{"id":"https://openalex.org/W4390480920","doi":"https://doi.org/10.1109/humanoids57100.2023.10375239","title":"Daily Assistive View Control Learning of Low-Cost Low-Rigidity Robot via Large-Scale Vision-Language Model","display_name":"Daily Assistive View Control Learning of Low-Cost Low-Rigidity Robot via Large-Scale Vision-Language Model","publication_year":2023,"publication_date":"2023-12-12","ids":{"openalex":"https://openalex.org/W4390480920","doi":"https://doi.org/10.1109/humanoids57100.2023.10375239"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids57100.2023.10375239","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/humanoids57100.2023.10375239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE-RAS 22nd International Conference on Humanoid Robots (Humanoids)","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/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/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/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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18228331,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9937999844551086,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9916999936103821,"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/computer-science","display_name":"Computer science","score":0.7304481863975525},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7068390250205994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6504421234130859},{"id":"https://openalex.org/keywords/rigidity","display_name":"Rigidity (electromagnetism)","score":0.5148579478263855},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48375678062438965},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.477705717086792},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.47512418031692505},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45904937386512756},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.456143856048584},{"id":"https://openalex.org/keywords/social-robot","display_name":"Social robot","score":0.4147569537162781},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.38630372285842896},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13250413537025452},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08027127385139465}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7304481863975525},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7068390250205994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6504421234130859},{"id":"https://openalex.org/C160343418","wikidata":"https://www.wikidata.org/wiki/Q185256","display_name":"Rigidity (electromagnetism)","level":2,"score":0.5148579478263855},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48375678062438965},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.477705717086792},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.47512418031692505},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45904937386512756},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.456143856048584},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.4147569537162781},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.38630372285842896},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13250413537025452},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08027127385139465},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids57100.2023.10375239","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/humanoids57100.2023.10375239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE-RAS 22nd International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1980287119","https://openalex.org/W2025412857","https://openalex.org/W2026093575","https://openalex.org/W2096268286","https://openalex.org/W2163267929","https://openalex.org/W2409009991","https://openalex.org/W2498917392","https://openalex.org/W2767706754","https://openalex.org/W2950697717","https://openalex.org/W2962716343","https://openalex.org/W2965291511","https://openalex.org/W3106763053","https://openalex.org/W3166396011","https://openalex.org/W4200395103","https://openalex.org/W4221167444","https://openalex.org/W4383108296","https://openalex.org/W4383108320","https://openalex.org/W6631190155","https://openalex.org/W6704906208","https://openalex.org/W6791353385","https://openalex.org/W6801810553","https://openalex.org/W6809938868","https://openalex.org/W6846310961"],"related_works":["https://openalex.org/W1886477626","https://openalex.org/W2762381663","https://openalex.org/W4385196987","https://openalex.org/W1540467731","https://openalex.org/W2108809812","https://openalex.org/W218732962","https://openalex.org/W2175869054","https://openalex.org/W2724299411","https://openalex.org/W2164234705","https://openalex.org/W2175714038"],"abstract_inverted_index":{"In":[0],"this":[1,105],"study,":[2],"we":[3,46],"develop":[4],"a":[5,28,44,48,54,72,95],"simple":[6],"daily":[7,23],"assistive":[8],"robot":[9,20,57,116],"that":[10],"controls":[11],"its":[12],"own":[13],"vision":[14],"according":[15],"to":[16],"linguistic":[17],"instructions.":[18],"The":[19,59],"performs":[21],"several":[22],"tasks":[24],"such":[25,43],"as":[26],"recording":[27],"user's":[29],"face,":[30],"hands,":[31],"or":[32],"screen,":[33],"and":[34,65,75,86],"remotely":[35],"capturing":[36],"images":[37],"of":[38,104],"desired":[39],"locations.":[40],"To":[41],"construct":[42],"robot,":[45],"combine":[47],"pretrained":[49],"large-scale":[50],"vision-language":[51],"model":[52],"with":[53,113],"low-cost":[55],"low-rigidity":[56],"arm.":[58],"correlation":[60],"between":[61],"the":[62,78,102],"robot's":[63],"physical":[64],"visual":[66],"information":[67],"is":[68,94],"learned":[69],"probabilistically":[70],"using":[71],"neural":[73],"network,":[74],"changes":[76,83],"in":[77,84],"probability":[79],"distribution":[80],"based":[81],"on":[82],"time":[85],"environment":[87],"are":[88],"considered":[89],"by":[90,108],"parametric":[91],"bias,":[92],"which":[93],"learnable":[96],"network":[97],"input":[98],"variable.":[99],"We":[100],"demonstrate":[101],"effectiveness":[103],"learning":[106],"method":[107],"open-vocabulary":[109],"view":[110],"control":[111],"experiments":[112],"an":[114],"actual":[115],"arm,":[117],"MyCobot.":[118]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}