{"id":"https://openalex.org/W4377705198","doi":"https://doi.org/10.1109/icara56516.2023.10125866","title":"Towards Clear Evaluation of Robotic Visual Semantic Navigation","display_name":"Towards Clear Evaluation of Robotic Visual Semantic Navigation","publication_year":2023,"publication_date":"2023-02-10","ids":{"openalex":"https://openalex.org/W4377705198","doi":"https://doi.org/10.1109/icara56516.2023.10125866"},"language":"en","primary_location":{"id":"doi:10.1109/icara56516.2023.10125866","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icara56516.2023.10125866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 9th International Conference on Automation, Robotics and Applications (ICARA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5082689781","display_name":"Carlos Guti\u00e9rrez-\u00c1lvarez","orcid":"https://orcid.org/0000-0002-5624-0076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlos Guti\u00e9rrez-\u00c1lvarez","raw_affiliation_strings":["University of Alcalá,Department of Signal Theory and Communications,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alcalá,Department of Signal Theory and Communications,Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035834340","display_name":"Sergio Hern\u00e1ndez-Garc\u00eda","orcid":"https://orcid.org/0000-0001-7254-9594"},"institutions":[{"id":"https://openalex.org/I182083151","display_name":"Universidad Rey Juan Carlos","ror":"https://ror.org/01v5cv687","country_code":"ES","type":"education","lineage":["https://openalex.org/I182083151"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Sergio Hern\u00e1ndez-Garc\u00eda","raw_affiliation_strings":["Rey Juan Carlos University, Superior Polytechnic School of Computer Science,Móstoles,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rey Juan Carlos University, Superior Polytechnic School of Computer Science,Móstoles,Spain","institution_ids":["https://openalex.org/I182083151"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043825648","display_name":"Nadia Nasri","orcid":"https://orcid.org/0000-0002-9005-6184"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nadia Nasri","raw_affiliation_strings":["University of Alcalá,Department of Signal Theory and Communications,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alcalá,Department of Signal Theory and Communications,Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069990831","display_name":"Alfredo Cuesta\u2010Infante","orcid":"https://orcid.org/0000-0002-3328-501X"},"institutions":[{"id":"https://openalex.org/I182083151","display_name":"Universidad Rey Juan Carlos","ror":"https://ror.org/01v5cv687","country_code":"ES","type":"education","lineage":["https://openalex.org/I182083151"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alfredo Cuesta-Infante","raw_affiliation_strings":["Rey Juan Carlos University, Superior Polytechnic School of Computer Science,Móstoles,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rey Juan Carlos University, Superior Polytechnic School of Computer Science,Móstoles,Spain","institution_ids":["https://openalex.org/I182083151"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042331786","display_name":"Roberto J. L\u00f3pez-Sastre","orcid":"https://orcid.org/0000-0002-2477-0152"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roberto J. L\u00f3pez-Sastre","raw_affiliation_strings":["University of Alcalá,Department of Signal Theory and Communications,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alcalá,Department of Signal Theory and Communications,Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"139","issue":null,"first_page":"340","last_page":"345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9995999932289124,"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/computer-science","display_name":"Computer science","score":0.782386302947998},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6029374599456787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5886729955673218},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5485183000564575},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5157027840614319},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5003259181976318},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4829396605491638},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47575992345809937},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3924909830093384},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35330575704574585},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1537337303161621}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.782386302947998},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6029374599456787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5886729955673218},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5485183000564575},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5157027840614319},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5003259181976318},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4829396605491638},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47575992345809937},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3924909830093384},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35330575704574585},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1537337303161621},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icara56516.2023.10125866","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icara56516.2023.10125866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 