{"id":"https://openalex.org/W4391768696","doi":"https://doi.org/10.1109/itsc57777.2023.10422463","title":"Safe Reinforcement Learning for Mixed-Autonomy Platoon Control","display_name":"Safe Reinforcement Learning for Mixed-Autonomy Platoon Control","publication_year":2023,"publication_date":"2023-09-24","ids":{"openalex":"https://openalex.org/W4391768696","doi":"https://doi.org/10.1109/itsc57777.2023.10422463"},"language":"en","primary_location":{"id":"doi:10.1109/itsc57777.2023.10422463","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/itsc57777.2023.10422463","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 26th 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/A5082705388","display_name":"Jingyuan Zhou","orcid":"https://orcid.org/0000-0003-0061-219X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jingyuan Zhou","raw_affiliation_strings":["National University of Singapore,Department of Civil and Environmental Engineering,Singapore,119077"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Civil and Environmental Engineering,Singapore,119077","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051451837","display_name":"Longhao Yan","orcid":"https://orcid.org/0000-0002-0167-0888"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Longhao Yan","raw_affiliation_strings":["National University of Singapore,Department of Civil and Environmental Engineering,Singapore,119077"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Civil and Environmental Engineering,Singapore,119077","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102513295","display_name":"Kaidi Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kaidi Yang","raw_affiliation_strings":["National University of Singapore,Department of Civil and Environmental Engineering,Singapore,119077"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Civil and Environmental Engineering,Singapore,119077","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5744","last_page":"5749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9717000126838684,"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":0.9717000126838684,"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/platoon","display_name":"Platoon","score":0.8775084614753723},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.749235212802887},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5982271432876587},{"id":"https://openalex.org/keywords/autonomy","display_name":"Autonomy","score":0.47675618529319763},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4084242284297943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24702703952789307},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.06106215715408325}],"concepts":[{"id":"https://openalex.org/C2777735972","wikidata":"https://www.wikidata.org/wiki/Q1061967","display_name":"Platoon","level":3,"score":0.8775084614753723},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.749235212802887},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5982271432876587},{"id":"https://openalex.org/C65414064","wikidata":"https://www.wikidata.org/wiki/Q484105","display_name":"Autonomy","level":2,"score":0.47675618529319763},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4084242284297943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24702703952789307},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.06106215715408325},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc57777.2023.10422463","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/itsc57777.2023.10422463","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 26th 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":30,"referenced_works":["https://openalex.org/W1977330774","https://openalex.org/W1980569135","https://openalex.org/W2073177254","https://openalex.org/W2276329747","https://openalex.org/W2410447053","https://openalex.org/W2586823359","https://openalex.org/W2736601468","https://openalex.org/W2891548292","https://openalex.org/W2921436962","https://openalex.org/W2963864421","https://openalex.org/W2966735560","https://openalex.org/W2968547875","https://openalex.org/W3151221903","https://openalex.org/W3152858716","https://openalex.org/W3153676008","https://openalex.org/W3206719808","https://openalex.org/W3210590548","https://openalex.org/W4290943640","https://openalex.org/W4294562617","https://openalex.org/W4308068353","https://openalex.org/W4312433875","https://openalex.org/W4317385006","https://openalex.org/W4318541446","https://openalex.org/W4320085920","https://openalex.org/W4352977012","https://openalex.org/W4389692462","https://openalex.org/W6684921986","https://openalex.org/W6741002519","https://openalex.org/W6751535212","https://openalex.org/W6849745047"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4286572054","https://openalex.org/W3171462553","https://openalex.org/W2555207388","https://openalex.org/W2983996496","https://openalex.org/W3189590538","https://openalex.org/W4389240635","https://openalex.org/W2461853023","https://openalex.org/W2136133395","https://openalex.org/W2935722734"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2],"(DRL)":[3],"has":[4],"been":[5],"demonstrated":[6],"to":[7,45,49,86,88],"be":[8],"effective":[9],"for":[10],"the":[11,79,116,123],"control":[12],"of":[13,125],"mixed-autonomy":[14],"platoons.":[15],"However,":[16],"incorporating":[17],"safety":[18,43,67,76,102,117],"considerations":[19],"into":[20,78],"DRL":[21,47,72],"typically":[22],"relies":[23,56],"on":[24,57],"designing":[25],"collision":[26],"avoidance-based":[27],"reward":[28],"functions,":[29],"which":[30,55],"lack":[31],"collision-free":[32,53],"guarantees.":[33],"To":[34],"address":[35],"this":[36],"research":[37],"gap,":[38],"we":[39],"introduce":[40],"a":[41,58],"differentiable":[42,59],"layer":[44,118],"convert":[46],"actions":[48,51],"safe":[50],"with":[52],"guarantees,":[54],"quadratic":[60],"programming":[61],"problem":[62],"featuring":[63],"Control":[64],"Barrier":[65],"Function-based":[66],"constraints.":[68],"The":[69],"proposed":[70,97],"safety-informed":[71],"approach":[73],"explicitly":[74],"integrates":[75],"constraints":[77],"training":[80,120],"process":[81],"and":[82,112],"enables":[83],"our":[84,96],"method":[85,98],"adapt":[87],"varying":[89],"safety-critical":[90],"scenarios.":[91],"Simulation":[92],"results":[93],"demonstrate":[94],"that":[95],"effectively":[99],"ensures":[100],"CAV":[101],"in":[103],"mixed":[104],"platoon":[105],"environments":[106],"while":[107],"simultaneously":[108],"enhancing":[109],"traffic":[110],"capacity":[111],"string":[113],"stability.":[114],"Furthermore,":[115],"expedites":[119],"by":[121],"reducing":[122],"range":[124],"exploration.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}