{"id":"https://openalex.org/W7138243861","doi":"https://doi.org/10.1609/aaai.v40i22.38899","title":"PanoNav: Mapless Zero-Shot Object Navigation with Panoramic Scene Parsing and Dynamic Memory","display_name":"PanoNav: Mapless Zero-Shot Object Navigation with Panoramic Scene Parsing and Dynamic Memory","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138243861","doi":"https://doi.org/10.1609/aaai.v40i22.38899"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i22.38899","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38899","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i22.38899","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052824979","display_name":"Qunchao Jin","orcid":"https://orcid.org/0000-0002-0976-9401"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qunchao Jin","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou)"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129656082","display_name":"Yilin Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yilin Wu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou)"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129669106","display_name":"Changhao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changhao Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou)"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052824979"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5880597,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"22","first_page":"18351","last_page":"18359"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.917900025844574,"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":0.917900025844574,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.014999999664723873,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.013199999928474426,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6877999901771545},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5992000102996826},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.489300012588501},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.3952000141143799},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3926999866962433},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3781999945640564},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.36059999465942383},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.35499998927116394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7542999982833862},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6877999901771545},{"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/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5992000102996826},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5209000110626221},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.489300012588501},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C5799516","wikidata":"https://www.wikidata.org/wiki/Q4110915","display_name":"Visual odometry","level":3,"score":0.26159998774528503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i22.38899","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38899","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i22.38899","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38899","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7520984411239624,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"object":[1],"navigation":[2,129],"(ZSON)":[3],"in":[4,138],"unseen":[5],"environments":[6],"remains":[7],"a":[8,72,80,88,106,112],"challenging":[9],"problem":[10],"for":[11],"household":[12],"robots,":[13],"requiring":[14],"strong":[15],"perceptual":[16],"understanding":[17],"and":[18,27,105,121,141],"decision-making":[19],"capabilities.":[20],"While":[21],"recent":[22],"methods":[23],"leverage":[24],"metric":[25],"maps":[26],"Large":[28,48],"Language":[29,49],"Models":[30,50],"(LLMs),":[31],"they":[32,61],"often":[33],"depend":[34],"on":[35,126],"depth":[36],"sensors":[37],"or":[38],"prebuilt":[39],"maps,":[40],"limiting":[41],"the":[42,95,127],"spatial":[43,96],"reasoning":[44],"ability":[45],"of":[46,74,99],"Multimodal":[47],"(MLLMs).":[51],"Mapless":[52],"ZSON":[53,84],"approaches":[54],"have":[55],"emerged":[56],"to":[57,67,71,93,117],"address":[58],"this,":[59],"but":[60],"typically":[62],"make":[63],"short-sighted":[64],"decisions,":[65],"leading":[66],"local":[68,123],"deadlocks":[69],"due":[70],"lack":[73],"historical":[75],"context.":[76],"We":[77],"propose":[78],"PanoNav,":[79],"fully":[81],"RGB-only,":[82],"mapless":[83],"framework":[85],"that":[86,132],"integrates":[87],"Panoramic":[89],"Scene":[90],"Parsing":[91],"module":[92],"unlock":[94],"parsing":[97],"potential":[98],"MLLMs":[100],"from":[101],"panoramic":[102],"RGB":[103],"inputs,":[104],"Memory-guided":[107],"Decision-Making":[108],"mechanism":[109],"enhanced":[110],"by":[111],"Dynamic":[113],"Bounded":[114],"Memory":[115],"Queue":[116],"incorporate":[118],"exploration":[119],"history":[120],"avoid":[122],"deadlocks.":[124],"Experiments":[125],"public":[128],"benchmark":[130],"show":[131],"PanoNav":[133],"significantly":[134],"outperforms":[135],"representative":[136],"baselines":[137],"both":[139],"SR":[140],"SPL":[142],"metrics.":[143]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}