{"id":"https://openalex.org/W4399118830","doi":"https://doi.org/10.1109/tiv.2024.3406679","title":"HGRL: Human-Driving-Data Guided Reinforcement Learning for Autonomous Driving","display_name":"HGRL: Human-Driving-Data Guided Reinforcement Learning for Autonomous Driving","publication_year":2024,"publication_date":"2024-05-29","ids":{"openalex":"https://openalex.org/W4399118830","doi":"https://doi.org/10.1109/tiv.2024.3406679"},"language":"en","primary_location":{"id":"doi:10.1109/tiv.2024.3406679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tiv.2024.3406679","pdf_url":null,"source":{"id":"https://openalex.org/S4210199657","display_name":"IEEE Transactions on Intelligent Vehicles","issn_l":"2379-8858","issn":["2379-8858","2379-8904"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Vehicles","raw_type":"journal-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/A5079631480","display_name":"Hejian Zhuang","orcid":"https://orcid.org/0009-0005-2534-5528"},"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":"Hejian Zhuang","raw_affiliation_strings":["School of Automotive Studies, Tongji University, Shanghai, China","School of Automotive Studies, Tongji University, Shanghai, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"School of Automotive Studies, Tongji University, Shanghai, P.R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063286550","display_name":"Hongqing Chu","orcid":"https://orcid.org/0000-0002-8015-9788"},"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":"Hongqing Chu","raw_affiliation_strings":["School of Automotive Studies, Tongji University, Shanghai, China","School of Automotive Studies, Tongji University, Shanghai, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"School of Automotive Studies, Tongji University, Shanghai, P.R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100684138","display_name":"Yafei Wang","orcid":"https://orcid.org/0000-0003-4880-5054"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yafei Wang","raw_affiliation_strings":["School of Mechanical Engineering, Shanghai Jiaotong University, Shanghai, China","School of Mechanical Engineering, Shanghai Jiaotong University, Shanghai, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Mechanical Engineering, Shanghai Jiaotong University, Shanghai, P.R. China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064212745","display_name":"Bingzhao Gao","orcid":"https://orcid.org/0000-0001-5155-7835"},"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":"Bingzhao Gao","raw_affiliation_strings":["School of Automotive Studies, Tongji University, Shanghai, China","School of Automotive Studies, Tongji University, Shanghai, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"School of Automotive Studies, Tongji University, Shanghai, P.R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074996561","display_name":"Hong Chen","orcid":"https://orcid.org/0000-0002-1724-8649"},"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":"Hong Chen","raw_affiliation_strings":["College of Electronics and Information Engineering, Tongji University, Shanghai, China","College of Electronics and Information Engineering, Tongji University, Shanghai, P.R. China"],"affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"College of Electronics and Information Engineering, Tongji University, Shanghai, P.R. China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5079631480"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":1.5137,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81144223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"9","issue":"12","first_page":"8089","last_page":"8103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9764999747276306,"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":0.9764999747276306,"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":0.9330000281333923,"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":0.6524541974067688},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5617341995239258},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.494790256023407},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4386856257915497},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3222518265247345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2763707637786865},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09498807787895203}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6524541974067688},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5617341995239258},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.494790256023407},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4386856257915497},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3222518265247345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2763707637786865},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09498807787895203}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tiv.2024.3406679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tiv.2024.3406679","pdf_url":null,"source":{"id":"https://openalex.org/S4210199657","display_name":"IEEE