{"id":"https://openalex.org/W4416748358","doi":"https://doi.org/10.1109/iros60139.2025.11246855","title":"Modeling Human-like Driving Behavior Based on Maximum Entropy Deep Inverse Reinforcement Learning","display_name":"Modeling Human-like Driving Behavior Based on Maximum Entropy Deep Inverse Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748358","doi":"https://doi.org/10.1109/iros60139.2025.11246855"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5010936276","display_name":"Jiamin Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamin Shi","raw_affiliation_strings":["Xi&#x2019;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,Xi&#x2019;an,P.R. China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi&#x2019;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,Xi&#x2019;an,P.R. China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009484245","display_name":"Tangyike Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tangyike Zhang","raw_affiliation_strings":["Xi&#x2019;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,Xi&#x2019;an,P.R. China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi&#x2019;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,Xi&#x2019;an,P.R. China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100774271","display_name":"Shitao Chen","orcid":"https://orcid.org/0000-0002-9422-3058"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shitao Chen","raw_affiliation_strings":["Xi&#x2019;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,Xi&#x2019;an,P.R. China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi&#x2019;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,Xi&#x2019;an,P.R. China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047405956","display_name":"Nanning Zheng","orcid":"https://orcid.org/0000-0003-1608-8257"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":["Xi&#x2019;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,Xi&#x2019;an,P.R. China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi&#x2019;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,Xi&#x2019;an,P.R. China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031227866","display_name":"Jingmin Xin","orcid":"https://orcid.org/0000-0003-1906-2327"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingmin Xin","raw_affiliation_strings":["Xi&#x2019;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,Xi&#x2019;an,P.R. China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi&#x2019;an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics,Xi&#x2019;an,P.R. China,710049","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.4247,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67243091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"17420","last_page":"17427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9664000272750854,"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":0.9664000272750854,"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":0.008200000040233135,"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/T10524","display_name":"Traffic control and management","score":0.00559999980032444,"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/trajectory","display_name":"Trajectory","score":0.6207000017166138},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.508400022983551},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.498199999332428},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.49410000443458557},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46970000863075256},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.35190001130104065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6328999996185303},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6207000017166138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5343999862670898},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.508400022983551},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.49410000443458557},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46970000863075256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40959998965263367},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1965455100","https://openalex.org/W2056877664","https://openalex.org/W2744369598","https://openalex.org/W2891385160","https://openalex.org/W2942735643","https://openalex.org/W2968983352","https://openalex.org/W2979863294","https://openalex.org/W2990696475","https://openalex.org/W3037606473","https://openalex.org/W3091165146","https://openalex.org/W3121045039","https://openalex.org/W3128395826","https://openalex.org/W3132033106","https://openalex.org/W3164005523","https://openalex.org/W3176912151","https://openalex.org/W4210422063","https://openalex.org/W4309592030","https://openalex.org/W4385325797","https://openalex.org/W4386066695","https://openalex.org/W4388878649","https://openalex.org/W4391769151","https://openalex.org/W4391929651","https://openalex.org/W4401414869"],"related_works":[],"abstract_inverted_index":{"Modeling":[0],"expert":[1],"driving":[2,34,44,119,170],"behavior":[3],"is":[4],"crucial":[5],"for":[6,80,90],"the":[7,38,47,62,97,103,108,115,123,139,145,149,152,162,165],"successful":[8],"implementation":[9],"of":[10,49,99,118,125,151,164],"human-like":[11],"autonomous":[12],"driving.":[13],"In":[14,106],"this":[15],"paper,":[16],"we":[17],"propose":[18],"a":[19,85,112],"new":[20],"sampling-based":[21],"Maximum":[22],"Entropy":[23],"Deep":[24],"Inverse":[25],"Reinforcement":[26],"Learning":[27],"(MEDIRL)":[28],"framework.":[29],"It":[30],"leverages":[31],"naturalistic":[32],"human":[33],"data":[35],"to":[36,60,71,95,114],"train":[37],"reward":[39,48,74,132,157],"model":[40,154],"and":[41,84,144],"thus":[42],"evaluates":[43],"behaviors":[45,120,171],"from":[46],"sampled":[50,126],"candidate":[51,127],"trajectories.":[52],"The":[53],"proposed":[54,109,153,166],"framework":[55,110],"utilizes":[56],"deep":[57],"neural":[58],"networks":[59],"learn":[61],"feature-reward":[63],"mapping,":[64],"which":[65],"offers":[66,111],"superior":[67],"fitting":[68],"capabilities":[69],"compared":[70],"traditional":[72],"linear":[73],"functions.":[75],"A":[76],"polynomial":[77],"trajectory":[78,88],"sampler":[79,89],"long-term":[81],"decision":[82],"making":[83],"dynamic":[86],"window":[87],"short-term":[91],"planning":[92],"are":[93,136],"adopted":[94],"simplify":[96],"calculation":[98],"partition":[100],"function":[101],"in":[102,155,168],"MEDIRL":[104],"algorithm.":[105],"addition,":[107],"solution":[113],"probability":[116],"estimation":[117],"by":[121],"calculating":[122],"likelihood":[124],"trajectories":[128],"based":[129],"on":[130,138],"their":[131],"values.":[133],"Comparative":[134],"experiments":[135],"conducted":[137],"NGSIM":[140],"US-101":[141],"Highway":[142],"dataset,":[143],"experimental":[146],"results":[147],"demonstrate":[148],"superiority":[150],"personalizing":[156],"functions,":[158],"as":[159,161],"well":[160],"applicability":[163],"method":[167],"modeling":[169],"across":[172],"various":[173],"time":[174],"horizons.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-28T22:27:27.802056","created_date":"2025-11-28T00:00:00"}
