{"id":"https://openalex.org/W4283590445","doi":"https://doi.org/10.1142/s2301385023310027","title":"Reinforcement Learning Applications in Unmanned Vehicle Control: A Comprehensive Overview","display_name":"Reinforcement Learning Applications in Unmanned Vehicle Control: A Comprehensive Overview","publication_year":2022,"publication_date":"2022-06-27","ids":{"openalex":"https://openalex.org/W4283590445","doi":"https://doi.org/10.1142/s2301385023310027"},"language":"en","primary_location":{"id":"doi:10.1142/s2301385023310027","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s2301385023310027","pdf_url":null,"source":{"id":"https://openalex.org/S4210169569","display_name":"Unmanned Systems","issn_l":"2301-3850","issn":["2301-3850","2301-3869"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Unmanned Systems","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/A5025228565","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0001-8365-8008"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Liu","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University, Beijing 100191, P.\u00a0R.\u00a0China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University, Beijing 100191, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089224471","display_name":"Bahare Kiumarsi","orcid":"https://orcid.org/0000-0002-9701-8375"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bahare Kiumarsi","raw_affiliation_strings":["Michigan State University, East Lansing, MI 48823, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, MI 48823, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020552889","display_name":"Yusuf Kartal","orcid":"https://orcid.org/0000-0002-0295-8584"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusuf Kartal","raw_affiliation_strings":["University of Texas at Arlington Research Institute, Fort Worth, TX 76118, USA"],"raw_orcid":"https://orcid.org/0000-0002-0295-8584","affiliations":[{"raw_affiliation_string":"University of Texas at Arlington Research Institute, Fort Worth, TX 76118, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050254061","display_name":"Ahmet Taha Koru","orcid":"https://orcid.org/0000-0001-8191-2324"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmet Taha Koru","raw_affiliation_strings":["University of Texas at Arlington Research Institute, Fort Worth, TX 76118, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington Research Institute, Fort Worth, TX 76118, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063118155","display_name":"Hamidreza Modares","orcid":"https://orcid.org/0000-0003-0800-5140"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamidreza Modares","raw_affiliation_strings":["Michigan State University, East Lansing, MI 48823, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, MI 48823, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["University of Texas at Arlington Research Institute, Fort Worth, TX 76118, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington Research Institute, Fort Worth, TX 76118, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4989,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.93573462,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"11","issue":"01","first_page":"17","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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":0.9998999834060669,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9801999926567078,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9674000144004822,"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/hamilton\u2013jacobi\u2013bellman-equation","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","score":0.8931154608726501},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8435797691345215},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6862166523933411},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6104405522346497},{"id":"https://openalex.org/keywords/actuator","display_name":"Actuator","score":0.5987549424171448},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.5843496918678284},{"id":"https://openalex.org/keywords/vehicle-dynamics","display_name":"Vehicle dynamics","score":0.5386211276054382},{"id":"https://openalex.org/keywords/unmanned-underwater-vehicle","display_name":"Unmanned underwater vehicle","score":0.4960211217403412},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4902384877204895},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.45369791984558105},{"id":"https://openalex.org/keywords/system-dynamics","display_name":"System dynamics","score":0.431831032037735},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.4306972622871399},{"id":"https://openalex.org/keywords/underwater","display_name":"Underwater","score":0.4066718816757202},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2452700138092041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23473864793777466},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.23204374313354492},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14348188042640686},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.09411200881004333},{"id":"https://openalex.org/keywords/aerospace-engineering","display_name":"Aerospace