{"id":"https://openalex.org/W4408712141","doi":"https://doi.org/10.1109/itsc58415.2024.10920026","title":"Refine Reinforcement Learning for Safety Training of Autonomous Driving","display_name":"Refine Reinforcement Learning for Safety Training of Autonomous Driving","publication_year":2024,"publication_date":"2024-09-24","ids":{"openalex":"https://openalex.org/W4408712141","doi":"https://doi.org/10.1109/itsc58415.2024.10920026"},"language":"en","primary_location":{"id":"doi:10.1109/itsc58415.2024.10920026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc58415.2024.10920026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","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/A5104230443","display_name":"Fukun Yang","orcid":"https://orcid.org/0009-0001-4130-6562"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fukun Yang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing Key Laboratory for Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing Key Laboratory for Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057174728","display_name":"Zhiqun Hu","orcid":"https://orcid.org/0000-0002-5666-1401"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqun Hu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing Key Laboratory for Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing Key Laboratory for Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100710887","display_name":"Yuanming Zhang","orcid":"https://orcid.org/0000-0002-0100-0219"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanming Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing Key Laboratory for Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing Key Laboratory for Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102010856","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0002-6729-1987"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications,Chongqing,China"],"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications,Chongqing,China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047884904","display_name":"Guixin Wang","orcid":"https://orcid.org/0000-0002-4850-9207"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guixin Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing Key Laboratory for Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing Key Laboratory for Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5104230443"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31618266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"856","last_page":"863"},"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":0.994700014591217,"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":0.993399977684021,"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":0.7366796731948853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6173968315124512},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.606306791305542},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4228362441062927},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36347389221191406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3384186625480652},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18575656414031982},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.056395381689071655}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7366796731948853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6173968315124512},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.606306791305542},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4228362441062927},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36347389221191406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3384186625480652},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18575656414031982},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.056395381689071655},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc58415.2024.10920026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc58415.2024.10920026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1005521175","display_name":null,"funder_award_id":"2022YFB2601802","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1965455100","https://openalex.org/W2056877664","https://openalex.org/W2766447205","https://openalex.org/W2804791273","https://openalex.org/W2904263972","https://openalex.org/W2951360122","https://openalex.org/W2973229164","https://openalex.org/W3037164854","https://openalex.org/W3038287124","https://openalex.org/W3090027660","https://openalex.org/W3115737827","https://openalex.org/W3195968524","https://openalex.org/W4297733535","https://openalex.org/W4297824337","https://openalex.org/W4394844796","https://openalex.org/W6770009701","https://openalex.org/W6780587392"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"The":[0,50,129],"random":[1],"exploration":[2],"nature":[3],"of":[4,48,69,100,118,127,139],"reinforcement":[5,31],"learning":[6,32],"(RL)":[7],"impedes":[8],"the":[9,18,46,66,74,80,89,93,98,101,121,125,137,148,156],"way":[10],"to":[11,17,35,53,64,87,114,123],"achieve":[12],"human-like":[13],"autonomous":[14],"driving,":[15],"owing":[16],"prohibitively":[19],"high":[20],"safety":[21,138],"requirement.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26,85,109],"propose":[27,86],"a":[28],"deep":[29],"refine":[30],"(DR2L)":[33],"approach":[34],"removing":[36],"non-safety-critical":[37],"actions":[38,71],"and":[39,72,104],"reconstructing":[40],"critical":[41,67],"ones,":[42],"which":[43,96],"effectively":[44,135],"enhance":[45,124],"efficiency":[47],"exploration.":[49],"core":[51],"is":[52],"design":[54,110],"an":[55],"action":[56,75],"filter":[57],"based":[58],"on":[59],"two-stage":[60],"vehicle":[61],"motion":[62],"model":[63],"calculate":[65],"value":[68],"dangerous":[70],"reconstructe":[73],"space":[76],"by":[77],"filtering":[78],"out":[79],"obvious":[81],"incorrect":[82],"actions.":[83],"Besides,":[84],"use":[88],"beta":[90,149],"distribution":[91],"as":[92,120],"stochastic":[94],"policy,":[95],"eliminates":[97],"bias":[99],"Gaussian":[102,157],"policy":[103,150,158,165],"provides":[105,151],"faster":[106,153],"convergence.":[107],"Finally,":[108],"spacial-temporal":[111],"attention":[112],"network":[113],"extract":[115],"hidden":[116],"information":[117],"environment":[119],"state":[122],"performance":[126],"RL.":[128],"simulation":[130],"shows":[131],"that":[132,147],"DR2L":[133],"can":[134],"improve":[136],"agent":[140],"during":[141],"training":[142],"process.":[143],"Our":[144],"resutls":[145],"show":[146],"significantly":[152],"convergence":[154],"over":[155],"when":[159],"both":[160],"are":[161],"used":[162],"with":[163],"proximal":[164],"optimization":[166],"(PPO).":[167]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}