{"id":"https://openalex.org/W4312714128","doi":"https://doi.org/10.1109/tits.2022.3218705","title":"Safe Reinforcement Learning for Single Train Trajectory Optimization via Shield SARSA","display_name":"Safe Reinforcement Learning for Single Train Trajectory Optimization via Shield SARSA","publication_year":2022,"publication_date":"2022-11-10","ids":{"openalex":"https://openalex.org/W4312714128","doi":"https://doi.org/10.1109/tits.2022.3218705"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2022.3218705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2022.3218705","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/A5032282906","display_name":"Zicong Zhao","orcid":"https://orcid.org/0000-0003-1066-4575"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zicong Zhao","raw_affiliation_strings":["State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1066-4575","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059372733","display_name":"Jing Xun","orcid":"https://orcid.org/0000-0003-1656-4719"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Xun","raw_affiliation_strings":["State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1656-4719","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078042992","display_name":"Xuguang Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuguang Wen","raw_affiliation_strings":["Guangxi Key Laboratory of International Join for China-ASEAN Comprehensive Transportation, Nanning University, Nanning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Key Laboratory of International Join for China-ASEAN Comprehensive Transportation, Nanning University, Nanning, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081101609","display_name":"Jianqiu Chen","orcid":"https://orcid.org/0000-0002-5942-1569"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianqiu Chen","raw_affiliation_strings":["Guangxi Key Laboratory of International Join for China-ASEAN Comprehensive Transportation, Nanning University, Nanning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Key Laboratory of International Join for China-ASEAN Comprehensive Transportation, Nanning University, Nanning, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3755,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.92700897,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"24","issue":"1","first_page":"412","last_page":"428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11568","display_name":"Railway Systems and Energy Efficiency","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T11568","display_name":"Railway Systems and Energy Efficiency","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10842","display_name":"Railway Engineering and Dynamics","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T10698","display_name":"Transportation Planning and Optimization","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7247416973114014},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5795254111289978},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.5414137840270996},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5129880309104919},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.47669336199760437},{"id":"https://openalex.org/keywords/speed-limit","display_name":"Speed limit","score":0.4733574390411377},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4587149918079376},{"id":"https://openalex.org/keywords/time-constraint","display_name":"Time constraint","score":0.4574533998966217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32885247468948364},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3287438750267029},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.3135070204734802},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30151447653770447}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7247416973114014},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5795254111289978},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.5414137840270996},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5129880309104919},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.47669336199760437},{"id":"https://openalex.org/C2780210587","wikidata":"https://www.wikidata.org/wiki/Q1077350","display_name":"Speed limit","level":2,"score":0.4733574390411377},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4587149918079376},{"id":"https://openalex.org/C2775907273","wikidata":"https://www.wikidata.org/wiki/Q7805281","display_name":"Time constraint","level":2,"score":0.4574533998966217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32885247468948364},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3287438750267029},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3135070204734802},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30151447653770447},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C147176958","wikidata":"https://www.wikidata.org/wiki/Q77590","display_name":"Civil