{"id":"https://openalex.org/W4389666601","doi":"https://doi.org/10.1109/iros55552.2023.10342038","title":"Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios","display_name":"Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389666601","doi":"https://doi.org/10.1109/iros55552.2023.10342038"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5061100056","display_name":"Yiren Lu","orcid":"https://orcid.org/0000-0003-2302-1851"},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Yiren Lu","raw_affiliation_strings":["Waymo Research"],"affiliations":[{"raw_affiliation_string":"Waymo Research","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037720811","display_name":"Justin Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Justin Fu","raw_affiliation_strings":["Waymo Research"],"affiliations":[{"raw_affiliation_string":"Waymo Research","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048032272","display_name":"George Tucker","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113520","display_name":"Brain (Germany)","ror":"https://ror.org/01gamcy45","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210113520"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"George Tucker","raw_affiliation_strings":["Google Research, Brain Team"],"affiliations":[{"raw_affiliation_string":"Google Research, Brain Team","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113520"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065822895","display_name":"Xinlei Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xinlei Pan","raw_affiliation_strings":["Waymo Research"],"affiliations":[{"raw_affiliation_string":"Waymo Research","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028247918","display_name":"Eli Bronstein","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Eli Bronstein","raw_affiliation_strings":["Waymo Research"],"affiliations":[{"raw_affiliation_string":"Waymo Research","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008334918","display_name":"Rebecca Roelofs","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rebecca Roelofs","raw_affiliation_strings":["Waymo Research"],"affiliations":[{"raw_affiliation_string":"Waymo Research","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014258241","display_name":"Benjamin Sapp","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benjamin Sapp","raw_affiliation_strings":["Waymo Research"],"affiliations":[{"raw_affiliation_string":"Waymo Research","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082212958","display_name":"Brandyn White","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Brandyn White","raw_affiliation_strings":["Waymo Research"],"affiliations":[{"raw_affiliation_string":"Waymo Research","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002971435","display_name":"Aleksandra Faust","orcid":"https://orcid.org/0000-0002-3268-8685"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113520","display_name":"Brain (Germany)","ror":"https://ror.org/01gamcy45","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210113520"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Aleksandra Faust","raw_affiliation_strings":["Google Research, Brain Team"],"affiliations":[{"raw_affiliation_string":"Google Research, Brain Team","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113520"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056879203","display_name":"Shimon Whiteson","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shimon Whiteson","raw_affiliation_strings":["Waymo Research"],"affiliations":[{"raw_affiliation_string":"Waymo Research","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081024054","display_name":"Dragomir Anguelov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dragomir Anguelov","raw_affiliation_strings":["Waymo Research"],"affiliations":[{"raw_affiliation_string":"Waymo Research","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"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"]},{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113520","display_name":"Brain (Germany)","ror":"https://ror.org/01gamcy45","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210113520"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Sergey Levine","raw_affiliation_strings":["Google Research, Brain Team","UC Berkeley"],"affiliations":[{"raw_affiliation_string":"Google Research, Brain Team","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113520"]},{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5061100056"],"corresponding_institution_ids":["https://openalex.org/I4210145145"],"apc_list":null,"apc_paid":null,"fwci":6.7756,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.97703468,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7553","last_page":"7560"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9979000091552734,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.9793999791145325,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.815645158290863},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.729183554649353},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.711348295211792},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6382913589477539},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4840206801891327},