{"id":"https://openalex.org/W4391423004","doi":"https://doi.org/10.1109/icar58858.2023.10406465","title":"Bypassing the Simulation-to-Reality Gap: Online Reinforcement Learning Using a Supervisor","display_name":"Bypassing the Simulation-to-Reality Gap: Online Reinforcement Learning Using a Supervisor","publication_year":2023,"publication_date":"2023-12-05","ids":{"openalex":"https://openalex.org/W4391423004","doi":"https://doi.org/10.1109/icar58858.2023.10406465"},"language":"en","primary_location":{"id":"doi:10.1109/icar58858.2023.10406465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icar58858.2023.10406465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 21st International Conference on Advanced Robotics (ICAR)","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/A5076940088","display_name":"Benjamin Evans","orcid":"https://orcid.org/0000-0001-6312-1203"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Benjamin David Evans","raw_affiliation_strings":["Stellenbosch University,Department of Electrical and Electronic Engineering,South Africa","Department of Electrical and Electronic Engineering, Stellenbosch University, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stellenbosch University,Department of Electrical and Electronic Engineering,South Africa","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Stellenbosch University, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063677428","display_name":"Johannes Betz","orcid":"https://orcid.org/0000-0001-9197-2849"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johannes Betz","raw_affiliation_strings":["Technical University of Munich,Professorship Autonomous Vehicle Systems,Munich,Germany","Professorship Autonomous Vehicle Systems, Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Professorship Autonomous Vehicle Systems,Munich,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Professorship Autonomous Vehicle Systems, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089057605","display_name":"Hongrui Zheng","orcid":"https://orcid.org/0000-0002-1284-285X"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongrui Zheng","raw_affiliation_strings":["University of Pennsylvania,Department of Electrical and Systems Engineering,Philadelphia,USA","Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania,Department of Electrical and Systems Engineering,Philadelphia,USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091413322","display_name":"Herman A. Engelbrecht","orcid":"https://orcid.org/0000-0001-8753-8994"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Herman A. Engelbrecht","raw_affiliation_strings":["Stellenbosch University,Department of Electrical and Electronic Engineering,South Africa","Department of Electrical and Electronic Engineering, Stellenbosch University, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stellenbosch University,Department of Electrical and Electronic Engineering,South Africa","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Stellenbosch University, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009445756","display_name":"Rahul Mangharam","orcid":"https://orcid.org/0000-0002-3388-8283"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Mangharam","raw_affiliation_strings":["University of Pennsylvania,Department of Electrical and Systems Engineering,Philadelphia,USA","Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania,Department of Electrical and Systems Engineering,Philadelphia,USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065610954","display_name":"Hendrik Willem Jordaan","orcid":"https://orcid.org/0000-0002-6466-6456"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Hendrik W. Jordaan","raw_affiliation_strings":["Stellenbosch University,Department of Electrical and Electronic Engineering,South Africa","Department of Electrical and Electronic Engineering, Stellenbosch University, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stellenbosch University,Department of Electrical and Electronic Engineering,South Africa","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Stellenbosch University, South Africa","institution_ids":["https://openalex.org/I26092322"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"325","last_page":"331"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9983000159263611,"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"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9983000159263611,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9941999912261963,"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/T10524","display_name":"Traffic control and