engineering","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2022.3218705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2022.3218705","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":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.9100000262260437}],"awards":[{"id":"https://openalex.org/G4195470973","display_name":null,"funder_award_id":"62073026","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8670592652","display_name":null,"funder_award_id":"RCS2021ZT007","funder_id":"https://openalex.org/F4320323067","funder_display_name":"State Key Laboratory of Rail Traffic Control and Safety"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323067","display_name":"State Key Laboratory of Rail Traffic Control and Safety","ror":"https://ror.org/01yj56c84"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W92438854","https://openalex.org/W1603678020","https://openalex.org/W1761635979","https://openalex.org/W1840625103","https://openalex.org/W1845972764","https://openalex.org/W1852135537","https://openalex.org/W1853065930","https://openalex.org/W1931027396","https://openalex.org/W2009975158","https://openalex.org/W2023808162","https://openalex.org/W2038814776","https://openalex.org/W2087025933","https://openalex.org/W2095113878","https://openalex.org/W2109028470","https://openalex.org/W2121506959","https://openalex.org/W2165167046","https://openalex.org/W2226549490","https://openalex.org/W2273088453","https://openalex.org/W2432285071","https://openalex.org/W2526006345","https://openalex.org/W2606446473","https://openalex.org/W2761475530","https://openalex.org/W2766282873","https://openalex.org/W2787908307","https://openalex.org/W2904134767","https://openalex.org/W2963530628","https://openalex.org/W2963575966","https://openalex.org/W2963604565","https://openalex.org/W2968104655","https://openalex.org/W2969591543","https://openalex.org/W2985713881","https://openalex.org/W2990350875","https://openalex.org/W2991598122","https://openalex.org/W3034840734","https://openalex.org/W3041202696","https://openalex.org/W3045372678","https://openalex.org/W3081881315","https://openalex.org/W3095545966","https://openalex.org/W3116060049","https://openalex.org/W3134035453","https://openalex.org/W3157756504","https://openalex.org/W3170805047","https://openalex.org/W3173493645","https://openalex.org/W4214717370","https://openalex.org/W4293515130","https://openalex.org/W6603835682","https://openalex.org/W6635948928","https://openalex.org/W6640490175","https://openalex.org/W6677916933","https://openalex.org/W6779812412"],"related_works":["https://openalex.org/W618248309","https://openalex.org/W2377336366","https://openalex.org/W1601203902","https://openalex.org/W2075798043","https://openalex.org/W4390419160","https://openalex.org/W2102464536","https://openalex.org/W2361332776","https://openalex.org/W4225671779","https://openalex.org/W1568097102","https://openalex.org/W2193463989"],"abstract_inverted_index":{"The":[0,155],"single":[1],"train":[2],"trajectory":[3],"optimization,":[4],"also":[5],"known":[6],"as":[7],"speed":[8,88,98],"profile":[9,89],"optimization":[10],"(SPO),":[11],"is":[12,54,101],"a":[13,25,46,50,66,92,108,115],"traditional":[14],"problem":[15],"to":[16,36,57,127,142,166],"minimize":[17],"the":[18,38,42,59,74,77,80,86,97,129,133,144,148,152,160,170],"traction":[19],"energy":[20],"consumption":[21],"of":[22,27,45,76,132],"trains.":[23],"As":[24],"kind":[26],"optimal":[28],"method,":[29],"reinforcement":[30],"learning":[31,43,130],"(RL)":[32],"has":[33],"been":[34],"used":[35,56,141],"solve":[37],"SPO":[39,81],"problem.":[40],"In":[41],"process":[44,131],"common":[47],"RL":[48,94],"algorithm,":[49],"soft":[51,67,153],"constraint":[52,68],"(punishment)":[53],"always":[55],"keep":[58],"agent":[60],"away":[61],"from":[62,163],"unsafe":[63],"states.":[64],"However,":[65],"can":[69],"not":[70],"guarantee":[71],"and":[72,113,151,173],"explain":[73],"safety":[75],"result.":[78],"For":[79],"problem,":[82],"it":[83],"means":[84],"that":[85],"optimized":[87],"obtained":[90],"by":[91],"simple":[93],"may":[95],"break":[96],"limit":[99],"which":[100],"unacceptable":[102],"in":[103],"reality.":[104],"This":[105],"paper":[106],"proposes":[107],"protection":[109],"mechanism":[110],"called":[111],"Shield":[112,116],"constructs":[114],"SARSA":[117],"(":[118],"<inline-formula":[119],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[120],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[121],"<tex-math":[122],"notation=\"LaTeX\">${S}$":[123],"</tex-math></inline-formula>":[124],"-SARSA)":[125],"algorithm":[126,150],"protect":[128],"high-speed":[134],"train.":[135],"Four":[136],"different":[137],"reward":[138],"functions":[139],"are":[140],"compare":[143],"protective":[145,171],"efficacy":[146,172],"between":[147],"proposed":[149],"constraint.":[154],"numerical":[156],"experiments":[157],"based":[158],"on":[159],"line":[161],"data":[162],"Wuxi":[164],"East":[165],"Suzhou":[167],"North":[168],"verify":[169],"effectiveness.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}