{"id":"https://openalex.org/W7140776371","doi":"https://doi.org/10.1109/ieeeconf67917.2025.11443839","title":"History-Augmented Vision-Language Models for Frontier-Based Zero-Shot Object Navigation","display_name":"History-Augmented Vision-Language Models for Frontier-Based Zero-Shot Object Navigation","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W7140776371","doi":"https://doi.org/10.1109/ieeeconf67917.2025.11443839"},"language":null,"primary_location":{"id":"doi:10.1109/ieeeconf67917.2025.11443839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf67917.2025.11443839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 59th Asilomar Conference on Signals, Systems, and Computers","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/A5120354141","display_name":"Mobin Habibpour","orcid":null},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mobin Habibpour","raw_affiliation_strings":["Clemson University,Holcombe Department of Electrical and Computer Engineering,Clemson,SC,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clemson University,Holcombe Department of Electrical and Computer Engineering,Clemson,SC,USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130673831","display_name":"Fatemeh Afghah","orcid":null},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fatemeh Afghah","raw_affiliation_strings":["Clemson University,Holcombe Department of Electrical and Computer Engineering,Clemson,SC,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clemson University,Holcombe Department of Electrical and Computer Engineering,Clemson,SC,USA","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"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":0.68293694,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"280","last_page":"284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8550999760627747,"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":0.8550999760627747,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.020999999716877937,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.014100000262260437,"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/object","display_name":"Object (grammar)","score":0.47690001130104065},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2621999979019165},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2540000081062317},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.250900000333786},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2492000013589859}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6155999898910522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5989000201225281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5740000009536743},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.47690001130104065},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2492000013589859},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2484000027179718},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2468000054359436}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf67917.2025.11443839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf67917.2025.11443839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 59th Asilomar Conference on Signals, Systems, and Computers","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":9,"referenced_works":["https://openalex.org/W4312360147","https://openalex.org/W4389666115","https://openalex.org/W4392939491","https://openalex.org/W4401417061","https://openalex.org/W4401417236","https://openalex.org/W4402727764","https://openalex.org/W4410294893","https://openalex.org/W4413147769","https://openalex.org/W7133204856"],"related_works":[],"abstract_inverted_index":{"Object":[0],"Goal":[1],"Navigation":[2],"(ObjectNav)":[3],"challenges":[4],"robots":[5],"to":[6,47,70,93,119,149],"find":[7],"objects":[8],"in":[9,83],"unseen":[10],"environments,":[11],"demanding":[12],"sophisticated":[13],"reasoning.":[14,40],"While":[15],"Vision-Language":[16],"Models":[17],"(VLMs)":[18],"show":[19],"potential,":[20],"current":[21],"ObjectNav":[22,60],"methods":[23],"often":[24],"employ":[25],"them":[26],"superficially,":[27],"primarily":[28],"using":[29],"vision-language":[30],"embeddings":[31],"for":[32,98,114,163],"object-scene":[33],"similarity":[34],"checks":[35],"rather":[36],"than":[37],"leveraging":[38],"deeper":[39],"This":[41,54],"limits":[42],"contextual":[43],"understanding":[44],"and":[45,137,166],"leads":[46],"practical":[48],"issues":[49],"like":[50],"repetitive":[51],"navigation":[52,99],"behaviors.":[53],"paper":[55],"introduces":[56],"a":[57,109,132],"novel":[58],"zero-shot":[59,151],"framework":[61],"that":[62],"pioneers":[63],"the":[64,85,116,124,154],"use":[65],"of":[66,157],"dynamic,":[67],"history-aware":[68],"prompting":[69,161],"more":[71,164],"deeply":[72],"integrate":[73],"VLM":[74,86,160],"reasoning":[75],"into":[76],"frontier-based":[77],"exploration.":[78],"Our":[79],"core":[80],"innovation":[81],"lies":[82],"providing":[84],"with":[87],"action":[88],"history":[89],"context,":[90],"enabling":[91],"it":[92],"generate":[94],"semantic":[95],"guidance":[96],"scores":[97],"actions":[100],"while":[101],"actively":[102],"avoiding":[103],"decision":[104],"loops.":[105],"We":[106],"also":[107],"introduce":[108],"VLM-assisted":[110],"waypoint":[111],"generation":[112],"mechanism":[113],"refining":[115],"final":[117],"approach":[118,130],"detected":[120],"objects.":[121],"Evaluated":[122],"on":[123],"HM3D":[125],"dataset":[126],"within":[127],"Habitat,":[128],"our":[129,158],"achieves":[131],"46%":[133],"Success":[134,139],"Rate":[135],"(SR)":[136],"24.8%":[138],"weighted":[140],"by":[141],"Path":[142],"Length":[143],"(SPL).":[144],"These":[145],"results":[146],"are":[147],"comparable":[148],"state-of-the-art":[150],"methods,":[152],"demonstrating":[153],"significant":[155],"potential":[156],"history-augmented":[159],"strategy":[162],"robust":[165],"context-aware":[167],"robotic":[168],"navigation.":[169]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-27T00:00:00"}