No Cover Image

Journal article 874 views

Neural Network Model-Based Control for Manipulator: An Autoencoder Perspective

Zhan Li, Shuai Li Orcid Logo

IEEE Transactions on Neural Networks and Learning Systems, Volume: 32, Issue: 5, Pages: 1 - 15

Swansea University Authors: Zhan Li, Shuai Li Orcid Logo

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.1109/tnnls.2021.3109953

Abstract

Recently, neural network model-based control has received wide interests in kinematics control of manipulators. To enhance learning ability of neural network models, the autoencoder method is used as a powerful tool to achieve deep learning and has gained success in recent years. However, the perfor...

Full description

Published in: IEEE Transactions on Neural Networks and Learning Systems
ISSN: 2162-237X 2162-2388
Published: Institute of Electrical and Electronics Engineers (IEEE) 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa57895
first_indexed 2021-09-15T06:22:36Z
last_indexed 2024-11-14T12:12:40Z
id cronfa57895
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2023-10-18T10:22:49.0455096</datestamp><bib-version>v2</bib-version><id>57895</id><entry>2021-09-15</entry><title>Neural Network Model-Based Control for Manipulator: An Autoencoder Perspective</title><swanseaauthors><author><sid>94f19a09e17bad497ef1b4a0992c1d56</sid><firstname>Zhan</firstname><surname>Li</surname><name>Zhan Li</name><active>true</active><ethesisStudent>false</ethesisStudent></author><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>2021-09-15</date><deptcode>MACS</deptcode><abstract>Recently, neural network model-based control has received wide interests in kinematics control of manipulators. To enhance learning ability of neural network models, the autoencoder method is used as a powerful tool to achieve deep learning and has gained success in recent years. However, the performance of existing autoencoder approaches for manipulator control may be still largely dependent on the quality of data, and for extreme cases with noisy data it may even fail. How to incorporate the model knowledge into the autoencoder controller design with an aim to increase the robustness and reliability remains a challenging problem. In this work, a sparse autoencoder controller for kinematic control of manipulators with weights obtained directly from the robot model rather than training data is proposed for the first time. By encoding and decoding the control target though a new dynamic recurrent neural network architecture, the control input can be solved through a new sparse optimization formulation. In this work, input saturation, which holds for almost all practical systems but usually is ignored for analysis simplicity, is also considered in the controller construction. Theoretical analysis and extensive simulations demonstrate that the proposed sparse autoencoder controller with input saturation can make the end-effector of the manipulator system track the desired path efficiently. Further performance comparison and evaluation against the additive noise and parameter uncertainty substantiate robustness of the proposed sparse autoencoder manipulator controller.</abstract><type>Journal Article</type><journal>IEEE Transactions on Neural Networks and Learning Systems</journal><volume>32</volume><journalNumber>5</journalNumber><paginationStart>1</paginationStart><paginationEnd>15</paginationEnd><publisher>Institute of Electrical and Electronics Engineers (IEEE)</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>2162-237X</issnPrint><issnElectronic>2162-2388</issnElectronic><keywords/><publishedDay>14</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-09-14</publishedDate><doi>10.1109/tnnls.2021.3109953</doi><url/><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2023-10-18T10:22:49.0455096</lastEdited><Created>2021-09-15T07:21:07.1298431</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><order>1</order></author><author><firstname>Shuai</firstname><surname>Li</surname><orcid>0000-0001-8316-5289</orcid><order>2</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2023-10-18T10:22:49.0455096 v2 57895 2021-09-15 Neural Network Model-Based Control for Manipulator: An Autoencoder Perspective 94f19a09e17bad497ef1b4a0992c1d56 Zhan Li Zhan Li true false 42ff9eed09bcd109fbbe484a0f99a8a8 0000-0001-8316-5289 Shuai Li Shuai Li true false 2021-09-15 MACS Recently, neural network model-based control has received wide interests in kinematics control of manipulators. To enhance learning ability of neural network models, the autoencoder method is used as a powerful tool to achieve deep learning and has gained success in recent years. However, the performance of