{"id":"https://openalex.org/W3010740942","doi":"https://doi.org/10.1109/tvt.2020.2979493","title":"Stabilization Approaches for Reinforcement Learning-Based End-to-End Autonomous Driving","display_name":"Stabilization Approaches for Reinforcement Learning-Based End-to-End Autonomous Driving","publication_year":2020,"publication_date":"2020-03-09","ids":{"openalex":"https://openalex.org/W3010740942","doi":"https://doi.org/10.1109/tvt.2020.2979493","mag":"3010740942"},"language":"en","primary_location":{"id":"doi:10.1109/tvt.2020.2979493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvt.2020.2979493","pdf_url":null,"source":{"id":"https://openalex.org/S10936095","display_name":"IEEE Transactions on Vehicular Technology","issn_l":"0018-9545","issn":["0018-9545","1939-9359"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Vehicular Technology","raw_type":"journal-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/A5077992146","display_name":"Siyuan Chen","orcid":"https://orcid.org/0000-0003-4140-9729"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Chen","raw_affiliation_strings":["State Key Laboratory of Intelligent Control and Decision of Complex Systems, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4140-9729","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Control and Decision of Complex Systems, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100416064","display_name":"Meiling Wang","orcid":"https://orcid.org/0000-0002-3618-7423"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meiling Wang","raw_affiliation_strings":["State Key Laboratory of Intelligent Control and Decision of Complex Systems, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3618-7423","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Control and Decision of Complex Systems, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029808668","display_name":"Wenjie Song","orcid":"https://orcid.org/0000-0002-4121-908X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Song","raw_affiliation_strings":["State Key Laboratory of Intelligent Control and Decision of Complex Systems, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4121-908X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Control and Decision of Complex Systems, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062124960","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0003-3964-2433"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["State Key Laboratory of Intelligent Control and Decision of Complex Systems, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3964-2433","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Control and Decision of Complex Systems, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100704698","display_name":"Yujun Li","orcid":"https://orcid.org/0000-0002-8701-5971"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujun Li","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091459774","display_name":"Mengyin Fu","orcid":"https://orcid.org/0000-0002-5520-7127"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyin Fu","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China","State Key Laboratory of Intelligent Control and Decision of Complex Systems, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Control and Decision of Complex Systems, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2625,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.94229841,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"69","issue":"5","first_page":"4740","last_page":"4750"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9995999932289124,"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":0.9995999932289124,"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":0.996999979019165,"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":0.9916999936103821,"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":0.8173233270645142},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.75907301902771},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.684357762336731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6633992195129395},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6497659087181091},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5234555602073669},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4587107300758362},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3505510091781616}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8173233270645142},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.75907301902771},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.684357762336731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6633992195129395},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6497659087181091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5234555602073669},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4587107300758362},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3505510091781616},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvt.2020.2979493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvt.2020.2979493","pdf_url":null,"source":{"id":"https://openalex.org/S10936095","display_name":"IEEE Transactions on Vehicular