{"id":"https://openalex.org/W4400875752","doi":"https://doi.org/10.3390/s24144735","title":"Open-Vocabulary Predictive World Models from Sensor Observations","display_name":"Open-Vocabulary Predictive World Models from Sensor Observations","publication_year":2024,"publication_date":"2024-07-21","ids":{"openalex":"https://openalex.org/W4400875752","doi":"https://doi.org/10.3390/s24144735","pmid":"https://pubmed.ncbi.nlm.nih.gov/39066133"},"language":"en","primary_location":{"id":"doi:10.3390/s24144735","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24144735","pdf_url":"https://www.mdpi.com/1424-8220/24/14/4735/pdf?version=1721702402","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/24/14/4735/pdf?version=1721702402","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022811365","display_name":"Robin Karlsson","orcid":"https://orcid.org/0000-0001-6106-9616"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Robin Karlsson","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya 464-8603, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6106-9616","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya 464-8603, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016967911","display_name":"R. Asfandiyarov","orcid":"https://orcid.org/0000-0002-6631-9220"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruslan Asfandiyarov","raw_affiliation_strings":["Independent Researcher, 1005 Lausanne, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-6631-9220","affiliations":[{"raw_affiliation_string":"Independent Researcher, 1005 Lausanne, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037312161","display_name":"Alexander Carballo","orcid":"https://orcid.org/0000-0002-5941-2195"},"institutions":[{"id":"https://openalex.org/I42405503","display_name":"Gifu University","ror":"https://ror.org/024exxj48","country_code":"JP","type":"education","lineage":["https://openalex.org/I42405503"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Alexander Carballo","raw_affiliation_strings":["Department of Electrical, Electronic and Computer Engineering, Gifu University, Gifu 501-1112, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical, Electronic and Computer Engineering, Gifu University, Gifu 501-1112, Japan","institution_ids":["https://openalex.org/I42405503"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025530694","display_name":"Keisuke Fujii","orcid":"https://orcid.org/0000-0001-5487-4297"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Fujii","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya 464-8603, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5487-4297","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya 464-8603, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110527908","display_name":"Kento Ohtani","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kento Ohtani","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya 464-8603, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya 464-8603, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042118446","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0002-0330-1787"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuya Takeda","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya 464-8603, Japan","TIER IV, Nagoya 450-6610, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya 464-8603, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"TIER IV, Nagoya 450-6610, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5022811365"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":0.4635,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61913765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"24","issue":"14","first_page":"4735","last_page":"4735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9969000220298767,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9969000220298767,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9968000054359436,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.993399977684021,"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/computer-science","display_name":"Computer science","score":0.7113574743270874},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6823519468307495},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5709213018417358},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5514814853668213},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.550067126750946},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49983716011047363},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4987356662750244},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4744454622268677},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4496706426143646},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.16803503036499023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7113574743270874},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6823519468307495},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5709213018417358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5514814853668213},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.550067126750946},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49983716011047363},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4987356662750244},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4744454622268677},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4496706426143646},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.16803503036499023},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":4,"locations":[{"id":"doi:10.3390/s24144735","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24144735","pdf_url":"https://www.mdpi.com/1424-8220/24/14/4735/pdf?version=1721702402","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:39066133","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39066133","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11281213","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11281213","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11281213/pdf/sensors-24-04735.