{"id":"https://openalex.org/W3088508929","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207497","title":"Robust Reinforcement Learning-based Autonomous Driving Agent for Simulation and Real World","display_name":"Robust Reinforcement Learning-based Autonomous Driving Agent for Simulation and Real World","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3088508929","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207497","mag":"3088508929"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2009.11212","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Peter Almasi","orcid":null},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Peter Almasi","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, HUNGARY"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, HUNGARY","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Robert Moni","orcid":null},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Robert Moni","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, HUNGARY"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, HUNGARY","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":null,"display_name":"Balint Gyires-Toth","orcid":null},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Balint Gyires-Toth","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, HUNGARY"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, HUNGARY","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":1.5085,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.86512707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"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":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10036","display_name":"Advanced Neural Network Applications","score":0.9937000274658203,"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":0.7378000020980835},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6682999730110168},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.48010000586509705},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.43549999594688416},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.3993000090122223},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.3314000070095062},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3098999857902527}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7378000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6700999736785889},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6682999730110168},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5958999991416931},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43549999594688416},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.4113999903202057},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.37709999084472656},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.30410000681877136},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.2720000147819519},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2572999894618988},{"id":"https://openalex.org/C118974865","wikidata":"https://www.wikidata.org/wiki/Q7300773","display_name":"Real-time Control System","level":3,"score":0.2572000026702881},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2009.11212","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.11212","pdf_url":"https://arxiv.org/pdf/2009.11212","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2009.11212","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.11212","pdf_url":"https://arxiv.org/pdf/2009.11212","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1747778109","https://openalex.org/W2112796928","https://openalex.org/W2145339207","https://openalex.org/W2583993537","https://openalex.org/W2605102758","https://openalex.org/W2737347195","https://openalex.org/W2766447205","https://openalex.org/W2806163172","https://openalex.org/W2807785345","https://openalex.org/W2968116426","https://openalex.org/W2981207549","https://openalex.org/W2982316857","https://openalex.org/W6637967152","https://openalex.org/W6678097026","https://openalex.org/W6684338915","https://openalex.org/W6704559304","https://openalex.org/W6737454590","https://openalex.org/W6747123330","https://openalex.org/W6748481559","https://openalex.org/W6750574679","https://openalex.org/W6760018712","https://openalex.org/W6772005887","https://openalex.org/W6966558720"],"related_works":[],"abstract_inverted_index":{"Deep":[0,86],"Reinforcement":[1],"Learning":[2],"(DRL)":[3],"has":[4,124],"been":[5],"successfully":[6],"used":[7],"to":[8,27,38,48,59,66,104,125,140,151],"solve":[9],"different":[10],"challenges,":[11],"e.g.":[12],"complex":[13],"board":[14],"and":[15,45,100,110,146],"computer":[16],"games,":[17],"recently.":[18],"However,":[19],"solving":[20],"real-world":[21,63,111],"robotics":[22],"tasks":[23],"with":[24],"DRL":[25],"seems":[26],"be":[28,37],"a":[29,43,56,74,97,108,131],"more":[30],"difficult":[31],"challenge.":[32],"The":[33,113,135],"desired":[34],"approach":[35],"would":[36],"train":[39],"the":[40,49,67,92,118,122,127],"agent":[41,93,123,137],"in":[42,55,62,96,107,117],"simulator":[44,57],"transfer":[46],"it":[47,101],"real":[50],"world.":[51],"Still,":[52],"models":[53],"trained":[54,95,136],"tend":[58],"perform":[60],"poorly":[61],"environments":[64],"due":[65],"differences.":[68],"In":[69,89],"this":[70],"paper,":[71],"we":[72],"present":[73],"DRL-based":[75],"algorithm":[76],"that":[77],"is":[78,94,102,115,138,149],"capable":[79],"of":[80],"performing":[81],"autonomous":[82],"robot":[83],"control":[84],"using":[85],"Q-Networks":[87],"(DQN).":[88],"our":[90],"approach,":[91],"simulated":[98,109],"environment":[99],"able":[103,139],"navigate":[105],"both":[106],"environment.":[112],"method":[114],"evaluated":[116],"Duckietown":[119],"environment,":[120],"where":[121],"follow":[126],"lane":[128],"based":[129],"on":[130,142],"monocular":[132],"camera":[133],"input.":[134],"run":[141],"limited":[143],"hardware":[144],"resources":[145],"its":[147],"performance":[148],"comparable":[150],"state-of-the-art":[152],"approaches.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-10-01T00:00:00"}