{"id":"https://openalex.org/W3191807689","doi":"https://doi.org/10.1109/iros51168.2021.9636301","title":"Transformer-based deep imitation learning for dual-arm robot manipulation","display_name":"Transformer-based deep imitation learning for dual-arm robot manipulation","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3191807689","doi":"https://doi.org/10.1109/iros51168.2021.9636301","mag":"3191807689"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9636301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636301","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-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/A5102020002","display_name":"Hee\u2010Cheol Kim","orcid":"https://orcid.org/0000-0002-5399-7647"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Heecheol Kim","raw_affiliation_strings":["Laboratory for Intelligent Systems and Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Intelligent Systems and Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019675297","display_name":"Yoshiyuki Ohmura","orcid":"https://orcid.org/0000-0002-9158-5360"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiyuki Ohmura","raw_affiliation_strings":["Laboratory for Intelligent Systems and Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Intelligent Systems and Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010543059","display_name":"Yasuo Kuniyoshi","orcid":"https://orcid.org/0000-0001-8443-4161"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuo Kuniyoshi","raw_affiliation_strings":["Laboratory for Intelligent Systems and Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","Univ.\\ of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Intelligent Systems and Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Univ.\\ of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.3661,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.99625877,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8965","last_page":"8972"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"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":0.9995999932289124,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9911999702453613,"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/computer-science","display_name":"Computer science","score":0.7271732091903687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6847992539405823},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6289924383163452},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6100978255271912},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5821435451507568},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.5625973343849182},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4908798336982727},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4743836224079132},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.4496855139732361},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35209888219833374},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3498973250389099},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15872710943222046},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06483355164527893}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271732091903687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6847992539405823},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6289924383163452},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6100978255271912},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5821435451507568},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.5625973343849182},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4908798336982727},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4743836224079132},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4496855139732361},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35209888219833374},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3498973250389099},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15872710943222046},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06483355164527893},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros51168.2021.9636301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636301","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322832","display_name":"University of Tokyo","ror":"https://ror.org/057zh3y96"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1485260844","https://openalex.org/W1579853615","https://openalex.org/W1799366690","https://openalex.org/W2005870832","https://openalex.org/W2147168033","https://openalex.org/W2558355904","https://openalex.org/W2626792426","https://openalex.org/W2737635200","https://openalex.org/W2805530149","https://openalex.org/W2896457183","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963669336","https://openalex.org/W2968917279","https://openalex.org/W2994689640","https://openalex.org/W3030163527","https://openalex.org/W3032185005","https://openalex.org/W3035422918","https://openalex.org/W3040547430","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3106302274","https://openalex.org/W3111551570","https://openalex.org/W3128000279","https://openalex.org/W3180355996","https://openalex.org/W3209916982","https://openalex.org/W4248990817","https://openalex.org/W4292779060","https://openalex.org/W4385245566","https://openalex.org/W6634817459","https://openalex.org/W6730099494","https://openalex.org/W6739901393","https://openalex.org/W6741545047","https://openalex.org/W6751795147","https://openalex.org/W6767164110","https://openalex.org/W6778485988","https://openalex.org/W6784396901","https://openalex.org/W6784556858"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2658949566"],"abstract_inverted_index":{"Deep":[0],"imitation":[1,92,125],"learning":[2,93,126],"is":[3,88],"promising":[4],"for":[5],"solving":[6],"dexterous":[7],"manipulation":[8,27,34,97,111,143],"tasks":[9,28,98,112],"because":[10],"it":[11],"does":[12],"not":[13],"require":[14],"an":[15],"environment":[16],"model":[17],"and":[18,50,76,141],"pre-programmed":[19],"robot":[20,46],"behavior.":[21],"However,":[22],"its":[23],"application":[24],"to":[25,90,94,130],"dual-arm":[26,33,96,110],"remains":[29],"challenging.":[30],"In":[31],"a":[32,64,73,83,114],"setup,":[35],"the":[36,44,56,100,122,131,135,148,152],"increased":[37],"number":[38],"of":[39,55,85],"state":[40],"dimensions":[41],"caused":[42],"by":[43],"additional":[45],"manipulators":[47],"causes":[48],"distractions":[49,140],"results":[51,119],"in":[52,72,99],"poor":[53],"performance":[54,144],"neural":[57],"networks.":[58],"We":[59],"address":[60],"this":[61],"issue":[62],"using":[63,113],"self-attention":[65,86,153],"mechanism":[66],"that":[67,121],"computes":[68],"dependencies":[69],"between":[70],"elements":[71],"sequential":[74],"input":[75],"focuses":[77],"on":[78,109],"important":[79,132],"elements.":[80],"A":[81],"Transformer,":[82],"variant":[84],"architecture,":[87],"applied":[89],"deep":[91,124],"solve":[95],"real":[101,115],"world.":[102],"The":[103,117],"proposed":[104],"method":[105],"has":[106],"been":[107],"tested":[108],"robot.":[116],"experimental":[118],"demonstrated":[120],"Transformer-based":[123],"architecture":[127,150],"can":[128],"attend":[129],"features":[133],"among":[134],"sensory":[136],"inputs,":[137],"therefore":[138],"reducing":[139],"improving":[142],"when":[145],"compared":[146],"with":[147],"baseline":[149],"without":[151],"mechanisms.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}