{"id":"https://openalex.org/W2962716343","doi":"https://doi.org/10.1109/icra.2018.8460699","title":"Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions","display_name":"Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2962716343","doi":"https://doi.org/10.1109/icra.2018.8460699","mag":"2962716343"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2018.8460699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8460699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","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/A5076807302","display_name":"Jun Hatori","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166566","display_name":"Preferred Networks (Japan)","ror":"https://ror.org/05xeefy56","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210166566"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jun Hatori","raw_affiliation_strings":["Preferred Networks, Inc"],"affiliations":[{"raw_affiliation_string":"Preferred Networks, Inc","institution_ids":["https://openalex.org/I4210166566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034125752","display_name":"Yuta Kikuchi","orcid":"https://orcid.org/0000-0002-1802-5260"},"institutions":[{"id":"https://openalex.org/I4210166566","display_name":"Preferred Networks (Japan)","ror":"https://ror.org/05xeefy56","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210166566"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuta Kikuchi","raw_affiliation_strings":["Preferred Networks, Inc"],"affiliations":[{"raw_affiliation_string":"Preferred Networks, Inc","institution_ids":["https://openalex.org/I4210166566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112876488","display_name":"Sosuke Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166566","display_name":"Preferred Networks (Japan)","ror":"https://ror.org/05xeefy56","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210166566"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sosuke Kobayashi","raw_affiliation_strings":["Preferred Networks, Inc"],"affiliations":[{"raw_affiliation_string":"Preferred Networks, Inc","institution_ids":["https://openalex.org/I4210166566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085499213","display_name":"Kuniyuki Takahashi","orcid":"https://orcid.org/0000-0001-7912-4134"},"institutions":[{"id":"https://openalex.org/I4210166566","display_name":"Preferred Networks (Japan)","ror":"https://ror.org/05xeefy56","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210166566"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kuniyuki Takahashi","raw_affiliation_strings":["Preferred Networks, Inc"],"affiliations":[{"raw_affiliation_string":"Preferred Networks, Inc","institution_ids":["https://openalex.org/I4210166566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020740517","display_name":"Yuta Tsuboi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166566","display_name":"Preferred Networks (Japan)","ror":"https://ror.org/05xeefy56","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210166566"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuta Tsuboi","raw_affiliation_strings":["Preferred Networks, Inc"],"affiliations":[{"raw_affiliation_string":"Preferred Networks, Inc","institution_ids":["https://openalex.org/I4210166566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041236481","display_name":"Yuya Unno","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166566","display_name":"Preferred Networks (Japan)","ror":"https://ror.org/05xeefy56","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210166566"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuya Unno","raw_affiliation_strings":["Preferred Networks, Inc"],"affiliations":[{"raw_affiliation_string":"Preferred Networks, Inc","institution_ids":["https://openalex.org/I4210166566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010520720","display_name":"Wilson Ko","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166566","display_name":"Preferred Networks (Japan)","ror":"https://ror.org/05xeefy56","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210166566"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wilson Ko","raw_affiliation_strings":["Preferred Networks, Inc"],"affiliations":[{"raw_affiliation_string":"Preferred Networks, Inc","institution_ids":["https://openalex.org/I4210166566"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016566504","display_name":"Jethro Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166566","display_name":"Preferred Networks (Japan)","ror":"https://ror.org/05xeefy56","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210166566"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jethro Tan","raw_affiliation_strings":["Preferred Networks, Inc"],"affiliations":[{"raw_affiliation_string":"Preferred Networks, Inc","institution_ids":["https://openalex.org/I4210166566"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5076807302"],"corresponding_institution_ids":["https://openalex.org/I4210166566"],"apc_list":null,"apc_paid":null,"fwci":8.0747,"has_fulltext":false,"cited_by_count":174,"citation_normalized_percentile":{"value":0.98136147,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3774","last_page":"3781"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9952999949455261,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9900000095367432,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8623862862586975},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.8096882104873657},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.7176175117492676},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.6991230249404907},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6449240446090698},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