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4593806862831116},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4032643437385559},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13476714491844177},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07382363080978394}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.815645158290863},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.729183554649353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.711348295211792},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6382913589477539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4840206801891327},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4593806862831116},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4032643437385559},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13476714491844177},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07382363080978394},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W1544016679","https://openalex.org/W1583837637","https://openalex.org/W2098152875","https://openalex.org/W2145339207","https://openalex.org/W2167224731","https://openalex.org/W2342840547","https://openalex.org/W2559878382","https://openalex.org/W2560678327","https://openalex.org/W2609009256","https://openalex.org/W2741122588","https://openalex.org/W2781726626","https://openalex.org/W2788862220","https://openalex.org/W2837605352","https://openalex.org/W2947630374","https://openalex.org/W2962894046","https://openalex.org/W2962977206","https://openalex.org/W2963277051","https://openalex.org/W2963322416","https://openalex.org/W2963411833","https://openalex.org/W2963625099","https://openalex.org/W2964061343","https://openalex.org/W2968983352","https://openalex.org/W2980087597","https://openalex.org/W2982745079","https://openalex.org/W2996474936","https://openalex.org/W3028769608","https://openalex.org/W3033324992","https://openalex.org/W3108486966","https://openalex.org/W3157893055","https://openalex.org/W3171077607","https://openalex.org/W3172360140","https://openalex.org/W3193987867","https://openalex.org/W3196864007","https://openalex.org/W3203018838","https://openalex.org/W3203076355","https://openalex.org/W4230519770","https://openalex.org/W4283320485","https://openalex.org/W4287115177","https://openalex.org/W4301501993","https://openalex.org/W4306882120","https://openalex.org/W4308068586","https://openalex.org/W4320458958","https://openalex.org/W6640174482","https://openalex.org/W6684338915","https://openalex.org/W6704559304","https://openalex.org/W6718092244","https://openalex.org/W6728155968","https://openalex.org/W6730700719","https://openalex.org/W6736482081","https://openalex.org/W6742461812","https://openalex.org/W6745935785","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6754470798","https://openalex.org/W6755103542","https://openalex.org/W6768870957","https://openalex.org/W6769043036","https://openalex.org/W6779265984","https://openalex.org/W6790830454","https://openalex.org/W6796589144","https://openalex.org/W6796929002","https://openalex.org/W6797256610","https://openalex.org/W6800926788","https://openalex.org/W6803274636","https://openalex.org/W6839505761","https://openalex.org/W6847397276","https://openalex.org/W6849793003"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2665305151"],"abstract_inverted_index":{"Imitation":[0],"learning":[1,30,49,53,151],"(IL)":[2],"is":[3,141],"a":[4,77,146],"simple":[5,55],"and":[6,39,62,87,149],"powerful":[7],"way":[8],"to":[9,21,34],"use":[10],"high-quality":[11],"human":[12,163],"driving":[13,65,85,155,164],"data,":[14,86,119],"which":[15],"can":[16,57,107],"be":[17],"collected":[18],"at":[19],"scale,":[20],"produce":[22],"human-like":[23],"behavior.":[24],"However,":[25],"policies":[26,66],"based":[27],"on":[28,79,126],"imitation":[29,48,71,106,148],"alone":[31],"often":[32],"fail":[33],"sufficiently":[35],"account":[36],"for":[37],"safety":[38,61],"reliability":[40,63],"concerns.":[41],"In":[42,73],"this":[43,140],"paper,":[44],"we":[45,75],"show":[46],"how":[47],"combined":[50,147],"with":[51],"reinforcement":[52,150],"using":[54],"rewards":[56],"substan-tially":[58],"improve":[59],"the":[60,117,127,142],"of":[64,83,98,145,160],"over":[67,80],"those":[68],"learned":[69],"from":[70],"alone.":[72],"particular,":[74],"train":[76],"policy":[78],"lOOk":[81],"miles":[82],"urban":[84],"measure":[88],"its":[89],"effectiveness":[90],"in":[91,110,135,153],"test":[92],"scenarios":[93,112,130],"grouped":[94],"by":[95,116],"different":[96],"levels":[97],"collision":[99],"likelihood.":[100],"Our":[101],"analysis":[102],"shows":[103],"that":[104,113,156],"while":[105],"perform":[108],"well":[109],"low-difficulty":[111],"are":[114],"well-covered":[115],"demonstration":[118],"our":[120,138],"proposed":[121],"approach":[122,152],"significantly":[123],"improves":[124],"robustness":[125],"most":[128],"challenging":[129],"(over":[131],"38":[132],"%":[133],"reduction":[134],"failures).":[136],"To":[137],"knowledge,":[139],"first":[143],"application":[144],"autonomous":[154],"utilizes":[157],"large":[158],"amounts":[159],"real-":[161],"world":[162],"data.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":32},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":7}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}