{"id":"https://openalex.org/W4401747997","doi":"https://doi.org/10.1109/lra.2024.3448237","title":"Task-Driven Autonomous Driving: Balanced Strategies Integrating Curriculum Reinforcement Learning and Residual Policy","display_name":"Task-Driven Autonomous Driving: Balanced Strategies Integrating Curriculum Reinforcement Learning and Residual Policy","publication_year":2024,"publication_date":"2024-08-22","ids":{"openalex":"https://openalex.org/W4401747997","doi":"https://doi.org/10.1109/lra.2024.3448237"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3448237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3448237","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5010936276","display_name":"Jiamin Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiamin Shi","raw_affiliation_strings":["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'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"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'an Jiaotong University, Xi'an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009484245","display_name":"Tangyike Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tangyike Zhang","raw_affiliation_strings":["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'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"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'an Jiaotong University, Xi'an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111128676","display_name":"Ziqi Zong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziqi Zong","raw_affiliation_strings":["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'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"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'an Jiaotong University, Xi'an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100774271","display_name":"Shitao Chen","orcid":"https://orcid.org/0000-0002-9422-3058"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shitao Chen","raw_affiliation_strings":["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'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"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'an Jiaotong University, Xi'an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031227866","display_name":"Jingmin Xin","orcid":"https://orcid.org/0000-0003-1906-2327"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingmin Xin","raw_affiliation_strings":["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'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"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'an Jiaotong University, Xi'an, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047405956","display_name":"Nanning Zheng","orcid":"https://orcid.org/0000-0003-1608-8257"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":["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'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"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'an Jiaotong University, Xi'an, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5010936276"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.996,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74421473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"9","issue":"11","first_page":"9454","last_page":"9461"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.6636000275611877,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.6636000275611877,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7470521330833435},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6832281351089478},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.6296442747116089},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.57639479637146},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.5349944829940796},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5094566941261292},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4236936867237091},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32483142614364624},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2833384871482849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23439225554466248},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19273972511291504},{"id":"https://openalex.org/keywords/pedagogy","display_name":"Pedagogy","score":0.18642809987068176},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14076361060142517},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.11240029335021973},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10464009642601013}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7470521330833435},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6832281351089478},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.6296442747116089},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.57639479637146},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5349944829940796},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5094566941261292},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4236936867237091},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32483142614364624},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2833384871482849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23439225554466248},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19273972511291504},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.18642809987068176},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14076361060142517},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.11240029335021973},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10464009642601013},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3448237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3448237","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1646707810","https://openalex.org/W1869778509","https://openalex.org/W1972044564","https://openalex.org/W2107338474","https://openalex.org/W2231315878","https://openalex.org/W2296073425","https://openalex.org/W2505763307","https://openalex.org/W2575032143","https://openalex.org/W2736601468","https://openalex.org/W2736791111","https://openalex.org/W2869375357","https://openalex.org/W2904845482","https://openalex.org/W2963322416","https://openalex.org/W2968983352","https://openalex.org/W2977843878","https://openalex.org/W3012544020","https://openalex.org/W3040707741","https://openalex.org/W3113314866","https://openalex.org/W3123742938","https://openalex.org/W3130519362","https://openalex.org/W3161095009","https://openalex.org/W3187048847","https://openalex.org/W3200438282","https://openalex.org/W3202294003","https://openalex.org/W4221155471","https://openalex.org/W4226406084","https://openalex.org/W4286374783","https://openalex.org/W4322730824","https://openalex.org/W4365807717","https://openalex.org/W4401415702","https://openalex.org/W6639086533","https://openalex.org/W6741002519","https://openalex.org/W6761754428","https://openalex.org/W6775683342","https://openalex.org/W6810682420"],"related_works":["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","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Achieving":[0],"fully":[1],"autonomous":[2,99],"driving":[3],"in":[4,68,148],"urban":[5],"traffic":[6,20,70],"scenarios":[7],"is":[8,113],"a":[9,27,38,43,47,75],"significant":[10],"challenge":[11],"that":[12,81],"necessitates":[13],"balancing":[14],"safety,":[15],"efficiency,":[16],"and":[17,65,101,125,134],"compliance":[18],"with":[19,140],"regulations.":[21],"In":[22],"this":[23],"letter,":[24],"we":[25,73],"introduce":[26],"novel":[28],"Curriculum":[29],"Residual":[30],"Hierarchical":[31],"Reinforcement":[32],"Learning":[33],"(CR-HRL)":[34],"framework.":[35],"It":[36],"integrates":[37],"rule-based":[39,133],"planning":[40],"model":[41],"as":[42],"guiding":[44],"mechanism,":[45],"while":[46],"deep":[48],"reinforcement":[49],"learning":[50,79],"algorithm":[51],"generates":[52],"supplementary":[53],"residual":[54],"strategies.":[55],"This":[56],"combination":[57],"enables":[58],"the":[59,83,91,96,103,110,122],"RL":[60,135],"agent":[61],"to":[62],"perform":[63],"safe":[64],"efficient":[66],"overtaking":[67],"complex":[69],"scenarios.":[71],"Furthermore,":[72],"implement":[74],"detailed":[76],"three-stage":[77],"curriculum":[78,92],"strategy":[80,93],"enhances":[82],"training":[84],"process.":[85],"By":[86],"progressively":[87],"increasing":[88],"task":[89],"complexity,":[90],"effectively":[94],"guides":[95],"exploration":[97],"of":[98,105,109,128],"vehicles":[100,142],"improves":[102],"reusability":[104],"sub-strategies.":[106],"The":[107],"effectiveness":[108],"CR-HRL":[111],"framework":[112,130],"confirmed":[114],"through":[115],"ablation":[116],"experiments.":[117],"Comparative":[118],"experiments":[119],"further":[120],"highlight":[121],"superior":[123],"efficiency":[124],"decision-making":[126],"capabilities":[127],"our":[129],"over":[131],"traditional":[132],"baseline":[136],"methods.":[137],"Tests":[138],"conducted":[139],"actual":[141],"also":[143],"demonstrate":[144],"its":[145],"practical":[146],"applicability":[147],"real-world":[149],"settings.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}