{"id":"https://openalex.org/W4390224584","doi":"https://doi.org/10.1109/dtpi59677.2023.10365415","title":"Embed Trajectory Imitation in Reinforcement Learning: A Hybrid Method for Autonomous Vehicle Planning","display_name":"Embed Trajectory Imitation in Reinforcement Learning: A Hybrid Method for Autonomous Vehicle Planning","publication_year":2023,"publication_date":"2023-11-07","ids":{"openalex":"https://openalex.org/W4390224584","doi":"https://doi.org/10.1109/dtpi59677.2023.10365415"},"language":"en","primary_location":{"id":"doi:10.1109/dtpi59677.2023.10365415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dtpi59677.2023.10365415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 3rd International Conference on Digital Twins and Parallel Intelligence (DTPI)","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/A5115076751","display_name":"Yuxiao Wang","orcid":"https://orcid.org/0009-0007-8547-9514"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiao Wang","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Management and Control for Complex System Institute of Automation,Beijing,China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Management and Control for Complex System Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Management and Control for Complex System Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex System Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057269411","display_name":"Xingyuan Dai","orcid":"https://orcid.org/0000-0001-7517-5049"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyuan Dai","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Management and Control for Complex System Institute of Automation,Beijing,China","State Key Laboratory of Management and Control for Complex System Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Management and Control for Complex System Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]},{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex System Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kara Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kara Wang","raw_affiliation_strings":["Anhui University,School of Artificial Intelligence,Hefei,China","School of Artificial Intelligence, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui University,School of Artificial Intelligence,Hefei,China","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082189035","display_name":"Hub Ali","orcid":"https://orcid.org/0000-0002-6323-2322"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hub Ali","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Management and Control for Complex System Institute of Automation,Beijing,China","State Key Laboratory of Management and Control for Complex System Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Management and Control for Complex System Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]},{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex System Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042359485","display_name":"Fenghua Zhu","orcid":"https://orcid.org/0000-0003-2886-6968"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fenghua Zhu","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Management and Control for Complex System Institute of Automation,Beijing,China","State Key Laboratory of Management and Control for Complex System Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Management and Control for Complex System Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]},{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex System Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.998199999332428,"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":0.9965999722480774,"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":0.8584703207015991},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7469713687896729},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.693579375743866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5709822773933411},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5344573259353638},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.5193715691566467},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5145320296287537},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49187326431274414}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8584703207015991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7469713687896729},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.693579375743866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5709822773933411},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5344573259353638},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.5193715691566467},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5145320296287537},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49187326431274414},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dtpi59677.2023.10365415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dtpi59677.2023.10365415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 3rd International Conference on Digital Twins and Parallel Intelligence (DTPI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2069239883","https://openalex.org/W2736601468","https://openalex.org/W2905173465","https://openalex.org/W2963277051","https://openalex.org/W2972088616","https://openalex.org/W2990123902","https://openalex.org/W3003665832","https://openalex.org/W3009593063","https://openalex.org/W3128395826","https://openalex.org/W3130288902","https://openalex.org/W3209943843","https://openalex.org/W4200160430","https://openalex.org/W4226257065","https://openalex.org/W4285278949","https://openalex.org/W4312081617","https://openalex.org/W4312550876","https://openalex.org/W4327662239","https://openalex.org/W4383108473","https://openalex.org/W4389666601","https://openalex.org/W6718092244","https://openalex.org/W6741002519","https://openalex.org/W6780503301"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W3160494304","https://openalex.org/W2768698792"],"abstract_inverted_index":{"Learning-based":[0],"autonomous":[1,64],"vehicle":[2,65],"trajectory":[3,87],"planning":[4],"methods":[5,154],"have":[6,29],"shown":[7],"excellent":[8],"performance":[9],"in":[10,71,109],"a":[11,58,106],"variety":[12],"of":[13,90,128],"complex":[14],"traffic":[15],"scenarios.":[16],"However,":[17],"the":[18,53,94,110,129],"existing":[19,82],"imitation":[20],"learning":[21,25],"(IL)":[22],"and":[23,36,40,51,126,146,149],"reinforcement":[24],"(RL)":[26],"algorithms":[27],"still":[28],"their":[30,48],"limitations,":[31,54],"such":[32,102],"as":[33,93],"poor":[34],"safety":[35],"generalizability":[37],"for":[38,44,63],"IL,":[39],"low":[41],"data":[42],"efficiency":[43],"RL.":[45,100,120],"To":[46],"leverage":[47],"respective":[49],"advantages":[50],"mitigate":[52],"this":[55],"paper":[56],"proposes":[57],"novel":[59],"hybrid":[60],"RL":[61,147,153],"algorithm":[62,130],"planning,":[66],"where":[67],"IL":[68,95,145],"is":[69],"embedded":[70],"it":[72],"to":[73,119],"guide":[74],"its":[75],"exploration":[76],"with":[77,98],"expert":[78,114],"knowledge.":[79],"Different":[80],"from":[81],"approaches,":[83],"we":[84,104,122],"use":[85],"multi-step":[86],"prediction":[88],"instead":[89],"behavior":[91,157],"cloning":[92],"method":[96],"integrated":[97],"online":[99],"Through":[101],"design,":[103],"make":[105],"further":[107],"step":[108],"research":[111],"about":[112],"how":[113],"demonstration":[115],"can":[116],"be":[117],"helpful":[118],"Moreover,":[121],"conduct":[123],"parallel":[124],"training":[125],"testing":[127],"based":[131],"on":[132],"real-world":[133],"driving":[134],"data.":[135],"Experimental":[136],"results":[137],"demonstrate":[138],"that":[139],"our":[140],"proposed":[141],"approach":[142],"outperforms":[143],"standalone":[144],"methods,":[148],"performs":[150],"better":[151],"than":[152],"enhanced":[155],"by":[156],"cloning.":[158]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}