方法。

IF 5.2 2区 工程技术 Q1 ENGINEERING, MECHANICAL
Nonlinear Dynamics Pub Date : 2025-01-01 Epub Date: 2025-06-15 DOI:10.1007/s11071-025-11329-3
Jun Ye, Xiaowei Zhao, Yougang Bian, Manjiang Hu, Hongyang Dong
{"title":"安全约束和干扰下的最优控制:一种多步、非策略自适应动态规划方法。","authors":"Jun Ye, Xiaowei Zhao, Yougang Bian, Manjiang Hu, Hongyang Dong","doi":"10.1007/s11071-025-11329-3","DOIUrl":null,"url":null,"abstract":"<p><p>This paper introduces a multi-step, off-policy adaptive dynamic programming approach, in both model-free and model-based variants, intending to solve optimal control problems under disturbances and safety constraints. To provide a more accurate estimation of the performance function in the policy evaluation step, we employ an interleaved training method in the model-free scheme and utilize a prior model in the model-based version to mitigate the underestimation issue of the accumulated utility function. To further counteract the underestimation of the terminal performance function, dual critic neural networks are utilized. Additionally, to ensure a well-balanced trade-off between safety and performance requirements, the original unconstrained policy improvement process is transformed into a constrained optimization task with a far-sighted safety function. Furthermore, an actor-critic-disturbance framework is designed to handle safety constraints during the zero-sum game process, in which the disturbance policy and the performance function are alternately updated during the PEV step. Based on this, a rigorous theoretical analysis is conducted to evaluate the convergence property of the proposed method. Finally, simulation results and practical experiments demonstrate the effectiveness and safety of the proposed method.</p>","PeriodicalId":19723,"journal":{"name":"Nonlinear Dynamics","volume":"113 17","pages":"22973-22999"},"PeriodicalIF":5.2000,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12321936/pdf/","citationCount":"0","resultStr":"{\"title\":\"Optimal control under safety constraints and disturbances: a multi-step, off-policy adaptive dynamic programming approach.\",\"authors\":\"Jun Ye, Xiaowei Zhao, Yougang Bian, Manjiang Hu, Hongyang Dong\",\"doi\":\"10.1007/s11071-025-11329-3\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>This paper introduces a multi-step, off-policy adaptive dynamic programming approach, in both model-free and model-based variants, intending to solve optimal control problems under disturbances and safety constraints. To provide a more accurate estimation of the performance function in the policy evaluation step, we employ an interleaved training method in the model-free scheme and utilize a prior model in the model-based version to mitigate the underestimation issue of the accumulated utility function. To further counteract the underestimation of the terminal performance function, dual critic neural networks are utilized. Additionally, to ensure a well-balanced trade-off between safety and performance requirements, the original unconstrained policy improvement process is transformed into a constrained optimization task with a far-sighted safety function. Furthermore, an actor-critic-disturbance framework is designed to handle safety constraints during the zero-sum game process, in which the disturbance policy and the performance function are alternately updated during the PEV step. Based on this, a rigorous theoretical analysis is conducted to evaluate the convergence property of the proposed method. Finally, simulation results and practical experiments demonstrate the effectiveness and safety of the proposed method.</p>\",\"PeriodicalId\":19723,\"journal\":{\"name\":\"Nonlinear Dynamics\",\"volume\":\"113 17\",\"pages\":\"22973-22999\"},\"PeriodicalIF\":5.2000,\"publicationDate\":\"2025-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12321936/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Nonlinear Dynamics\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1007/s11071-025-11329-3\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/6/15 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, MECHANICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nonlinear Dynamics","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s11071-025-11329-3","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/6/15 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}
引用次数: 0

摘要

本文介绍了一种多步骤、无模型和基于模型的自适应动态规划方法,旨在解决扰动和安全约束下的最优控制问题。为了在策略评估步骤中提供更准确的性能函数估计,我们在无模型方案中采用交错训练方法,在基于模型的方案中利用先验模型来缓解累积效用函数的低估问题。为了进一步消除对终端性能函数的低估,采用了双批评家神经网络。此外,为了确保安全和性能需求之间的平衡,将原来的无约束政策改进过程转化为具有前瞻性安全功能的约束优化任务。在零和博弈过程中,设计了一个参与者临界干扰框架来处理安全约束,其中在PEV步骤中交替更新干扰策略和性能函数。在此基础上,对该方法的收敛性进行了严格的理论分析。仿真结果和实际实验验证了该方法的有效性和安全性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Optimal control under safety constraints and disturbances: a multi-step, off-policy adaptive dynamic programming approach.

Optimal control under safety constraints and disturbances: a multi-step, off-policy adaptive dynamic programming approach.

Optimal control under safety constraints and disturbances: a multi-step, off-policy adaptive dynamic programming approach.

Optimal control under safety constraints and disturbances: a multi-step, off-policy adaptive dynamic programming approach.

This paper introduces a multi-step, off-policy adaptive dynamic programming approach, in both model-free and model-based variants, intending to solve optimal control problems under disturbances and safety constraints. To provide a more accurate estimation of the performance function in the policy evaluation step, we employ an interleaved training method in the model-free scheme and utilize a prior model in the model-based version to mitigate the underestimation issue of the accumulated utility function. To further counteract the underestimation of the terminal performance function, dual critic neural networks are utilized. Additionally, to ensure a well-balanced trade-off between safety and performance requirements, the original unconstrained policy improvement process is transformed into a constrained optimization task with a far-sighted safety function. Furthermore, an actor-critic-disturbance framework is designed to handle safety constraints during the zero-sum game process, in which the disturbance policy and the performance function are alternately updated during the PEV step. Based on this, a rigorous theoretical analysis is conducted to evaluate the convergence property of the proposed method. Finally, simulation results and practical experiments demonstrate the effectiveness and safety of the proposed method.

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
Nonlinear Dynamics
Nonlinear Dynamics 工程技术-工程:机械
CiteScore
9.00
自引率
17.90%
发文量
966
审稿时长
5.9 months
期刊介绍: Nonlinear Dynamics provides a forum for the rapid publication of original research in the field. The journal’s scope encompasses all nonlinear dynamic phenomena associated with mechanical, structural, civil, aeronautical, ocean, electrical, and control systems. Review articles and original contributions are based on analytical, computational, and experimental methods. The journal examines such topics as perturbation and computational methods, symbolic manipulation, dynamic stability, local and global methods, bifurcations, chaos, and deterministic and random vibrations. The journal also investigates Lie groups, multibody dynamics, robotics, fluid-solid interactions, system modeling and identification, friction and damping models, signal analysis, and measurement techniques.
×
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