Walking Stability Control Method for Biped Robot on Uneven Ground Based on Deep Q-Network

Walking Stability Control Method for Biped Robot on Uneven Ground Based on Deep Q-Network

TP242; A gait control method for a biped robot based on the deep Q-network (DQN) algorithm is proposed to enhance the stability of walking on uneven ground.This control strategy is an intelligent learning method of posture adjustment.A robot is taken as an agent and trained to walk steadily on an un...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:北京理工大学学报（英文版） 2019-09, Vol.28 (3), p.598-605
Hauptverfasser: Baoling Han, Yuting Zhao, Qingsheng Luo
Format: Artikel
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 605
container_issue 3
container_start_page 598
container_title 北京理工大学学报（英文版）
container_volume 28
creator Baoling Han
Yuting Zhao
Qingsheng Luo
description TP242; A gait control method for a biped robot based on the deep Q-network (DQN) algorithm is proposed to enhance the stability of walking on uneven ground.This control strategy is an intelligent learning method of posture adjustment.A robot is taken as an agent and trained to walk steadily on an uneven surface with obstacles,using a simple reward function based on forward progress.The reward-punishment (RP) mechanism of the DQN algorithm is established after obtaining the offline gait which was generated in advance foot trajectory planning.Instead of implementing a complex dynamic model,the proposed method enables the biped robot to learn to adjust its posture on the uneven ground and ensures walking stability.The performance and effectiveness of the proposed algorithm was validated in the V-REP simulation environment.The results demonstrate that the biped robot's lateral tile angle is less than 3° after implementing the proposed method and the walking stability is obviously improved.
doi_str_mv 10.15918/j.jbit1004-0579.18059
format Article
fullrecord <record><control><sourceid>wanfang_jour</sourceid><recordid>TN_cdi_wanfang_journals_bjlgdxxb_e201903023</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><wanfj_id>bjlgdxxb_e201903023</wanfj_id><sourcerecordid>bjlgdxxb_e201903023</sourcerecordid><originalsourceid>FETCH-LOGICAL-s1063-6e697bf9b92af493b0c4887bfcb799f706586ae321758c88025e7c305800b3b33</originalsourceid><addsrcrecordid>eNo9zV1LwzAYBeBcKDjm_oLkXlrfJE2bXLqqmzAVP4Z4VZI2melKMtrMzX9vQfHqwHPgHIQuCKSESyKu2rTVLhKALAFeyJQI4PIETf7lDM2GwWkgQlApsnyCPt5Vt3V-g1-j0q5z8RuXwcc-dPjBxM_QYBt6PHc70-CXoEPEweO1N1_G40Uf9r7BczWM5cg3xuzwc_Jo4iH023N0alU3mNlfTtH67vatXCarp8V9eb1KBgI5S3KTy0JbqSVVNpNMQ50JMUqtCyltATkXuTKMkoKLWgig3BQ1Ay4ANNOMTdHl7-5Beav8pmrDvvfjY6XbbtMcj7oyFIgEBpSxH-kEVrU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Walking Stability Control Method for Biped Robot on Uneven Ground Based on Deep Q-Network</title><source>Alma/SFX Local Collection</source><creator>Baoling Han ; Yuting Zhao ; Qingsheng Luo</creator><creatorcontrib>Baoling Han ; Yuting Zhao ; Qingsheng Luo</creatorcontrib><description>TP242; A gait control method for a biped robot based on the deep Q-network (DQN) algorithm is proposed to enhance the stability of walking on uneven ground.This control strategy is an intelligent learning method of posture adjustment.A robot is taken as an agent and trained to walk steadily on an uneven surface with obstacles,using a simple reward function based on forward progress.The reward-punishment (RP) mechanism of the DQN algorithm is established after obtaining the offline gait which was generated in advance foot trajectory planning.Instead of implementing a complex dynamic model,the proposed method enables the biped robot to learn to adjust its posture on the uneven ground and ensures walking stability.The performance and effectiveness of the proposed algorithm was validated in the V-REP simulation environment.The results demonstrate that the biped robot's lateral tile angle is less than 3° after implementing the proposed method and the walking stability is obviously improved.</description><identifier>ISSN: 1004-0579</identifier><identifier>DOI: 10.15918/j.jbit1004-0579.18059</identifier><language>eng</language><publisher>School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China%School of Mechatronic Engineering, Beijing Institute of Technology, Beijing 100081, China</publisher><ispartof>北京理工大学学报（英文版）, 2019-09, Vol.28 (3), p.598-605</ispartof><rights>Copyright © Wanfang Data Co. Ltd. All Rights Reserved.</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Uhttp://www.wanfangdata.com.cn/images/PeriodicalImages/bjlgdxxb-e/bjlgdxxb-e.jpg</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Baoling Han</creatorcontrib><creatorcontrib>Yuting Zhao</creatorcontrib><creatorcontrib>Qingsheng Luo</creatorcontrib><title>Walking Stability Control Method for Biped Robot on Uneven Ground Based on Deep Q-Network</title><title>北京理工大学学报（英文版）</title><description>TP242; A gait control method for a biped robot based on the deep Q-network (DQN) algorithm is proposed to enhance the stability of walking on uneven ground.This control strategy is an intelligent learning method of posture adjustment.A robot is taken as an agent and trained to walk steadily on an uneven surface with obstacles,using a simple reward function based on forward progress.The reward-punishment (RP) mechanism of the DQN algorithm is established after obtaining the offline gait which was generated in advance foot trajectory planning.Instead of implementing a complex dynamic model,the proposed method enables the biped robot to learn to adjust its posture on the uneven ground and ensures walking stability.The performance and effectiveness of the proposed algorithm was validated in the V-REP simulation environment.The results demonstrate that the biped robot's lateral tile angle is less than 3° after implementing the proposed method and the walking stability is obviously improved.