{"id":"https://openalex.org/W4413926122","doi":"https://doi.org/10.1109/icra55743.2025.11127507","title":"NavigateDiff: Visual Predictors are Zero-Shot Navigation Assistants","display_name":"NavigateDiff: Visual Predictors are Zero-Shot Navigation Assistants","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413926122","doi":"https://doi.org/10.1109/icra55743.2025.11127507"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127507","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5113116658","display_name":"Yiran Qin","orcid":"https://orcid.org/0009-0008-4561-0685"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiran Qin","raw_affiliation_strings":["Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054794151","display_name":"Ao Sun","orcid":"https://orcid.org/0000-0001-9853-4868"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ao Sun","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064040649","display_name":"Yuze Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuze Hong","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408076","display_name":"Bo Wang","orcid":"https://orcid.org/0000-0002-2918-1912"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Benyou Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003608795","display_name":"Ruimao Zhang","orcid":"https://orcid.org/0000-0001-9511-7532"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruimao Zhang","raw_affiliation_strings":["Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113116658"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28291211,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12002","last_page":"12002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9886999726295471,"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":0.9886999726295471,"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":0.7630117535591125},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6482341289520264},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6168997883796692},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4384801685810089},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.401662141084671},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40093305706977844},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07657444477081299}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7630117535591125},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6482341289520264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6168997883796692},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4384801685810089},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.401662141084671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40093305706977844},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07657444477081299},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127507","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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":3,"referenced_works":["https://openalex.org/W3034728521","https://openalex.org/W4301206121","https://openalex.org/W4312929500"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Navigating":[0],"unfamiliar":[1],"environments":[2],"presents":[3],"significant":[4],"challenges":[5],"for":[6],"household":[7],"robots,":[8],"requiring":[9],"the":[10,54,58,89,94,107,120,126,139,172,184],"ability":[11,60],"to":[12,29,42,52,65,105,117,148,182],"recognize":[13],"and":[14,19,39,44,57,159,164,174,186],"reason":[15],"about":[16],"novel":[17],"decoration":[18],"layout.":[20],"Existing":[21],"reinforcement":[22],"learning":[23],"methods":[24],"cannot":[25],"be":[26],"directly":[27],"transferred":[28],"new":[30],"environments,":[31],"as":[32,143],"they":[33],"typically":[34],"rely":[35],"on":[36],"extensive":[37,168],"mapping":[38],"exploration,":[40],"leading":[41],"time-consuming":[43],"inefficient.":[45],"To":[46],"address":[47],"these":[48],"challenges,":[49],"we":[50,112,170],"try":[51],"transfer":[53],"logical":[55],"knowledge":[56],"generalization":[59,160],"of":[61,110,176,188],"pretrained":[62],"foundation":[63],"models":[64],"zero-shot":[66],"navigation.":[67],"By":[68],"integrating":[69],"a":[70,75,83],"large":[71],"vision-language":[72],"model":[73],"with":[74,125],"diffusion":[76],"network,":[77],"our":[78,177],"approach":[79,155],"named":[80],"NavigateDiff":[81],"constructs":[82],"visual":[84],"predictor":[85],"that":[86,119,137],"continuously":[87],"predicts":[88],"agent's":[90],"potential":[91,181],"observations":[92],"in":[93,191],"next":[95],"step":[96],"which":[97],"can":[98],"assist":[99],"robots":[100],"generate":[101],"robust":[102],"actions.":[103],"Furthermore,":[104],"adapt":[106],"temporal":[108,114],"property":[109],"navigation,":[111],"introduce":[113],"historical":[115],"information":[116,134],"ensure":[118],"predicted":[121,140],"image":[122,151],"is":[123],"aligned":[124],"navigation":[127,152,157,190],"scene.":[128],"We":[129],"then":[130],"carefully":[131],"designed":[132],"an":[133],"fusion":[135],"framework":[136],"embeds":[138],"future":[141],"frames":[142],"guidance":[144],"into":[145],"goalreaching":[146],"policy":[147],"solve":[149],"downstream":[150],"tasks.":[153],"This":[154],"enhances":[156],"control":[158],"across":[161],"both":[162],"simulated":[163],"real-world":[165],"environments.":[166],"Through":[167],"experimentation,":[169],"demonstrate":[171],"robustness":[173],"versatility":[175],"method,":[178],"showcasing":[179],"its":[180],"improve":[183],"efficiency":[185],"effectiveness":[187],"robotic":[189],"diverse":[192],"settings.":[193],"Project":[194],"Page:":[195],"https://21styouth.github.io/NavigateDiff/.":[196]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
