{"id":"https://openalex.org/W4416749727","doi":"https://doi.org/10.1109/iros60139.2025.11246644","title":"Efficient Learning of A Unified Policy For Whole-body Manipulation and Locomotion Skills","display_name":"Efficient Learning of A Unified Policy For Whole-body Manipulation and Locomotion Skills","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749727","doi":"https://doi.org/10.1109/iros60139.2025.11246644"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5050568236","display_name":"Dianyong Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dianyong Hou","raw_affiliation_strings":["Zhejiang University,Institute of Cyber-Systems and Control,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Institute of Cyber-Systems and Control,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103758927","display_name":"Chengrui Zhu","orcid":"https://orcid.org/0009-0000-1837-4586"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengrui Zhu","raw_affiliation_strings":["Zhejiang University,Institute of Cyber-Systems and Control,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Institute of Cyber-Systems and Control,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390201","display_name":"Zhen Zhang","orcid":"https://orcid.org/0000-0003-3031-3350"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Zhang","raw_affiliation_strings":["Zhejiang University,Institute of Cyber-Systems and Control,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Institute of Cyber-Systems and Control,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351565","display_name":"Zhibin Li","orcid":"https://orcid.org/0000-0003-4752-5528"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhibin Li","raw_affiliation_strings":["University College London,Department of Computer Science,London,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London,Department of Computer Science,London,United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112621558","display_name":"Chuang Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuang Guo","raw_affiliation_strings":["Zhejiang University,Institute of Cyber-Systems and Control,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Institute of Cyber-Systems and Control,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100724297","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0003-4822-8939"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology of Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology of Zhejiang University,China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5455","last_page":"5461"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.8845999836921692,"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":0.8845999836921692,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0333000011742115,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.031300000846385956,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7832000255584717},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.6500999927520752},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6366999745368958},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5946000218391418},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4607999920845032},{"id":"https://openalex.org/keywords/local-optimum","display_name":"Local optimum","score":0.45190000534057617},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.38440001010894775}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7832000255584717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6664999723434448},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.6500999927520752},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6366999745368958},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5946000218391418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47929999232292175},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4607999920845032},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3804999887943268},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.3472999930381775},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3391999900341034},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.313400000333786},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.27559998631477356},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C2985527887","wikidata":"https://www.wikidata.org/wiki/Q1587588","display_name":"Robot manipulator","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W134451811","https://openalex.org/W2146633262","https://openalex.org/W2415044741","https://openalex.org/W2575705757","https://openalex.org/W2911087563","https://openalex.org/W2944561196","https://openalex.org/W2951360122","https://openalex.org/W2964198579","https://openalex.org/W3093922502","https://openalex.org/W3142410314","https://openalex.org/W3165789564","https://openalex.org/W4205430897","https://openalex.org/W4214634122","https://openalex.org/W4294280815","https://openalex.org/W4307117577","https://openalex.org/W4376851120","https://openalex.org/W4383108204","https://openalex.org/W4385858056","https://openalex.org/W4388901983","https://openalex.org/W4390938336","https://openalex.org/W4401413688","https://openalex.org/W4405785337"],"related_works":[],"abstract_inverted_index":{"Equipping":[0],"quadruped":[1,123],"robots":[2],"with":[3,51,126],"manipulators":[4],"provides":[5,88],"unique":[6],"loco-manipulation":[7],"capabilities,":[8],"enabling":[9],"diverse":[10],"practical":[11],"applications.":[12],"This":[13,86],"integration":[14,87],"creates":[15],"a":[16,32,70,120,127,145],"more":[17],"complex":[18],"system":[19],"that":[20,73],"has":[21,115],"increased":[22],"difficulties":[23],"in":[24],"modeling":[25],"and":[26,61,106,131],"control.":[27],"Reinforcement":[28],"learning":[29,40],"(RL)":[30],"offers":[31],"promising":[33],"solution":[34,57],"to":[35,97,148],"address":[36],"these":[37,66],"challenges":[38],"by":[39],"optimal":[41],"control":[42],"policies":[43],"through":[44],"interaction.":[45],"Nevertheless,":[46],"RL":[47,84,103],"methods":[48],"often":[49],"struggle":[50],"local":[52,110],"optima":[53,111],"when":[54],"exploring":[55],"large":[56],"spaces":[58],"for":[59],"motion":[60],"manipulation":[62],"tasks.":[63],"To":[64],"overcome":[65],"limitations,":[67],"we":[68],"propose":[69],"novel":[71],"approach":[72],"integrates":[74],"an":[75],"explicit":[76],"kinematic":[77],"model":[78],"of":[79,93,139],"the":[80,83,91,94,98,102,109,136],"manipulator":[81],"into":[82],"framework.":[85],"feedback":[89],"on":[90,119],"mapping":[92],"body":[95],"postures":[96],"manipulator\u2019s":[99],"workspace,":[100],"guiding":[101],"exploration":[104],"process":[105],"effectively":[107],"mitigating":[108],"issue.":[112],"Our":[113],"algorithm":[114],"been":[116],"successfully":[117],"deployed":[118],"DeepRobotics":[121],"X20":[122],"robot":[124],"equipped":[125],"Unitree":[128],"Z1":[129],"manipulator,":[130],"extensive":[132],"experimental":[133],"results":[134],"demonstrate":[135],"superior":[137],"performance":[138],"this":[140],"approach.":[141],"We":[142],"have":[143],"established":[144],"project":[146],"website":[147],"showcase":[149],"our":[150],"experiments.":[151]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}