No Cover Image

Journal article 774 views 962 downloads

Dynamic Neural Networks for Motion-Force Control of Redundant Manipulators: An Optimization Perspective

Zhihao Xu, Shuai Li Orcid Logo, Xuefeng Zhou, Songbin Zhou, Taobao Cheng

IEEE Transactions on Industrial Electronics, Volume: 68, Issue: 2, Pages: 1 - 1

Swansea University Author: Shuai Li Orcid Logo

Check full text

DOI (Published version): 10.1109/tie.2020.2970635

Abstract

Accurate position-force control is a core and challenging problem in robotics, especially for manipulators with redundant DOFs. For example, trajectory tracking based control usually fails for grinding robots due to intolerable impact forces imposed onto the end-effectors. The main difficulties lie...

Full description

Published in: IEEE Transactions on Industrial Electronics
ISSN: 0278-0046 1557-9948
Published: Institute of Electrical and Electronics Engineers (IEEE) 2020
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa53696
first_indexed 2020-03-02T13:18:15Z
last_indexed 2021-01-08T04:18:51Z
id cronfa53696
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-01-07T12:30:50.8819275</datestamp><bib-version>v2</bib-version><id>53696</id><entry>2020-03-02</entry><title>Dynamic Neural Networks for Motion-Force Control of Redundant Manipulators: An Optimization Perspective</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>2020-03-02</date><deptcode>ACEM</deptcode><abstract>Accurate position-force control is a core and challenging problem in robotics, especially for manipulators with redundant DOFs. For example, trajectory tracking based control usually fails for grinding robots due to intolerable impact forces imposed onto the end-effectors. The main difficulties lie in the coupling of motion and contact force, redundancy resolution and physical constraints, etc. In this paper, we propose a novel motionforce control strategy in the framework of projection recurrent neural networks. Tracking error and contact force are described in orthogonal spaces respectively, and by selecting minimizing joint torque as secondary task, the control problem is formulated as a quadratic-programming (QP) problem under multiple constraints. In order to obtain real-time optimization of joint toque which is non-convex relative to joint angles, the original QP is reconstructed in velocity level, where the original objective function is replaced by its time derivative. Then a dynamic neural network which is convergence provable is established to solve the modified QP problem online. This work generalizes projection recurrent neural network based position control of manipulators to that of position-force control, which opens a new avenue to shift position-force control of manipulators from pure control perspective to cross design with both convergence and optimality consideration. Numerical and experimental results show that the proposed scheme achieves accurate position-force control, and is capable of handling inequality constraints such as joint angular, velocity and torque limitations, simultaneously, consumption of joint torque can be decreased effectively.</abstract><type>Journal Article</type><journal>IEEE Transactions on Industrial Electronics</journal><volume>68</volume><journalNumber>2</journalNumber><paginationStart>1</paginationStart><paginationEnd>1</paginationEnd><publisher>Institute of Electrical and Electronics Engineers (IEEE)</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0278-0046</issnPrint><issnElectronic>1557-9948</issnElectronic><keywords/><publishedDay>5</publishedDay><publishedMonth>2</publishedMonth><publishedYear>2020</publishedYear><publishedDate>2020-02-05</publishedDate><doi>10.1109/tie.2020.2970635</doi><url/><notes/><college>COLLEGE NANME</college><department>Aerospace, Civil, Electrical, and Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>ACEM</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2021-01-07T12:30:50.8819275</lastEdited><Created>2020-03-02T10:10:34.4892485</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering</level></path><authors><author><firstname>Zhihao</firstname><surname>Xu</surname><order>1</order></author><author><firstname>Shuai</firstname><surname>Li</surname><orcid>0000-0001-8316-5289</orcid><order>2</order></author><author><firstname>Xuefeng</firstname><surname>Zhou</surname><order>3</order></author><author><firstname>Songbin</firstname><surname>Zhou</surname><order>4</order></author><author><firstname>Taobao</firstname><surname>Cheng</surname><order>5</order></author></authors><documents><document><filename>53696__16734__f9d4b722ff694858ada2283b0833befb.pdf</filename><originalFilename>xu2020.pdf</originalFilename><uploaded>2020-03-02T10:15:37.1914468</uploaded><type>Output</type><contentLength>5830014</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2020-03-02T00:00:00.0000000</embargoDate><copyrightCorrect>true</copyrightCorrect><language>English</language></document></documents><OutputDurs/></rfc1807>
