No Cover Image

Journal article 392 views 112 downloads

Recursive recurrent neural network: A novel model for manipulator control with different levels of physical constraints

Zhan Li Orcid Logo, Shuai Li Orcid Logo

CAAI Transactions on Intelligence Technology, Volume: 8, Issue: 3, Pages: 622 - 634

Swansea University Author: Shuai Li Orcid Logo

  • 60977_VoR.pdf

    PDF | Version of Record

    © 2022The Authors. This is an open access article under the terms of the Creative Commons Attribution‐NonCommercial‐NoDerivs License

    Download (1.97MB)

Check full text

DOI (Published version): 10.1049/cit2.12125

Abstract

Manipulators actuate joints to let end effectors to perform precise path tracking tasks. Recurrent neural network which is described by dynamic models with parallel processing capability, is a powerful tool for kinematic control of manipulators. Due to physical limitations and actuation saturation o...

Full description

Published in: CAAI Transactions on Intelligence Technology
ISSN: 2468-2322 2468-2322
Published: Institution of Engineering and Technology (IET) 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa60977
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2022-08-30T16:10:45Z
last_indexed 2023-01-13T19:21:30Z
id cronfa60977
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>60977</id><entry>2022-08-30</entry><title>Recursive recurrent neural network: A novel model for manipulator control with different levels of physical constraints</title><swanseaauthors><author><sid>42ff9eed09bcd109fbbe484a0f99a8a8</sid><ORCID>0000-0001-8316-5289</ORCID><firstname>Shuai</firstname><surname>Li</surname><name>Shuai Li</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2022-08-30</date><deptcode>MECH</deptcode><abstract>Manipulators actuate joints to let end effectors to perform precise path tracking tasks. Recurrent neural network which is described by dynamic models with parallel processing capability, is a powerful tool for kinematic control of manipulators. Due to physical limitations and actuation saturation of manipulator joints, the involvement of joint constraints for kinematic control of manipulators is essential and critical. However, current existing manipulator control methods based on recurrent neural networks mainly handle with limited levels of joint angular constraints, and to the best of our knowledge, methods for kinematic control of manipulators with higher order joint constraints based on recurrent neural networks are not yet reported. In this study, for the first time, a novel recursive recurrent network model is proposed to solve the kinematic control issue for manipulators with different levels of physical constraints, and the proposed recursive recurrent neural network can be formulated as a new manifold system to ensure control solution within all of the joint constraints in different orders. The theoretical analysis shows the stability and the purposed recursive recurrent neural network and its convergence to solution. Simulation results further demonstrate the effectiveness of the proposed method in end-effector path tracking control under different levels of joint constraints based on the Kuka manipulator system. Comparisons with other methods such as the pseudoinverse-based method and conventional recurrent neural network method substantiate the superiority of the proposed method.</abstract><type>Journal Article</type><journal>CAAI Transactions on Intelligence Technology</journal><volume>8</volume><journalNumber>3</journalNumber><paginationStart>622</paginationStart><paginationEnd>634</paginationEnd><publisher>Institution of Engineering and Technology (IET)</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>2468-2322</issnPrint><issnElectronic>2468-2322</issnElectronic><keywords/><publishedDay>1</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-09-01</publishedDate><doi>10.1049/cit2.12125</doi><url>http://dx.doi.org/10.1049/cit2.12125</url><notes/><college>COLLEGE NANME</college><department>Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MECH</DepartmentCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>This work is partially supported by the IMPACT Fund of Swansea University.</funders><projectreference/><lastEdited>2023-11-16T14:34:08.9503738</lastEdited><Created>2022-08-30T11:51:02.1301697</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Zhan</firstname><surname>Li</surname><orcid>0000-0002-3928-1642</orcid><order>1</order></author><author><firstname>Shuai</firstname><surname>Li</surname><orcid>0000-0001-8316-5289</orcid><order>2</order></author></authors><documents><document><filename>60977__25049__5746165081544c73aaa83ec387a9e4b5.pdf</filename><originalFilename>60977_VoR.pdf</originalFilename><uploaded>2022-08-30T17:11:36.4790718</uploaded><type>Output</type><contentLength>2068752</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2022The Authors. This is an open access article under the terms of the Creative Commons Attribution‐NonCommercial‐NoDerivs License</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by-nc-nd/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 60977 2022-08-30 Recursive recurrent neural network: A novel model for manipulator control with different levels of physical constraints 42ff9eed09bcd109fbbe484a0f99a8a8 0000-0001-8316-5289 Shuai Li Shuai Li true false 2022-08-30 MECH Manipulators actuate joints to let end effectors to perform precise path tracking tasks. Recurrent neural network which is described by dynamic models with parallel processing capability, is a powerful