Transactions on Intelligent Vehicles","issn_l":"2379-8858","issn":["2379-8858","2379-8904"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Vehicles","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1163267705","display_name":null,"funder_award_id":"62273256","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4941439742","display_name":null,"funder_award_id":"62373289","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/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":45,"referenced_works":["https://openalex.org/W2096883759","https://openalex.org/W2107338474","https://openalex.org/W2763110165","https://openalex.org/W2788862220","https://openalex.org/W2837605352","https://openalex.org/W2896642734","https://openalex.org/W2942735643","https://openalex.org/W2946231253","https://openalex.org/W2951360122","https://openalex.org/W3105200428","https://openalex.org/W3127561923","https://openalex.org/W3130288902","https://openalex.org/W3138984732","https://openalex.org/W3176912151","https://openalex.org/W3206298348","https://openalex.org/W4210444794","https://openalex.org/W4210870706","https://openalex.org/W4210909794","https://openalex.org/W4226257065","https://openalex.org/W4285272860","https://openalex.org/W4286253093","https://openalex.org/W4312550876","https://openalex.org/W4323338414","https://openalex.org/W4327662239","https://openalex.org/W4376166839","https://openalex.org/W4377298394","https://openalex.org/W4387415195","https://openalex.org/W4387448538","https://openalex.org/W4389044710","https://openalex.org/W4389382590","https://openalex.org/W4390422151","https://openalex.org/W4392406006","https://openalex.org/W6627932998","https://openalex.org/W6718092244","https://openalex.org/W6739585900","https://openalex.org/W6757817989","https://openalex.org/W6778875248","https://openalex.org/W6778883912","https://openalex.org/W6778961322","https://openalex.org/W6796168157","https://openalex.org/W6796289742","https://openalex.org/W6804244202","https://openalex.org/W6809583738","https://openalex.org/W6850848496","https://openalex.org/W6855173278"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,76],"(RL)":[2],"shows":[3],"promise":[4],"for":[5,195],"autonomous":[6,204],"driving":[7,36,92,103,116,148,176,205],"decision-making.":[8],"However,":[9],"designing":[10],"appropriate":[11],"reward":[12,32,109,121,200],"functions":[13,201],"to":[14,38,80,99,112],"guide":[15,39],"RL":[16,40,127],"agents":[17],"towards":[18],"complex":[19],"optimization":[20],"objectives":[21],"is":[22,78,97,123,137],"challenging.":[23],"This":[24],"article":[25],"proposes":[26],"a":[27,67,72,82,108,126,134],"framework":[28,45,77],"that":[29,187],"learns":[30],"the":[31,101,114,119,131,140,154,158,169,188,193],"function":[33,122],"from":[34,66,146],"human":[35,91,102],"data":[37],"agent's":[41],"learning.":[42],"The":[43,94],"proposed":[44,132,155,189],"consists":[46],"of":[47,163,198],"three":[48],"components:":[49],"trajectory":[50],"sample,":[51],"offline":[52,74],"preference":[53,75],"learning,":[54],"and":[55,166],"RL.":[56],"Firstly,":[57],"feasible":[58,88],"trajectories":[59,89,143],"are":[60,144],"generated":[61,87],"by":[62,85],"sampling":[63],"end":[64],"targets":[65],"reachable":[68],"state":[69],"space.":[70],"Subsequently,":[71],"novel":[73],"utilized":[79],"train":[81],"transformer":[83,95],"network":[84,96,172],"comparing":[86],"with":[90,151,179],"trajectories.":[93],"used":[98],"model":[100],"decision-making":[104,177,206],"process,":[105],"thereby":[106],"obtaining":[107],"function.":[110],"Finally,":[111],"obtain":[113],"final":[115],"decision":[117,164,182],"network,":[118],"derived":[120,145],"incorporated":[124],"into":[125],"framework.":[128],"To":[129],"validate":[130],"method,":[133],"highway":[135],"simulator":[136],"established":[138],"where":[139],"surrounding":[141],"vehicle":[142],"real-world":[147],"scenarios.":[149],"Compared":[150],"baseline":[152],"algorithms,":[153],"method":[156,190],"achieves":[157],"best":[159],"performances":[160],"in":[161,175,202],"terms":[162],"safety":[165],"human-likeness.":[167],"Additionally,":[168],"learned":[170],"policy":[171],"performs":[173],"well":[174],"tasks":[178],"longer":[180],"total":[181],"steps.":[183],"Experimental":[184],"results":[185],"demonstrate":[186],"can":[191],"obviate":[192],"requirement":[194],"manual":[196],"design":[197],"sophisticated":[199],"RL-based":[203],"systems.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}