9th International Conference on Automation, Robotics and Applications (ICARA)","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":30,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W2736601468","https://openalex.org/W2950872548","https://openalex.org/W2962732398","https://openalex.org/W2962887844","https://openalex.org/W2963523627","https://openalex.org/W3004691725","https://openalex.org/W3036497058","https://openalex.org/W3036498537","https://openalex.org/W3095029720","https://openalex.org/W3133093447","https://openalex.org/W3136553706","https://openalex.org/W3166396011","https://openalex.org/W3201759799","https://openalex.org/W3211462570","https://openalex.org/W4214717370","https://openalex.org/W4286973470","https://openalex.org/W4287112297","https://openalex.org/W4298857966","https://openalex.org/W4300971732","https://openalex.org/W4312386498","https://openalex.org/W4312707839","https://openalex.org/W6638088447","https://openalex.org/W6729556111","https://openalex.org/W6773029903","https://openalex.org/W6779913221","https://openalex.org/W6789598788","https://openalex.org/W6791353385","https://openalex.org/W6797065961","https://openalex.org/W6800673378"],"related_works":["https://openalex.org/W2341492732","https://openalex.org/W3187193180","https://openalex.org/W106542691","https://openalex.org/W4287027380","https://openalex.org/W1699080303","https://openalex.org/W4297799326","https://openalex.org/W3116064965","https://openalex.org/W2378211422","https://openalex.org/W3193760048","https://openalex.org/W2768698792"],"abstract_inverted_index":{"In":[0,107],"this":[1,108],"paper":[2],"we":[3,110],"address":[4],"the":[5,43,66,76,84,87,92,118,122,187,196,205,210,215],"problem":[6],"of":[7,42,65,124,180,204],"visual":[8,53,175],"semantic":[9],"navigation":[10,88,144,189],"(VSN),":[11],"in":[12,48,83,90,168,195],"which":[13,91],"a":[14,36,63,112,126,163,169,178,201],"robot":[15],"needs":[16],"to":[17,22,29,71],"navigate":[18],"through":[19],"an":[20,24,135],"environment":[21],"reach":[23],"object":[25],"having":[26],"only":[27],"access":[28],"egocentric":[30],"RGB":[31],"perception":[32],"sensors.":[33],"This":[34,191],"is":[35,69,193,219],"recently":[37],"explored":[38],"problem,":[39,120],"where":[40],"most":[41],"approaches":[44],"leverage":[45],"last":[46],"advances":[47],"deep":[49],"learning":[50,58],"models":[51],"for":[52,117,140,185],"perception,":[54],"combined":[55],"with":[56,121,200],"reinforcement":[57],"(RL)":[59],"strategies.":[60],"Nonetheless,":[61],"after":[62],"review":[64],"literature,":[67],"it":[68],"complicated":[70],"perform":[72],"direct":[73],"comparisons":[74],"between":[75],"different":[77,104],"solutions.":[78],"The":[79],"main":[80,206],"difficulties":[81],"lie":[82],"fact":[85],"that":[86],"environments":[89],"experimental":[93,115,198],"metrics":[94],"are":[95,97],"reported":[96],"not":[98],"accessible,":[99],"and":[100,142,149,214],"each":[101],"approach":[102],"uses":[103],"RL":[105],"libraries.":[106],"paper,":[109],"release":[111],"publicly":[113],"available":[114,220],"setup":[116],"VSN":[119,165,207],"aim":[123],"providing":[125],"clear":[127],"benchmark.":[128],"It":[129],"has":[130],"been":[131],"constructed":[132],"using":[133,156],"pyRIL,":[134],"open":[136],"source":[137],"python":[138],"library":[139],"RL,":[141],"two":[143,181],"environments:":[145],"Miniwolrd-Maze":[146],"from":[147,153],"gym-miniworld,":[148],"one":[150],"3D":[151],"scene":[152],"HM3D":[154],"dataset":[155],"AI":[157],"Habitat":[158],"simulator.":[159],"We":[160],"finally":[161],"propose":[162],"state-of-the-art":[164],"model,":[166],"consisting":[167],"Contrastive":[170],"Language":[171],"Image":[172],"Pretraining":[173],"(CLIP)":[174],"encoder":[176],"plus":[177],"set":[179],"recurrent":[182],"neural":[183],"networks":[184],"producing":[186],"discrete":[188],"actions.":[190],"model":[192],"evaluated":[194],"proposed":[197],"setup,":[199],"careful":[202],"analysis":[203],"challenges,":[208],"namely:":[209],"sparse":[211],"rewards":[212],"problem;":[213],"exploitation-exploration":[216],"trade-off.":[217],"Code":[218],"at:":[221],"https://github.com/gramuah/vsn.":[222]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}