spelling 2021-01-07T12:30:50.8819275 v2 53696 2020-03-02 Dynamic Neural Networks for Motion-Force Control of Redundant Manipulators: An Optimization Perspective 42ff9eed09bcd109fbbe484a0f99a8a8 0000-0001-8316-5289 Shuai Li Shuai Li true false 2020-03-02 ACEM Accurate position-force control is a core and challenging problem in robotics, especially for manipulators with redundant DOFs. For example, trajectory tracking based control usually fails for grinding robots due to intolerable impact forces imposed onto the end-effectors. The main difficulties lie in the coupling of motion and contact force, redundancy resolution and physical constraints, etc. In this paper, we propose a novel motionforce control strategy in the framework of projection recurrent neural networks. Tracking error and contact force are described in orthogonal spaces respectively, and by selecting minimizing joint torque as secondary task, the control problem is formulated as a quadratic-programming (QP) problem under multiple constraints. In order to obtain real-time optimization of joint toque which is non-convex relative to joint angles, the original QP is reconstructed in velocity level, where the original objective function is replaced by its time derivative. Then a dynamic neural network which is convergence provable is established to solve the modified QP problem online. This work generalizes projection recurrent neural network based position control of manipulators to that of position-force control, which opens a new avenue to shift position-force control of manipulators from pure control perspective to cross design with both convergence and optimality consideration. Numerical and experimental results show that the proposed scheme achieves accurate position-force control, and is capable of handling inequality constraints such as joint angular, velocity and torque limitations, simultaneously, consumption of joint torque can be decreased effectively. Journal Article IEEE Transactions on Industrial Electronics 68 2 1 1 Institute of Electrical and Electronics Engineers (IEEE) 0278-0046 1557-9948 5 2 2020 2020-02-05 10.1109/tie.2020.2970635 COLLEGE NANME Aerospace, Civil, Electrical, and Mechanical Engineering COLLEGE CODE ACEM Swansea University 2021-01-07T12:30:50.8819275 2020-03-02T10:10:34.4892485 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering Zhihao Xu 1 Shuai Li 0000-0001-8316-5289 2 Xuefeng Zhou 3 Songbin Zhou 4 Taobao Cheng 5 53696__16734__f9d4b722ff694858ada2283b0833befb.pdf xu2020.pdf 2020-03-02T10:15:37.1914468 Output 5830014 application/pdf Accepted Manuscript true 2020-03-02T00:00:00.0000000 true English
title Dynamic Neural Networks for Motion-Force Control of Redundant Manipulators: An Optimization Perspective
spellingShingle Dynamic Neural Networks for Motion-Force Control of Redundant Manipulators: An Optimization Perspective
Shuai Li
title_short Dynamic Neural Networks for Motion-Force Control of Redundant Manipulators: An Optimization Perspective
title_full Dynamic Neural Networks for Motion-Force Control of Redundant Manipulators: An Optimization Perspective
title_fullStr Dynamic Neural Networks for Motion-Force Control of Redundant Manipulators: An Optimization Perspective
title_full_unstemmed Dynamic Neural Networks for Motion-Force Control of Redundant Manipulators: An Optimization Perspective
title_sort Dynamic Neural Networks for Motion-Force Control of Redundant Manipulators: An Optimization Perspective
author_id_str_mv 42ff9eed09bcd109fbbe484a0f99a8a8
author_id_fullname_str_mv 42ff9eed09bcd109fbbe484a0f99a8a8_***_Shuai Li
author Shuai Li
author2 Zhihao Xu
Shuai Li
Xuefeng Zhou
Songbin Zhou
Taobao Cheng
format Journal article
container_title IEEE Transactions on Industrial Electronics
container_volume 68
container_issue 2
container_start_page 1
publishDate 2020
institution Swansea University
issn 0278-0046
1557-9948
doi_str_mv 10.1109/tie.2020.2970635
publisher Institute of Electrical and Electronics Engineers (IEEE)
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 Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering
document_store_str 1
active_str 0
description Accurate position-force control is a core and challenging problem in robotics, especially for manipulators with redundant DOFs. For example, trajectory tracking based control usually fails for grinding robots due to intolerable impact forces imposed onto the end-effectors. The main difficulties lie in the coupling of motion and contact force, redundancy resolution and physical constraints, etc. In this paper, we propose a novel motionforce control strategy in the framework of projection recurrent neural networks. Tracking error and contact force are described in orthogonal spaces respectively, and by selecting minimizing joint torque as secondary task, the control problem is formulated as a quadratic-programming (QP) problem under multiple constraints. In order to obtain real-time optimization of joint toque which is non-convex relative to joint angles, the original QP is reconstructed in velocity level, where the original objective function is replaced by its time derivative. Then a dynamic neural network which is convergence provable is established to solve the modified QP problem online. This work generalizes projection recurrent neural network based position control of manipulators to that of position-force control, which opens a new avenue to shift position-force control of manipulators from pure control perspective to cross design with both convergence and optimality consideration. Numerical and experimental results show that the proposed scheme achieves accurate position-force control, and is capable of handling inequality constraints such as joint angular, velocity and torque limitations, simultaneously, consumption of joint torque can be decreased effectively.
published_date 2020-02-05T04:56:08Z
_version_ 1821380044076875776
score 11.04748

Similar Items