{"id":"https://openalex.org/W7158641555","doi":"https://doi.org/10.48550/arxiv.2604.26946","title":"Three-Step Nav: A Hierarchical Global-Local Planner for Zero-Shot Vision-and-Language Navigation","display_name":"Three-Step Nav: A Hierarchical Global-Local Planner for Zero-Shot Vision-and-Language Navigation","publication_year":2026,"publication_date":"2026-04-29","ids":{"openalex":"https://openalex.org/W7158641555","doi":"https://doi.org/10.48550/arxiv.2604.26946"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.26946","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26946","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2604.26946","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134898720","display_name":"Wanrong Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Wanrong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134915810","display_name":"Yunhao Ge","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge, Yunhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054494771","display_name":"Laurent Itti","orcid":"https://orcid.org/0000-0002-0168-2977"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Itti, Laurent","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":0.9438999891281128,"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":0.9438999891281128,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.01209999993443489,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0052999998442828655,"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/trajectory","display_name":"Trajectory","score":0.6784999966621399},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.6668000221252441},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5774000287055969},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.5667999982833862},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5102999806404114},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.475600004196167},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46459999680519104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6983000040054321},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6784999966621399},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6668000221252441},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5774000287055969},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.5667999982833862},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5102999806404114},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46459999680519104},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.42969998717308044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.385699987411499},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32760000228881836},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.28999999165534973},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C3020136221","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time sequence","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2556999921798706},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.26946","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26946","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.26946","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26946","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Breakthrough":[0],"progress":[1],"in":[2],"vision-based":[3],"navigation":[4],"through":[5],"unknown":[6],"environments":[7],"has":[8],"been":[9],"achieved":[10],"by":[11,26,52],"using":[12],"multimodal":[13],"large":[14],"language":[15],"models":[16,19],"(MLLMs).":[17],"These":[18],"can":[20],"plan":[21],"a":[22,77,89],"sequence":[23],"of":[24],"motions":[25],"evaluating":[27],"the":[28,36,42,97,102,112,145],"current":[29,45,98],"view":[30],"at":[31,154],"each":[32],"time":[33],"step":[34],"against":[35],"task":[37],"and":[38,62,87,147],"goal":[39],"given":[40],"to":[41,56,72,83,95,115],"agent.":[43],"However,":[44],"zero-shot":[46,142],"Vision-and-Language":[47],"Navigation":[48],"(VLN)":[49],"agents":[50],"powered":[51],"MLLMs":[53],"still":[54],"tend":[55],"drift":[57,118],"off":[58],"course,":[59],"halt":[60],"prematurely,":[61],"achieve":[63],"low":[64],"overall":[65],"success":[66],"rates.":[67],"We":[68],"propose":[69],"Three-Step":[70,138],"Nav":[71,139],"counteract":[73],"these":[74],"failures":[75],"with":[76,101,135],"three-view":[78],"protocol:":[79],"First,":[80],"\"look":[81,93,109],"forward\"":[82],"extract":[84],"global":[85],"landmarks":[86],"sketch":[88],"coarse":[90],"plan.":[91],"Then,":[92],"now\"":[94],"align":[96],"visual":[99],"observation":[100],"next":[103],"sub-goal":[104],"for":[105],"fine-grained":[106],"guidance.":[107],"Finally,":[108],"backward\"":[110],"audits":[111],"entire":[113],"trajectory":[114],"correct":[116],"accumulated":[117],"before":[119],"stopping.":[120],"Requiring":[121],"no":[122],"gradient":[123],"updates":[124],"or":[125],"task-specific":[126],"fine-tuning,":[127],"our":[128],"planner":[129],"drops":[130],"into":[131],"existing":[132],"VLN":[133],"pipelines":[134],"minimal":[136],"overhead.":[137],"achieves":[140],"state-of-the-art":[141],"performance":[143],"on":[144],"R2R-CE":[146],"RxR-CE":[148],"dataset.":[149],"Our":[150],"code":[151],"is":[152],"available":[153],"https://github.com/ZoeyZheng0/3-step-Nav.":[155]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-01T00:00:00"}