{"id":"https://openalex.org/W4417305426","doi":"https://doi.org/10.1080/01691864.2025.2599950","title":"Visual robot navigation adaptive to directional cues using vision-language models and conditional diffusion models","display_name":"Visual robot navigation adaptive to directional cues using vision-language models and conditional diffusion models","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W4417305426","doi":"https://doi.org/10.1080/01691864.2025.2599950"},"language":"en","primary_location":{"id":"doi:10.1080/01691864.2025.2599950","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01691864.2025.2599950","pdf_url":null,"source":{"id":"https://openalex.org/S192584203","display_name":"Advanced Robotics","issn_l":"0169-1864","issn":["0169-1864","1568-5535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019748224","display_name":"Shintaro Nakaoka","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137853","display_name":"Toyota Motor Corporation (Japan)","ror":"https://ror.org/02zqm6r10","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4210137853"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shintaro Nakaoka","raw_affiliation_strings":["Toyota Motor Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Motor Corporation","institution_ids":["https://openalex.org/I4210137853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018497299","display_name":"Kosei Tanada","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137853","display_name":"Toyota Motor Corporation (Japan)","ror":"https://ror.org/02zqm6r10","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4210137853"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kosei Tanada","raw_affiliation_strings":["Toyota Motor Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Motor Corporation","institution_ids":["https://openalex.org/I4210137853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104242922","display_name":"Kazuhito Tanaka","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137853","display_name":"Toyota Motor Corporation (Japan)","ror":"https://ror.org/02zqm6r10","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4210137853"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhito Tanaka","raw_affiliation_strings":["Toyota Motor Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Motor Corporation","institution_ids":["https://openalex.org/I4210137853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093917266","display_name":"Takuma Sugino","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137853","display_name":"Toyota Motor Corporation (Japan)","ror":"https://ror.org/02zqm6r10","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4210137853"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuma Sugino","raw_affiliation_strings":["Toyota Motor Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Motor Corporation","institution_ids":["https://openalex.org/I4210137853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101735344","display_name":"Yuki Kondo","orcid":"https://orcid.org/0000-0002-5263-8722"},"institutions":[{"id":"https://openalex.org/I4210137853","display_name":"Toyota Motor Corporation (Japan)","ror":"https://ror.org/02zqm6r10","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4210137853"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Kondo","raw_affiliation_strings":["Toyota Motor Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Motor Corporation","institution_ids":["https://openalex.org/I4210137853"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031827214","display_name":"Shigemichi Matsuzaki","orcid":"https://orcid.org/0000-0002-4795-6005"},"institutions":[{"id":"https://openalex.org/I4210137853","display_name":"Toyota Motor Corporation (Japan)","ror":"https://ror.org/02zqm6r10","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4210137853"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shigemichi Matsuzaki","raw_affiliation_strings":["Toyota Motor Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Motor Corporation","institution_ids":["https://openalex.org/I4210137853"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5031827214"],"corresponding_institution_ids":["https://openalex.org/I4210137853"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35503478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"1","first_page":"10","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.22630000114440918,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.22630000114440918,"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/T10427","display_name":"Visual perception and processing mechanisms","score":0.1273999959230423,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.1088000014424324,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5195000171661377},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3582000136375427},{"id":"https://openalex.org/keywords/sensory-cue","display_name":"Sensory cue","score":0.34610000252723694},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3043000102043152},{"id":"https://openalex.org/keywords/mobile-robot-navigation","display_name":"Mobile robot navigation","score":0.27250000834465027}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.699400007724762},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6934000253677368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.684499979019165},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5195000171661377},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3582000136375427},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.27250000834465027},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2635999917984009}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/01691864.2025.2599950","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01691864.2025.2599950","pdf_url":null,"source":{"id":"https://openalex.org/S192584203","display_name":"Advanced Robotics","issn_l":"0169-1864","issn":["0169-1864","1568-5535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Robotics","raw_type":"journal-article"},{"id":"pmh:doi:10.6084/m9.figshare.30879851","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Media"}],"best_oa_location":{"id":"pmh:doi:10.6084/m9.figshare.30879851","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Media"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1480699419","https://openalex.org/W1901129140","https://openalex.org/W1933349210","https://openalex.org/W2029143333","https://openalex.org/W2129205316","https://openalex.org/W2136891917","https://openalex.org/W2150839555","https://openalex.org/W2157725521","https://openalex.org/W2164548818","https://openalex.org/W2921106744","https://openalex.org/W2947311533","https://openalex.org/W3007289063","https://openalex.org/W3134972302","https://openalex.org/W4243724405","https://openalex.org/W4252907012","https://openalex.org/W4287888303","https://openalex.org/W4385403811","https://openalex.org/W4389665733","https://openalex.org/W4390873054","https://openalex.org/W4392866655","https://openalex.org/W4401417422","https://openalex.org/W4401972943","https://openalex.org/W4402354022","https://openalex.org/W4402727764","https://openalex.org/W4403448419","https://openalex.org/W4413925126"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,44,84,111],"method":[4],"for":[5,136],"visual":[6,23,47,139],"robot":[7],"navigation":[8,24,48,86],"guided":[9,46],"by":[10],"diverse":[11],"directional":[12,53,75],"cues,":[13],"such":[14],"as":[15],"human":[16],"pointing":[17],"gestures":[18],"and":[19,60,77,106,122,133],"arrow":[20,107],"signages.":[21],"Existing":[22],"policies":[25],"often":[26],"focus":[27],"solely":[28],"on":[29],"scene":[30],"traversability":[31],"or":[32],"specific":[33],"cue":[34,120],"types,":[35],"limiting":[36],"their":[37],"generality.":[38],"To":[39],"address":[40],"this,":[41],"we":[42],"propose":[43],"unified":[45],"framework":[49],"that":[50,82],"interprets":[51],"various":[52],"cues":[54,76,108],"using":[55],"large":[56],"Vision-Language":[57],"Models":[58],"(VLMs)":[59],"adapts":[61],"its":[62],"behavior":[63],"via":[64],"conditional":[65],"diffusion":[66,134],"models.":[67],"The":[68],"VLM":[69],"recognizes":[70],"the":[71,96,100,125,128],"semantic":[72],"meaning":[73],"of":[74,130],"provides":[78],"textual":[79],"direction":[80],"labels":[81],"condition":[83],"probabilistic":[85],"policy.":[87],"Through":[88],"experiments":[89],"with":[90],"real":[91],"robots":[92],"in":[93,118],"office":[94],"environments,":[95],"proposed":[97],"system":[98],"demonstrates":[99],"ability":[101],"to":[102],"follow":[103],"both":[104],"gesture":[105],"adaptively":[109],"within":[110],"single":[112],"model.":[113],"While":[114],"some":[115],"limitations":[116],"remain":[117],"real-time":[119],"recognition":[121],"collision-free":[123],"operation,":[124],"results":[126],"highlight":[127],"potential":[129],"combining":[131],"VLMs":[132],"models":[135],"socially":[137],"adaptive":[138],"navigation.":[140]},"counts_by_year":[],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2025-12-14T00:00:00"}
