{"id":"https://openalex.org/W4400131926","doi":"https://doi.org/10.1080/01691864.2024.2366995","title":"Robotic environmental state recognition with pre-trained vision-language models and black-box optimization","display_name":"Robotic environmental state recognition with pre-trained vision-language models and black-box optimization","publication_year":2024,"publication_date":"2024-06-28","ids":{"openalex":"https://openalex.org/W4400131926","doi":"https://doi.org/10.1080/01691864.2024.2366995"},"language":"en","primary_location":{"id":"doi:10.1080/01691864.2024.2366995","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1080/01691864.2024.2366995","pdf_url":null,"source":{"id":"https://openalex.org/S192584203","display_name":"Advanced Robotics","issn_l":"0169-1864","issn":["0169-1864","1568-5535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.17519","any_repository_has_fulltext":true},"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":["The Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","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":["The Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","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":["The Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","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":["The Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","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":["The Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08784921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9911999702453613,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9911999702453613,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9765999913215637,"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":0.9747999906539917,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.7148401737213135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5884508490562439},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5724735260009766},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.49499863386154175},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4635303318500519},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4358077347278595},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4216506779193878}],"concepts":[{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.7148401737213135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5884508490562439},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5724735260009766},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.49499863386154175},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4635303318500519},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4358077347278595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4216506779193878},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/01691864.2024.2366995","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1080/01691864.2024.2366995","pdf_url":null,"source":{"id":"https://openalex.org/S192584203","display_name":"Advanced Robotics","issn_l":"0169-1864","issn":["0169-1864","1568-5535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Robotics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2409.17519","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.17519","pdf_url":"https://arxiv.org/pdf/2409.17519","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.17519","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.17519","pdf_url":"https://arxiv.org/pdf/2409.17519","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.6600000262260437,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400131926.pdf"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1985428381","https://openalex.org/W2026311529","https://openalex.org/W2109042184","https://openalex.org/W2540400161","https://openalex.org/W2766093809","https://openalex.org/W3038288066","https://openalex.org/W3091891304","https://openalex.org/W4383108296","https://openalex.org/W4383108320","https://openalex.org/W4386071707","https://openalex.org/W4390480939","https://openalex.org/W4392667247","https://openalex.org/W4395097844","https://openalex.org/W6676279030"],"related_works":["https://openalex.org/W2047881532","https://openalex.org/W2285795935","https://openalex.org/W4389072557","https://openalex.org/W4319452366","https://openalex.org/W4293695278","https://openalex.org/W3013663659","https://openalex.org/W2727407240","https://openalex.org/W3197218948","https://openalex.org/W2141612310","https://openalex.org/W2994097316"],"abstract_inverted_index":{"In":[0,44,121],"order":[1],"for":[2,15,54],"robots":[3,55],"to":[4,17,38,41,88,155,161,189],"autonomously":[5],"navigate":[6],"and":[7,70,106,151,166,168,175,186],"operate":[8],"in":[9,111],"diverse":[10],"environments,":[11],"it":[12,85,188],"is":[13,86,96,104,109],"essential":[14],"them":[16],"recognize":[18,89],"the":[19,25,28,57,123,134,148,159,170,181,190],"state":[20,30,40,52,145],"of":[21,76,136,172,183],"their":[22],"environment.":[23],"On":[24],"other":[26],"hand,":[27],"environmental":[29,51],"recognition":[31,53,124,191],"has":[32],"traditionally":[33],"involved":[34],"distinct":[35],"methods":[36],"tailored":[37],"each":[39,144],"be":[42,127,156],"recognized.":[43],"this":[45],"study,":[46],"we":[47],"perform":[48],"a":[49,93,101,112,194],"unified":[50],"through":[56],"spoken":[58],"language":[59],"with":[60,82],"pre-trained":[61],"large-scale":[62],"vision-language":[63],"models.":[64],"We":[65,79,178],"apply":[66,187],"Visual":[67],"Question":[68],"Answering":[69],"Image-to-Text":[71],"Retrieval,":[72],"which":[73],"are":[74],"tasks":[75],"Vision-Language":[77],"Models.":[78],"show":[80],"that":[81],"our":[83,184],"method,":[84],"possible":[87],"not":[90],"only":[91,147],"whether":[92,100,107],"room":[94],"door":[95,103],"open/closed,":[97],"but":[98],"also":[99],"transparent":[102],"open/closed":[105],"water":[108],"running":[110],"sink,":[113],"without":[114],"training":[115],"neural":[116],"networks":[117],"or":[118],"manual":[119],"programming.":[120],"addition,":[122],"accuracy":[125],"can":[126],"improved":[128],"by":[129],"selecting":[130],"appropriate":[131],"texts":[132,138],"from":[133],"set":[135,150],"prepared":[137],"based":[139],"on":[140,193],"black-box":[141],"optimization.":[142],"For":[143],"recognition,":[146],"text":[149],"its":[152],"weighting":[153],"need":[154,160],"changed,":[157],"eliminating":[158],"prepare":[162],"multiple":[163],"different":[164],"models":[165],"programs,":[167],"facilitating":[169],"management":[171],"source":[173],"code":[174],"computer":[176],"resource.":[177],"experimentally":[179],"demonstrate":[180],"effectiveness":[182],"method":[185],"behavior":[192],"mobile":[195],"robot,":[196],"Fetch.":[197]},"counts_by_year":[],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}