{"id":"https://openalex.org/W4323338425","doi":"https://doi.org/10.1109/tits.2023.3250720","title":"SRL-TR<sup>2</sup>: A Safe Reinforcement Learning Based TRajectory TRacker Framework","display_name":"SRL-TR<sup>2</sup>: A Safe Reinforcement Learning Based TRajectory TRacker Framework","publication_year":2023,"publication_date":"2023-03-06","ids":{"openalex":"https://openalex.org/W4323338425","doi":"https://doi.org/10.1109/tits.2023.3250720"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2023.3250720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2023.3250720","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Transportation 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/A5091841796","display_name":"Chengyu Wang","orcid":"https://orcid.org/0000-0003-1910-6297"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyu Wang","raw_affiliation_strings":["Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1910-6297","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057155774","display_name":"Luhan Wang","orcid":"https://orcid.org/0000-0002-7056-5416"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luhan Wang","raw_affiliation_strings":["Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7056-5416","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019111566","display_name":"Zhaoming Lu","orcid":"https://orcid.org/0000-0002-0182-1770"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoming Lu","raw_affiliation_strings":["Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0182-1770","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007193367","display_name":"Xinghe Chu","orcid":"https://orcid.org/0000-0002-9363-6336"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinghe Chu","raw_affiliation_strings":["Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9363-6336","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032135313","display_name":"Zhengrui Shi","orcid":"https://orcid.org/0009-0001-2342-0986"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengrui Shi","raw_affiliation_strings":["Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-2342-0986","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029668190","display_name":"Jiayin Deng","orcid":"https://orcid.org/0000-0002-6772-9168"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayin Deng","raw_affiliation_strings":["Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6772-9168","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046672905","display_name":"Tianyang Su","orcid":"https://orcid.org/0009-0006-0591-1331"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyang Su","raw_affiliation_strings":["Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-0591-1331","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063484071","display_name":"Guochu Shou","orcid":"https://orcid.org/0000-0002-8271-0246"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guochu Shou","raw_affiliation_strings":["Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8271-0246","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000851572","display_name":"Xiangming Wen","orcid":"https://orcid.org/0000-0003-2793-6696"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangming Wen","raw_affiliation_strings":["Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2793-6696","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence, Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":2.538,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.90758503,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"24","issue":"6","first_page":"5765","last_page":"5780"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9972000122070312,"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/T10524","display_name":"Traffic control and management","score":0.9847999811172485,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8663264513015747},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6265450716018677},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5802760720252991},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5664384961128235},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.446059912443161},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43253031373023987},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.42321985960006714},{"id":"https://openalex.org/keywords/trajectory-optimization","display_name":"Trajectory optimization","score":0.41599664092063904},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3317019045352936}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8663264513015747},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6265450716018677},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5802760720252991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5664384961128235},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.446059912443161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43253031373023987},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.42321985960006714},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.41599664092063904},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3317019045352936},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2023.3250720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2023.3250720","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Transportation Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3073296280","display_name":null,"funder_award_id":"2019YFB1803300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8613326744","display_name":null,"funder_award_id":"Z191100001119028","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"}],"funders":[{