No Cover Image

Journal article 743 views 394 downloads

Visual Servoing of Humanoid Dual-Arm Robot with Neural Learning Enhanced Skill Transferring Control

Chenguang Yang, Junshen Chen, Zhaojie Ju, Andy S. K. Annamalai

International Journal of Humanoid Robotics, Start page: 1750023

Swansea University Author: Chenguang Yang

Check full text

DOI (Published version): 10.1142/S0219843617500232

Abstract

This paper presents a novel combination of visual servoing (VS) control and neural network (NN) learning on humanoid dual-arm robot. A VS control system is built by using stereo vision to obtain the 3D point cloud of a target object. A least square-based method is proposed to reduce the stochastic e...

Full description

Published in: International Journal of Humanoid Robotics
ISSN: 0219-8436 1793-6942
Published: 2017
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa34937
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2017-08-18T18:51:29Z
last_indexed 2018-02-09T05:25:34Z
id cronfa34937
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2017-11-10T11:44:13.2326612</datestamp><bib-version>v2</bib-version><id>34937</id><entry>2017-08-18</entry><title>Visual Servoing of Humanoid Dual-Arm Robot with Neural Learning Enhanced Skill Transferring Control</title><swanseaauthors><author><sid>d2a5024448bfac00a9b3890a8404380b</sid><ORCID/><firstname>Chenguang</firstname><surname>Yang</surname><name>Chenguang Yang</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2017-08-18</date><deptcode>EEN</deptcode><abstract>This paper presents a novel combination of visual servoing (VS) control and neural network (NN) learning on humanoid dual-arm robot. A VS control system is built by using stereo vision to obtain the 3D point cloud of a target object. A least square-based method is proposed to reduce the stochastic error in workspace calibration. An NN controller is designed to compensate for the effect of uncertainties in payload and other parameters (both internal and external) during the tracking control. In contrast to the conventional NN controller, a deterministic learning technique is utilized in this work, to enable the learned neural knowledge to be reused before current dynamics changes. A skill transfer mechanism is also developed to apply the neural learned knowledge from one arm to the other, to increase the neural learning efficiency. Tracked trajectory of object is used to provide target position to the coordinated dual arms of a Baxter robot in the experimental study. Robotic implementations has demonstrated the efficiency of the developed VS control system and has verified the effectiveness of the proposed NN controller with knowledge-reuse and skill transfer features.</abstract><type>Journal Article</type><journal>International Journal of Humanoid Robotics</journal><paginationStart>1750023</paginationStart><publisher/><issnPrint>0219-8436</issnPrint><issnElectronic>1793-6942</issnElectronic><keywords>Neural networks; deterministic learning; visual servoing; stereo vision</keywords><publishedDay>31</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2017</publishedYear><publishedDate>2017-12-31</publishedDate><doi>10.1142/S0219843617500232</doi><url/><notes/><college>COLLEGE NANME</college><department>Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>EEN</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2017-11-10T11:44:13.2326612</lastEdited><Created>2017-08-18T14:42:46.3313212</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Uncategorised</level></path><authors><author><firstname>Chenguang</firstname><surname>Yang</surname><orcid/><order>1</order></author><author><firstname>Junshen</firstname><surname>Chen</surname><order>2</order></author><author><firstname>Zhaojie</firstname><surname>Ju</surname><order>3</order></author><author><firstname>Andy S. K.</firstname><surname>Annamalai</surname><order>4</order></author></authors><documents><document><filename>0034937-18082017144535.pdf</filename><originalFilename>Typesetting_done_1750023.pdf</originalFilename><uploaded>2017-08-18T14:45:35.1730000</uploaded><type>Output</type><contentLength>3711087</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2018-10-17T00:00:00.0000000</embargoDate><copyrightCorrect>false</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2017-11-10T11:44:13.2326612 v2 34937 2017-08-18 Visual Servoing of Humanoid Dual-Arm Robot with Neural Learning Enhanced Skill Transferring Control d2a5024448bfac00a9b3890a8404380b Chenguang Yang Chenguang Yang true false 2017-08-18 EEN This paper presents