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:5fe4055bd6bd438f9323aa40cf9317f9","is_oa":true,"landing_page_url":"https://doaj.org/article/5fe4055bd6bd438f9323aa40cf9317f9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 24, Iss 14, p 4735 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/s24144735","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24144735","pdf_url":"https://www.mdpi.com/1424-8220/24/14/4735/pdf?version=1721702402","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400875752.pdf","grobid_xml":"https://content.openalex.org/works/W4400875752.grobid-xml"},"referenced_works_count":133,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W1484723123","https://openalex.org/W1990012555","https://openalex.org/W1991084701","https://openalex.org/W1991742456","https://openalex.org/W2022071145","https://openalex.org/W2034806191","https://openalex.org/W2049981393","https://openalex.org/W2084920657","https://openalex.org/W2097696373","https://openalex.org/W2116484132","https://openalex.org/W2147800946","https://openalex.org/W2148228392","https://openalex.org/W2150066425","https://openalex.org/W2401640538","https://openalex.org/W2523049145","https://openalex.org/W2560609797","https://openalex.org/W2600383743","https://openalex.org/W2611104282","https://openalex.org/W2738588019","https://openalex.org/W2761873684","https://openalex.org/W2765302304","https://openalex.org/W2770604561","https://openalex.org/W2786969620","https://openalex.org/W2798365772","https://openalex.org/W2810132790","https://openalex.org/W2883471708","https://openalex.org/W2890003176","https://openalex.org/W2894458036","https://openalex.org/W2901707509","https://openalex.org/W2908804015","https://openalex.org/W2944512428","https://openalex.org/W2952394248","https://openalex.org/W2953127211","https://openalex.org/W2954174912","https://openalex.org/W2963255313","https://openalex.org/W2963305465","https://openalex.org/W2963420272","https://openalex.org/W2963917315","https://openalex.org/W2964294967","https://openalex.org/W2965803762","https://openalex.org/W2970641574","https://openalex.org/W2978091520","https://openalex.org/W3010003086","https://openalex.org/W3011955763","https://openalex.org/W3015443842","https://openalex.org/W3034482833","https://openalex.org/W3034604951","https://openalex.org/W3034669477","https://openalex.org/W3035623224","https://openalex.org/W3035686681","https://openalex.org/W3035970457","https://openalex.org/W3036452913","https://openalex.org/W3041956526","https://openalex.org/W3043547428","https://openalex.org/W3089979672","https://openalex.org/W3094502228","https://openalex.org/W3100744475","https://openalex.org/W3106570356","https://openalex.org/W3109395584","https://openalex.org/W3109585842","https://openalex.org/W3117234758","https://openalex.org/W3135367836","https://openalex.org/W3163853881","https://openalex.org/W3166762869","https://openalex.org/W3172084025","https://openalex.org/W3172477795","https://openalex.org/W3173668541","https://openalex.org/W3174688521","https://openalex.org/W3176974620","https://openalex.org/W3177583232","https://openalex.org/W3179351458","https://openalex.org/W3183092879","https://openalex.org/W3198460218","https://openalex.org/W3203597819","https://openalex.org/W3206020460","https://openalex.org/W3206072662","https://openalex.org/W3209727914","https://openalex.org/W3211640812","https://openalex.org/W3211800993","https://openalex.org/W4214530037","https://openalex.org/W4221143046","https://openalex.org/W4221154908","https://openalex.org/W4226058394","https://openalex.org/W4226352076","https://openalex.org/W4241543438","https://openalex.org/W4251009746","https://openalex.org/W4252102199","https://openalex.org/W4281485151","https://openalex.org/W4285069854","https://openalex.org/W4285428875","https://openalex.org/W4288055738","https://openalex.org/W4292432849","https://openalex.org/W4296604360","https://openalex.org/W4297161808","https://openalex.org/W4305039135","https://openalex.org/W4306820534","https://openalex.org/W4312420092","https://openalex.org/W4312458986","https://openalex.org/W4312480149","https://openalex.org/W4312563428","https://openalex.org/W4312815172","https://openalex.org/W4312912313","https://openalex.org/W4312935996","https://openalex.org/W4312960937","https://openalex.org/W4313017495","https://openalex.org/W4315778466","https://openalex.org/W4318751399","https://openalex.org/W4321855229","https://openalex.org/W4382999410","https://openalex.org/W4383097638","https://openalex.org/W4385431115","https://openalex.org/W4385800787","https://openalex.org/W4386065742","https://openalex.org/W4386066126","https://openalex.org/W4386075561","https://openalex.org/W4389519620","https://openalex.org/W4390872744","https://openalex.org/W4390874280","https://openalex.org/W6604803494","https://openalex.org/W6640963894","https://openalex.org/W6689402649","https://openalex.org/W6745935785","https://openalex.org/W6752670383","https://openalex.org/W6756256016","https://openalex.org/W6770507128","https://openalex.org/W6779305259","https://openalex.org/W6783988234","https://openalex.org/W6790875985","https://openalex.org/W6811433417","https://openalex.org/W6838393215","https://openalex.org/W6838634903","https://openalex.org/W6846310961"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2145836866","https://openalex.org/W2803255133","https://openalex.org/W2909431601"],"abstract_inverted_index":{"Cognitive":[0],"scientists":[1],"believe":[2],"that":[3,70,111],"adaptable":[4],"intelligent":[5],"agents":[6],"like":[7,128],"humans":[8],"perform":[9],"spatial":[10],"reasoning":[11],"tasks":[12],"by":[13,88],"learned":[14,158],"causal":[15],"mental":[16],"simulation.":[17],"The":[18,45,92],"problem":[19],"of":[20,56,78,84],"learning":[21,36,105,151],"these":[22],"simulations":[23],"is":[24,47],"called":[25],"predictive":[26,38],"world":[27,39],"modeling.":[28],"We":[29,68,143],"present":[30],"the":[31,71,95,102,112,145],"first":[32],"framework":[33],"for":[34,153],"a":[35,50,148],"open-vocabulary":[37],"model":[40,46,74],"(OV-PWM)":[41],"from":[42,64],"sensor":[43],"observations.":[44,67],"implemented":[48],"through":[49],"hierarchical":[51],"variational":[52],"autoencoder":[53],"(HVAE)":[54],"capable":[55],"predicting":[57],"diverse":[58,121],"and":[59,119,122,157],"accurate":[60,123],"fully":[61],"observed":[62],"environments":[63],"accumulated":[65],"partial":[66],"show":[69,110],"OV-PWM":[72,93,113,146],"can":[73,114],"high-dimensional":[75],"embedding":[76],"maps":[77],"latent":[79,117],"compositional":[80],"embeddings":[81],"representing":[82],"sets":[83],"overlapping":[85],"semantics":[86,137],"inferable":[87],"sufficient":[89],"similarity":[90],"inference.":[91],"simplifies":[94],"prior":[96],"two-stage":[97],"closed-set":[98],"PWM":[99],"approach":[100],"to":[101,162],"single-stage":[103],"end-to-end":[104],"method.":[106],"CARLA":[107],"simulator":[108],"experiments":[109],"learn":[115],"compact":[116],"representations":[118],"generate":[120],"worlds":[124],"with":[125],"fine":[126],"details":[127],"road":[129],"markings,":[130],"achieving":[131],"69":[132],"mIoU":[133],"over":[134],"six":[135],"query":[136],"on":[138],"an":[139],"urban":[140],"evaluation":[141],"sequence.":[142],"propose":[144],"as":[147],"versatile":[149],"continual":[150],"paradigm":[152],"providing":[154],"spatio-semantic":[155],"memory":[156],"internal":[159],"simulation":[160],"capabilities":[161],"future":[163],"general-purpose":[164],"mobile":[165],"robots.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}