engineering","score":0.07950225472450256}],"concepts":[{"id":"https://openalex.org/C196978813","wikidata":"https://www.wikidata.org/wiki/Q3302775","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","level":3,"score":0.8931154608726501},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8435797691345215},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6862166523933411},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6104405522346497},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.5987549424171448},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.5843496918678284},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.5386211276054382},{"id":"https://openalex.org/C2778740559","wikidata":"https://www.wikidata.org/wiki/Q2496586","display_name":"Unmanned underwater vehicle","level":3,"score":0.4960211217403412},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4902384877204895},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.45369791984558105},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.431831032037735},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4306972622871399},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.4066718816757202},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2452700138092041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23473864793777466},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.23204374313354492},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14348188042640686},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.09411200881004333},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.07950225472450256},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s2301385023310027","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s2301385023310027","pdf_url":null,"source":{"id":"https://openalex.org/S4210169569","display_name":"Unmanned Systems","issn_l":"2301-3850","issn":["2301-3850","2301-3869"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Unmanned Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1742339193","display_name":null,"funder_award_id":"W911NF-20-1-0132","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G4155764213","display_name":null,"funder_award_id":"N00014-18-1-2221","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W92805021","https://openalex.org/W132264163","https://openalex.org/W1576452626","https://openalex.org/W1576721254","https://openalex.org/W1793264465","https://openalex.org/W1907796993","https://openalex.org/W1914756871","https://openalex.org/W1972809999","https://openalex.org/W1977655452","https://openalex.org/W1996964737","https://openalex.org/W2004011682","https://openalex.org/W2012451615","https://openalex.org/W2024303516","https://openalex.org/W2081514674","https://openalex.org/W2085194340","https://openalex.org/W2086975818","https://openalex.org/W2138424909","https://openalex.org/W2148439597","https://openalex.org/W2288654255","https://openalex.org/W2413000173","https://openalex.org/W2484646121","https://openalex.org/W2592856010","https://openalex.org/W2596192431","https://openalex.org/W2757564505","https://openalex.org/W2772589676","https://openalex.org/W2795566994","https://openalex.org/W2885871221","https://openalex.org/W2898358912","https://openalex.org/W2907275873","https://openalex.org/W2907916537","https://openalex.org/W2907944110","https://openalex.org/W2912471136","https://openalex.org/W2954378215","https://openalex.org/W2963569053","https://openalex.org/W2986030537","https://openalex.org/W3006868075","https://openalex.org/W3011971877","https://openalex.org/W3013960924","https://openalex.org/W3019384758","https://openalex.org/W3045974612","https://openalex.org/W3049386870","https://openalex.org/W3086351065","https://openalex.org/W3088521775","https://openalex.org/W3110417209","https://openalex.org/W3119919588","https://openalex.org/W3126004433","https://openalex.org/W3149053487","https://openalex.org/W3152953026","https://openalex.org/W3191768628","https://openalex.org/W3208542285","https://openalex.org/W3214814008","https://openalex.org/W4206216124","https://openalex.org/W4210445430","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2358967034","https://openalex.org/W2155717523","https://openalex.org/W2024495128","https://openalex.org/W4319881067","https://openalex.org/W3130577778","https://openalex.org/W1974398766","https://openalex.org/W2087292112","https://openalex.org/W2623995997","https://openalex.org/W1600702449","https://openalex.org/W2114352060"],"abstract_inverted_index":{"This":[0,99],"paper":[1],"briefly":[2],"reviews":[3],"the":[4,7,30,59,79,87,96],"dynamics":[5,31],"and":[6,20,27,38,64,112],"control":[8,18,46,110,115],"architectures":[9],"of":[10,32,61],"unmanned":[11,24,33,74,118],"vehicles;":[12],"reinforcement":[13],"learning":[14],"(RL)":[15],"in":[16,23,29,58,73,104],"optimal":[17,54,88,109,113],"theory;":[19],"RL-based":[21,68],"applications":[22],"vehicles.":[25],"Nonlinearities":[26],"uncertainties":[28],"vehicles":[34],"(e.g.":[35],"aerial,":[36],"underwater,":[37],"tailsitter":[39],"vehicles)":[40],"pose":[41],"critical":[42],"challenges":[43],"to":[44,52,77],"their":[45],"systems.":[47,120],"Solving":[48],"Hamilton\u2013Jacobi\u2013Bellman":[49],"(HJB)":[50],"equations":[51],"find":[53],"controllers":[55],"becomes":[56],"difficult":[57],"presence":[60],"nonlinearities,":[62],"uncertainties,":[63],"actuator":[65],"faults.":[66],"Therefore,":[67],"approaches":[69],"are":[70],"widely":[71],"used":[72],"vehicle":[75,119],"systems":[76],"solve":[78],"HJB":[80],"equations.":[81],"To":[82],"this":[83],"end,":[84],"they":[85],"learn":[86],"solutions":[89],"by":[90],"using":[91],"online":[92],"data":[93],"measured":[94],"along":[95],"system":[97],"trajectories.":[98],"approach":[100],"is":[101],"very":[102],"practical":[103],"partially":[105],"or":[106],"completely":[107],"model-free":[108],"design":[111,116],"fault-tolerant":[114],"for":[117]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