6107704639434814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6104745268821716},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6048120260238647},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5353729128837585},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5204225182533264},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5074545741081238},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5048516392707825},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.49673181772232056},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4420514404773712},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14586955308914185},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.071714848279953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8623862862586975},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.8096882104873657},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7176175117492676},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6991230249404907},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6449240446090698},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6107704639434814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6104745268821716},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6048120260238647},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5353729128837585},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5204225182533264},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5074545741081238},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5048516392707825},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.49673181772232056},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4420514404773712},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14586955308914185},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.071714848279953},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2018.8460699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8460699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1527575280","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W2015013512","https://openalex.org/W2031489346","https://openalex.org/W2066624635","https://openalex.org/W2108598243","https://openalex.org/W2123024445","https://openalex.org/W2144960104","https://openalex.org/W2171361956","https://openalex.org/W2194775991","https://openalex.org/W2240541372","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2296334766","https://openalex.org/W2474390746","https://openalex.org/W2479423890","https://openalex.org/W2489434015","https://openalex.org/W2563399268","https://openalex.org/W2571175805","https://openalex.org/W2736923367","https://openalex.org/W2737607256","https://openalex.org/W2953062165","https://openalex.org/W2963758027","https://openalex.org/W2964284374","https://openalex.org/W3106250896","https://openalex.org/W6620707391","https://openalex.org/W6631516269","https://openalex.org/W6639102338","https://openalex.org/W6640773114","https://openalex.org/W6654406822","https://openalex.org/W6676297131","https://openalex.org/W6678470764","https://openalex.org/W6681075545","https://openalex.org/W6685230081","https://openalex.org/W6687483927","https://openalex.org/W6690082500","https://openalex.org/W6691231616","https://openalex.org/W6691503852","https://openalex.org/W6721769334","https://openalex.org/W6723035356","https://openalex.org/W6724784328","https://openalex.org/W6741230357","https://openalex.org/W6764969349","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W4382791734","https://openalex.org/W1516679419","https://openalex.org/W190396239","https://openalex.org/W2104168095","https://openalex.org/W3174008653","https://openalex.org/W2765804957","https://openalex.org/W2962716343","https://openalex.org/W4288099861","https://openalex.org/W2893411096","https://openalex.org/W4224919006"],"abstract_inverted_index":{"Comprehension":[0],"of":[1,32,42,121,138],"spoken":[2,19,36,59,69,87],"natural":[3,80,126],"language":[4,81],"is":[5,21,62],"an":[6,147],"essential":[7],"skill":[8],"for":[9,54,93],"robots":[10,56,94],"to":[11,24,64,84,95,124],"communicate":[12],"with":[13,57,79],"humans":[14],"effectively.":[15],"However,":[16],"handling":[17],"unconstrained":[18,58,86],"instructions":[20,127],"challenging":[22],"due":[23],"(1)":[25],"complex":[26],"structures":[27],"and":[28,38,89,132],"the":[29,50,119,139],"wide":[30],"variety":[31],"expressions":[33],"used":[34],"in":[35,68],"language,":[37,60],"(2)":[39],"inherent":[40],"ambiguity":[41,67,98],"human":[43,129],"instructions.":[44,70],"In":[45],"this":[46],"paper,":[47],"we":[48,72,117],"propose":[49,90],"first":[51],"comprehensive":[52],"system":[53,123],"controlling":[55],"which":[61],"able":[63],"effectively":[65],"resolve":[66,96],"Specifically,":[71],"integrate":[73],"deep":[74],"learning-based":[75],"object":[76,140],"detection":[77],"together":[78],"processing":[82],"technologies":[83],"handle":[85],"instructions,":[88],"a":[91,106,112],"method":[92],"instruction":[97],"through":[99,146],"dialogue.":[100],"Through":[101],"our":[102,122],"experiments":[103],"on":[104],"both":[105],"simulated":[107],"environment":[108],"as":[109,111],"well":[110],"physical":[113],"industrial":[114],"robot":[115],"arm,":[116],"demonstrate":[118],"ability":[120],"understand":[125],"from":[128],"operators":[130],"effectively,":[131],"show":[133],"how":[134],"higher":[135],"success":[136],"rates":[137],"picking":[141],"task":[142],"can":[143],"be":[144],"achieved":[145],"interactive":[148],"clarification":[149],"process.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":28},{"year":2021,"cited_by_count":33},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":7}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}