{"id":"https://openalex.org/W4415821490","doi":"https://doi.org/10.1109/ro-man63969.2025.11217852","title":"Bi-LAT: Bilateral Control-Based Imitation Learning via Natural Language and Action Chunking with Transformers","display_name":"Bi-LAT: Bilateral Control-Based Imitation Learning via Natural Language and Action Chunking with Transformers","publication_year":2025,"publication_date":"2025-08-25","ids":{"openalex":"https://openalex.org/W4415821490","doi":"https://doi.org/10.1109/ro-man63969.2025.11217852"},"language":null,"primary_location":{"id":"doi:10.1109/ro-man63969.2025.11217852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man63969.2025.11217852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","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/A5103144110","display_name":"Takumi Kobayashi","orcid":"https://orcid.org/0000-0002-4932-3607"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takumi Kobayashi","raw_affiliation_strings":["The University of Osaka,Graduate School of Information Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Osaka,Graduate School of Information Science and Technology","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022934757","display_name":"Masato Kobayashi","orcid":"https://orcid.org/0000-0001-9703-2858"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Kobayashi","raw_affiliation_strings":["The University of Osaka,Graduate School of Information Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Osaka,Graduate School of Information Science and Technology","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093836217","display_name":"Thanpimon Buamanee","orcid":null},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Thanpimon Buamanee","raw_affiliation_strings":["The University of Osaka,Graduate School of Information Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Osaka,Graduate School of Information Science and Technology","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056350914","display_name":"Yuki Uranishi","orcid":"https://orcid.org/0000-0001-6027-0334"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Uranishi","raw_affiliation_strings":["The University of Osaka,Graduate School of Information Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Osaka,Graduate School of Information Science and Technology","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98285908"],"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":"1609","last_page":"1616"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.761900007724762,"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":0.761900007724762,"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/T10982","display_name":"Motor Control and Adaptation","score":0.1306000053882599,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.026799999177455902,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.5971999764442444},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.5163000226020813},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.48809999227523804},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.460099995136261},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.45249998569488525},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4171000123023987},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.37790000438690186},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.3596999943256378},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.3517000079154968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6819999814033508},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.5971999764442444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5286999940872192},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.5163000226020813},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4627000093460083},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45249998569488525},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4171000123023987},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3596999943256378},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.3517000079154968},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C161759796","wikidata":"https://www.wikidata.org/wiki/Q3982902","display_name":"Teleoperation","level":3,"score":0.3443000018596649},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C34868163","wikidata":"https://www.wikidata.org/wiki/Q5141211","display_name":"Cognitive imitation","level":3,"score":0.32170000672340393},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3075000047683716},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3034999966621399},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2881999909877777},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C107953548","wikidata":"https://www.wikidata.org/wiki/Q1172433","display_name":"Wired glove","level":3,"score":0.27070000767707825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man63969.2025.11217852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man63969.2025.11217852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","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":20,"referenced_works":["https://openalex.org/W2096323098","https://openalex.org/W2102279668","https://openalex.org/W2962764994","https://openalex.org/W3204498073","https://openalex.org/W4213417100","https://openalex.org/W4214501175","https://openalex.org/W4312234379","https://openalex.org/W4385430674","https://openalex.org/W4390729586","https://openalex.org/W4390873312","https://openalex.org/W4400770903","https://openalex.org/W4401417048","https://openalex.org/W4401751184","https://openalex.org/W4402673453","https://openalex.org/W4403534685","https://openalex.org/W4403918530","https://openalex.org/W4405785482","https://openalex.org/W4405787555","https://openalex.org/W4407449452","https://openalex.org/W4412886823"],"related_works":[],"abstract_inverted_index":{"We":[0,77],"present":[1],"Bi-LAT,":[2],"a":[3,63],"novel":[4],"imitation":[5,137],"learning":[6],"framework":[7],"that":[8,102,110],"unifies":[9],"bilateral":[10],"control":[11],"with":[12],"natural":[13,133],"language":[14,95,124,134],"processing":[15],"to":[16,42,69],"achieve":[17],"precise":[18],"force":[19,72,92,105,116],"modulation":[20],"in":[21,74,81],"robotic":[22],"manipulation.":[23],"Bi-LAT":[24,67,111],"leverages":[25],"joint":[26],"position,":[27],"velocity,":[28],"and":[29,39,97,145],"torque":[30],"data":[31],"from":[32],"leader-follower":[33],"teleoperation":[34],"while":[35],"also":[36],"integrating":[37,132],"visual":[38],"linguistic":[40],"cues":[41,135],"dynamically":[43],"adjust":[44],"applied":[45],"force.":[46],"By":[47],"encoding":[48],"human":[49],"instructions":[50],"such":[51],"as":[52],"\"softly":[53],"grasp":[54,91],"the":[55,60,87,114,129,140,154],"cup\"":[56],"or":[57],"\"strongly":[58],"twist":[59],"sponge\"":[61],"through":[62],"multimodal":[64],"Transformer-based":[65],"model,":[66],"learns":[68],"distinguish":[70],"nuanced":[71],"requirements":[73],"real-world":[75],"tasks.":[76],"demonstrate":[78,128],"Bi-LAT\u2019s":[79],"performance":[80],"(1)":[82],"unimanual":[83],"cup-stacking":[84],"scenario":[85],"where":[86],"robot":[88],"accurately":[89],"modulates":[90],"based":[93],"on":[94],"commands,":[96],"(2)":[98],"bimanual":[99],"sponge-twisting":[100],"task":[101],"requires":[103],"coordinated":[104],"control.":[106],"Experimental":[107],"results":[108],"show":[109],"effectively":[112],"reproduces":[113],"instructed":[115],"levels,":[117],"particularly":[118],"when":[119],"incorporating":[120],"SigLIP":[121],"among":[122],"tested":[123],"encoders.":[125],"Our":[126],"findings":[127],"potential":[130],"of":[131],"into":[136],"learning,":[138],"paving":[139],"way":[141],"for":[142],"more":[143],"intuitive":[144],"adaptive":[146],"human\u2013robot":[147],"interaction.":[148],"For":[149],"additional":[150],"material,":[151],"please":[152],"visit":[153],"website:":[155],"https://mertcookimg.github.io/bi-lat/":[156]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-03T00:00:00"}