{"id":"https://openalex.org/W4402673447","doi":"https://doi.org/10.1109/tiv.2024.3463468","title":"Safe Reinforcement Learning for Autonomous Driving by Using Disturbance-Observer-Based Control Barrier Functions","display_name":"Safe Reinforcement Learning for Autonomous Driving by Using Disturbance-Observer-Based Control Barrier Functions","publication_year":2024,"publication_date":"2024-09-20","ids":{"openalex":"https://openalex.org/W4402673447","doi":"https://doi.org/10.1109/tiv.2024.3463468"},"language":"en","primary_location":{"id":"doi:10.1109/tiv.2024.3463468","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tiv.2024.3463468","pdf_url":null,"source":{"id":"https://openalex.org/S4210199657","display_name":"IEEE Transactions on Intelligent Vehicles","issn_l":"2379-8858","issn":["2379-8858","2379-8904"],"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 Vehicles","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/A5100430423","display_name":"Zhengyu Hou","orcid":"https://orcid.org/0000-0003-1741-8473"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Zhengyu Hou","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380168","display_name":"Wenjun Liu","orcid":"https://orcid.org/0000-0001-6917-4111"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wenjun Liu","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063781430","display_name":"Alois Knoll","orcid":"https://orcid.org/0000-0003-4840-076X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alois Knoll","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100430423"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":2.0342,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86274036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"10","issue":"6","first_page":"3782","last_page":"3791"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9804999828338623,"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":0.9804999828338623,"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":0.9771999716758728,"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/T10805","display_name":"Vehicle Dynamics and Control Systems","score":0.9406999945640564,"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/disturbance","display_name":"Disturbance (geology)","score":0.7467767000198364},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6536463499069214},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5125477313995361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49098899960517883},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4039227366447449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35324668884277344},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.0715833306312561}],"concepts":[{"id":"https://openalex.org/C2777601987","wikidata":"https://www.wikidata.org/wiki/Q5283581","display_name":"Disturbance (geology)","level":2,"score":0.7467767000198364},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6536463499069214},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5125477313995361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49098899960517883},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4039227366447449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35324668884277344},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0715833306312561},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tiv.2024.3463468","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tiv.2024.3463468","pdf_url":null,"source":{"id":"https://openalex.org/S4210199657","display_name":"IEEE Transactions on Intelligent Vehicles","issn_l":"2379-8858","issn":["2379-8858","2379-8904"],"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 Vehicles","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2230652337","https://openalex.org/W2489231587","https://openalex.org/W2560504659","https://openalex.org/W2616635592","https://openalex.org/W2619551236","https://openalex.org/W2889711700","https://openalex.org/W2963575966","https://openalex.org/W2966735560","https://openalex.org/W3011888914","https://openalex.org/W3038180127","https://openalex.org/W3048735518","https://openalex.org/W3119915811","https://openalex.org/W3120459386","https://openalex.org/W3135239772","https://openalex.org/W3150718622","https://openalex.org/W3154507809","https://openalex.org/W3171453668","https://openalex.org/W3195647294","https://openalex.org/W3207727352","https://openalex.org/W4221125501","https://openalex.org/W4283590445","https://openalex.org/W4292249799"],"related_works":["https://openalex.org/W2038604956","https://openalex.org/W2296560746","https://openalex.org/W2338222801","https://openalex.org/W2347583731","https://openalex.org/W2106602008","https://openalex.org/W2067832159","https://openalex.org/W2153353177","https://openalex.org/W3156121563","https://openalex.org/W2355389557","https://openalex.org/W4382279073"],"abstract_inverted_index":{"Recently,":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"has":[4],"been":[5],"increasingly":[6],"used":[7],"in":[8,23,201,209],"autonomous":[9],"driving":[10],"(AD)":[11],"navigation":[12,19],"control":[13,20,85,161,173],"systems.":[14],"However,":[15],"most":[16],"RL-based":[17],"AD":[18],"systems":[21],"remain":[22],"the":[24,55,73,90,97,111,114,118,121,125,139,176,183,189,197],"simulation":[25],"stage.":[26],"Its":[27],"practical":[28],"application":[29],"is":[30,95,155],"limited":[31],"due":[32],"to":[33,108,175],"growing":[34],"safety":[35,38,56,78,98,140,153,185,203],"concerns.":[36],"The":[37,164],"of":[39,57,82,117,141,199],"these":[40],"algorithms":[41],"remains":[42],"uncertain":[43],"when":[44],"confronted":[45],"with":[46,76,211,217],"real-world":[47],"disturbances":[48],"and":[49,84,120,145,182,192,195,214],"vehicle":[50,119,132,179],"model":[51,116,133,159],"uncertainties.":[52],"To":[53,137],"enhance":[54],"RL,":[58],"we":[59],"propose":[60],"a":[61,77,106,129,150],"disturbance":[62],"observer":[63],"(DOB)":[64],"based":[65,157],"safe":[66,165],"soft":[67],"actor-critic":[68],"(SAC)":[69],"algorithm":[70,75],"that":[71],"combines":[72],"SAC":[74,91,190],"constraints":[79,99],"filter":[80,100],"composed":[81],"DOB":[83,107,177],"barrier":[86],"function":[87],"(CBF).":[88],"When":[89],"agent's":[92],"action":[93,166],"output":[94],"unsafe,":[96],"will":[101,167],"alter":[102],"it.":[103],"We":[104,187],"employ":[105],"accurately":[109],"estimate":[110],"difference":[112],"between":[113],"nominal":[115],"actual":[122],"model,":[123,180],"i.e.,":[124],"lumped":[126],"disturbances.":[127],"Then,":[128],"more":[130],"accurate":[131],"can":[134],"be":[135,168],"obtained.":[136],"ensure":[138],"DOB-SAC":[142],"under":[143],"complex":[144],"dynamically":[146],"changing":[147],"environmental":[148],"conditions,":[149],"further":[151],"predictive":[152,160,184],"constraint":[154],"defined":[156],"on":[158],"(MPC)":[162],"ideas.":[163],"rendered":[169],"using":[170],"safety-critical":[171],"optimal":[172],"according":[174],"compensated":[178],"CBF,":[181],"constraints.":[186,204],"discuss":[188],"architecture":[191],"training":[193],"details,":[194],"investigate":[196],"effectiveness":[198],"CBF":[200],"modeling":[202],"Joint":[205],"simulations":[206],"are":[207],"conducted":[208],"scenarios":[210],"static":[212],"obstacles":[213],"intersection":[215],"scenes":[216],"dynamic":[218],"obstacles.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7}],"updated_date":"2026-03-30T08:08:38.191290","created_date":"2025-10-10T00:00:00"}