{"id":"https://openalex.org/W4388623405","doi":"https://doi.org/10.1109/ro-man57019.2023.10309466","title":"VAFOR: Proactive Voice Assistant for Object Retrieval in the Physical World","display_name":"VAFOR: Proactive Voice Assistant for Object Retrieval in the Physical World","publication_year":2023,"publication_date":"2023-08-28","ids":{"openalex":"https://openalex.org/W4388623405","doi":"https://doi.org/10.1109/ro-man57019.2023.10309466"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man57019.2023.10309466","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ro-man57019.2023.10309466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","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/A5021639106","display_name":"Bekatan Satyev","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bekatan Satyev","raw_affiliation_strings":["is an independent researcher in Korea"],"affiliations":[{"raw_affiliation_string":"is an independent researcher in Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053725843","display_name":"Hyemin Ahn","orcid":"https://orcid.org/0000-0001-8081-6023"},"institutions":[{"id":"https://openalex.org/I3130020584","display_name":"International Graduate School of English","ror":"https://ror.org/0181xpd52","country_code":"KR","type":"education","lineage":["https://openalex.org/I3130020584"]},{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyemin Ahn","raw_affiliation_strings":["the Artificial Intelligence Graduate School(AIGS), UNIST,Ulsan,Korea","the Artificial Intelligence Graduate School(AIGS), UNIST, Ulsan, Korea"],"affiliations":[{"raw_affiliation_string":"the Artificial Intelligence Graduate School(AIGS), UNIST,Ulsan,Korea","institution_ids":["https://openalex.org/I3130020584","https://openalex.org/I48566637"]},{"raw_affiliation_string":"the Artificial Intelligence Graduate School(AIGS), UNIST, Ulsan, Korea","institution_ids":["https://openalex.org/I3130020584","https://openalex.org/I48566637"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021639106"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1454985,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"654","last_page":"659"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9957000017166138,"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"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.770744800567627},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7458661198616028},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6608632802963257},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5112545490264893},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5019302368164062},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.47507375478744507},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4670644700527191},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.459381639957428},{"id":"https://openalex.org/keywords/voice-command-device","display_name":"Voice command device","score":0.45303523540496826},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4433956444263458},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38952863216400146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.2567621171474457},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1335439383983612},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10467535257339478}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770744800567627},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7458661198616028},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6608632802963257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5112545490264893},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5019302368164062},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.47507375478744507},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4670644700527191},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.459381639957428},{"id":"https://openalex.org/C178718744","wikidata":"https://www.wikidata.org/wiki/Q2350070","display_name":"Voice command device","level":2,"score":0.45303523540496826},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4433956444263458},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38952863216400146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2567621171474457},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1335439383983612},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10467535257339478},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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":2,"locations":[{"id":"doi:10.1109/ro-man57019.2023.10309466","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ro-man57019.2023.10309466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarworks.unist.ac.kr:201301/66346","is_oa":false,"landing_page_url":"https://scholarworks.unist.ac.kr/handle/201301/66346","pdf_url":null,"source":{"id":"https://openalex.org/S4306401118","display_name":"Scholarworks@UNIST (Ulsan National Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I48566637","host_organization_name":"Ulsan National Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I48566637"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"CONFERENCE"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","score":0.800000011920929,"display_name":"Zero hunger"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2128112149","https://openalex.org/W2413992829","https://openalex.org/W2793662128","https://openalex.org/W3128663629","https://openalex.org/W4221152848","https://openalex.org/W4224912544","https://openalex.org/W4292779060","https://openalex.org/W4293584584","https://openalex.org/W4302305808","https://openalex.org/W6750227808","https://openalex.org/W6778883912","https://openalex.org/W6809509765","https://openalex.org/W6845648307","https://openalex.org/W6877283504"],"related_works":["https://openalex.org/W2357191878","https://openalex.org/W1997078944","https://openalex.org/W1968065688","https://openalex.org/W1552846815","https://openalex.org/W2142945567","https://openalex.org/W2030332364","https://openalex.org/W4221144054","https://openalex.org/W2005459225","https://openalex.org/W4289829835","https://openalex.org/W2604548540"],"abstract_inverted_index":{"In":[0,220],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,11,30,65,130,134,139,147,156,159,177,180,200,230,249],"proactive":[6],"robotic":[7,183],"voice":[8],"assistant":[9],"with":[10,84,179,199,215],"perceive-reason-act":[12,104],"loop":[13,105],"that":[14,48,81,198,225],"carries":[15],"out":[16],"pick-and-place":[17],"operations":[18],"based":[19,233],"on":[20,116,234],"verbal":[21,60,131,151],"commands.":[22],"Unlike":[23],"existing":[24],"systems,":[25],"our":[26,95],"robot":[27,205],"can":[28,82,206],"retrieve":[29],"target":[31,37,76,90,169,187,210],"object":[32,77,91,114,170,188,211],"not":[33],"only":[34],"when":[35,58],"the":[36,51,59,75,89,102,117,126,150,168,172,186,193,204,208,226,235,241,244],"is":[38,62,223],"explicitly":[39],"spelled":[40],"out,":[41],"but":[42],"also":[43],"given":[44],"an":[45,113],"indirect":[46,93],"command":[47,61,132,152],"implicitly":[49],"reflects":[50],"human":[52],"intention":[53],"or":[54],"emotion.":[55],"For":[56],"instance,":[57],"\u201cI":[63],"had":[64],"busy":[66],"day,":[67],"so":[68],"I":[69],"didn\u2019t":[70],"have":[71],"much":[72],"to":[73,121,166,192],"eat.\u201d,":[74],"would":[78],"be":[79],"something":[80],"help":[83],"hunger.":[85],"To":[86],"successfully":[87],"estimate":[88],"from":[92,133,212],"commands,":[94],"framework":[96],"consists":[97],"of":[98,141,149,228,243,251],"separate":[99],"modules":[100],"for":[101,109,137,158,175],"complete":[103],"as":[106,144,146],"follows.":[107],"First,":[108],"perception,":[110],"it":[111,191,222],"runs":[112],"detector":[115],"robot\u2019s":[118],"onboard":[119],"computer":[120],"detect":[122],"all":[123],"objects":[124,143],"in":[125,164,171],"surroundings":[127],"and":[128,189,255],"records":[129],"microphone.":[135],"Second,":[136],"reasoning,":[138],"list":[140],"available":[142,258],"well":[145],"transcription":[148],"are":[153,257],"integrated":[154],"into":[155],"prompt":[157,237],"Large":[160],"Language":[161],"Model":[162],"(LLM)":[163],"order":[165],"identify":[167,207],"command.":[173],"Finally,":[174],"action,":[176],"TurtleBot3":[178],"5":[181],"DOF":[182],"arm":[184],"finds":[185],"brings":[190],"human.":[194],"Our":[195,253],"experiments":[196],"show":[197],"properly":[201],"designed":[202],"prompt,":[203],"correct":[209],"implicit":[213],"commands":[214],"at":[216,259],"most":[217],"97%":[218],"accuracy.":[219],"addition,":[221],"shown":[224],"technique":[227],"fine-tuning":[229],"language":[231,246],"model":[232,247],"proposed":[236],"designing":[238],"process":[239],"amplifies":[240],"performance":[242],"smallest":[245],"by":[248],"factor":[250],"five.":[252],"data":[254],"code":[256],"https://github.com/bekatan/vafor":[260]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}