{"id":"https://openalex.org/W4390422151","doi":"https://doi.org/10.1109/tiv.2023.3348134","title":"RL-Driven MPPI: Accelerating Online Control Laws Calculation With Offline Policy","display_name":"RL-Driven MPPI: Accelerating Online Control Laws Calculation With Offline Policy","publication_year":2023,"publication_date":"2023-12-29","ids":{"openalex":"https://openalex.org/W4390422151","doi":"https://doi.org/10.1109/tiv.2023.3348134"},"language":"en","primary_location":{"id":"doi:10.1109/tiv.2023.3348134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tiv.2023.3348134","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/A5103004604","display_name":"Yue Qu","orcid":"https://orcid.org/0000-0002-4409-4630"},"institutions":[{"id":"https://openalex.org/I4210101451","display_name":"Nanjing University of Industry Technology","ror":"https://ror.org/00qf07q44","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210101451"]},{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yue Qu","raw_affiliation_strings":["School of Mechanical Engineering, Nanjing Vocational University of Industry Technology, Nanjing, China","School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4409-4630","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Nanjing Vocational University of Industry Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210101451"]},{"raw_affiliation_string":"School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"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":["College of Automotive Studies, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8015-9788","affiliations":[{"raw_affiliation_string":"College of Automotive Studies, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064437242","display_name":"Shuhua Gao","orcid":"https://orcid.org/0000-0003-3208-9620"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhua Gao","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-3208-9620","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101530275","display_name":"Jun Guan","orcid":"https://orcid.org/0000-0002-8800-1109"},"institutions":[{"id":"https://openalex.org/I4210096899","display_name":"Jiangsu University of Science and Technology","ror":"https://ror.org/00tyjp878","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210096899"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Guan","raw_affiliation_strings":["School of Automation, Jiangsu University of Science and Technology, Zhenjiang, China"],"raw_orcid":"https://orcid.org/0000-0002-8800-1109","affiliations":[{"raw_affiliation_string":"School of Automation, Jiangsu University of Science and Technology, Zhenjiang, China","institution_ids":["https://openalex.org/I4210096899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103027556","display_name":"Haoqi Yan","orcid":"https://orcid.org/0009-0000-3018-4339"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqi Yan","raw_affiliation_strings":["School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-3018-4339","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028599970","display_name":"Liming Xiao","orcid":"https://orcid.org/0009-0006-4566-1103"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liming Xiao","raw_affiliation_strings":["School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-4566-1103","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747108","display_name":"Shengbo Eben Li","orcid":"https://orcid.org/0000-0003-4923-3633"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbo Eben Li","raw_affiliation_strings":["State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China","Center for Intelligent Connected Vehicles and Transportation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4923-3633","affiliations":[{"raw_affiliation_string":"State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Intelligent Connected Vehicles and Transportation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067909017","display_name":"Jingliang Duan","orcid":"https://orcid.org/0000-0002-3697-1576"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingliang Duan","raw_affiliation_strings":["School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3697-1576","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5103004604"],"corresponding_institution_ids":["https://openalex.org/I4210101451","https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":3.984,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.95007166,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"9","issue":"2","first_page":"3605","last_page":"3616"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9746999740600586,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9746999740600586,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10768","display_name":"Electric Vehicles and Infrastructure","score":0.9690999984741211,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11276","display_name":"Solar Radiation and