{"id":"https://openalex.org/W4404172112","doi":"https://doi.org/10.1145/3697467.3697643","title":"Research on Autonomous Driving Decision-making Strategies based Deep Reinforcement Learning","display_name":"Research on Autonomous Driving Decision-making Strategies based Deep Reinforcement Learning","publication_year":2024,"publication_date":"2024-08-09","ids":{"openalex":"https://openalex.org/W4404172112","doi":"https://doi.org/10.1145/3697467.3697643"},"language":"en","primary_location":{"id":"doi:10.1145/3697467.3697643","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3697467.3697643","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 4th  International Conference on Internet of Things and Machine Learning","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3697467.3697643","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055707039","display_name":"Zixiang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zixiang Wang","raw_affiliation_strings":["College of Engineering and Computer Science, Syracuse University, Syracuse, USA"],"raw_orcid":"https://orcid.org/0009-0005-8783-7755","affiliations":[{"raw_affiliation_string":"College of Engineering and Computer Science, Syracuse University, Syracuse, USA","institution_ids":["https://openalex.org/I70983195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114240003","display_name":"Hao Yan","orcid":"https://orcid.org/0009-0007-1257-8511"},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Yan","raw_affiliation_strings":["College of Engineering and Computer Science, Syracuse University, Syracuse, USA"],"raw_orcid":"https://orcid.org/0009-0007-1257-8511","affiliations":[{"raw_affiliation_string":"College of Engineering and Computer Science, Syracuse University, Syracuse, USA","institution_ids":["https://openalex.org/I70983195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111255860","display_name":"Changsong Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changsong Wei","raw_affiliation_strings":["Independent Researcher, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0009-0008-8898-9189","affiliations":[{"raw_affiliation_string":"Independent Researcher, Chengdu, Sichuan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junyu Wang","orcid":"https://orcid.org/0009-0008-2204-5820"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junyu Wang","raw_affiliation_strings":["UCLA Computer Science Department, University of California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0009-0008-2204-5820","affiliations":[{"raw_affiliation_string":"UCLA Computer Science Department, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101139729","display_name":"Bo Shi","orcid":"https://orcid.org/0000-0003-0297-8654"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shi Bo","raw_affiliation_strings":["Graduate School of arts and sciences, Boston University, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0003-0297-8654","affiliations":[{"raw_affiliation_string":"Graduate School of arts and sciences, Boston University, Boston, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":null,"display_name":"Minheng Xiao","orcid":"https://orcid.org/0009-0001-8398-9322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minheng Xiao","raw_affiliation_strings":["Department of Integrated System Engineering, Ohio State University, Columbus, USA"],"raw_orcid":"https://orcid.org/0009-0001-8398-9322","affiliations":[{"raw_affiliation_string":"Department of Integrated System Engineering, Ohio State University, Columbus, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"211","last_page":"215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9994000196456909,"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/T10370","display_name":"Traffic and Road Safety","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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":0.83854079246521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6656761169433594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4653172492980957},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.346327543258667}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.83854079246521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6656761169433594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4653172492980957},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.346327543258667}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3697467.3697643","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3697467.3697643","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 4th  International Conference on Internet of Things and Machine Learning","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3697467.3697643","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3697467.3697643","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 4th  International Conference on Internet of Things and Machine Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2124298315","https://openalex.org/W2904263972","https://openalex.org/W3047375952","https://openalex.org/W3121045039","https://openalex.org/W3138181334","https://openalex.org/W3211345831","https://openalex.org/W4200081874","https://openalex.org/W4226257065","https://openalex.org/W4236133481","https://openalex.org/W4250703471","https://openalex.org/W4288076087","https://openalex.org/W6791656131"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"The":[0],"behavior":[1],"decision-making":[2,16,40,92,132,168],"subsystem":[3],"is":[4,25,52,71],"a":[5,82,95,184],"key":[6],"component":[7],"of":[8,18,29,33,48,146,156,186],"the":[9,15,19,22,30,34,37,45,90,115,119,124,131,136,144,147,152,157,167,179],"autonomous":[10],"driving":[11,79,91,161,187],"system,":[12],"which":[13,73],"reflects":[14],"ability":[17],"vehicle":[20],"and":[21,24,50,58,77,84,105,154],"driver,":[23],"an":[26,65],"important":[27],"symbol":[28],"high-level":[31],"intelligence":[32],"vehicle.":[35],"However,":[36],"existing":[38],"rule-based":[39,181],"schemes":[41],"are":[42],"limited":[43],"by":[44,88,122,134],"prior":[46],"knowledge":[47],"designers,":[49],"it":[51],"difficult":[53],"to":[54,117,150],"cope":[55],"with":[56],"complex":[57,83],"changeable":[59,85],"traffic":[60,86],"scenarios.":[61],"In":[62],"this":[63],"work,":[64],"advanced":[66],"deep":[67,172],"reinforcement":[68,96,173],"learning":[69,97,174],"model":[70,158],"adopted,":[72],"can":[74],"autonomously":[75],"learn":[76],"optimize":[78],"strategies":[80],"in":[81,143,159,183],"environment":[87],"modeling":[89],"process":[93],"as":[94],"problem.":[98],"Specifically,":[99],"we":[100],"used":[101],"Deep":[102],"Q-Network":[103],"(DQN)":[104],"Proximal":[106],"Policy":[107],"Optimization":[108],"(PPO)":[109],"for":[110],"comparative":[111],"experiments.":[112],"DQN":[113],"guides":[114],"agent":[116],"choose":[118],"best":[120],"action":[121],"approximating":[123],"state-action":[125],"value":[126],"function,":[127],"while":[128],"PPO":[129],"improves":[130],"quality":[133],"optimizing":[135],"policy":[137],"function.":[138],"We":[139],"also":[140],"introduce":[141],"improvements":[142],"design":[145],"reward":[148],"function":[149],"promote":[151],"robustness":[153],"adaptability":[155],"real-world":[160],"situations.":[162],"Experimental":[163],"results":[164],"show":[165],"that":[166],"strategy":[169],"based":[170],"on":[171],"has":[175],"better":[176],"performance":[177],"than":[178],"traditional":[180],"method":[182],"variety":[185],"tasks.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}