{"id":"https://openalex.org/W4416749948","doi":"https://doi.org/10.1109/iros60139.2025.11246115","title":"SDA-LLM: Spatial DisAmbiguation via Multi-turn Vision-Language Dialogues for Robot Navigation","display_name":"SDA-LLM: Spatial DisAmbiguation via Multi-turn Vision-Language Dialogues for Robot Navigation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749948","doi":"https://doi.org/10.1109/iros60139.2025.11246115"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5100751227","display_name":"Kuan-Lin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Kuan-Lin Chen","raw_affiliation_strings":["National Yang Ming Chiao Tung University (NYCU),College of Artificial Intelligence,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University (NYCU),College of Artificial Intelligence,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102796288","display_name":"Tzu-Ti Wei","orcid":"https://orcid.org/0009-0004-9676-524X"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tzu-Ti Wei","raw_affiliation_strings":["National Yang Ming Chiao Tung University (NYCU),College of Artificial Intelligence,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University (NYCU),College of Artificial Intelligence,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047287790","display_name":"Ming-Lun Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ming-Lun Lee","raw_affiliation_strings":["National Yang Ming Chiao Tung University (NYCU),College of Artificial Intelligence,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University (NYCU),College of Artificial Intelligence,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063501042","display_name":"Li-Tzu Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li-Tzu Yeh","raw_affiliation_strings":["National Yang Ming Chiao Tung University (NYCU),College of Artificial Intelligence,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University (NYCU),College of Artificial Intelligence,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111902785","display_name":"Elizabeth Kao","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Elaine Kao","raw_affiliation_strings":["National Yang Ming Chiao Tung University (NYCU),College of Artificial Intelligence,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University (NYCU),College of Artificial Intelligence,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111740069","display_name":"Yu\u2010Chee Tseng","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Chee Tseng","raw_affiliation_strings":["National Yang Ming Chiao Tung University (NYCU),College of Artificial Intelligence,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University (NYCU),College of Artificial Intelligence,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050310630","display_name":"Jen\u2010Jee Chen","orcid":"https://orcid.org/0000-0002-5453-3887"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Jee Chen","raw_affiliation_strings":["National Yang Ming Chiao Tung University (NYCU),College of Artificial Intelligence,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University (NYCU),College of Artificial Intelligence,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100751227"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40229778,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4275","last_page":"4282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9502000212669373,"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":0.9502000212669373,"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/T11904","display_name":"Spatial Cognition and Navigation","score":0.011900000274181366,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.008700000122189522,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/ambiguity","display_name":"Ambiguity","score":0.7465000152587891},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6608999967575073},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6223000288009644},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.5572999715805054},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4977000057697296},{"id":"https://openalex.org/keywords/service-robot","display_name":"Service robot","score":0.4722999930381775},{"id":"https://openalex.org/keywords/mobile-robot-navigation","display_name":"Mobile robot navigation","score":0.4212000072002411},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.3540000021457672}],"concepts":[{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7465000152587891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7202000021934509},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6608999967575073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6593000292778015},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6223000288009644},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5748000144958496},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.5572999715805054},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4977000057697296},{"id":"https://openalex.org/C2776228582","wikidata":"https://www.wikidata.org/wiki/Q7455797","display_name":"Service robot","level":3,"score":0.4722999930381775},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.4212000072002411},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3650999963283539},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.290800005197525},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":25,"referenced_works":["https://openalex.org/W1595410283","https://openalex.org/W2116360390","https://openalex.org/W2118429180","https://openalex.org/W2211722331","https://openalex.org/W2737529802","https://openalex.org/W2998008599","https://openalex.org/W3008195728","https://openalex.org/W3034500398","https://openalex.org/W3156232414","https://openalex.org/W3165915253","https://openalex.org/W3170641298","https://openalex.org/W3174887918","https://openalex.org/W3195026654","https://openalex.org/W3203663566","https://openalex.org/W4226294355","https://openalex.org/W4312434279","https://openalex.org/W4362663195","https://openalex.org/W4382934641","https://openalex.org/W4383108296","https://openalex.org/W4386083015","https://openalex.org/W4390874575","https://openalex.org/W4393154152","https://openalex.org/W4398756379","https://openalex.org/W4401414899","https://openalex.org/W4402716047"],"related_works":[],"abstract_inverted_index":{"When":[0],"users":[1],"give":[2],"natural":[3],"language":[4,91],"instructions":[5],"to":[6,15,33,102,116,123,137,145,165],"service":[7],"robots,":[8],"positional":[9,43],"information":[10],"is":[11,45,63,158],"often":[12],"referenced":[13],"relative":[14,28],"objects":[16,53],"in":[17,55,66,104,128],"the":[18,34,42,46,56,60,71,100,118,143,152,159],"environment":[19,57],"rather":[20],"than":[21],"absolute":[22],"coordinates.":[23],"However,":[24],"humans":[25],"naturally":[26],"use":[27],"references.":[29],"For":[30],"example,":[31],"in\u201cGo":[32],"chair":[35],"and":[36,74,94,130],"pick":[37],"up":[38],"empty":[39],"bottles\u201d,":[40],"where":[41],"reference":[44],"chair,":[47],"ambiguity":[48],"arises":[49],"when":[50,59],"multiple":[51,67],"similar":[52],"co-exist":[54],"or":[58],"robot\u2019s":[61],"view":[62],"limited,":[64],"resulting":[65],"possible":[68],"interpretations":[69],"of":[70,121,154],"same":[72],"command":[73],"affecting":[75],"navigation":[76,149],"decisions.":[77],"To":[78,151],"address":[79,166],"this":[80,134,157],"issue,":[81],"we":[82],"propose":[83],"a":[84,89,95,114,124,138],"two-level":[85],"framework":[86],"that":[87],"integrates":[88],"large":[90],"model":[92,97],"(LLM)":[93],"vision-language":[96],"(VLM),":[98],"allowing":[99],"robot":[101,144],"engage":[103],"multi-turn":[105],"dialogues":[106,122],"for":[107],"spatial":[108,167],"disambiguation.":[109],"Our":[110],"method":[111],"first":[112,160],"utilizes":[113],"VLM":[115],"map":[117],"semantic":[119],"meanings":[120],"unique":[125],"object":[126,135],"ID":[127,136],"images":[129],"then":[131],"further":[132],"maps":[133],"3D":[139],"depth":[140],"map,":[141],"enabling":[142],"accurately":[146],"determine":[147],"its":[148],"target.":[150],"best":[153],"our":[155],"knowledge,":[156],"work":[161],"leveraging":[162],"foundation":[163],"models":[164],"ambiguity.":[168]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}
