{"id":"https://openalex.org/W4405433979","doi":"https://doi.org/10.48550/arxiv.2412.10137","title":"Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environments","display_name":"Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environments","publication_year":2024,"publication_date":"2024-12-13","ids":{"openalex":"https://openalex.org/W4405433979","doi":"https://doi.org/10.48550/arxiv.2412.10137"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2412.10137","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.10137","pdf_url":"https://arxiv.org/pdf/2412.10137","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.10137","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056739524","display_name":"Kehan Chen","orcid":"https://orcid.org/0000-0002-6783-5438"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chen, Kehan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101399813","display_name":"Dong An","orcid":"https://orcid.org/0000-0002-1347-8535"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"An, Dong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059386453","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-3151-5555"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038918940","display_name":"Rongtao Xu","orcid":"https://orcid.org/0000-0003-4619-9679"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Rongtao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045379790","display_name":"Yifei Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Yifei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088062859","display_name":"Yonggen Ling","orcid":"https://orcid.org/0000-0001-8294-6286"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ling, Yonggen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089444805","display_name":"Ian Reid","orcid":"https://orcid.org/0000-0001-7790-6423"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reid, Ian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5115602506","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0001-5224-8647"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Liang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5056739524"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9929999709129333,"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":0.9929999709129333,"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":0.9621999859809875,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9559000134468079,"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/shot","display_name":"Shot (pellet)","score":0.774796724319458},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.7284048795700073},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.7127496600151062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6069604158401489},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5994411706924438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4929630756378174},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33565765619277954},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21075975894927979},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12630829215049744},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.07655808329582214},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06742298603057861}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.774796724319458},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.7284048795700073},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.7127496600151062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6069604158401489},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5994411706924438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4929630756378174},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33565765619277954},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21075975894927979},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12630829215049744},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.07655808329582214},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06742298603057861},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2412.10137","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.10137","pdf_url":"https://arxiv.org/pdf/2412.10137","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.10137","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.10137","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.10137","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.10137","pdf_url":"https://arxiv.org/pdf/2412.10137","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405433979.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"We":[0],"address":[1],"the":[2,12,22,69,75,82,111,125,133,147],"task":[3],"of":[4,24,151],"Vision-Language":[5],"Navigation":[6],"in":[7,97,143,161],"Continuous":[8],"Environments":[9],"(VLN-CE)":[10],"under":[11],"zero-shot":[13,49],"setting.":[14],"Zero-shot":[15],"VLN-CE":[16,50,130],"is":[17],"particularly":[18],"challenging":[19],"due":[20],"to":[21,34,119],"absence":[23],"expert":[25],"demonstrations":[26],"for":[27,85],"training":[28],"and":[29,74,90,113,140,153,169],"minimal":[30],"environment":[31],"structural":[32],"prior":[33],"guide":[35],"navigation.":[36],"To":[37],"confront":[38],"these":[39],"challenges,":[40],"we":[41],"propose":[42],"a":[43,52,98,107],"Constraint-Aware":[44,70,76],"Navigator":[45],"(CA-Nav),":[46],"which":[47],"reframes":[48],"as":[51,88],"sequential,":[53],"constraint-aware":[54,99],"sub-instruction":[55],"completion":[56,83],"process.":[57],"CA-Nav":[58,123,157],"continuously":[59],"translates":[60],"sub-instructions":[61,87,96],"into":[62],"navigation":[63,92,121],"plans":[64],"using":[65,116],"two":[66,129],"core":[67],"modules:":[68],"Sub-instruction":[71],"Manager":[72],"(CSM)":[73],"Value":[77],"Mapper":[78],"(CVM).":[79],"CSM":[80],"defines":[81],"criteria":[84],"decomposed":[86],"constraints":[89],"tracks":[91],"progress":[93],"by":[94,103,137],"switching":[95],"manner.":[100],"CVM,":[101],"guided":[102],"CSM's":[104],"constraints,":[105],"generates":[106],"value":[108],"map":[109],"on":[110,128,146],"fly":[112],"refines":[114],"it":[115],"superpixel":[117],"clustering":[118],"improve":[120],"stability.":[122],"achieves":[124],"state-of-the-art":[126],"performance":[127],"benchmarks,":[131],"surpassing":[132],"previous":[134],"best":[135],"method":[136],"12":[138],"percent":[139,142],"13":[141],"Success":[144],"Rate":[145],"validation":[148],"unseen":[149],"splits":[150],"R2R-CE":[152],"RxR-CE,":[154],"respectively.":[155],"Moreover,":[156],"demonstrates":[158],"its":[159],"effectiveness":[160],"real-world":[162],"robot":[163],"deployments":[164],"across":[165],"various":[166],"indoor":[167],"scenes":[168],"instructions.":[170]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
