{"id":"https://openalex.org/W4390576807","doi":"https://doi.org/10.1109/tie.2023.3317853","title":"Model-Based Safe Reinforcement Learning With Time-Varying Constraints: Applications to Intelligent Vehicles","display_name":"Model-Based Safe Reinforcement Learning With Time-Varying Constraints: Applications to Intelligent Vehicles","publication_year":2024,"publication_date":"2024-01-04","ids":{"openalex":"https://openalex.org/W4390576807","doi":"https://doi.org/10.1109/tie.2023.3317853"},"language":"en","primary_location":{"id":"doi:10.1109/tie.2023.3317853","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tie.2023.3317853","pdf_url":"https://ieeexplore.ieee.org/ielx7/41/4387790/10381514.pdf","source":{"id":"https://openalex.org/S58031724","display_name":"IEEE Transactions on Industrial Electronics","issn_l":"0278-0046","issn":["0278-0046","1557-9948"],"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 Industrial Electronics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/41/4387790/10381514.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101668802","display_name":"Xinglong Zhang","orcid":"https://orcid.org/0000-0002-0587-2487"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinglong Zhang","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043548738","display_name":"Yaoqian Peng","orcid":"https://orcid.org/0000-0001-5141-616X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoqian Peng","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012004938","display_name":"Biao Luo","orcid":"https://orcid.org/0000-0002-3353-2586"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Luo","raw_affiliation_strings":["School of Automation, Central South University, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100721259","display_name":"Wei Pan","orcid":"https://orcid.org/0000-0003-1121-9879"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Wei Pan","raw_affiliation_strings":["Department of Cognitive Robotics, Delft University of Technology, Delft, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Cognitive Robotics, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020386015","display_name":"Haibin Xie","orcid":"https://orcid.org/0000-0001-6408-9348"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibin Xie","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101668802"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":5.7527,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.96455372,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"71","issue":"10","first_page":"12744","last_page":"12753"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9641000032424927,"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"}},"topics":[{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9641000032424927,"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"}},{"id":"https://openalex.org/T10808","display_name":"Electric and Hybrid Vehicle Technologies","score":0.927299976348877,"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":0.8328142762184143},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.641556978225708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5885670185089111},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5750453472137451},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.5351826548576355},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.5336464643478394},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4481941759586334},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.42635378241539},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4196586608886719},{"id":"https://openalex.org/keywords/vehicle-dynamics","display_name":"Vehicle dynamics","score":0.41479581594467163},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3625016212463379},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.32466161251068115},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.3097376823425293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2708250880241394},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.24824434518814087},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16814717650413513}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8328142762184143},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.641556978225708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5885670185089111},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5750453472137451},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.5351826548576355},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.5336464643478394},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4481941759586334},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.42635378241539},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4196586608886719},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.41479581594467163},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3625016212463379},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.32466161251068115},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.3097376823425293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2708250880241394},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.24824434518814087},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16814717650413513},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tie.2023.3317853","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tie.2023.3317853","pdf_url":"https://ieeexplore.ieee.org/ielx7/41/4387790/10381514.pdf","source":{"id":"https://openalex.org/S58031724","display_name":"IEEE Transactions on Industrial Electronics","issn_l":"0278-0046","issn":["0278-0046","1557-9948"],"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 Industrial