{"id":"https://openalex.org/W4413393756","doi":"https://doi.org/10.23919/acc63710.2025.11107738","title":"End-to-end Reinforcement Learning for Autonomous Racing: Bridging the sim-to-real gap","display_name":"End-to-end Reinforcement Learning for Autonomous Racing: Bridging the sim-to-real gap","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413393756","doi":"https://doi.org/10.23919/acc63710.2025.11107738"},"language":"en","primary_location":{"id":"doi:10.23919/acc63710.2025.11107738","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"article","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/A5119375070","display_name":"Csan\u00e1d Budai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117195","display_name":"Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Csan\u00e1d Budai","raw_affiliation_strings":["Hungarian Research Network (HUN-REN),Institute for Computer Science and Control (SZTAKI),Budapest,Hungary,H-1111"],"affiliations":[{"raw_affiliation_string":"Hungarian Research Network (HUN-REN),Institute for Computer Science and Control (SZTAKI),Budapest,Hungary,H-1111","institution_ids":["https://openalex.org/I4210117195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119375071","display_name":"Tam\u00e1s Sz\u00e9les","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117195","display_name":"Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Tam\u00e1s Sz\u00e9les","raw_affiliation_strings":["Hungarian Research Network (HUN-REN),Institute for Computer Science and Control (SZTAKI),Budapest,Hungary,H-1111"],"affiliations":[{"raw_affiliation_string":"Hungarian Research Network (HUN-REN),Institute for Computer Science and Control (SZTAKI),Budapest,Hungary,H-1111","institution_ids":["https://openalex.org/I4210117195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081056211","display_name":"Bal\u00e1zs N\u00e9meth","orcid":"https://orcid.org/0000-0003-0211-3204"},"institutions":[{"id":"https://openalex.org/I4210117195","display_name":"Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Bal\u00e1zs N\u00e9meth","raw_affiliation_strings":["Hungarian Research Network (HUN-REN),Institute for Computer Science and Control (SZTAKI),Budapest,Hungary,H-1111"],"affiliations":[{"raw_affiliation_string":"Hungarian Research Network (HUN-REN),Institute for Computer Science and Control (SZTAKI),Budapest,Hungary,H-1111","institution_ids":["https://openalex.org/I4210117195"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038755734","display_name":"P\u00e9ter G\u00e1sp\u00e1r","orcid":"https://orcid.org/0000-0003-3388-1724"},"institutions":[{"id":"https://openalex.org/I4210117195","display_name":"Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"P\u00e9ter G\u00e1sp\u00e1r","raw_affiliation_strings":["Hungarian Research Network (HUN-REN),Institute for Computer Science and Control (SZTAKI),Budapest,Hungary,H-1111"],"affiliations":[{"raw_affiliation_string":"Hungarian Research Network (HUN-REN),Institute for Computer Science and Control (SZTAKI),Budapest,Hungary,H-1111","institution_ids":["https://openalex.org/I4210117195"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5119375070"],"corresponding_institution_ids":["https://openalex.org/I4210117195"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1106474,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"200","last_page":"205"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9710000157356262,"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":0.9710000157356262,"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/T10808","display_name":"Electric and Hybrid Vehicle Technologies","score":0.9599000215530396,"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/T12810","display_name":"Real-time simulation and control systems","score":0.9309999942779541,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.8818837404251099},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6489459872245789},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6288753747940063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5502312183380127},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4235234558582306},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3289252817630768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3211289346218109},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2522512674331665},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.1827298402786255},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1752493977546692}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8818837404251099},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6489459872245789},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6288753747940063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5502312183380127},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4235234558582306},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3289252817630768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3211289346218109},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2522512674331665},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1827298402786255},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1752493977546692}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/acc63710.2025.11107738","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.sztaki.hu:11067","is_oa":false,"landing_page_url":"https://eprints.sztaki.hu/11067/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401907","display_name":"SZTAKI Publication Repository (Hungarian Academy of Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I7597260","host_organization_name":"Hungarian Academy of Sciences","host_organization_lineage":["https://openalex.org/I7597260"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2605102758","https://openalex.org/W2982095652","https://openalex.org/W3088310808","https://openalex.org/W3090027660","https://openalex.org/W3130441894","https://openalex.org/W4211094662","https://openalex.org/W4237591687","https://openalex.org/W4281757468","https://openalex.org/W4385363794","https://openalex.org/W4389352651","https://openalex.org/W4393941736","https://openalex.org/W4394674699","https://openalex.org/W4396564042"],"related_works":["https://openalex.org/W4408719353","https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2151749779","https://openalex.org/W2054685365","https://openalex.org/W4310083477","https://openalex.org/W2056057048","https://openalex.org/W2328553770","https://openalex.org/W2667588871"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,42,70],"is":[3,15,78,87,98],"a":[4,24,45,57,61,81,93,106],"promising":[5],"technique":[6],"that":[7,59,86,100,108],"can":[8,22,109],"help":[9],"create":[10,23],"autonomous":[11],"agents.":[12],"However,":[13],"it":[14],"still":[16],"an":[17],"open":[18],"problem":[19],"how":[20],"one":[21],"controller":[25],"with":[26,71],"robust":[27],"operation":[28],"for":[29,40,49],"real-world":[30,41],"automotive":[31],"systems.":[32],"The":[33,76],"difficulty":[34],"lies":[35],"in":[36,92,105],"either":[37],"sample":[38],"efficiency":[39],"or":[43],"developing":[44],"good":[46],"enough":[47],"simulator":[48],"training.":[50],"This":[51],"paper":[52],"addresses":[53],"the":[54,64,101,111,116],"latter,":[55],"proposing":[56],"method":[58,77],"provides":[60],"solution":[62],"to":[63,89],"sim-to-real":[65],"gap":[66],"through":[67],"domain":[68],"randomization,":[69],"disturbances,":[72],"and":[73],"observation":[74],"preprocessing.":[75],"validated":[79],"on":[80],"small-scale":[82],"F1TENTH-type":[83],"test":[84],"vehicle,":[85],"trained":[88],"race":[90],"autonomously":[91],"fully":[94],"end-to-end":[95],"manner.":[96],"It":[97],"demonstrated":[99],"training":[102],"process":[103],"results":[104],"policy":[107],"drive":[110],"car":[112],"safely":[113],"even":[114],"over":[115],"grip":[117],"limit.":[118]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}