management","score":0.9817000031471252,"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/supervisor","display_name":"Supervisor","score":0.8264073133468628},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.807274341583252},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6492392420768738},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6154835820198059},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.5690263509750366},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5685175657272339},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4476364254951477},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4312889575958252},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.42555558681488037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39277324080467224}],"concepts":[{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.8264073133468628},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.807274341583252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6492392420768738},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6154835820198059},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.5690263509750366},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5685175657272339},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4476364254951477},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4312889575958252},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.42555558681488037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39277324080467224},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icar58858.2023.10406465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icar58858.2023.10406465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 21st International Conference on Advanced Robotics (ICAR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W2120179083","https://openalex.org/W2567705466","https://openalex.org/W2585477135","https://openalex.org/W2622408375","https://openalex.org/W2740508249","https://openalex.org/W2869375357","https://openalex.org/W2887709062","https://openalex.org/W2951357333","https://openalex.org/W2959091704","https://openalex.org/W2963086870","https://openalex.org/W2966735560","https://openalex.org/W2968983352","https://openalex.org/W2972050850","https://openalex.org/W2999762404","https://openalex.org/W3020712699","https://openalex.org/W3068678661","https://openalex.org/W3088310808","https://openalex.org/W3102621632","https://openalex.org/W3115648115","https://openalex.org/W3120778962","https://openalex.org/W3121342653","https://openalex.org/W3136325136","https://openalex.org/W3188004887","https://openalex.org/W3205950063","https://openalex.org/W4210870706","https://openalex.org/W4211094662","https://openalex.org/W4221157983","https://openalex.org/W4281705700","https://openalex.org/W4285102517","https://openalex.org/W4285228542","https://openalex.org/W4293255219","https://openalex.org/W4297795161","https://openalex.org/W4301501993","https://openalex.org/W6639175102","https://openalex.org/W6683397050","https://openalex.org/W6743563064","https://openalex.org/W6748839928","https://openalex.org/W6772100842","https://openalex.org/W6787219693"],"related_works":["https://openalex.org/W4387731985","https://openalex.org/W2755149878","https://openalex.org/W2941808082","https://openalex.org/W2468425257","https://openalex.org/W4377009725","https://openalex.org/W4379086698","https://openalex.org/W2528721242","https://openalex.org/W4320164562","https://openalex.org/W2356364326","https://openalex.org/W2372069567"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,170],"(DRL)":[3],"is":[4,30,44,54,71,131,141],"a":[5,95,100,107,112,119,138,175,180,189],"promising":[6],"method":[7,96,167,206],"to":[8,51,68,74,103,122,192],"learn":[9],"control":[10],"policies":[11],"for":[12],"robots":[13],"only":[14],"from":[15],"demonstration":[16],"and":[17,46,86,135,162,173,216],"experience.":[18],"To":[19],"cover":[20],"the":[21,26,75,80,83,87,125,129,145,152,157,217],"whole":[22],"dynamic":[23],"behaviour":[24],"of":[25,97,182],"robot,":[27],"DRL":[28,49,101,158],"training":[29,43,99,156],"an":[31],"active":[32],"exploration":[33],"process":[34],"typically":[35],"performed":[36],"in":[37,64,171,227],"simulation":[38,42,84,172,198],"environments.":[39],"Although":[40],"this":[41,91],"cheap":[45],"fast,":[47],"applying":[48],"algorithms":[50],"real-world":[52,183],"settings":[53],"difficult.":[55],"If":[56],"agents":[57,208,219],"are":[58],"trained":[59,218,226],"until":[60],"they":[61],"perform":[62],"safely":[63],"simulation,":[65],"transferring":[66],"them":[67],"physical":[69,88,108,176],"systems":[70],"difficult":[72],"due":[73],"sim-to-real":[76,153],"gap":[77],"caused":[78],"by":[79,110,128],"difference":[81],"between":[82],"dynamics":[85],"robot.":[89],"In":[90],"paper,":[92],"we":[93,149,186],"present":[94],"online":[98,188],"agent":[102,130],"drive":[104,193],"autonomously":[105,194],"on":[106,144,174],"vehicle":[109,191],"using":[111],"model-based":[113],"safety":[114],"supervisor.":[115],"Our":[116],"solution":[117],"uses":[118],"supervisory":[120],"system":[121],"check":[123],"if":[124],"action":[126,140],"selected":[127],"safe":[132,139],"or":[133],"unsafe":[134],"ensure":[136],"that":[137,204],"always":[142],"implemented":[143],"vehicle.":[146,177],"With":[147],"this,":[148],"can":[150],"bypass":[151],"problem":[154],"while":[155,213],"algorithm":[159],"safely,":[160],"quickly,":[161],"efficiently.":[163],"We":[164,178],"compare":[165],"our":[166,205],"with":[168,195,209],"conventional":[169],"provide":[179],"variety":[181],"experiments":[184],"where":[185],"train":[187],"small-scale":[190],"no":[196],"prior":[197],"training.":[199],"The":[200],"evaluation":[201],"results":[202],"show":[203],"trains":[207],"improved":[210],"sample":[211],"efficiency":[212],"never":[214],"crashing,":[215],"demonstrate":[220],"better":[221],"driving":[222],"performance":[223],"than":[224],"those":[225],"simulation.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}