{"id":"https://openalex.org/W7135241609","doi":"https://doi.org/10.1109/tase.2026.3673779","title":"Reinforcement Learning-Based Whole-Body Motion Control for Humanoids With Position-Controlled Joints","display_name":"Reinforcement Learning-Based Whole-Body Motion Control for Humanoids With Position-Controlled Joints","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7135241609","doi":"https://doi.org/10.1109/tase.2026.3673779"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2026.3673779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3673779","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076070712","display_name":"Chengju J. Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chengju Liu","raw_affiliation_strings":["State Key Laboratory of Autonomous Intelligent Unmanned System, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Autonomous Intelligent Unmanned System, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088387048","display_name":"Kaiyan Xiao","orcid":"https://orcid.org/0000-0003-3764-8938"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiyan Xiao","raw_affiliation_strings":["Robot and Artificial Intelligence Laboratory, College of Electronic and Information Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Robot and Artificial Intelligence Laboratory, College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037011474","display_name":"Mengxian Hu","orcid":"https://orcid.org/0009-0004-9844-5768"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxian Hu","raw_affiliation_strings":["State Key Laboratory of Autonomous Intelligent Unmanned System, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Autonomous Intelligent Unmanned System, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028782831","display_name":"Qin Fang","orcid":"https://orcid.org/0000-0003-4040-2154"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Fang","raw_affiliation_strings":["Robot and Artificial Intelligence Laboratory, College of Electronic and Information Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Robot and Artificial Intelligence Laboratory, College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109698133","display_name":"Zheng Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Xu","raw_affiliation_strings":["Robot and Artificial Intelligence Laboratory, College of Electronic and Information Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Robot and Artificial Intelligence Laboratory, College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078610325","display_name":"Qing Chen","orcid":"https://orcid.org/0000-0002-2191-6558"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qijun Chen","raw_affiliation_strings":["State Key Laboratory of Autonomous Intelligent Unmanned System, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Autonomous Intelligent Unmanned System, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5076070712"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86626417,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"6564","last_page":"6578"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.6391000151634216,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.6391000151634216,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.12610000371932983,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.041200000792741776,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/motion-control","display_name":"Motion control","score":0.5328999757766724},{"id":"https://openalex.org/keywords/grippers","display_name":"Grippers","score":0.4878999888896942},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.46050000190734863},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.45419999957084656},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.44749999046325684},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.43950000405311584},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.43470001220703125},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.37929999828338623},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3544999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5799000263214111},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.5328999757766724},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.44749999046325684},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.43950000405311584},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.42879998683929443},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.36980000138282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3666999936103821},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3544999957084656},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.31839999556541443},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.3075999915599823},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.30630001425743103},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2939000129699707},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C8652668","wikidata":"https://www.wikidata.org/wiki/Q1340324","display_name":"Robot end effector","level":3,"score":0.2711000144481659},{"id":"https://openalex.org/C49240428","wikidata":"https://www.wikidata.org/wiki/Q3305953","display_name":"Vibration control","level":3,"score":0.26510000228881836},{"id":"https://openalex.org/C167123822","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automatic control","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.2506999969482422},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2026.3673779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3673779","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"holds":[3],"great":[4],"promise":[5],"for":[6,65,201],"generating":[7],"dynamic":[8],"whole-body":[9,66,156],"motions":[10],"on":[11,92,167],"humanoid":[12,207],"robots,":[13],"but":[14],"its":[15],"real-world":[16,39],"application":[17],"is":[18],"hindered":[19],"by":[20,26,96,137],"the":[21,42,93,118,168],"significant":[22],"sim-to-real":[23,203],"gap":[24],"caused":[25],"actuator":[27,78,193],"model":[28,79],"mismatch.":[29],"Most":[30],"simulators":[31],"assume":[32],"torque-controlled":[33],"or":[34],"idealized":[35],"PD":[36],"actuators,":[37],"whereas":[38],"platforms":[40],"like":[41],"NAO":[43,170],"robot":[44,95,171],"employ":[45],"position-controlled":[46],"joints":[47],"with":[48],"hidden,":[49],"proprietary":[50],"control":[51,68,157],"loops":[52],"and":[53,80,101,149,163,187,195],"nonlinear":[54],"dynamics.":[55],"To":[56],"bridge":[57],"this":[58,145],"gap,":[59],"we":[60,88,111,125,153],"present":[61],"a":[62,81,127,155],"simulation-to-reality":[63],"framework":[64],"motion":[67,150,197],"that":[69,116,132,191],"integrates":[70],"two":[71],"key":[72],"components:":[73],"an":[74],"equivalent":[75,113],"torque-space":[76],"PID":[77,114],"neural":[82],"network-based":[83],"inverse":[84,129],"kinematics":[85,130],"method.":[86],"First,":[87],"perform":[89],"system":[90],"identification":[91],"physical":[94,169],"analyzing":[97],"step":[98],"response":[99],"data":[100],"computing":[102],"ground-truth":[103],"joint":[104,120,142],"torques":[105],"via":[106,159],"Lagrangian":[107],"dynamics,":[108],"from":[109],"which":[110],"estimate":[112],"parameters":[115],"replicate":[117],"real":[119],"dynamics":[121],"in":[122,161,205],"simulation.":[123],"Second,":[124],"design":[126],"learnable":[128],"module":[131],"maps":[133],"human":[134],"motion,":[135],"represented":[136],"end-effector":[138],"trajectories,":[139],"into":[140],"robot-executable":[141],"commands.":[143],"Using":[144],"high-fidelity":[146],"simulation":[147],"environment":[148],"retargeting":[151],"pipeline,":[152],"train":[154],"policy":[158],"RL":[160],"IsaacLab":[162],"deploy":[164],"it":[165],"directly":[166],"without":[172],"any":[173],"fine-tuning.":[174],"Experimental":[175],"results":[176],"demonstrate":[177],"successful":[178],"reproduction":[179],"of":[180],"diverse":[181],"human-like":[182],"motions,":[183],"including":[184],"waving,":[185],"squatting,":[186],"bimanual":[188],"coordination,":[189],"validating":[190],"accurate":[192],"modeling":[194],"structured":[196],"representation":[198],"are":[199],"essential":[200],"reliable":[202],"transfer":[204],"learning-based":[206],"control.":[208],"(Supplementary":[209],"video":[210],"link:":[211],"https://youtu.be/zLWXgGZQAFk).":[212]},"counts_by_year":[],"updated_date":"2026-03-21T06:30:42.041108","created_date":"2026-03-14T00:00:00"}
