SIA OpenIR  > 空间自动化技术研究室
Novel power-exponent-type modified RNN for RMP scheme of redundant manipulators with noise and physical constraints
Tong YC(佟玉闯1,2,3; Liu JG(刘金国)1,2
Department空间自动化技术研究室
Source PublicationNeurocomputing
ISSN0925-2312
2022
Volume467Pages:266-281
Indexed BySCI ; EI
EI Accession number20214211033277
WOS IDWOS:000709984900009
Contribution Rank1
Funding OrganizationNational Key R & D Program of China (Grant No. 2018YFB1304600) ; Natural Science Foundation of China (Grant No. 51775541) ; CAS Interdisciplinary Innovation Team (Grant No. JCTD-2018-11)
KeywordRedundant manipulator Repetitive motion planning Recurrent neural network Noise Physical constraint
Abstract

Noise and physical constraints of redundant manipulators are the two major challenges in the repetitive motion planning (RMP) problems. Therefore, this paper proposed a power-exponent-type modified recurrent neural network (PET-MRNN) to simultaneously address both noise and physical constraints. Moreover, PET-MRNN model is activated by a new Sbp-sinh type nonlinear activation function proposed in this paper. The Sbp-sinh type activation function is first applied to such time varying quadratic program (TVQP) solving and possesses excellent convergence performance. Theoretical analysis proves that the PET-MRNN model can completely eliminate noise disturbance through learning and compensation during the convergence process, and then converge the residual error to zero and obtain the theoretical solution. Finally, simulation and experiments further proved the superiority of the PET-MRNN and the Sbp-sinh type activation function.

Language英语
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/29800
Collection空间自动化技术研究室
中国科学院沈阳自动化研究所
Corresponding AuthorLiu JG(刘金国)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation (SIA), Chinese Academy of Sciences (CAS), China
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences (CAS), China
3.University of the Chinese Academy of Science, Beijing, China
Recommended Citation
GB/T 7714
Tong YC(佟玉闯,Liu JG. Novel power-exponent-type modified RNN for RMP scheme of redundant manipulators with noise and physical constraints[J]. Neurocomputing,2022,467:266-281.
APA Tong YC,&Liu JG.(2022).Novel power-exponent-type modified RNN for RMP scheme of redundant manipulators with noise and physical constraints.Neurocomputing,467,266-281.
MLA Tong YC,et al."Novel power-exponent-type modified RNN for RMP scheme of redundant manipulators with noise and physical constraints".Neurocomputing 467(2022):266-281.
Files in This Item:
File Name/Size DocType Version Access License
Novel power-exponent(4465KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Tong YC(佟玉闯]'s Articles
[Liu JG(刘金国)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Tong YC(佟玉闯]'s Articles
[Liu JG(刘金国)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Tong YC(佟玉闯]'s Articles
[Liu JG(刘金国)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Novel power-exponent-type modified RNN for RMP scheme of redundant manipulators with noise and physical constraints.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.