{"id":"https://openalex.org/W4383108320","doi":"https://doi.org/10.1109/icra48891.2023.10160390","title":"VQA-based Robotic State Recognition Optimized with Genetic Algorithm","display_name":"VQA-based Robotic State Recognition Optimized with Genetic Algorithm","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108320","doi":"https://doi.org/10.1109/icra48891.2023.10160390"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/A5087094940","display_name":"Kento Kawaharazuka","orcid":"https://orcid.org/0000-0002-7464-7187"},"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":true,"raw_author_name":"Kento Kawaharazuka","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano-Informatics,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano-Informatics,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048932127","display_name":"Yoshiki Obinata","orcid":"https://orcid.org/0000-0003-1429-4401"},"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":"Yoshiki Obinata","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano-Informatics,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano-Informatics,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050690629","display_name":"Naoaki Kanazawa","orcid":"https://orcid.org/0009-0002-3527-3087"},"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":"Naoaki Kanazawa","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano-Informatics,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano-Informatics,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101836795","display_name":"Kei Okada","orcid":"https://orcid.org/0000-0001-6606-6692"},"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":"Kei Okada","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano-Informatics,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano-Informatics,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047218430","display_name":"Masayuki Inaba","orcid":"https://orcid.org/0000-0003-1273-1567"},"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":"Masayuki Inaba","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano-Informatics,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano-Informatics,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5087094940"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":2.7164,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.92094275,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8306","last_page":"8311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8166652917861938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6751543283462524},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.601099967956543},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5971062183380127},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4771375358104706},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.44483277201652527},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4190288782119751},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.41541358828544617},{"id":"https://openalex.org/keywords/genetic-algorithm","display_name":"Genetic algorithm","score":0.4138690233230591},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34601929783821106},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3359941840171814},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3221941590309143},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2263372838497162}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8166652917861938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6751543283462524},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.601099967956543},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5971062183380127},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4771375358104706},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.44483277201652527},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4190288782119751},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.41541358828544617},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.4138690233230591},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34601929783821106},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3359941840171814},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3221941590309143},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2263372838497162},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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":18,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W1979174748","https://openalex.org/W2026311529","https://openalex.org/W2109042184","https://openalex.org/W2345238407","https://openalex.org/W2540400161","https://openalex.org/W2811089878","https://openalex.org/W3038288066","https://openalex.org/W3091891304","https://openalex.org/W3166396011","https://openalex.org/W4221167444","https://openalex.org/W4281633595","https://openalex.org/W6644923555","https://openalex.org/W6676279030","https://openalex.org/W6704906208","https://openalex.org/W6791353385","https://openalex.org/W6809938868","https://openalex.org/W6839015040"],"related_works":["https://openalex.org/W2168627904","https://openalex.org/W2515552481","https://openalex.org/W156769215","https://openalex.org/W1570348318","https://openalex.org/W2015444353","https://openalex.org/W3013494979","https://openalex.org/W4308101915","https://openalex.org/W2102726926","https://openalex.org/W3194047734","https://openalex.org/W2251005117"],"abstract_inverted_index":{"State":[0],"recognition":[1,41,71,96,111],"of":[2,94,109,120,137,144,151,158],"objects":[3],"and":[4,28,91,141,155],"environment":[5],"in":[6,11,34,49,72,103],"robots":[7],"has":[8],"been":[9,162],"conducted":[10],"various":[12,82],"ways.":[13],"In":[14,32],"most":[15],"cases,":[16],"this":[17,35],"is":[18,64],"executed":[19],"by":[20],"processing":[21],"point":[22],"clouds,":[23],"learning":[24],"images":[25],"with":[26],"annotations,":[27],"using":[29,61,112,122],"specialized":[30],"sensors.":[31],"contrast,":[33],"study,":[36],"we":[37,114],"propose":[38],"a":[39,50,57,123,138,145,152],"state":[40,70,95,110,157],"method":[42],"that":[43,128],"applies":[44],"Visual":[45],"Question":[46],"Answering":[47],"(VQA)":[48],"Pre-Trained":[51],"Vision-Language":[52],"Model":[53],"(PTVLM)":[54],"trained":[55],"from":[56],"large-scale":[58],"dataset.":[59],"By":[60],"VQA,":[62,113],"it":[63],"possible":[65,83],"to":[66,85,105,164],"intuitively":[67],"describe":[68],"robotic":[69],"the":[73,77,88,92,100,107,135,142,149,156],"spoken":[74],"language.":[75],"On":[76],"other":[78],"hand,":[79],"there":[80],"are":[81],"ways":[84],"ask":[86],"about":[87],"same":[89],"event,":[90],"performance":[93,108],"differs":[97],"depending":[98],"on":[99],"question.":[101],"Therefore,":[102],"order":[104],"improve":[106],"search":[115],"for":[116],"an":[117],"appropriate":[118],"combination":[119],"questions":[121],"genetic":[124],"algorithm.":[125],"We":[126],"show":[127],"our":[129],"system":[130],"can":[131],"recognize":[132],"not":[133],"only":[134],"open/closed":[136,150],"refrigerator":[139],"door":[140,154],"on/off":[143],"display,":[146],"but":[147],"also":[148],"transparent":[153],"water,":[159],"which":[160],"have":[161],"difficult":[163],"recognize.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
