{"id":"https://openalex.org/W3209552190","doi":"https://doi.org/10.1109/itsc48978.2021.9564880","title":"Learn collision-free self-driving skills at urban intersections with model-based reinforcement learning","display_name":"Learn collision-free self-driving skills at urban intersections with model-based reinforcement learning","publication_year":2021,"publication_date":"2021-09-19","ids":{"openalex":"https://openalex.org/W3209552190","doi":"https://doi.org/10.1109/itsc48978.2021.9564880","mag":"3209552190"},"language":"en","primary_location":{"id":"doi:10.1109/itsc48978.2021.9564880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc48978.2021.9564880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","raw_type":"proceedings-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/A5082794136","display_name":"Yang Guan","orcid":"https://orcid.org/0000-0003-0689-0510"},"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":true,"raw_author_name":"Yang Guan","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007325049","display_name":"Yangang Ren","orcid":"https://orcid.org/0000-0002-1173-7230"},"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":"Yangang Ren","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004124678","display_name":"Haitong Ma","orcid":"https://orcid.org/0000-0002-9943-0638"},"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":"Haitong Ma","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"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":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101697324","display_name":"Qi Sun","orcid":"https://orcid.org/0000-0002-2664-2509"},"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":"Qi Sun","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101422609","display_name":"Yifan Dai","orcid":"https://orcid.org/0000-0002-2065-3768"},"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"]},{"id":"https://openalex.org/I4210125878","display_name":"Suzhou Research Institute","ror":"https://ror.org/03ebk0c60","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210125878"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Dai","raw_affiliation_strings":["Suzhou Automotive Research Institute, Tsinghua University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Suzhou Automotive Research Institute, Tsinghua University, Suzhou, China","institution_ids":["https://openalex.org/I4210125878","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100640936","display_name":"Bo Cheng","orcid":"https://orcid.org/0000-0002-1753-2922"},"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":"Bo Cheng","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5082794136"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.5499,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.66240389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3462","last_page":"3469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9997000098228455,"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":0.9993000030517578,"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/T10370","display_name":"Traffic and Road Safety","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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":0.7999523878097534},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6805917024612427},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.6517292261123657},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5461292862892151},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5425771474838257},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5182409286499023},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5139889121055603},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.472999632358551},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.4389747381210327},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4347797632217407},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.4312957525253296},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.361300528049469},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3215170204639435},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3039000332355499},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26662367582321167},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15501824021339417},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13708725571632385}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7999523878097534},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6805917024612427},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.6517292261123657},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5461292862892151},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5425771474838257},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5182409286499023},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5139889121055603},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.472999632358551},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.4389747381210327},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4347797632217407},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.4312957525253296},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.361300528049469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3215170204639435},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3039000332355499},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26662367582321167},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15501824021339417},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13708725571632385},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc48978.2021.9564880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc48978.2021.9564880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W300028405","https://openalex.org/W1587371456","https://openalex.org/W1831549348","https://openalex.org/W1971086298","https://openalex.org/W1971259793","https://openalex.org/W2000194319","https://openalex.org/W2145339207","https://openalex.org/W2343568200","https://openalex.org/W2766447205","https://openalex.org/W2781726626","https://openalex.org/W2842089854","https://openalex.org/W2903709398","https://openalex.org/W2962867954","https://openalex.org/W2962902376","https://openalex.org/W2964043796","https://openalex.org/W2975767248","https://openalex.org/W2990123902","https://openalex.org/W3002044607","https://openalex.org/W3015549988","https://openalex.org/W3088218629","https://openalex.org/W3090027660","https://openalex.org/W3104639963","https://openalex.org/W3134476446","https://openalex.org/W4295719664","https://openalex.org/W6692846177","https://openalex.org/W6745935785","https://openalex.org/W6747473740","https://openalex.org/W6948184010"],"related_works":["https://openalex.org/W4317634134","https://openalex.org/W1819938260","https://openalex.org/W2340892746","https://openalex.org/W4391307509","https://openalex.org/W3163022373","https://openalex.org/W626552678","https://openalex.org/W2742483371","https://openalex.org/W607781325","https://openalex.org/W3005999311","https://openalex.org/W4381746183"],"abstract_inverted_index":{"Intersection":[0],"is":[1,26,169],"one":[2],"of":[3,67,201],"the":[4,33,57,74,80,93,108,113,146,163,178,195,199,220,233],"most":[5],"complex":[6,46],"and":[7,18,59,71,99,149,176,211],"accident-prone":[8],"urban":[9],"traffic":[10,24,229],"scenarios":[11,47],"for":[12,48],"autonomous":[13],"driving":[14,226],"wherein":[15],"making":[16],"safe":[17],"computationally":[19],"efficient":[20],"decisions":[21],"with":[22,79,104,156],"high-density":[23],"flow":[25],"usually":[27],"non-trivial.":[28],"Current":[29],"rule-based":[30],"methods":[31],"decompose":[32],"decision-making":[34,58],"task":[35],"into":[36,152],"several":[37],"serial":[38],"sub-modules,":[39],"resulting":[40],"in":[41,209,212],"long":[42],"computation":[43,115,234],"time":[44,235],"at":[45],"on-board":[49],"computing":[50],"devices.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55,119,204],"formulate":[56],"control":[60,167,188],"problem":[61,103,143,155],"under":[62,227],"intersections":[63],"as":[64],"a":[65,77,85,101,121,132,141,157,213,237],"process":[66],"optimal":[68,166],"path":[69,78],"selection":[70],"tracking,":[72],"where":[73],"former":[75],"selects":[76],"best":[81],"safety":[82,105,160],"measure":[83],"from":[84],"set":[86],"generated":[87],"only":[88],"considering":[89],"static":[90],"information,":[91],"while":[92,231],"latter":[94],"then":[95],"considers":[96],"dynamic":[97],"obstacles":[98],"solve":[100],"tracking":[102],"constraints":[106,193],"using":[107],"chosen":[109],"path.":[110],"To":[111,197],"avoid":[112],"heavy":[114],"introduced":[116],"by":[117,171,236],"that,":[118],"develop":[120],"reinforcement":[122],"learning":[123],"algorithm":[124],"called":[125],"generalized":[126],"exterior":[127,182],"point":[128,183],"(GEP)":[129],"to":[130,190],"find":[131],"neural":[133],"network":[134],"(NN)":[135],"solution":[136],"offline.":[137],"It":[138],"first":[139],"constructs":[140],"multi-task":[142],"involving":[144],"all":[145],"candidate":[147],"paths":[148],"transforms":[150],"it":[151],"an":[153,181],"unconstrained":[154],"penalty":[158],"on":[159],"violations.":[161],"Afterward,":[162],"approximate":[164],"feasible":[165],"policy":[168,189,222],"obtained":[170],"alternatively":[172],"performing":[173],"gradient":[174],"descent":[175],"enlarging":[177],"penalty.":[179],"As":[180],"type":[184],"method,":[185,203],"GEP":[186],"permits":[187],"violate":[191],"inequality":[192],"during":[194],"iterations.":[196],"verify":[198],"effectiveness":[200],"our":[202],"carried":[205],"out":[206],"experiments":[207],"both":[208],"simulation":[210],"real":[214],"road":[215],"test.":[216],"Results":[217],"demonstrate":[218],"that":[219],"learned":[221],"can":[223],"realize":[224],"collision-free":[225],"different":[228],"conditions":[230],"reducing":[232],"large":[238],"margin.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}