{"id":"https://openalex.org/W4416749301","doi":"https://doi.org/10.1109/iros60139.2025.11246272","title":"Safe Reinforcement Learning with a Predictive Safety Filter for Motion Planning and Control: A Drifting Vehicle Example","display_name":"Safe Reinforcement Learning with a Predictive Safety Filter for Motion Planning and Control: A Drifting Vehicle Example","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749301","doi":"https://doi.org/10.1109/iros60139.2025.11246272"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5078788222","display_name":"Bei Zhou","orcid":"https://orcid.org/0009-0000-8365-3629"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bei Zhou","raw_affiliation_strings":["Zhejiang University,State Key Laboratory of Industrial Control Technology,Hang Zhou,China,310058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,State Key Laboratory of Industrial Control Technology,Hang Zhou,China,310058","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119950408","display_name":"Baha Zarrouki","orcid":null},"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":"Baha Zarrouki","raw_affiliation_strings":["Technical University of Munich,Professorship of Autonomous Vehicle Systems,Garching,Germany,85748"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Professorship of Autonomous Vehicle Systems,Garching,Germany,85748","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107843711","display_name":"M. Piccinini","orcid":null},"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":"Mattia Piccinini","raw_affiliation_strings":["Technical University of Munich,Professorship of Autonomous Vehicle Systems,Garching,Germany,85748"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Professorship of Autonomous Vehicle Systems,Garching,Germany,85748","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071803923","display_name":"Cheng Hu","orcid":"https://orcid.org/0000-0003-1322-2828"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Hu","raw_affiliation_strings":["Zhejiang University,State Key Laboratory of Industrial Control Technology,Hang Zhou,China,310058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,State Key Laboratory of Industrial Control Technology,Hang Zhou,China,310058","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054697474","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0002-7669-1886"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Zhejiang University,State Key Laboratory of Industrial Control Technology,Hang Zhou,China,310058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,State Key Laboratory of Industrial Control Technology,Hang Zhou,China,310058","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063677428","display_name":"Johannes Betz","orcid":"https://orcid.org/0000-0001-9197-2849"},"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":"Johannes Betz","raw_affiliation_strings":["Technical University of Munich,Professorship of Autonomous Vehicle Systems,Garching,Germany,85748"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Professorship of Autonomous Vehicle Systems,Garching,Germany,85748","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4196","last_page":"4203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.260699987411499,"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":0.260699987411499,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.1770000010728836,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.15070000290870667,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7440999746322632},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5536999702453613},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.5376999974250793},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5335999727249146},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.5202999711036682},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4943999946117401},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.4616999924182892},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.45179998874664307}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7440999746322632},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5536999702453613},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.5376999974250793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5360000133514404},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5335999727249146},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.5202999711036682},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4943999946117401},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.4616999924182892},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42879998683929443},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3792000114917755},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3695000112056732},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.359499990940094},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C127757376","wikidata":"https://www.wikidata.org/wiki/Q2056514","display_name":"Active safety","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.32899999618530273},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3167000114917755},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2816999852657318},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2621999979019165}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1964565648","https://openalex.org/W2147524078","https://openalex.org/W2418627435","https://openalex.org/W2513536421","https://openalex.org/W2796775309","https://openalex.org/W2973229164","https://openalex.org/W2981761302","https://openalex.org/W2999762404","https://openalex.org/W3142005321","https://openalex.org/W3194630475","https://openalex.org/W4285102561","https://openalex.org/W4285228542","https://openalex.org/W4296838344","https://openalex.org/W4308068706","https://openalex.org/W4313886728","https://openalex.org/W4320011039","https://openalex.org/W4385764501","https://openalex.org/W4389474010","https://openalex.org/W4391741307","https://openalex.org/W4396728162","https://openalex.org/W4400188071","https://openalex.org/W4400644950","https://openalex.org/W4401878972","https://openalex.org/W4402262580","https://openalex.org/W4402402057","https://openalex.org/W4402780532","https://openalex.org/W4405055855","https://openalex.org/W4407558816"],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"drifting":[1],"is":[2],"a":[3,82,111,146],"complex":[4],"and":[5,14,22,34,74,129,132,158],"crucial":[6],"maneuver":[7],"for":[8,90],"safety-critical":[9,176],"scenarios":[10],"like":[11],"slippery":[12],"roads":[13],"emergency":[15],"collision":[16],"avoidance,":[17],"requiring":[18],"precise":[19],"motion":[20,25,88,107],"planning":[21,26],"control.":[23],"Traditional":[24],"methods":[27],"often":[28,54],"struggle":[29],"with":[30,99],"the":[31,118,138,170],"high":[32,42],"instability":[33],"unpredictability":[35],"of":[36,140,172],"drifting,":[37],"particularly":[38],"when":[39],"operating":[40],"at":[41],"speeds.":[43],"Recent":[44],"learning-based":[45],"approaches":[46],"have":[47,60],"attempted":[48],"to":[49,103,122,162,168],"tackle":[50],"this":[51],"issue":[52],"but":[53],"rely":[55],"on":[56,145],"expert":[57],"knowledge":[58],"or":[59],"limited":[61],"exploration":[62],"capabilities.":[63],"Additionally,":[64],"they":[65],"do":[66],"not":[67],"effectively":[68],"address":[69],"safety":[70],"concerns":[71],"during":[72],"learning":[73],"deployment.":[75],"To":[76],"overcome":[77],"these":[78],"limitations,":[79],"we":[80],"propose":[81],"novel":[83],"Safe":[84],"Reinforcement":[85],"Learning":[86],"(RL)-based":[87],"planner":[89],"autonomous":[91,173],"drifting.":[92],"Our":[93],"approach":[94],"integrates":[95],"an":[96],"RL":[97],"agent":[98],"model-based":[100],"drift":[101,106,134,153],"dynamics":[102],"determine":[104],"desired":[105],"states,":[108],"while":[109],"incorporating":[110],"Predictive":[112],"Safety":[113],"Filter":[114],"(PSF)":[115],"that":[116],"adjusts":[117],"agent\u2019s":[119],"actions":[120],"online":[121],"prevent":[123],"unsafe":[124],"states.":[125],"This":[126,165],"ensures":[127],"safe":[128],"efficient":[130],"learning,":[131],"stable":[133],"operation.":[135],"We":[136],"validate":[137],"effectiveness":[139],"our":[141],"method":[142],"through":[143],"simulations":[144],"Matlab-Carsim":[147],"platform,":[148],"demonstrating":[149],"significant":[150],"improvements":[151],"in":[152,175],"performance,":[154],"reduced":[155],"tracking":[156],"errors,":[157],"computational":[159],"efficiency":[160],"compared":[161],"traditional":[163],"methods.":[164],"strategy":[166],"promises":[167],"extend":[169],"capabilities":[171],"vehicles":[174],"maneuvers.":[177]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}