{"id":"https://openalex.org/W4408697165","doi":"https://doi.org/10.1109/itsc58415.2024.10920092","title":"Stability Enhanced Hierarchical Reinforcement Learning for Autonomous Driving with Parameterized Trajectory Action","display_name":"Stability Enhanced Hierarchical Reinforcement Learning for Autonomous Driving with Parameterized Trajectory Action","publication_year":2024,"publication_date":"2024-09-24","ids":{"openalex":"https://openalex.org/W4408697165","doi":"https://doi.org/10.1109/itsc58415.2024.10920092"},"language":"en","primary_location":{"id":"doi:10.1109/itsc58415.2024.10920092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc58415.2024.10920092","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/A5002603813","display_name":"Gang Jin","orcid":"https://orcid.org/0000-0002-0128-7395"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guizhe Jin","raw_affiliation_strings":["School of Automotive Studies, Tongji University,Shanghai,China,201804"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036776153","display_name":"Zhuoren Li","orcid":"https://orcid.org/0000-0001-6246-3404"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoren Li","raw_affiliation_strings":["School of Automotive Studies, Tongji University,Shanghai,China,201804"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073740136","display_name":"Bo Leng","orcid":"https://orcid.org/0000-0003-3513-1708"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Leng","raw_affiliation_strings":["School of Automotive Studies, Tongji University,Shanghai,China,201804"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035108858","display_name":"Wei Han","orcid":"https://orcid.org/0000-0002-5702-4842"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Han","raw_affiliation_strings":["School of Automotive Studies, Tongji University,Shanghai,China,201804"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060995005","display_name":"Lu Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Xiong","raw_affiliation_strings":["School of Automotive Studies, Tongji University,Shanghai,China,201804"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031111706","display_name":"Jia Hu","orcid":"https://orcid.org/0000-0002-0900-7992"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Hu","raw_affiliation_strings":["College of Transportation Engineering, Tongji University,Shanghai,China,201804"],"affiliations":[{"raw_affiliation_string":"College of Transportation Engineering, Tongji University,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341048","display_name":"Nan Li","orcid":"https://orcid.org/0000-0002-2375-8098"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Li","raw_affiliation_strings":["School of Automotive Studies, Tongji University,Shanghai,China,201804"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5002603813"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.5918,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68021448,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3020","last_page":"3026"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9872000217437744,"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":0.9872000217437744,"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/T10524","display_name":"Traffic control and management","score":0.9771999716758728,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9602000117301941,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8204234838485718},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.7868449687957764},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7510464787483215},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6773470640182495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6011795401573181},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.555321216583252},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4546400308609009},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.38151073455810547},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22601228952407837},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.15365815162658691},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13426780700683594},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06325417757034302}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8204234838485718},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.7868449687957764},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7510464787483215},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6773470640182495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6011795401573181},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.555321216583252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4546400308609009},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.38151073455810547},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22601228952407837},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.15365815162658691},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13426780700683594},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06325417757034302},{"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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc58415.2024.10920092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc58415.2024.10920092","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/G624529336","display_name":null,"funder_award_id":"2021YFB2501201,2022YFE0117100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6270547606","display_name":null,"funder_award_id":"52372394","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/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1965455100","https://openalex.org/W2025391876","https://openalex.org/W2056877664","https://openalex.org/W2145339207","https://openalex.org/W2773381986","https://openalex.org/W2795064979","https://openalex.org/W2896642734","https://openalex.org/W2965757358","https://openalex.org/W3121045039","https://openalex.org/W3127561923","https://openalex.org/W3209253128","https://openalex.org/W3211302749","https://openalex.org/W4214496626","https://openalex.org/W4308080211","https://openalex.org/W4312550876","https://openalex.org/W4375796951","https://openalex.org/W4386219277","https://openalex.org/W4388513480","https://openalex.org/W4388936582","https://openalex.org/W4391768434","https://openalex.org/W6631190155","https://openalex.org/W6755326576","https://openalex.org/W6853778389"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W1494268238","https://openalex.org/W154868527","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2480116122","https://openalex.org/W4255576661","https://openalex.org/W1516574938","https://openalex.org/W2625725254","https://openalex.org/W2563912921"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"has":[3],"become":[4],"a":[5,54],"potential":[6],"method":[7,45,60,118],"for":[8,133],"autonomous":[9,134],"driving":[10,15,40,70,125],"to":[11,13,90],"adapt":[12],"complex":[14],"environments":[16],"with":[17,35,93],"high":[18],"flexibility.":[19],"However,":[20],"the":[21,27,32,39,48,73,81,99,108,116,129],"popular":[22],"RL":[23,44,86],"paradigm":[24],"directly":[25],"outputting":[26],"vehicle":[28],"control":[29,78],"commands":[30,79],"makes":[31],"future":[33],"motion":[34,49],"fluctuation.":[36],"To":[37],"improve":[38],"behavior":[41],"stability":[42,55],"of":[43,107],"while":[46],"ensuring":[47],"flexibility,":[50],"this":[51],"paper":[52],"proposes":[53],"enhanced":[56],"hierarchical":[57],"reinforcement":[58],"learning":[59],"based":[61],"on":[62],"parameterized":[63,100],"trajectory":[64],"action":[65,101],"(RL-PTA).":[66],"It":[67],"offers":[68],"feasible":[69],"path":[71,91],"in":[72,80],"long":[74],"horizon":[75,83],"and":[76,98,122,131],"real-time":[77],"short":[82],"simultaneously.":[84],"The":[85,111],"agent":[87],"actively":[88],"contributes":[89],"generation":[92],"discrete-continuous":[94],"hybrid":[95,109],"parameter":[96],"actions,":[97],"space":[102],"also":[103],"ensures":[104],"optimal":[105],"consistency":[106],"output.":[110],"experiment":[112],"results":[113],"show":[114],"that":[115],"proposed":[117],"can":[119],"generate":[120],"flexible":[121],"stable":[123],"lane-change":[124],"behavior,":[126],"thereby":[127],"improving":[128],"efficiency":[130],"safety":[132],"driving.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}