existing autoencoder approaches for manipulator control may be still largely dependent on the quality of data, and for extreme cases with noisy data it may even fail. How to incorporate the model knowledge into the autoencoder controller design with an aim to increase the robustness and reliability remains a challenging problem. In this work, a sparse autoencoder controller for kinematic control of manipulators with weights obtained directly from the robot model rather than training data is proposed for the first time. By encoding and decoding the control target though a new dynamic recurrent neural network architecture, the control input can be solved through a new sparse optimization formulation. In this work, input saturation, which holds for almost all practical systems but usually is ignored for analysis simplicity, is also considered in the controller construction. Theoretical analysis and extensive simulations demonstrate that the proposed sparse autoencoder controller with input saturation can make the end-effector of the manipulator system track the desired path efficiently. Further performance comparison and evaluation against the additive noise and parameter uncertainty substantiate robustness of the proposed sparse autoencoder manipulator controller. Journal Article IEEE Transactions on Neural Networks and Learning Systems 32 5 1 15 Institute of Electrical and Electronics Engineers (IEEE) 2162-237X 2162-2388 14 9 2021 2021-09-14 10.1109/tnnls.2021.3109953 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University 2023-10-18T10:22:49.0455096 2021-09-15T07:21:07.1298431 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Zhan Li 1 Shuai Li 0000-0001-8316-5289 2
title Neural Network Model-Based Control for Manipulator: An Autoencoder Perspective
spellingShingle Neural Network Model-Based Control for Manipulator: An Autoencoder Perspective
Zhan Li
Shuai Li
title_short Neural Network Model-Based Control for Manipulator: An Autoencoder Perspective
title_full Neural Network Model-Based Control for Manipulator: An Autoencoder Perspective
title_fullStr Neural Network Model-Based Control for Manipulator: An Autoencoder Perspective
title_full_unstemmed Neural Network Model-Based Control for Manipulator: An Autoencoder Perspective
title_sort Neural Network Model-Based Control for Manipulator: An Autoencoder Perspective
author_id_str_mv 94f19a09e17bad497ef1b4a0992c1d56
42ff9eed09bcd109fbbe484a0f99a8a8
author_id_fullname_str_mv 94f19a09e17bad497ef1b4a0992c1d56_***_Zhan Li
42ff9eed09bcd109fbbe484a0f99a8a8_***_Shuai Li
author Zhan Li
Shuai Li
author2 Zhan Li
Shuai Li
format Journal article
container_title IEEE Transactions on Neural Networks and Learning Systems
container_volume 32
container_issue 5
container_start_page 1
publishDate 2021
institution Swansea University
issn 2162-237X
2162-2388
doi_str_mv 10.1109/tnnls.2021.3109953
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 Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 0
active_str 0
description Recently, neural network model-based control has received wide interests in kinematics control of manipulators. To enhance learning ability of neural network models, the autoencoder method is used as a powerful tool to achieve deep learning and has gained success in recent years. However, the performance of existing autoencoder approaches for manipulator control may be still largely dependent on the quality of data, and for extreme cases with noisy data it may even fail. How to incorporate the model knowledge into the autoencoder controller design with an aim to increase the robustness and reliability remains a challenging problem. In this work, a sparse autoencoder controller for kinematic control of manipulators with weights obtained directly from the robot model rather than training data is proposed for the first time. By encoding and decoding the control target though a new dynamic recurrent neural network architecture, the control input can be solved through a new sparse optimization formulation. In this work, input saturation, which holds for almost all practical systems but usually is ignored for analysis simplicity, is also considered in the controller construction. Theoretical analysis and extensive simulations demonstrate that the proposed sparse autoencoder controller with input saturation can make the end-effector of the manipulator system track the desired path efficiently. Further performance comparison and evaluation against the additive noise and parameter uncertainty substantiate robustness of the proposed sparse autoencoder manipulator controller.
published_date 2021-09-14T14:13:07Z
_version_ 1821415086177124352
score 11.048129

Similar Items