{"id":"https://openalex.org/W4415251416","doi":"https://doi.org/10.1109/arso68304.2026.11536111","title":"Bi-VLA: Bilateral Control-Based Imitation Learning via Vision-Language Fusion for Action Generation","display_name":"Bi-VLA: Bilateral Control-Based Imitation Learning via Vision-Language Fusion for Action Generation","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W4415251416","doi":"https://doi.org/10.1109/arso68304.2026.11536111"},"language":"en","primary_location":{"id":"doi:10.1109/arso68304.2026.11536111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/arso68304.2026.11536111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Advanced Robotics and its Social Impacts (ARSO)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.18865","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022934757","display_name":"Masato Kobayashi","orcid":"https://orcid.org/0000-0001-9703-2858"},"institutions":[{"id":"https://openalex.org/I14314212","display_name":"Osaka University of Economics","ror":"https://ror.org/04g11bp59","country_code":"JP","type":"education","lineage":["https://openalex.org/I14314212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Kobayashi","raw_affiliation_strings":["The University of Osaka,D3 Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Osaka,D3 Center","institution_ids":["https://openalex.org/I14314212"]}]},{"author_position":"last","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":["Graduate School of Information Science and Technology, The University of Osaka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Osaka","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00725721,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"225","last_page":"230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9987999796867371,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976000189781189,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9569000005722046,"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/task","display_name":"Task (project management)","score":0.6517000198364258},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6208000183105469},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5443999767303467},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5220000147819519},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.445499986410141},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.37389999628067017},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3684000074863434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6789000034332275},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6517000198364258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6309000253677368},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6208000183105469},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5443999767303467},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5220000147819519},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.445499986410141},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38359999656677246},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3379000127315521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32350000739097595},{"id":"https://openalex.org/C137878579","wikidata":"https://www.wikidata.org/wiki/Q9636076","display_name":"Joint attention","level":3,"score":0.3140000104904175},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.287200003862381},{"id":"https://openalex.org/C34868163","wikidata":"https://www.wikidata.org/wiki/Q5141211","display_name":"Cognitive imitation","level":3,"score":0.2784999907016754},{"id":"https://openalex.org/C2777379011","wikidata":"https://www.wikidata.org/wiki/Q938545","display_name":"Implicit learning","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2653000056743622},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.25040000677108765}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/arso68304.2026.11536111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/arso68304.2026.11536111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Advanced Robotics and its Social Impacts (ARSO)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.18865","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.18865","pdf_url":"https://arxiv.org/pdf/2509.18865","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.18865","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.18865","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.18865","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.18865","pdf_url":"https://arxiv.org/pdf/2509.18865","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"We":[0,82],"propose":[1],"Bilateral":[2],"Control-Based":[3],"Imitation":[4],"Learning":[5],"via":[6],"Vision-Language":[7],"Fusion":[8],"for":[9,43],"Action":[10],"Generation":[11],"(Bi-VLA),":[12],"a":[13,29],"novel":[14],"framework":[15],"that":[16,103,135],"extends":[17],"bilateral":[18,33,68,117,129],"control-based":[19,118],"imitation":[20,119],"learning":[21],"to":[22,115],"handle":[23],"more":[24],"than":[25],"one":[26,89],"task":[27,87,111],"within":[28],"single":[30],"model.":[31],"Conventional":[32],"control":[34,69],"methods":[35],"exploit":[36],"joint":[37,60],"angle,":[38,61],"velocity,":[39,62],"torque,":[40],"and":[41,63,73,79,94,109,131,138],"vision":[42,137],"precise":[44],"manipulation":[45],"but":[46],"require":[47],"task-specific":[48],"models,":[49],"limiting":[50],"their":[51],"generality.":[52],"Bi-VLA":[53,84,104,122,149],"overcomes":[54],"this":[55],"limitation":[56,126],"by":[57,98],"utilizing":[58],"robot":[59],"torque":[64],"data":[65],"from":[66],"leader-follower":[67],"with":[70],"visual":[71],"features":[72],"natural":[74],"language":[75,92,139],"instructions":[76],"through":[77],"SigLIP":[78],"FiLM-based":[80],"fusion.":[81],"validated":[83],"on":[85],"two":[86],"types:":[88],"requiring":[90],"supplementary":[91],"cues":[93],"another":[95],"distinguishable":[96],"solely":[97],"vision.":[99],"Real-robot":[100],"experiments":[101],"showed":[102],"successfully":[105],"interprets":[106],"vision-language":[107],"combinations":[108],"improves":[110],"success":[112],"rates":[113],"compared":[114],"conventional":[116],"learning.":[120],"Our":[121],"addresses":[123],"the":[124,146,158],"single-task":[125],"of":[127,148],"prior":[128],"approaches":[130],"provides":[132],"empirical":[133],"evidence":[134],"combining":[136],"significantly":[140],"enhances":[141],"versatility.":[142],"Experimental":[143],"results":[144],"validate":[145],"effectiveness":[147],"in":[150],"real-world":[151],"tasks.":[152],"For":[153],"additional":[154],"material,":[155],"please":[156],"visit":[157],"website:":[159],"https://mertcookimg.github.io/bi-vla/":[160]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-16T00:00:00"}