a novel combination of visual servoing (VS) control and neural network (NN) learning on humanoid dual-arm robot. A VS control system is built by using stereo vision to obtain the 3D point cloud of a target object. A least square-based method is proposed to reduce the stochastic error in workspace calibration. An NN controller is designed to compensate for the effect of uncertainties in payload and other parameters (both internal and external) during the tracking control. In contrast to the conventional NN controller, a deterministic learning technique is utilized in this work, to enable the learned neural knowledge to be reused before current dynamics changes. A skill transfer mechanism is also developed to apply the neural learned knowledge from one arm to the other, to increase the neural learning efficiency. Tracked trajectory of object is used to provide target position to the coordinated dual arms of a Baxter robot in the experimental study. Robotic implementations has demonstrated the efficiency of the developed VS control system and has verified the effectiveness of the proposed NN controller with knowledge-reuse and skill transfer features. Journal Article International Journal of Humanoid Robotics 1750023 0219-8436 1793-6942 Neural networks; deterministic learning; visual servoing; stereo vision 31 12 2017 2017-12-31 10.1142/S0219843617500232 COLLEGE NANME Engineering COLLEGE CODE EEN Swansea University 2017-11-10T11:44:13.2326612 2017-08-18T14:42:46.3313212 Faculty of Science and Engineering School of Engineering and Applied Sciences - Uncategorised Chenguang Yang 1 Junshen Chen 2 Zhaojie Ju 3 Andy S. K. Annamalai 4 0034937-18082017144535.pdf Typesetting_done_1750023.pdf 2017-08-18T14:45:35.1730000 Output 3711087 application/pdf Accepted Manuscript true 2018-10-17T00:00:00.0000000 false eng
title Visual Servoing of Humanoid Dual-Arm Robot with Neural Learning Enhanced Skill Transferring Control
spellingShingle Visual Servoing of Humanoid Dual-Arm Robot with Neural Learning Enhanced Skill Transferring Control
Chenguang Yang
title_short Visual Servoing of Humanoid Dual-Arm Robot with Neural Learning Enhanced Skill Transferring Control
title_full Visual Servoing of Humanoid Dual-Arm Robot with Neural Learning Enhanced Skill Transferring Control
title_fullStr Visual Servoing of Humanoid Dual-Arm Robot with Neural Learning Enhanced Skill Transferring Control
title_full_unstemmed Visual Servoing of Humanoid Dual-Arm Robot with Neural Learning Enhanced Skill Transferring Control
title_sort Visual Servoing of Humanoid Dual-Arm Robot with Neural Learning Enhanced Skill Transferring Control
author_id_str_mv d2a5024448bfac00a9b3890a8404380b
author_id_fullname_str_mv d2a5024448bfac00a9b3890a8404380b_***_Chenguang Yang
author Chenguang Yang
author2 Chenguang Yang
Junshen Chen
Zhaojie Ju
Andy S. K. Annamalai
format Journal article
container_title International Journal of Humanoid Robotics
container_start_page 1750023
publishDate 2017
institution Swansea University
issn 0219-8436
1793-6942
doi_str_mv 10.1142/S0219843617500232
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 Engineering and Applied Sciences - Uncategorised{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Uncategorised
document_store_str 1
active_str 0
description This paper presents a novel combination of visual servoing (VS) control and neural network (NN) learning on humanoid dual-arm robot. A VS control system is built by using stereo vision to obtain the 3D point cloud of a target object. A least square-based method is proposed to reduce the stochastic error in workspace calibration. An NN controller is designed to compensate for the effect of uncertainties in payload and other parameters (both internal and external) during the tracking control. In contrast to the conventional NN controller, a deterministic learning technique is utilized in this work, to enable the learned neural knowledge to be reused before current dynamics changes. A skill transfer mechanism is also developed to apply the neural learned knowledge from one arm to the other, to increase the neural learning efficiency. Tracked trajectory of object is used to provide target position to the coordinated dual arms of a Baxter robot in the experimental study. Robotic implementations has demonstrated the efficiency of the developed VS control system and has verified the effectiveness of the proposed NN controller with knowledge-reuse and skill transfer features.
published_date 2017-12-31T03:43:22Z
_version_ 1763752020552974336
score 11.016235

Similar Items