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W51508254","https://openalex.org/W1544016679","https://openalex.org/W1771410628","https://openalex.org/W1971984830","https://openalex.org/W2009594301","https://openalex.org/W2036021531","https://openalex.org/W2041109651","https://openalex.org/W2055418321","https://openalex.org/W2085277206","https://openalex.org/W2088595989","https://openalex.org/W2107537851","https://openalex.org/W2113374105","https://openalex.org/W2120179083","https://openalex.org/W2145339207","https://openalex.org/W2155465595","https://openalex.org/W2159291411","https://openalex.org/W2172117433","https://openalex.org/W2257979135","https://openalex.org/W2396317032","https://openalex.org/W2519503047","https://openalex.org/W2580909119","https://openalex.org/W2593768305","https://openalex.org/W2604382266","https://openalex.org/W2736601468","https://openalex.org/W2782695576","https://openalex.org/W2787938642","https://openalex.org/W2897661175","https://openalex.org/W2909696589","https://openalex.org/W2913300629","https://openalex.org/W2913416895","https://openalex.org/W2915117209","https://openalex.org/W2915987858","https://openalex.org/W2948652605","https://openalex.org/W2948769381","https://openalex.org/W2953127297","https://openalex.org/W2963519194","https://openalex.org/W2963569053","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2966735560","https://openalex.org/W2968983352","https://openalex.org/W2990243143","https://openalex.org/W2990747716","https://openalex.org/W2991066121","https://openalex.org/W2997310315","https://openalex.org/W2998284887","https://openalex.org/W3000280594","https://openalex.org/W3004840042","https://openalex.org/W3009331570","https://openalex.org/W3021797019","https://openalex.org/W3037262181","https://openalex.org/W3038180127","https://openalex.org/W3044015199","https://openalex.org/W3047772261","https://openalex.org/W3088310808","https://openalex.org/W3089594962","https://openalex.org/W3098075141","https://openalex.org/W3120778962","https://openalex.org/W3138294267","https://openalex.org/W3156861611","https://openalex.org/W4292078458","https://openalex.org/W4293545785","https://openalex.org/W4294562617","https://openalex.org/W4295352814","https://openalex.org/W4297824641","https://openalex.org/W4299825255","https://openalex.org/W4302570325","https://openalex.org/W6602057636","https://openalex.org/W6638018090","https://openalex.org/W6683633756","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6725448924","https://openalex.org/W6728252718","https://openalex.org/W6737893269","https://openalex.org/W6741002519","https://openalex.org/W6748839928","https://openalex.org/W6751535212","https://openalex.org/W6751720535","https://openalex.org/W6758924645","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2768698792","https://openalex.org/W4385832323","https://openalex.org/W4244391535","https://openalex.org/W2356996864","https://openalex.org/W2904060783","https://openalex.org/W2015393961","https://openalex.org/W2378339670","https://openalex.org/W2359353485","https://openalex.org/W2361427670","https://openalex.org/W2139910871"],"abstract_inverted_index":{"This":[0],"paper":[1],"aims":[2],"to":[3,37,73,97,116,188],"solve":[4],"the":[5,32,60,67,78,83,102,108,119,122,134,139,142,162,182,194],"trajectory":[6],"tracking":[7],"control":[8,120],"problem":[9],"for":[10],"an":[11,54,113],"autonomous":[12],"vehicle":[13,76],"based":[14],"on":[15,28],"reinforcement":[16,20],"learning":[17,21],"methods.":[18],"Existing":[19],"approaches":[22],"have":[23],"found":[24],"limited":[25],"successful":[26],"applications":[27],"safety-critical":[29],"tasks":[30],"in":[31,58],"real":[33],"world":[34],"mainly":[35],"due":[36],"two":[38],"challenges:":[39],"1)":[40],"sim-to-real":[41],"transfer;":[42],"2)":[43],"closed-loop":[44],"stability":[45,140],"and":[46,70,92,104,137,157,173],"safety":[47,68,109,123],"concern.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,86,111,129],"propose":[53],"actor-critic-style":[55],"framework":[56],"SRL-TR2,":[57],"which":[59],"RL-based":[61],"TRajectory":[62],"TRackers":[63],"are":[64,125],"trained":[65],"under":[66,181],"constraints":[69,124],"then":[71],"deployed":[72],"a":[74,88],"full-size":[75],"as":[77],"lateral":[79,175],"controller.":[80],"To":[81,106],"improve":[82,138],"generalization":[84],"ability,":[85],"adopt":[87],"light-weight":[89],"adapter":[90],"State":[91],"Action":[93],"Space":[94],"Alignment":[95],"(SASA)":[96],"establish":[98],"mapping":[99],"relations":[100],"between":[101],"simulation":[103,155],"reality.":[105],"address":[107],"concern,":[110],"leverage":[112],"expert":[114],"strategy":[115],"take":[117],"over":[118],"when":[121],"not":[126],"satisfied.":[127],"Hence,":[128],"conduct":[130],"safe":[131],"explorations":[132],"during":[133],"training":[135],"process":[136],"of":[141,193],"policy.":[143],"The":[144],"experiments":[145],"show":[146],"that":[147],"our":[148],"agents":[149],"can":[150],"achieve":[151],"one-shot":[152],"transfer":[153],"across":[154],"scenarios":[156],"unseen":[158],"realistic":[159],"scenarios,":[160],"finishing":[161],"field":[163,195],"tests":[164,196],"with":[165],"average":[166,174],"running":[167],"time":[168],"less":[169,177],"than":[170,178],"10":[171],"ms/step":[172],"error":[176],"0.1":[179],"m":[180],"speed":[183],"ranging":[184],"from":[185],"12":[186],"km/h":[187],"18":[189],"km/h.":[190],"A":[191],"video":[192],"is":[197],"available":[198],"at":[199],"<uri":[200],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[201],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://youtu.be/pjWcN_fV24g</uri>":[202],".":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}