{"id":"https://openalex.org/W7154469812","doi":"https://doi.org/10.1109/upinlbs68186.2025.11468428","title":"OV-Nav: Object Navigation Based on Large Vision Language Models and Hierarchical Scene Graph","display_name":"OV-Nav: Object Navigation Based on Large Vision Language Models and Hierarchical Scene Graph","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7154469812","doi":"https://doi.org/10.1109/upinlbs68186.2025.11468428"},"language":null,"primary_location":{"id":"doi:10.1109/upinlbs68186.2025.11468428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/upinlbs68186.2025.11468428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Ubiquitous Positioning, Indoor Navigation and Location-Based Services Conference (UPINLBS)","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/A5002891542","display_name":"Pengshuai Yin","orcid":"https://orcid.org/0000-0003-4224-9915"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengshuai Yin","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133720916","display_name":"Tianyi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Zhang","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lianzhong You","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianzhong You","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101935210","display_name":"Si Shi","orcid":"https://orcid.org/0000-0002-6952-9848"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Shi","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133645197","display_name":"Zhen Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Tian","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046935762","display_name":"Shoubin Chen","orcid":"https://orcid.org/0000-0002-9071-0051"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shoubin Chen","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022106396","display_name":"F. Richard Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"F. Richard Yu","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129721501","display_name":"Ming Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ming Yang","raw_affiliation_strings":["Hong Kong Polytechnic University,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Polytechnic University,Hong Kong,China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"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":0.68988735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9434999823570251,"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":0.9434999823570251,"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":0.00930000003427267,"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/T12031","display_name":"Speech and dialogue systems","score":0.005200000014156103,"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":0.5103999972343445},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.45879998803138733},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.37220001220703125},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.35030001401901245},{"id":"https://openalex.org/keywords/object-model","display_name":"Object model","score":0.3416000008583069},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.2962000072002411},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.28679999709129333}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.671500027179718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6639000177383423},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.652899980545044},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5103999972343445},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.3416000008583069},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.28679999709129333},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/upinlbs68186.2025.11468428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/upinlbs68186.2025.11468428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Ubiquitous Positioning, Indoor Navigation and Location-Based Services Conference (UPINLBS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"OV-Nav,":[3],"a":[4,58,69,83,106],"novel":[5,28],"zero-shot":[6],"framework":[7,104],"for":[8],"object":[9],"navigation":[10],"that":[11,63,87,109],"overcomes":[12],"the":[13,124],"contextual":[14],"limitations":[15],"of":[16,98],"existing":[17],"methods.":[18],"Current":[19],"approaches":[20],"rely":[21],"on":[22,123],"training":[23],"data":[24],"and":[25,43,100],"struggle":[26],"with":[27,48],"target":[29],"classes":[30],"during":[31,119],"testing.":[32],"Furthermore,":[33],"current":[34],"methods'":[35],"simplified":[36],"environmental":[37],"representations":[38],"restrict":[39],"their":[40],"scene":[41,61,93,116],"understanding":[42],"reasoning":[44],"capabilities":[45],"when":[46],"interacting":[47],"large":[49],"language":[50,72],"models":[51,73],"(LLMs).":[52],"OV-Nav":[53],"addresses":[54],"this":[55],"by":[56,114],"constructing":[57],"hierarchical":[59,84],"3D":[60],"graph":[62,96,117],"explicitly":[64],"encodes":[65],"object-room":[66],"relationships":[67],"in":[68],"structured,":[70],"visual":[71],"(VLMs)":[74],"compatible":[75],"format.":[76],"To":[77],"enhance":[78],"spatial":[79],"reasoning,":[80],"we":[81],"design":[82],"prompting":[85],"strategy":[86],"enables":[88],"VLMs":[89],"to":[90],"systematically":[91],"analyze":[92],"context":[94],"through":[95],"traversal":[97],"nodes":[99],"edges.":[101],"Additionally,":[102],"our":[103],"incorporates":[105],"rethinking":[107],"mechanism":[108],"dynamically":[110],"corrects":[111],"perception":[112],"errors":[113],"re-examining":[115],"inconsistencies":[118],"navigation.":[120],"Extensive":[121],"experiments":[122],"MP3D":[125],"benchmark":[126],"demonstrate":[127],"OV-Nav's":[128],"superiority":[129],"while":[130],"also":[131],"providing":[132],"human-interpretable":[133],"decision":[134],"paths.":[135],"The":[136],"code":[137],"will":[138],"be":[139],"made":[140],"publicly":[141],"available.":[142]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-16T00:00:00"}