SIA OpenIR  > 机器人学研究室
A Reinforcement Learning Neural Network for Robotic Manipulator Control
Hu YZ(胡亚洲)1,2; Si BL(斯白露)1
作者部门机器人学研究室
发表期刊NEURAL COMPUTATION
ISSN0899-7667
2018
卷号30期号:7页码:1983-2004
收录类别SCI ; EI
EI收录号20182605371589
WOS记录号WOS:000435657600008
产权排序1
资助机构National Key Research and Development Program of China
摘要

We propose a neural network model for reinforcement learning to control a robotic manipulator with unknown parameters and dead zones. The model is composed of three networks. The state of the robotic manipulator is predicted by the state network of the model, the action policy is learned by the action network, and the performance index of the action policy is estimated by a critic network. The three networks work together to optimize the performance index based on the reinforcement learning control scheme. The convergence of the learning methods is analyzed. Application of the proposed model on a simulated two-link robotic manipulator demonstrates the effectiveness and the stability of the model.

语种英语
WOS类目Computer Science, Artificial Intelligence ; Neurosciences
关键词[WOS]OUTPUT-FEEDBACK CONTROL ; DISCRETE-TIME-SYSTEMS ; ADAPTIVE-CONTROL ; NONLINEAR-SYSTEMS ; TRACKING CONTROL ; TARGET DETECTION ; DELAY SYSTEMS ; DESIGN
WOS研究方向Computer Science ; Neurosciences & Neurology
资助项目National Key Research and Development Program of China[2016YFC0801808]
引用统计
文献类型期刊论文
条目标识符http://ir.sia.cn/handle/173321/22142
专题机器人学研究室
通讯作者Hu YZ(胡亚洲)
作者单位1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
2.University of Chinese Academy of Sciences, Beijing 100049, China
推荐引用方式
GB/T 7714
Hu YZ,Si BL. A Reinforcement Learning Neural Network for Robotic Manipulator Control[J]. NEURAL COMPUTATION,2018,30(7):1983-2004.
APA Hu YZ,&Si BL.(2018).A Reinforcement Learning Neural Network for Robotic Manipulator Control.NEURAL COMPUTATION,30(7),1983-2004.
MLA Hu YZ,et al."A Reinforcement Learning Neural Network for Robotic Manipulator Control".NEURAL COMPUTATION 30.7(2018):1983-2004.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
A Reinforcement Lear(561KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Hu YZ(胡亚洲)]的文章
[Si BL(斯白露)]的文章
百度学术
百度学术中相似的文章
[Hu YZ(胡亚洲)]的文章
[Si BL(斯白露)]的文章
必应学术
必应学术中相似的文章
[Hu YZ(胡亚洲)]的文章
[Si BL(斯白露)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: A Reinforcement Learning Neural Network for Robotic Manipulator Control.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。