Conditional Adversarial Motion Priors by a Novel Retargeting Method for Versatile Humanoid Robot Control

Significant advancements have been made in the field of humanoid robot, particularly in walking control strategies. However, achieving straight‐legged walking remains a challenge. Both the traditional model‐based and the learning‐based control methods confront with difficulties in achieving natural...

Full description

Saved in:
Bibliographic Details
Published in:International journal of adaptive control and signal processing 2024-10
Main Authors: Zhang, Jinlin, Li, Zijing, Lu, Mengyue, Gan, Chunbiao
Format: Article
Language:English
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c118t-ce4b38a25f856adbbca9b6b1406c70a32003e8800b10b263cbece6af40c88a103
container_end_page
container_issue
container_start_page
container_title International journal of adaptive control and signal processing
container_volume
creator Zhang, Jinlin
Li, Zijing
Lu, Mengyue
Gan, Chunbiao
description Significant advancements have been made in the field of humanoid robot, particularly in walking control strategies. However, achieving straight‐legged walking remains a challenge. Both the traditional model‐based and the learning‐based control methods confront with difficulties in achieving natural humanoid gait feature. To address this issue, a general motion retargeting method is developed and also evaluated for humanoid robots with different structure, size and degrees of freedom. Moreover, a conditional adversarial motion priors method is proposed based on reinforcement learning and validated on the humanoid robot GTX‐III. Through various motion segments from the motion capture database, it is shown that this method can successfully enable the humanoid robot to perform straight‐legged walking with flexible and natural transitions between different gaits within a single discriminator network.
doi_str_mv 10.1002/acs.3915
format article
fullrecord <record><control><sourceid>crossref</sourceid><recordid>TN_cdi_crossref_primary_10_1002_acs_3915</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_1002_acs_3915</sourcerecordid><originalsourceid>FETCH-LOGICAL-c118t-ce4b38a25f856adbbca9b6b1406c70a32003e8800b10b263cbece6af40c88a103</originalsourceid><addsrcrecordid>eNotkFFLwzAUhYMoWKfgT8ijL533Nm2XPo6iTthUhvpabtJ0i3SNJHGwf2-LPp3DOZx74WPsFmGOANk96TAXFRZnLEGoqhQRi3OWgKwgLUW2uGRXIXwBjB2KhO1rN7Q2WjdQz5ft0fhA3o5-46aQv3nrfODqxIm_uKPp-dZE8jsT7bDjGxP3ruWd8_xzWkbbG776OdDgbMu3TrnIxwfRu_6aXXTUB3PzrzP28fjwXq_S9evTc71cpxpRxlSbXAlJWdHJoqRWKU2VKhXmUOoFkMgAhJESQCGorBRaGW1K6nLQUhKCmLG7v7vauxC86Zpvbw_kTw1CMxFqRkLNREj8Alp0WtY</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Conditional Adversarial Motion Priors by a Novel Retargeting Method for Versatile Humanoid Robot Control</title><source>Wiley</source><creator>Zhang, Jinlin ; Li, Zijing ; Lu, Mengyue ; Gan, Chunbiao</creator><creatorcontrib>Zhang, Jinlin ; Li, Zijing ; Lu, Mengyue ; Gan, Chunbiao</creatorcontrib><description>Significant advancements have been made in the field of humanoid robot, particularly in walking control strategies. However, achieving straight‐legged walking remains a challenge. Both the traditional model‐based and the learning‐based control methods confront with difficulties in achieving natural humanoid gait feature. To address this issue, a general motion retargeting method is developed and also evaluated for humanoid robots with different structure, size and degrees of freedom. Moreover, a conditional adversarial motion priors method is proposed based on reinforcement learning and validated on the humanoid robot GTX‐III. Through various motion segments from the motion capture database, it is shown that this method can successfully enable the humanoid robot to perform straight‐legged walking with flexible and natural transitions between different gaits within a single discriminator network.</description><identifier>ISSN: 0890-6327</identifier><identifier>EISSN: 1099-1115</identifier><identifier>DOI: 10.1002/acs.3915</identifier><language>eng</language><ispartof>International journal of adaptive control and signal processing, 2024-10</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c118t-ce4b38a25f856adbbca9b6b1406c70a32003e8800b10b263cbece6af40c88a103</cites><orcidid>0009-0001-6718-5121 ; 0000-0002-6597-5605</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27923,27924</link.rule.ids></links><search><creatorcontrib>Zhang, Jinlin</creatorcontrib><creatorcontrib>Li, Zijing</creatorcontrib><creatorcontrib>Lu, Mengyue</creatorcontrib><creatorcontrib>Gan, Chunbiao</creatorcontrib><title>Conditional Adversarial Motion Priors by a Novel Retargeting Method for Versatile Humanoid Robot Control</title><title>International journal of adaptive control and signal processing</title><description>Significant advancements have been made in the field