{"id":"https://openalex.org/W4405785243","doi":"https://doi.org/10.1109/iros58592.2024.10802160","title":"Bridging Language, Vision and Action: Multimodal VAEs in Robotic Manipulation Tasks","display_name":"Bridging Language, Vision and Action: Multimodal VAEs in Robotic Manipulation Tasks","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785243","doi":"https://doi.org/10.1109/iros58592.2024.10802160"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5070799483","display_name":"Gabriela \u0160ejnov\u00e1","orcid":"https://orcid.org/0000-0002-0045-6425"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Gabriela Sejnova","raw_affiliation_strings":["Czech Technical University in Prague,Czech Institute of Informatics, Robotics and Cybernetics,Prague,Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Technical University in Prague,Czech Institute of Informatics, Robotics and Cybernetics,Prague,Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018900043","display_name":"Michal Vavre\u010dka","orcid":"https://orcid.org/0000-0002-0152-2682"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Michal Vavrecka","raw_affiliation_strings":["Czech Technical University in Prague,Czech Institute of Informatics, Robotics and Cybernetics,Prague,Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Technical University in Prague,Czech Institute of Informatics, Robotics and Cybernetics,Prague,Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065125599","display_name":"Karla \u0160t\u011bp\u00e1nov\u00e1","orcid":"https://orcid.org/0000-0003-4239-2092"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Karla Stepanova","raw_affiliation_strings":["Czech Technical University in Prague,Czech Institute of Informatics, Robotics and Cybernetics,Prague,Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Technical University in Prague,Czech Institute of Informatics, Robotics and Cybernetics,Prague,Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I44504214"],"apc_list":null,"apc_paid":null,"fwci":1.0028,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79591692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"12522","last_page":"12528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.941100001335144,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.941100001335144,"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/bridging","display_name":"Bridging (networking)","score":0.8899873495101929},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6977484822273254},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4893574118614197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4731382429599762},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.434452623128891},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41746583580970764},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.328469455242157}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8899873495101929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6977484822273254},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4893574118614197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4731382429599762},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.434452623128891},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41746583580970764},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.328469455242157},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2913737934","https://openalex.org/W2980999634","https://openalex.org/W3003205975","https://openalex.org/W3153832461","https://openalex.org/W3184212829","https://openalex.org/W4206297508","https://openalex.org/W4213299273","https://openalex.org/W4309587412","https://openalex.org/W4383097638","https://openalex.org/W4385473486","https://openalex.org/W4389667233","https://openalex.org/W4391136507","https://openalex.org/W6640963894","https://openalex.org/W6730357551","https://openalex.org/W6748455135","https://openalex.org/W6767441326","https://openalex.org/W6779526176","https://openalex.org/W6779792965","https://openalex.org/W6790812491","https://openalex.org/W6793801364","https://openalex.org/W6798014761","https://openalex.org/W6839459284","https://openalex.org/W6850503672"],"related_works":["https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2272354214","https://openalex.org/W2084768720","https://openalex.org/W2043010663","https://openalex.org/W4248308508"],"abstract_inverted_index":{"In":[0],"this":[1,29],"work,":[2],"we":[3,88,112,132],"focus":[4],"on":[5,78,108,160,180],"unsupervised":[6,99,173],"vision-language-action":[7],"mapping":[8],"in":[9,98,103,123],"the":[10,41,50,60,64,84,109,120,135,161,168],"area":[11],"of":[12,40,52,63,149,166,175],"robotic":[13,100,176],"manipulation.":[14],"Recently,":[15],"multiple":[16],"approaches":[17],"employing":[18],"pre-trained":[19],"large":[20],"language":[21],"and":[22,36,66,91,164,182],"vision":[23,181],"models":[24],"have":[25],"been":[26,75],"proposed":[27],"for":[28,83,172],"task.":[30],"However,":[31],"they":[32],"are":[33],"computationally":[34],"demanding":[35],"require":[37],"careful":[38],"fine-tuning":[39],"produced":[42],"output.":[43],"A":[44],"more":[45],"lightweight":[46],"alter-native":[47],"would":[48],"be":[49,96],"implementation":[51],"multimodal":[53,93,170],"Variational":[54],"Autoencoders":[55],"(VAEs)":[56],"which":[57],"can":[58,95],"extract":[59],"latent":[61],"features":[62],"data":[65,82],"integrate":[67],"them":[68],"into":[69],"a":[70,104,114,124],"joint":[71],"representation,":[72],"as":[73,142],"has":[74],"demonstrated":[76],"mostly":[77],"image-image":[79],"or":[80,144,151],"image-text":[81],"state-of-the-art":[85],"models.":[86],"Here,":[87],"explore":[89],"whether":[90],"how":[92],"VAEs":[94,171],"employed":[97],"manipulation":[101],"tasks":[102],"simulated":[105],"environment.":[106],"Based":[107],"results":[110],"obtained,":[111],"propose":[113],"model-invariant":[115],"training":[116],"alternative":[117],"that":[118],"improves":[119],"models\u2019":[121],"performance":[122],"simulator":[125],"by":[126,138],"up":[127],"to":[128],"55":[129],"%.":[130],"Moreover,":[131],"systematically":[133],"evaluate":[134],"challenges":[136],"raised":[137],"individual":[139],"tasks,":[140],"such":[141],"object":[143],"robot":[145],"position":[146],"variability,":[147],"number":[148],"distractors,":[150],"task":[152],"length.":[153],"Our":[154],"work":[155],"thus":[156],"also":[157],"sheds":[158],"light":[159],"potential":[162],"benefits":[163],"limitations":[165],"using":[167],"current":[169],"learning":[174],"motion":[177],"trajectories":[178],"based":[179],"language.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}
