{"id":"https://openalex.org/W2905249540","doi":"https://doi.org/10.1109/itsc.2018.8569612","title":"Zero-shot Deep Reinforcement Learning Driving Policy Transfer for Autonomous Vehicles based on Robust Control","display_name":"Zero-shot Deep Reinforcement Learning Driving Policy Transfer for Autonomous Vehicles based on Robust Control","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2905249540","doi":"https://doi.org/10.1109/itsc.2018.8569612","mag":"2905249540"},"language":"en","primary_location":{"id":"doi:10.1109/itsc.2018.8569612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc.2018.8569612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","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/A5101767626","display_name":"Zhuo Xu","orcid":"https://orcid.org/0000-0002-5792-2589"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Xu","raw_affiliation_strings":["Department of Mechanical Engineering, University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101867083","display_name":"Chen Tang","orcid":"https://orcid.org/0000-0002-7536-9983"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Tang","raw_affiliation_strings":["Department of Mechanical Engineering, University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064077634","display_name":"Masayoshi Tomizuka","orcid":"https://orcid.org/0000-0003-0206-6639"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masayoshi Tomizuka","raw_affiliation_strings":["Department of Mechanical Engineering, University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2865","last_page":"2871"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10805","display_name":"Vehicle Dynamics and Control Systems","score":0.9970999956130981,"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/T10805","display_name":"Vehicle Dynamics and Control Systems","score":0.9970999956130981,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.996399998664856,"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":0.9943000078201294,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7958351373672485},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6893004775047302},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5506524443626404},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5150653719902039},{"id":"https://openalex.org/keywords/vehicle-dynamics","display_name":"Vehicle dynamics","score":0.4892706573009491},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.48876500129699707},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.47843268513679504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46555784344673157},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45011743903160095},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.4385245442390442},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4232971668243408},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.37352362275123596},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.344446063041687},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2562904953956604},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2302665114402771}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7958351373672485},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6893004775047302},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5506524443626404},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5150653719902039},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.4892706573009491},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.48876500129699707},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.47843268513679504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46555784344673157},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45011743903160095},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.4385245442390442},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4232971668243408},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.37352362275123596},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.344446063041687},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2562904953956604},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2302665114402771},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","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},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc.2018.8569612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc.2018.8569612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","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":29,"referenced_works":["https://openalex.org/W1544016679","https://openalex.org/W1990083550","https://openalex.org/W2025420234","https://openalex.org/W2133233905","https://openalex.org/W2139137304","https://openalex.org/W2167224731","https://openalex.org/W2173248099","https://openalex.org/W2230652337","https://openalex.org/W2342840547","https://openalex.org/W2343568200","https://openalex.org/W2426267443","https://openalex.org/W2529477964","https://openalex.org/W2530944449","https://openalex.org/W2559767995","https://openalex.org/W2563338958","https://openalex.org/W2736601468","https://openalex.org/W2768925084","https://openalex.org/W2963280855","https://openalex.org/W2963614114","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W3021796787","https://openalex.org/W3101442004","https://openalex.org/W4297824641","https://openalex.org/W4300446173","https://openalex.org/W4319988532","https://openalex.org/W6679847170","https://openalex.org/W6684338915","https://openalex.org/W6692846177"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W1941703695","https://openalex.org/W2031695474","https://openalex.org/W4323768008","https://openalex.org/W3131574667","https://openalex.org/W2586732548","https://openalex.org/W2145006118"],"abstract_inverted_index":{"Although":[0],"deep":[1,20,103],"reinforcement":[2],"learning":[3],"(deep":[4],"RL)":[5],"methods":[6],"have":[7,26],"lots":[8],"of":[9,55,149],"strengths":[10],"that":[11],"are":[12,112],"favorable":[13],"if":[14],"applied":[15,124],"to":[16,52,66,115,125,153],"autonomous":[17,24,72],"driving,":[18],"real":[19],"RL":[21,89,104],"applications":[22],"in":[23,71],"driving":[25,159],"been":[27],"slowed":[28],"down":[29],"by":[30],"the":[31,35,40,53,61,116,127,131,136,147,150],"modeling":[32,128],"gap":[33,129],"between":[34],"source":[36],"(training)":[37],"domain":[38],"and":[39,92,135,167],"target":[41,117],"(deployment)":[42],"domain.":[43],"Unlike":[44],"current":[45],"policy":[46],"transfer":[47,67,79,156],"approaches,":[48],"which":[49,81],"generally":[50],"limit":[51],"usage":[54],"uninterpretable":[56],"neural":[57],"network":[58],"representations":[59],"as":[60,140,162],"transferred":[62,113],"features,":[63],"we":[64,82],"propose":[65],"concrete":[68],"kinematic":[69],"quantities":[70],"driving.":[73],"The":[74,102],"proposed":[75,151],"robust-control-based":[76],"(RC)":[77],"generic":[78],"architecture,":[80],"call":[83],"RL-RC,":[84],"incorporates":[85],"a":[86,93],"transferable":[87],"hierarchical":[88],"trajectory":[90],"planner":[91],"robust":[94,120],"tracking":[95,121],"controller":[96],"based":[97],"on":[98],"disturbance":[99],"observer":[100],"(DOB).":[101],"policies":[105],"trained":[106],"with":[107],"known":[108],"nominal":[109],"dynamics":[110,133],"model":[111],"directly":[114],"domain,":[118],"DOB-based":[119],"control":[122],"is":[123],"tackle":[126],"including":[130],"vehicle":[132],"errors":[134],"external":[137],"disturbances":[138],"such":[139,161],"side":[141],"forces.":[142],"We":[143],"provide":[144],"simulations":[145],"validating":[146],"capability":[148],"method":[152],"achieve":[154],"zero-shot":[155],"across":[157],"multiple":[158],"scenarios":[160],"lane":[163,165],"keeping,":[164],"changing":[166],"obstacle":[168],"avoidance.":[169]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}