of humanoid robot, particularly in walking control strategies. However, achieving straight‐legged walking remains a challenge. Both the traditional model‐based and the learning‐based control methods confront with difficulties in achieving natural humanoid gait feature. To address this issue, a general motion retargeting method is developed and also evaluated for humanoid robots with different structure, size and degrees of freedom. Moreover, a conditional adversarial motion priors method is proposed based on reinforcement learning and validated on the humanoid robot GTX‐III. Through various motion segments from the motion capture database, it is shown that this method can successfully enable the humanoid robot to perform straight‐legged walking with flexible and natural transitions between different gaits within a single discriminator network.</description><issn>0890-6327</issn><issn>1099-1115</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNotkFFLwzAUhYMoWKfgT8ijL533Nm2XPo6iTthUhvpabtJ0i3SNJHGwf2-LPp3DOZx74WPsFmGOANk96TAXFRZnLEGoqhQRi3OWgKwgLUW2uGRXIXwBjB2KhO1rN7Q2WjdQz5ft0fhA3o5-46aQv3nrfODqxIm_uKPp-dZE8jsT7bDjGxP3ruWd8_xzWkbbG776OdDgbMu3TrnIxwfRu_6aXXTUB3PzrzP28fjwXq_S9evTc71cpxpRxlSbXAlJWdHJoqRWKU2VKhXmUOoFkMgAhJESQCGorBRaGW1K6nLQUhKCmLG7v7vauxC86Zpvbw_kTw1CMxFqRkLNREj8Alp0WtY</recordid><startdate>202410</startdate><enddate>202410</enddate><creator>Zhang, Jinlin</creator><creator>Li, Zijing</creator><creator>Lu, Mengyue</creator><creator>Gan, Chunbiao</creator><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0009-0001-6718-5121</orcidid><orcidid>https://orcid.org/0000-0002-6597-5605</orcidid></search><sort><creationdate>202410</creationdate><title>Conditional Adversarial Motion Priors by a Novel Retargeting Method for Versatile Humanoid Robot Control</title><author>Zhang, Jinlin ; Li, Zijing ; Lu, Mengyue ; Gan, Chunbiao</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c118t-ce4b38a25f856adbbca9b6b1406c70a32003e8800b10b263cbece6af40c88a103</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Jinlin</creatorcontrib><creatorcontrib>Li, Zijing</creatorcontrib><creatorcontrib>Lu, Mengyue</creatorcontrib><creatorcontrib>Gan, Chunbiao</creatorcontrib><collection>CrossRef</collection><jtitle>International journal of adaptive control and signal processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhang, Jinlin</au><au>Li, Zijing</au><au>Lu, Mengyue</au><au>Gan, Chunbiao</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Conditional Adversarial Motion Priors by a Novel Retargeting Method for Versatile Humanoid Robot Control</atitle><jtitle>International journal of adaptive control and signal processing</jtitle><date>2024-10</date><risdate>2024</risdate><issn>0890-6327</issn><eissn>1099-1115</eissn><abstract>Significant advancements have been made in the field of humanoid robot, particularly in walking control strategies. However, achieving straight‐legged walking remains a challenge. Both the traditional model‐based and the learning‐based control methods confront with difficulties in achieving natural humanoid gait feature. To address this issue, a general motion retargeting method is developed and also evaluated for humanoid robots with different structure, size and degrees of freedom. Moreover, a conditional adversarial motion priors method is proposed based on reinforcement learning and validated on the humanoid robot GTX‐III. Through various motion segments from the motion capture database, it is shown that this method can successfully enable the humanoid robot to perform straight‐legged walking with flexible and natural transitions between different gaits within a single discriminator network.</abstract><doi>10.1002/acs.3915</doi><orcidid>https://orcid.org/0009-0001-6718-5121</orcidid><orcidid>https://orcid.org/0000-0002-6597-5605</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0890-6327
ispartof International journal of adaptive control and signal processing, 2024-10
issn 0890-6327
1099-1115
language eng
recordid cdi_crossref_primary_10_1002_acs_3915
source Wiley
title Conditional Adversarial Motion Priors by a Novel Retargeting Method for Versatile Humanoid Robot Control
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T16%3A32%3A05IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Conditional%20Adversarial%20Motion%20Priors%20by%20a%20Novel%20Retargeting%20Method%20for%20Versatile%20Humanoid%20Robot%20Control&rft.jtitle=International%20journal%20of%20adaptive%20control%20and%20signal%20processing&rft.au=Zhang,%20Jinlin&rft.date=2024-10&rft.issn=0890-6327&rft.eissn=1099-1115&rft_id=info:doi/10.1002/acs.3915&rft_dat=%3Ccrossref%3E10_1002_acs_3915%3C/crossref%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c118t-ce4b38a25f856adbbca9b6b1406c70a32003e8800b10b263cbece6af40c88a103%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true