{"id":"https://openalex.org/W7161831566","doi":"https://doi.org/10.48550/arxiv.2605.19634","title":"P2DNav: Panorama-to-Downview Reasoning for Zero-shot Vision-and-Language Navigation","display_name":"P2DNav: Panorama-to-Downview Reasoning for Zero-shot Vision-and-Language Navigation","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7161831566","doi":"https://doi.org/10.48550/arxiv.2605.19634"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.19634","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19634","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.19634","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136506357","display_name":"Kai Sheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136509680","display_name":"Liuyi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Liuyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100958645","display_name":"Haojie Dai","orcid":"https://orcid.org/0009-0005-8399-8551"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Haojie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136587171","display_name":"Jinlong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jinlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043502041","display_name":"Yongrui Qin","orcid":"https://orcid.org/0000-0001-6534-3205"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Yongrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089600727","display_name":"Zongtao He","orcid":"https://orcid.org/0000-0002-2166-4450"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Zongtao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136583416","display_name":"Chengju Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Chengju","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136519620","display_name":"Qijun Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Qijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.982200026512146,"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":0.982200026512146,"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":0.004699999932199717,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0027000000700354576,"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/context","display_name":"Context (archaeology)","score":0.6134999990463257},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5636000037193298},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.5277000069618225},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47999998927116394},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4634999930858612},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4284000098705292},{"id":"https://openalex.org/keywords/waypoint","display_name":"Waypoint","score":0.41760000586509705},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.3905999958515167},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.3790000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722000002861023},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6134999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6123999953269958},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5636000037193298},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5509999990463257},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.5277000069618225},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47999998927116394},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4634999930858612},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C2781271823","wikidata":"https://www.wikidata.org/wiki/Q138081","display_name":"Waypoint","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3905999958515167},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3711000084877014},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3456000089645386},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2745000123977661},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.19634","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19634","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.19634","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19634","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Vision-and-language":[0],"navigation":[1,13,77,118],"(VLN)":[2],"requires":[3],"an":[4],"embodied":[5],"agent":[6],"to":[7,39,134,157],"ground":[8],"natural-language":[9],"instructions":[10],"into":[11,79],"executable":[12],"actions":[14],"in":[15,111],"unseen":[16],"environments.":[17],"Existing":[18],"zero-shot":[19,54,175,184,207],"methods":[20],"typically":[21],"rely":[22],"on":[23,151,164],"additional":[24],"waypoint":[25],"prediction":[26],"modules,":[27],"which":[28],"often":[29],"entangle":[30],"high-level":[31],"directional":[32],"reasoning":[33],"with":[34,180],"fine-grained":[35],"local":[36,87,148],"grounding,":[37],"leading":[38],"error-prone":[40],"and":[41,69,85,99,125,155,186,195,204],"unstable":[42],"decisions.":[43],"In":[44,114,177],"this":[45],"paper,":[46],"we":[47],"propose":[48],"P2DNav,":[49],"a":[50,96,102,121,131],"hierarchical":[51],"framework":[52],"for":[53,206,213],"vision-and-language":[55],"navigation.":[56,137],"P2DNav":[57,170,189],"consists":[58],"of":[59,147,193,201],"three":[60],"core":[61],"components:":[62],"Panorama-to-Downview":[63],"(P2D),":[64],"Sliding-Window":[65],"Dialogue":[66],"Memory":[67],"(SDM),":[68],"Reflective":[70],"Reorientation":[71],"Mechanism":[72],"(RRM).":[73],"P2D":[74],"explicitly":[75],"decomposes":[76],"decision-making":[78],"two":[80],"stages:":[81],"panoramic":[82,158],"direction":[83,94,159],"selection":[84,160],"downview":[86,108,153],"grounding.":[88],"It":[89],"first":[90],"selects":[91],"the":[92,107,145,152,165,181,199],"instruction-relevant":[93],"from":[95,106],"360\u00b0":[97],"panorama,":[98],"then":[100],"predicts":[101],"pixel-level":[103],"target":[104],"point":[105],"RGB":[109],"observation":[110,154],"that":[112,169],"direction.":[113],"addition,":[115],"SDM":[116],"organizes":[117],"history":[119],"as":[120],"multi-turn":[122],"dialogue":[123],"context":[124],"maintains":[126],"recent":[127],"visual":[128],"observations":[129],"within":[130],"sliding":[132],"window":[133],"support":[135],"long-horizon":[136],"RRM":[138,205],"further":[139],"enables":[140],"reflective":[141],"reorientation":[142],"by":[143],"assessing":[144],"reliability":[146],"grounding":[149],"based":[150],"returning":[156],"when":[161],"necessary.":[162],"Experiments":[163],"R2R-CE":[166],"benchmark":[167],"show":[168],"achieves":[171,190],"strong":[172],"performance":[173],"among":[174],"methods.":[176],"particular,":[178],"compared":[179],"state-of-the-art":[182],"(SOTA)":[183],"waypoint-based":[185],"waypoint-free":[187],"methods,":[188],"SR":[191],"gains":[192],"146.6%":[194],"58.9%,":[196],"respectively,":[197],"demonstrating":[198],"effectiveness":[200],"P2D,":[202],"SDM,":[203],"VLN.":[208],"Code":[209],"will":[210],"be":[211],"released":[212],"public":[214],"use.":[215]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-21T00:00:00"}