Photovoltaics","score":0.9660000205039978,"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":0.5734379291534424},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5224865078926086},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5172182321548462},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5079081654548645},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.48929235339164734},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.46868494153022766},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4420076906681061},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4230685532093048},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41334280371665955},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2310563027858734},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1593867540359497},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.1533832848072052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14636951684951782}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5734379291534424},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5224865078926086},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5172182321548462},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5079081654548645},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.48929235339164734},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.46868494153022766},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4420076906681061},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4230685532093048},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41334280371665955},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2310563027858734},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1593867540359497},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1533832848072052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14636951684951782},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tiv.2023.3348134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tiv.2023.3348134","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/G1267632332","display_name":null,"funder_award_id":"FRF-OT-23-02","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"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":37,"referenced_works":["https://openalex.org/W1527786550","https://openalex.org/W1971536112","https://openalex.org/W2067499857","https://openalex.org/W2090528409","https://openalex.org/W2410617946","https://openalex.org/W2584986912","https://openalex.org/W2736601468","https://openalex.org/W2738778707","https://openalex.org/W2795657119","https://openalex.org/W2807050419","https://openalex.org/W2963238245","https://openalex.org/W2972560617","https://openalex.org/W2973229164","https://openalex.org/W3015082424","https://openalex.org/W3043239066","https://openalex.org/W3127454018","https://openalex.org/W3174208427","https://openalex.org/W3207619101","https://openalex.org/W3211345831","https://openalex.org/W4213251304","https://openalex.org/W4214851269","https://openalex.org/W4225773298","https://openalex.org/W4285047692","https://openalex.org/W4287617987","https://openalex.org/W4308327070","https://openalex.org/W4315489514","https://openalex.org/W4323897042","https://openalex.org/W4360995553","https://openalex.org/W4362650413","https://openalex.org/W4366158867","https://openalex.org/W4376481351","https://openalex.org/W4387560490","https://openalex.org/W4387965994","https://openalex.org/W6638018090","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6857414025"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W4323768008","https://openalex.org/W3131574667","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778"],"abstract_inverted_index":{"Model":[0],"Predictive":[1],"Path":[2],"Integral":[3],"(MPPI)":[4],"is":[5,35,39,208],"a":[6,43,68,134,171,190],"recognized":[7],"sampling-based":[8],"approach":[9,181],"for":[10,163,174],"finite":[11],"horizon":[12],"optimal":[13],"control":[14,48,206,225],"problems.":[15],"However,":[16],"the":[17,30,81,84,99,107,111,119,144,153,175,212,218],"efficacy":[18],"and":[19,55,86,110,124,147,227],"computational":[20,56],"efficiency":[21,146],"of":[22,32,88,115,121,150,178],"prevailing":[23],"MPPI":[24,70,75,91,183,221],"methods":[25],"are":[26],"heavily":[27],"reliant":[28],"on":[29,83],"quality":[31,87],"rollouts.":[33],"This":[34,180],"problematic":[36],"because":[37],"it":[38,167],"hard":[40],"to":[41,52,133,138,168,184,210],"sample":[42,145,228],"low-cost":[44],"trajectory":[45],"using":[46],"random":[47,139],"sequences,":[49],"thereby":[50],"leading":[51],"inferior":[53],"performance":[54,197,226],"efficiency,":[57],"especially":[58],"under":[59],"constrained":[60],"resources.":[61],"To":[62],"address":[63],"this":[64],"issue,":[65],"we":[66],"propose":[67],"data-efficient":[69],"method":[71,222],"called":[72],"reinforcement":[73],"learning-driven":[74],"(RL-driven":[76],"MPPI),":[77],"which":[78,141],"significantly":[79,142],"reduces":[80],"dependency":[82],"quantity":[85],"samples.":[89],"RL-driven":[90,220],"employs":[92],"an":[93,160,186],"offline-online":[94],"policy":[95,101],"learning":[96],"scheme,":[97],"where":[98],"offline":[100],"learned":[102,156],"by":[103,129,157],"RL":[104,123,130,158],"serves":[105],"as":[106,170],"initial":[108,112],"solution":[109],"rollout":[113],"generator":[114],"MPPI,":[116],"effectively":[117],"combining":[118],"strengths":[120],"both":[122],"MPPI.":[125,151,179],"The":[126],"rollouts":[127],"generated":[128],"typically":[131],"correspond":[132],"lower":[135],"cost-to-go":[136],"compared":[137],"sampling,":[140],"boosts":[143],"convergence":[148],"speed":[149],"Moreover,":[152],"value":[154],"function":[155],"offers":[159],"accurate":[161],"estimation":[162],"infinite-horizon":[164,187],"cost-to-go,":[165],"enabling":[166],"serve":[169],"terminal":[172],"term":[173],"cost":[176,188],"criteria":[177],"empowers":[182],"approximate":[185],"with":[189],"shorter":[191],"prediction":[192],"horizon,":[193],"thus":[194],"enhancing":[195],"real-time":[196],"at":[198],"each":[199],"time":[200],"step.":[201],"An":[202],"unmanned":[203],"aerial":[204],"vehicle":[205],"task":[207],"conducted":[209],"evaluate":[211],"proposed":[213,219],"method.":[214],"Results":[215],"indicate":[216],"that":[217],"exhibits":[223],"superior":[224],"efficiency.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2025-10-10T00:00:00"}