{"id":"https://openalex.org/W7138037195","doi":"https://doi.org/10.1609/aaai.v40i34.40127","title":"Learning Diverse Bimanual Dexterous Manipulation Skills from Human Demonstrations","display_name":"Learning Diverse Bimanual Dexterous Manipulation Skills from Human Demonstrations","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138037195","doi":"https://doi.org/10.1609/aaai.v40i34.40127"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i34.40127","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i34.40127","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i34.40127","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102909434","display_name":"Bohan Zhou","orcid":"https://orcid.org/0000-0003-2860-559X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bohan Zhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129745805","display_name":"Haoqi Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoqi Yuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101542257","display_name":"Yuhui Fu","orcid":"https://orcid.org/0000-0002-7487-4857"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhui Fu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129732703","display_name":"Zongqing Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zongqing Lu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102909434"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38636364,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"34","first_page":"28919","last_page":"28927"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.47530001401901245,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.47530001401901245,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.42480000853538513,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.014800000004470348,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6761999726295471},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6057000160217285},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5450000166893005},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4984999895095825},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4763999879360199},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41819998621940613}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6761999726295471},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6057000160217285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5658000111579895},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5450000166893005},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4984999895095825},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4871000051498413},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4189999997615814},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3569999933242798},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.28610000014305115}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i34.40127","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i34.40127","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i34.40127","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i34.40127","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5177001953125}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Bimanual":[0],"dexterous":[1,71,135,148],"manipulation":[2],"is":[3],"a":[4,53,63,81,106,125,162],"critical":[5],"yet":[6],"underexplored":[7],"area":[8],"in":[9,30],"robotics.":[10],"Its":[11],"high-dimensional":[12],"action":[13],"space":[14],"and":[15,25,91,171,185,197,208],"inherent":[16],"task":[17,28,85,163,191],"complexity":[18],"present":[19,62],"significant":[20],"challenges":[21],"for":[22,66],"policy":[23,94],"learning,":[24,43],"the":[26,117,120,206],"limited":[27],"diversity":[29],"existing":[31,88],"benchmarks":[32],"hinders":[33],"general-purpose":[34],"skill":[35],"development.":[36],"Existing":[37],"approaches":[38],"largely":[39],"depend":[40],"on":[41,151,168,173,194,199],"reinforcement":[42],"often":[44],"constrained":[45],"by":[46],"intricately":[47],"designed":[48],"reward":[49,109],"functions":[50],"tailored":[51],"to":[52,96,180],"narrow":[54],"set":[55],"of":[56,132,166,189,213],"tasks.":[57,99,175],"In":[58],"this":[59],"work,":[60],"we":[61,78],"novel":[64],"approach":[65],"efficiently":[67],"learning":[68,95,131],"diverse":[69],"bimanual":[70,89,134,147],"skills":[72,136],"from":[73,87,137],"abundant":[74],"human":[75],"demonstrations.":[76],"Specifically,":[77],"introduce":[79],"BiDexHD,":[80,129],"framework":[82],"that":[83],"unifies":[84],"construction":[86],"datasets":[90],"employs":[92],"teacher-student":[93],"address":[97],"all":[98],"The":[100],"teacher":[101],"learns":[102],"state-based":[103],"policies":[104,123],"using":[105],"general":[107],"two-stage":[108],"function":[110],"across":[111,158],"tasks":[112,139,157,170,184,196],"with":[113],"shared":[114],"behaviors,":[115],"while":[116],"student":[118],"distills":[119],"learned":[121],"multi-task":[122],"into":[124],"vision-based":[126],"policy.":[127],"With":[128],"scalable":[130],"numerous":[133],"auto-constructed":[138],"becomes":[140],"feasible,":[141],"offering":[142],"promising":[143],"advances":[144],"toward":[145],"universal":[146],"manipulation.":[149],"Experiments":[150],"TACO":[152],"tool-using":[153],"dataset":[154],"spanning":[155],"141":[156],"6":[159],"categories":[160],"demonstrate":[161,205],"fulfillment":[164,192],"rate":[165,193],"74.59%":[167],"trained":[169,195],"51.07%":[172],"unseen":[174,200],"We":[176],"further":[177],"transfer":[178],"BiDexHD":[179],"11":[181],"ARCTIC":[182],"collaborative":[183],"achieve":[186],"an":[187],"average":[188],"80.49%":[190],"65.99%":[198],"task.":[201],"All":[202],"empirical":[203],"results":[204],"effectiveness":[207],"competitive":[209],"zero-shot":[210],"generalization":[211],"capabilities":[212],"BiDexHD.":[214]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}