{"id":"https://openalex.org/W2980730703","doi":"https://doi.org/10.1109/ecmr.2019.8870964","title":"Vision-based Navigation Using Deep Reinforcement Learning","display_name":"Vision-based Navigation Using Deep Reinforcement Learning","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2980730703","doi":"https://doi.org/10.1109/ecmr.2019.8870964","mag":"2980730703"},"language":"en","primary_location":{"id":"doi:10.1109/ecmr.2019.8870964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ecmr.2019.8870964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 European Conference on Mobile Robots (ECMR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1908.03627","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jonas Kulhanek","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Jonas Kulhanek","raw_affiliation_strings":["Cognitive Robotics, Faculty of 3mE, Delft University of Technology, Delft, CD, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Cognitive Robotics, Faculty of 3mE, Delft University of Technology, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Erik Derner","orcid":null},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Erik Derner","raw_affiliation_strings":["Department of Control Engineering, Czech Technical University in Prague, Prague, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Department of Control Engineering, Czech Technical University in Prague, Prague, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tim de Bruin","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Tim de Bruin","raw_affiliation_strings":["Cognitive Robotics, Faculty of 3mE, Delft University of Technology, Delft, CD, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Cognitive Robotics, Faculty of 3mE, Delft University of Technology, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":null,"display_name":"Robert Babuska","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Robert Babuska","raw_affiliation_strings":["Cognitive Robotics, Faculty of 3mE, Delft University of Technology, Delft, CD, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Cognitive Robotics, Faculty of 3mE, Delft University of Technology, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":3.9059,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.94977296,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9983000159263611,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7483000159263611},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5026000142097473},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4903999865055084},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4415999948978424},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.39730000495910645},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.37880000472068787},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.3698999881744385},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3522000014781952}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7483000159263611},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347999811172485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7275000214576721},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4903999865055084},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4415999948978424},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4097000062465668},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.39730000495910645},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3474000096321106},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3301999866962433},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C2780527621","wikidata":"https://www.wikidata.org/wiki/Q7936593","display_name":"Visual control","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.29989999532699585},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.28999999165534973},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ecmr.2019.8870964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ecmr.2019.8870964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 European Conference on Mobile Robots (ECMR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1908.03627","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.03627","pdf_url":"https://arxiv.org/pdf/1908.03627","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":"pmh:oai:tudelft.nl:uuid:1b6cf013-9b29-4082-98fa-0d9409f9b13a","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:1b6cf013-9b29-4082-98fa-0d9409f9b13a","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1908.03627","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.03627","pdf_url":"https://arxiv.org/pdf/1908.03627","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2046376809","https://openalex.org/W2064675550","https://openalex.org/W2119717200","https://openalex.org/W2154997814","https://openalex.org/W2194775991","https://openalex.org/W2557465155","https://openalex.org/W2570734388","https://openalex.org/W2962887844","https://openalex.org/W6683204974","https://openalex.org/W6692846177","https://openalex.org/W6743802245","https://openalex.org/W6747106673"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,34,100,144],"(RL)":[3],"has":[4,121],"been":[5,122],"successfully":[6],"applied":[7],"to":[8,20,45,66,101,110],"a":[9,27,32,42,46,103],"variety":[10],"of":[11,17,37,80,85,98,106,114,143,167],"game-like":[12],"environments.":[13,150],"However,":[14],"the":[15,58,78,81,86,91,96,107,112,127,160,165,174],"application":[16],"deep":[18],"RL":[19],"visual":[21,68,170],"navigation":[22,69,171],"with":[23,62],"realistic":[24],"environments":[25],"is":[26,138,141],"challenging":[28],"task.":[29],"We":[30,71],"propose":[31,72],"novel":[33],"architecture":[35],"capable":[36,142],"navigating":[38],"an":[39,50],"agent,":[40],"e.g.":[41],"mobile":[43],"robot,":[44],"target":[47,87],"given":[48],"by":[49,125],"image.":[51],"To":[52],"achieve":[53],"this,":[54],"we":[55],"have":[56],"extended":[57],"batched":[59],"A2C":[60],"algorithm":[61],"auxiliary":[63,75],"tasks":[64,94],"designed":[65],"improve":[67],"performance.":[70],"three":[73],"additional":[74],"tasks:":[76],"predicting":[77,90],"segmentation":[79],"observation":[82],"image":[83,88],"and":[84,89,109,158],"depth-map.":[92],"These":[93],"enable":[95],"use":[97],"supervised":[99],"pre-train":[102],"major":[104],"part":[105],"network":[108,136],"reduce":[111],"number":[113],"training":[115,119],"steps":[116],"substantially.":[117],"The":[118],"performance":[120,166],"further":[123],"improved":[124],"increasing":[126],"environment":[128,162],"complexity":[129],"gradually":[130],"over":[131],"time.":[132],"An":[133],"efficient":[134],"neural":[135],"structure":[137],"proposed,":[139],"which":[140],"for":[145],"multiple":[146,149],"targets":[147],"in":[148,154],"Our":[151],"method":[152],"navigates":[153],"continuous":[155],"state":[156],"spaces":[157],"on":[159],"AI2-THOR":[161],"simulator":[163],"surpasses":[164],"state-of-the-art":[168],"goal-oriented":[169],"methods":[172],"from":[173],"literature.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":8}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-10-25T00:00:00"}