</description><issn>1004-0579</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNo9zV1LwzAYBeBcKDjm_oLkXlrfJE2bXLqqmzAVP4Z4VZI2melKMtrMzX9vQfHqwHPgHIQuCKSESyKu2rTVLhKALAFeyJQI4PIETf7lDM2GwWkgQlApsnyCPt5Vt3V-g1-j0q5z8RuXwcc-dPjBxM_QYBt6PHc70-CXoEPEweO1N1_G40Uf9r7BczWM5cg3xuzwc_Jo4iH023N0alU3mNlfTtH67vatXCarp8V9eb1KBgI5S3KTy0JbqSVVNpNMQ50JMUqtCyltATkXuTKMkoKLWgig3BQ1Ay4ANNOMTdHl7-5Beav8pmrDvvfjY6XbbtMcj7oyFIgEBpSxH-kEVrU</recordid><startdate>20190901</startdate><enddate>20190901</enddate><creator>Baoling Han</creator><creator>Yuting Zhao</creator><creator>Qingsheng Luo</creator><general>School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China%School of Mechatronic Engineering, Beijing Institute of Technology, Beijing 100081, China</general><scope>2B.</scope><scope>4A8</scope><scope>92I</scope><scope>93N</scope><scope>PSX</scope><scope>TCJ</scope></search><sort><creationdate>20190901</creationdate><title>Walking Stability Control Method for Biped Robot on Uneven Ground Based on Deep Q-Network</title><author>Baoling Han ; Yuting Zhao ; Qingsheng Luo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-s1063-6e697bf9b92af493b0c4887bfcb799f706586ae321758c88025e7c305800b3b33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><toplevel>online_resources</toplevel><creatorcontrib>Baoling Han</creatorcontrib><creatorcontrib>Yuting Zhao</creatorcontrib><creatorcontrib>Qingsheng Luo</creatorcontrib><collection>Wanfang Data Journals - Hong Kong</collection><collection>WANFANG Data Centre</collection><collection>Wanfang Data Journals</collection><collection>万方数据期刊 - 香港版</collection><collection>China Online Journals (COJ)</collection><collection>China Online Journals (COJ)</collection><jtitle>北京理工大学学报（英文版）</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Baoling Han</au><au>Yuting Zhao</au><au>Qingsheng Luo</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Walking Stability Control Method for Biped Robot on Uneven Ground Based on Deep Q-Network</atitle><jtitle>北京理工大学学报（英文版）</jtitle><date>2019-09-01</date><risdate>2019</risdate><volume>28</volume><issue>3</issue><spage>598</spage><epage>605</epage><pages>598-605</pages><issn>1004-0579</issn><abstract>TP242; A gait control method for a biped robot based on the deep Q-network (DQN) algorithm is proposed to enhance the stability of walking on uneven ground.This control strategy is an intelligent learning method of posture adjustment.A robot is taken as an agent and trained to walk steadily on an uneven surface with obstacles,using a simple reward function based on forward progress.The reward-punishment (RP) mechanism of the DQN algorithm is established after obtaining the offline gait which was generated in advance foot trajectory planning.Instead of implementing a complex dynamic model,the proposed method enables the biped robot to learn to adjust its posture on the uneven ground and ensures walking stability.The performance and effectiveness of the proposed algorithm was validated in the V-REP simulation environment.The results demonstrate that the biped robot's lateral tile angle is less than 3° after implementing the proposed method and the walking stability is obviously improved.</abstract><pub>School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China%School of Mechatronic Engineering, Beijing Institute of Technology, Beijing 100081, China</pub><doi>10.15918/j.jbit1004-0579.18059</doi><tpages>8</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1004-0579
ispartof 北京理工大学学报（英文版）, 2019-09, Vol.28 (3), p.598-605
issn 1004-0579
language eng
recordid cdi_wanfang_journals_bjlgdxxb_e201903023
source Alma/SFX Local Collection
title Walking Stability Control Method for Biped Robot on Uneven Ground Based on Deep Q-Network
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T21%3A17%3A16IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-wanfang_jour&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Walking%20Stability%20Control%20Method%20for%20Biped%20Robot%20on%20Uneven%20Ground%20Based%20on%20Deep%20Q-Network&rft.jtitle=%E5%8C%97%E4%BA%AC%E7%90%86%E5%B7%A5%E5%A4%A7%E5%AD%A6%E5%AD%A6%E6%8A%A5%EF%BC%88%E8%8B%B1%E6%96%87%E7%89%88%EF%BC%89&rft.au=Baoling%20Han&rft.date=2019-09-01&rft.volume=28&rft.issue=3&rft.spage=598&rft.epage=605&rft.pages=598-605&rft.issn=1004-0579&rft_id=info:doi/10.15918/j.jbit1004-0579.18059&rft_dat=%3Cwanfang_jour%3Ebjlgdxxb_e201903023%3C/wanfang_jour%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_wanfj_id=bjlgdxxb_e201903023&rfr_iscdi=true