中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 复杂系统管理与控制国家重点实验室
Torque sensorless decentralized neuro-optimal control for modular and reconfigurable robots with uncertain environments

文献类型：期刊论文

作者Dong, Bo1,2; Zhou, Fan2; Liu, Keping2; Li, Yuanchun2
刊名NEUROCOMPUTING
出版日期2018-03-22
卷号282页码:60-73
关键词Modular and reconfigurable robot Decentralized control Adaptive dynamic programming (ADP) Optimal control Neural networks
ISSN号0925-2312
DOI10.1016/j.neucom.2017.12.012
通讯作者Liu, Keping(liukeping@ccut.edu.cn) ; Li, Yuanchun(liyc@ccut.edu.cn)
英文摘要A technical challenge of addressing the decentralized optimal control problem for modular and reconfigurable robots (MRRs) during environmental contacts is associated with optimal compensation of the uncertain contact force without using force/torque sensors. In this paper, a decentralized control approach is presented for torque sensorless MRRs in contact with uncertain environment via an adaptive dynamic programming (ADP)-based neuro-optimal compensation strategy. The dynamic model of the MRRs is formulated based on a novel joint torque estimation method, which is deployed for each joint model, and the joint dynamic information is utilized effectively to design the feedback controllers, thus making the decentralized optimal control problem of the environmental contacted MRR systems be formulated as an optimal compensation issue of model uncertainty. By using the ADP method, a local online policy iteration algorithm is employed to solve the Hamilton-Jacobi-Bellman (HJB) equation with a modified cost function, which is approximated by constructing a critic neural network, and then the approximate optimal control policy can be derived. The asymptotic stability of the closed-loop MRR system is proved by using the Lyapunov theory. At last, simulations and experiments are performed to verify the effectiveness of the proposed method. (C) 2017 Elsevier B.V. All rights reserved.
WOS关键词NONLINEAR INTERCONNECTED SYSTEMS ; REINFORCEMENT LEARNING CONTROL ; CONTROL DESIGN ; FRICTION COMPENSATION ; POLICY ITERATION ; TRACKING CONTROL ; ROBUST-CONTROL ; POSITION ; JOINT ; MANIPULATORS
资助项目National Natural Science Foundation of China[61374051] ; National Natural Science Foundation of China[61773075] ; National Natural Science Foundation of China[61703055] ; State Key Laboratory of Management and Control for Complex Systems[20150102] ; Scientific Technological Development Plan Project in Jilin Province of China[20160520013JH] ; Scientific Technological Development Plan Project in Jilin Province of China[20160414033GH] ; Scientific Technological Development Plan Project in Jilin Province of China[20150520112JH] ; Science and Technology project of Jilin Provincial Education Department of China[JJKH20170569KJ]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000424893200007
出版者ELSEVIER SCIENCE BV
资助机构National Natural Science Foundation of China ; State Key Laboratory of Management and Control for Complex Systems ; Scientific Technological Development Plan Project in Jilin Province of China ; Science and Technology project of Jilin Provincial Education Department of China
源URL[http://ir.ia.ac.cn/handle/173211/28269]  
专题自动化研究所_复杂系统管理与控制国家重点实验室
通讯作者Liu, Keping; Li, Yuanchun
作者单位1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
2.Changchun Univ Technol, Dept Control Sci & Engn, Changchun 130012, Jilin, Peoples R China
推荐引用方式
GB/T 7714		 Dong, Bo,Zhou, Fan,Liu, Keping,et al. Torque sensorless decentralized neuro-optimal control for modular and reconfigurable robots with uncertain environments[J]. NEUROCOMPUTING,2018,282:60-73.
APA Dong, Bo,Zhou, Fan,Liu, Keping,&Li, Yuanchun.(2018).Torque sensorless decentralized neuro-optimal control for modular and reconfigurable robots with uncertain environments.NEUROCOMPUTING,282,60-73.
MLA Dong, Bo,et al."Torque sensorless decentralized neuro-optimal control for modular and reconfigurable robots with uncertain environments".NEUROCOMPUTING 282(2018):60-73.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。