Electronics","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/03eb67ae-b43f-4625-a926-8923ab742b07","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/03eb67ae-b43f-4625-a926-8923ab742b07","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Zhang, X, Peng, Y, Luo, B, Pan, W, Xu, X & Xie, H 2024, 'Model-Based Safe Reinforcement Learning With Time-Varying Constraints : Applications to Intelligent Vehicles', IEEE Transactions on Industrial Electronics, vol. 71, no. 10, pp. 12744-12753. https://doi.org/10.1109/TIE.2023.3317853","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1109/tie.2023.3317853","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tie.2023.3317853","pdf_url":"https://ieeexplore.ieee.org/ielx7/41/4387790/10381514.pdf","source":{"id":"https://openalex.org/S58031724","display_name":"IEEE Transactions on Industrial Electronics","issn_l":"0278-0046","issn":["0278-0046","1557-9948"],"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 Industrial Electronics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1023919524","display_name":null,"funder_award_id":", Grant","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G37568934","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5057384242","display_name":null,"funder_award_id":"62003361","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5137249975","display_name":null,"funder_award_id":"62022094","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5196624177","display_name":null,"funder_award_id":"61825305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390576807.pdf","grobid_xml":"https://content.openalex.org/works/W4390576807.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1544016679","https://openalex.org/W1845972764","https://openalex.org/W1988538197","https://openalex.org/W2046376809","https://openalex.org/W2115562234","https://openalex.org/W2123871098","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2781726626","https://openalex.org/W2842089854","https://openalex.org/W2963105220","https://openalex.org/W2963864421","https://openalex.org/W2979211489","https://openalex.org/W2991391803","https://openalex.org/W2995409103","https://openalex.org/W2997285217","https://openalex.org/W3012839911","https://openalex.org/W3037804676","https://openalex.org/W3044818549","https://openalex.org/W3048735518","https://openalex.org/W3095669803","https://openalex.org/W3096918561","https://openalex.org/W3120964372","https://openalex.org/W3150718622","https://openalex.org/W3166557699","https://openalex.org/W3168269639","https://openalex.org/W3168575058","https://openalex.org/W3168692131","https://openalex.org/W3171392489","https://openalex.org/W3173921802","https://openalex.org/W3186317065","https://openalex.org/W3195968524","https://openalex.org/W3207250575","https://openalex.org/W4200103418","https://openalex.org/W4205769419","https://openalex.org/W4226371468","https://openalex.org/W4293545785","https://openalex.org/W4380538696","https://openalex.org/W6683153233","https://openalex.org/W6737893269","https://openalex.org/W6772456302"],"related_works":["https://openalex.org/W2381242807","https://openalex.org/W2751208925","https://openalex.org/W2347541121","https://openalex.org/W4288804799","https://openalex.org/W3089617106","https://openalex.org/W3032237421","https://openalex.org/W2080951048","https://openalex.org/W3011883280","https://openalex.org/W2390346111","https://openalex.org/W2120267624"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"safe":[3,49,109],"reinforcement":[4],"learning":[5,114],"(RL)":[6],"with":[7,24,58],"the":[8,73,98,130,140,164],"actor-critic":[9],"structure":[10,82],"has":[11],"gained":[12],"significant":[13],"interest":[14],"for":[15,52,150],"continuous":[16],"control":[17,22,54,62,80,85,176],"tasks.":[18],"However,":[19],"achieving":[20],"near-optimal":[21],"policies":[23],"safety":[25,43,86,102],"and":[26,61,107,117,147,156],"convergence":[27],"guarantees":[28],"remains":[29],"challenging.":[30],"Moreover,":[31],"few":[32],"works":[33],"have":[34],"focused":[35],"on":[36,113],"designing":[37],"RL":[38,50,127],"algorithms":[39,128],"that":[40],"handle":[41],"time-varying":[42,59,105],"constraints.":[44,63],"This":[45],"article":[46],"proposes":[47],"a":[48,76,90],"algorithm":[51,123],"optimal":[53],"of":[55,100,143,169],"nonlinear":[56],"systems":[57],"state":[60],"The":[64,121,160],"algorithm's":[65],"novelty":[66],"lies":[67],"in":[68,129],"two":[69,151],"key":[70],"aspects.":[71],"Firstly,":[72],"approach":[74],"introduces":[75],"unique":[77],"barrier":[78],"force-based":[79],"policy":[81,92,101],"to":[83,139],"ensure":[84],"during":[87],"learning.":[88],"Secondly,":[89],"multistep":[91],"evaluation":[93],"mechanism":[94],"is":[95,136],"employed,":[96],"enabling":[97],"prediction":[99],"risks":[103],"under":[104],"constraints":[106],"guiding":[108],"updates.":[110],"Theoretical":[111],"results":[112,162],"convergence,":[115],"stability,":[116],"robustness":[118],"are":[119],"proven.":[120],"proposed":[122],"outperforms":[124],"several":[125],"state-of-the-art":[126],"simulated":[131],"Safety":[132],"Gym":[133],"environment.":[134],"It":[135],"also":[137],"applied":[138],"real-world":[141],"problem":[142],"integrated":[144],"path":[145],"following":[146],"collision":[148],"avoidance":[149],"intelligent":[152],"vehicles\u2014a":[153],"differential-drive":[154],"vehicle":[155],"an":[157],"Ackermann-drive":[158],"one.":[159],"experimental":[161],"demonstrate":[163],"impressive":[165],"sim-to-real":[166],"transfer":[167],"capability":[168],"our":[170],"approach,":[171],"while":[172],"showcasing":[173],"satisfactory":[174],"online":[175],"performance.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2024-01-05T00:00:00"}