tool for kinematic control of manipulators. Due to physical limitations and actuation saturation of manipulator joints, the involvement of joint constraints for kinematic control of manipulators is essential and critical. However, current existing manipulator control methods based on recurrent neural networks mainly handle with limited levels of joint angular constraints, and to the best of our knowledge, methods for kinematic control of manipulators with higher order joint constraints based on recurrent neural networks are not yet reported. In this study, for the first time, a novel recursive recurrent network model is proposed to solve the kinematic control issue for manipulators with different levels of physical constraints, and the proposed recursive recurrent neural network can be formulated as a new manifold system to ensure control solution within all of the joint constraints in different orders. The theoretical analysis shows the stability and the purposed recursive recurrent neural network and its convergence to solution. Simulation results further demonstrate the effectiveness of the proposed method in end-effector path tracking control under different levels of joint constraints based on the Kuka manipulator system. Comparisons with other methods such as the pseudoinverse-based method and conventional recurrent neural network method substantiate the superiority of the proposed method. Journal Article CAAI Transactions on Intelligence Technology 8 3 622 634 Institution of Engineering and Technology (IET) 2468-2322 2468-2322 1 9 2023 2023-09-01 10.1049/cit2.12125 http://dx.doi.org/10.1049/cit2.12125 COLLEGE NANME Mechanical Engineering COLLEGE CODE MECH Swansea University SU Library paid the OA fee (TA Institutional Deal) This work is partially supported by the IMPACT Fund of Swansea University. 2023-11-16T14:34:08.9503738 2022-08-30T11:51:02.1301697 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Zhan Li 0000-0002-3928-1642 1 Shuai Li 0000-0001-8316-5289 2 60977__25049__5746165081544c73aaa83ec387a9e4b5.pdf 60977_VoR.pdf 2022-08-30T17:11:36.4790718 Output 2068752 application/pdf Version of Record true © 2022The Authors. This is an open access article under the terms of the Creative Commons Attribution‐NonCommercial‐NoDerivs License true eng http://creativecommons.org/licenses/by-nc-nd/4.0/
title Recursive recurrent neural network: A novel model for manipulator control with different levels of physical constraints
spellingShingle Recursive recurrent neural network: A novel model for manipulator control with different levels of physical constraints
Shuai Li
title_short Recursive recurrent neural network: A novel model for manipulator control with different levels of physical constraints
title_full Recursive recurrent neural network: A novel model for manipulator control with different levels of physical constraints
title_fullStr Recursive recurrent neural network: A novel model for manipulator control with different levels of physical constraints
title_full_unstemmed Recursive recurrent neural network: A novel model for manipulator control with different levels of physical constraints
title_sort Recursive recurrent neural network: A novel model for manipulator control with different levels of physical constraints
author_id_str_mv 42ff9eed09bcd109fbbe484a0f99a8a8
author_id_fullname_str_mv 42ff9eed09bcd109fbbe484a0f99a8a8_***_Shuai Li
author Shuai Li
author2 Zhan Li
Shuai Li
format Journal article
container_title CAAI Transactions on Intelligence Technology
container_volume 8
container_issue 3
container_start_page 622
publishDate 2023
institution Swansea University
issn 2468-2322
2468-2322
doi_str_mv 10.1049/cit2.12125
publisher Institution of Engineering and Technology (IET)
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url http://dx.doi.org/10.1049/cit2.12125
document_store_str 1
active_str 0
description Manipulators actuate joints to let end effectors to perform precise path tracking tasks. Recurrent neural network which is described by dynamic models with parallel processing capability, is a powerful tool for kinematic control of manipulators. Due to physical limitations and actuation saturation of manipulator joints, the involvement of joint constraints for kinematic control of manipulators is essential and critical. However, current existing manipulator control methods based on recurrent neural networks mainly handle with limited levels of joint angular constraints, and to the best of our knowledge, methods for kinematic control of manipulators with higher order joint constraints based on recurrent neural networks are not yet reported. In this study, for the first time, a novel recursive recurrent network model is proposed to solve the kinematic control issue for manipulators with different levels of physical constraints, and the proposed recursive recurrent neural network can be formulated as a new manifold system to ensure control solution within all of the joint constraints in different orders. The theoretical analysis shows the stability and the purposed recursive recurrent neural network and its convergence to solution. Simulation results further demonstrate the effectiveness of the proposed method in end-effector path tracking control under different levels of joint constraints based on the Kuka manipulator system. Comparisons with other methods such as the pseudoinverse-based method and conventional recurrent neural network method substantiate the superiority of the proposed method.
published_date 2023-09-01T14:34:07Z
_version_ 1782731502855913472
score 11.016771