Technology","issn_l":"0018-9545","issn":["0018-9545","1939-9359"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Vehicular Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G206231915","display_name":null,"funder_award_id":"91120003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2217668812","display_name":null,"funder_award_id":"61903034","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5448203614","display_name":null,"funder_award_id":"61973034","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6937405481","display_name":null,"funder_award_id":"2019TQ0035","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G7914619715","display_name":null,"funder_award_id":"U1913203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320327514","display_name":"Beijing Institute of Technology Research Fund Program for Young Scholars","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W92112976","https://openalex.org/W1191599655","https://openalex.org/W1533861849","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W1849277567","https://openalex.org/W1931877416","https://openalex.org/W1966456942","https://openalex.org/W1968962398","https://openalex.org/W1999874108","https://openalex.org/W2008791002","https://openalex.org/W2105560683","https://openalex.org/W2119112357","https://openalex.org/W2132400125","https://openalex.org/W2133233905","https://openalex.org/W2144304287","https://openalex.org/W2145339207","https://openalex.org/W2165150801","https://openalex.org/W2167224731","https://openalex.org/W2242368318","https://openalex.org/W2271840356","https://openalex.org/W2342840547","https://openalex.org/W2559767995","https://openalex.org/W2563338958","https://openalex.org/W2604173613","https://openalex.org/W2727840223","https://openalex.org/W2734506266","https://openalex.org/W2761862361","https://openalex.org/W2905173465","https://openalex.org/W2962894046","https://openalex.org/W2962957031","https://openalex.org/W2963277051","https://openalex.org/W2963322416","https://openalex.org/W2963727600","https://openalex.org/W2963858432","https://openalex.org/W2963864421","https://openalex.org/W2968983352","https://openalex.org/W2971254261","https://openalex.org/W2973588514","https://openalex.org/W2974005385","https://openalex.org/W3021252423","https://openalex.org/W4239873336","https://openalex.org/W4241811150","https://openalex.org/W4298857966","https://openalex.org/W4299805595","https://openalex.org/W4302570325","https://openalex.org/W6603709215","https://openalex.org/W6627932998","https://openalex.org/W6631943919","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6639204139","https://openalex.org/W6640174482","https://openalex.org/W6684205842","https://openalex.org/W6684338915","https://openalex.org/W6684921986","https://openalex.org/W6694517276","https://openalex.org/W6704559304","https://openalex.org/W6718092244","https://openalex.org/W6731187701","https://openalex.org/W6735738130","https://openalex.org/W6752781648"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W2355833770","https://openalex.org/W1985458517","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W4389650576","https://openalex.org/W2768698792"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,58,91],"learning":[2,59,64,92],"(DRL)":[3],"has":[4],"been":[5],"successfully":[6],"applied":[7,147],"to":[8,31,38,65,89,101,182],"end-to-end":[9,127,187],"autonomous":[10,23,128,188],"driving,":[11],"especially":[12],"in":[13,21,121,140,148,150,209,220,222],"simulation":[14],"environments.":[15],"However,":[16],"common":[17],"DRL":[18],"approaches":[19,37,135],"used":[20],"complex":[22],"driving":[24,129,189],"scenarios":[25],"sometimes":[26],"are":[27,131,136],"unstable":[28],"or":[29],"difficult":[30],"converge.":[32,228],"This":[33],"paper":[34],"proposes":[35],"two":[36,118],"improve":[39],"the":[40,43,55,81,90,97,103,114,141,159,167,173,185,195,202,210],"stability":[41],"of":[42,74,105,110,116,163],"policy":[44],"model":[45,162,190],"training":[46],"with":[47,62,70,177],"as":[48,52,181],"few":[49],"manual":[50,75],"data":[51,76],"possible.":[53],"For":[54,80],"first":[56],"approach,":[57,83],"is":[60,87,191,204],"combined":[61],"imitation":[63],"train":[66],"a":[67,71,154],"feature":[68],"network":[69,86],"small":[72],"amount":[73],"for":[77,194],"parameters":[78],"initialization.":[79],"second":[82],"an":[84],"auxiliary":[85],"added":[88],"framework,":[93],"which":[94,151,223],"can":[95,215,226],"leverage":[96],"real-time":[98],"measurement":[99],"information":[100],"deepen":[102],"understanding":[104],"environment,":[106],"without":[107],"any":[108],"guide":[109],"demonstrators.":[111],"To":[112],"verify":[113],"effectiveness":[115],"these":[117],"approaches,":[119],"simulations":[120],"image":[122],"information-based":[123,126],"and":[124,172,214,218],"lidar":[125],"systems":[130],"conducted,":[132],"respectively.":[133],"These":[134],"not":[137],"only":[138],"tested":[139],"virtual":[142,211],"game":[143,212],"world,":[144,213],"but":[145],"also":[146],"Gazebo,":[149],"we":[152],"build":[153],"3D":[155,169],"world":[156],"based":[157],"on":[158],"real":[160,168,174,196],"vehicle":[161],"Ranger":[164],"XP900":[165],"platform,":[166],"obstacle":[170],"model,":[171],"motion":[175],"constraints":[176],"inertial":[178],"characteristics,":[179],"so":[180],"ensure":[183],"that":[184,201],"trained":[186],"more":[192],"suitable":[193],"world.":[197],"Experimental":[198],"results":[199],"show":[200],"performance":[203],"increased":[205],"by":[206],"over":[207],"45%":[208],"converge":[216],"quickly":[217],"stably":[219],"Gazebo":[221],"previous":[224],"methods":[225],"hardly":[227]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}