{"id":"https://openalex.org/W4415822158","doi":"https://doi.org/10.1109/ro-man63969.2025.11217614","title":"A Model-Agnostic Approach for Semantically Driven Disambiguation in Human-Robot Interaction","display_name":"A Model-Agnostic Approach for Semantically Driven Disambiguation in Human-Robot Interaction","publication_year":2025,"publication_date":"2025-08-25","ids":{"openalex":"https://openalex.org/W4415822158","doi":"https://doi.org/10.1109/ro-man63969.2025.11217614"},"language":null,"primary_location":{"id":"doi:10.1109/ro-man63969.2025.11217614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man63969.2025.11217614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5030295286","display_name":"Fethiye Irmak Do\u011fan","orcid":"https://orcid.org/0000-0002-1733-7019"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Fethiye Irmak Dogan","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Stockholm,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039441955","display_name":"Maithili Patel","orcid":"https://orcid.org/0000-0001-8730-9198"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maithili Patel","raw_affiliation_strings":["Georgia Institute of Technology,School of Interactive Computing,Atlanta,Georgia,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Interactive Computing,Atlanta,Georgia,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030754694","display_name":"Weiyu Liu","orcid":"https://orcid.org/0000-0002-2113-5612"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiyu Liu","raw_affiliation_strings":["Georgia Institute of Technology,School of Interactive Computing,Atlanta,Georgia,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Interactive Computing,Atlanta,Georgia,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082559019","display_name":"Iolanda Leite","orcid":"https://orcid.org/0000-0002-2212-4325"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Iolanda Leite","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Stockholm,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033265891","display_name":"Sonia Chernova","orcid":"https://orcid.org/0000-0001-6320-0825"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sonia Chernova","raw_affiliation_strings":["Georgia Institute of Technology,School of Interactive Computing,Atlanta,Georgia,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Interactive Computing,Atlanta,Georgia,USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35825162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"649","last_page":"656"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.427700012922287,"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":0.427700012922287,"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":0.10499999672174454,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.0982000008225441,"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/leverage","display_name":"Leverage (statistics)","score":0.6621999740600586},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6148999929428101},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6028000116348267},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5188000202178955},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46129998564720154},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.32010000944137573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8070999979972839},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6621999740600586},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6148999929428101},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6028000116348267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5310999751091003},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5188000202178955},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40529999136924744},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35350000858306885},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.32010000944137573},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.27720001339912415},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man63969.2025.11217614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man63969.2025.11217614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1791197240","https://openalex.org/W1900424585","https://openalex.org/W2012870653","https://openalex.org/W2047189892","https://openalex.org/W2069235955","https://openalex.org/W2133327647","https://openalex.org/W2277195237","https://openalex.org/W2482333547","https://openalex.org/W2766693069","https://openalex.org/W2831952048","https://openalex.org/W2914592219","https://openalex.org/W2914812111","https://openalex.org/W2915579687","https://openalex.org/W2962716343","https://openalex.org/W2963244312","https://openalex.org/W2964339842","https://openalex.org/W2967883831","https://openalex.org/W2976490211","https://openalex.org/W2976611405","https://openalex.org/W2989785064","https://openalex.org/W2998012869","https://openalex.org/W3033090297","https://openalex.org/W3090727630","https://openalex.org/W3091195047","https://openalex.org/W3174456290","https://openalex.org/W3186412961","https://openalex.org/W3207798805","https://openalex.org/W4285102324","https://openalex.org/W4294871822","https://openalex.org/W4312562542","https://openalex.org/W4389252904","https://openalex.org/W4404599688"],"related_works":[],"abstract_inverted_index":{"Ambiguities":[0],"are":[1,109],"inevitable":[2],"in":[3,13,30,41,54,144],"human-robot":[4],"interaction,":[5],"especially":[6],"when":[7,155],"a":[8,14,21,31,50,127],"robot":[9,25,99,199],"follows":[10,165],"user":[11,22,171,208],"instructions":[12],"large,":[15],"shared":[16],"space.":[17],"For":[18,48],"example,":[19],"if":[20],"asks":[23],"the":[24,37,55,60,76,91,98,137,198],"to":[26,97,111,135,140,183,200],"find":[27],"an":[28,160,166],"object":[29,38,86,93,103],"home":[32],"environment":[33],"with":[34],"underspecified":[35],"instructions,":[36],"could":[39],"be":[40,53],"multiple":[42],"locations":[43,104],"depending":[44,64],"on":[45,59,65,85,122,203],"missing":[46],"factors.":[47],"instance,":[49],"bowl":[51],"might":[52],"kitchen":[56],"cabinet":[57],"or":[58,70,73,100,115],"dining":[61],"room":[62],"table,":[63],"whether":[66],"it":[67],"is":[68,94,181,211],"clean":[69],"dirty,":[71],"full":[72],"empty,":[74],"and":[75,125,154,192],"presence":[77],"of":[78,174],"other":[79],"objects":[80,143,202],"around":[81],"it.":[82],"Previous":[83],"works":[84],"search":[87],"have":[88,101],"assumed":[89],"that":[90,178],"queried":[92,142],"immediately":[95],"visible":[96],"predicted":[102],"using":[105],"one-shot":[106],"inferences,":[107],"which":[108,164],"likely":[110],"fail":[112],"for":[113],"ambiguous":[114],"partially":[116],"understood":[117],"instructions.":[118],"This":[119],"paper":[120],"focuses":[121],"these":[123],"gaps":[124],"presents":[126],"novel":[128],"model-agnostic":[129],"approach":[130,180],"leveraging":[131],"semantically":[132],"driven":[133],"clarifications":[134,194],"enhance":[136],"robot\u2019s":[138],"ability":[139],"locate":[141,201],"fewer":[145],"attempts.":[146,206],"Specifically,":[147],"we":[148,158],"leverage":[149],"different":[150,184],"knowledge":[151],"embedding":[152],"models,":[153],"ambiguities":[156],"arise,":[157],"propose":[159],"informative":[161,193],"clarification":[162],"method,":[163],"iterative":[167],"prediction":[168],"process.":[169],"The":[170,207],"experiment":[172,209],"evaluation":[173],"our":[175,179],"method":[176],"shows":[177],"applicable":[182],"custom":[185],"semantic":[186],"encoders":[187],"as":[188,190],"well":[189],"LLMs,":[191],"improve":[195],"performances,":[196],"enabling":[197],"its":[204],"first":[205],"data":[210],"publicly":[212],"available":[213],"at":[214],"https://github.com/IrmakDogan/ExpressionDataset.":[215]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-03T00:00:00"}