{"id":"https://openalex.org/W2909414402","doi":"https://doi.org/10.1109/iros.2018.8593420","title":"Safe Reinforcement Learning on Autonomous Vehicles","display_name":"Safe Reinforcement Learning on Autonomous Vehicles","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2909414402","doi":"https://doi.org/10.1109/iros.2018.8593420","mag":"2909414402"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2018.8593420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8593420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"preprint","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/A5063634505","display_name":"David Isele","orcid":"https://orcid.org/0000-0001-9749-6951"},"institutions":[{"id":"https://openalex.org/I4210145184","display_name":"Honda (United States)","ror":"https://ror.org/04vdmc602","country_code":"US","type":"company","lineage":["https://openalex.org/I1283473643","https://openalex.org/I4210145184"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Isele","raw_affiliation_strings":["Honda Research Institute, USA"],"affiliations":[{"raw_affiliation_string":"Honda Research Institute, USA","institution_ids":["https://openalex.org/I4210145184"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050227531","display_name":"Alireza Nakhaei","orcid":"https://orcid.org/0000-0001-9318-9372"},"institutions":[{"id":"https://openalex.org/I4210145184","display_name":"Honda (United States)","ror":"https://ror.org/04vdmc602","country_code":"US","type":"company","lineage":["https://openalex.org/I1283473643","https://openalex.org/I4210145184"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alireza Nakhaei","raw_affiliation_strings":["Honda Research Institute, USA"],"affiliations":[{"raw_affiliation_string":"Honda Research Institute, USA","institution_ids":["https://openalex.org/I4210145184"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112249344","display_name":"Kikuo Fujimura","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145184","display_name":"Honda (United States)","ror":"https://ror.org/04vdmc602","country_code":"US","type":"company","lineage":["https://openalex.org/I1283473643","https://openalex.org/I4210145184"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kikuo Fujimura","raw_affiliation_strings":["Honda Research Institute, USA"],"affiliations":[{"raw_affiliation_string":"Honda Research Institute, USA","institution_ids":["https://openalex.org/I4210145184"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063634505"],"corresponding_institution_ids":["https://openalex.org/I4210145184"],"apc_list":null,"apc_paid":null,"fwci":3.1417,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.91845218,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9987000226974487,"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":0.9876999855041504,"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":0.8689353466033936},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7207467555999756},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.6571996808052063},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5482063293457031},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5471758246421814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.510394275188446},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.47245457768440247},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3767912983894348},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17810985445976257},{"id":"https://openalex.org/keywords/transport-engineering","display_name":"Transport engineering","score":0.09420132637023926}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8689353466033936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7207467555999756},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.6571996808052063},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5482063293457031},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5471758246421814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.510394275188446},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.47245457768440247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3767912983894348},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17810985445976257},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.09420132637023926},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2018.8593420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8593420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W15411808","https://openalex.org/W134786152","https://openalex.org/W1520813427","https://openalex.org/W1542941925","https://openalex.org/W1845972764","https://openalex.org/W1869778509","https://openalex.org/W1897740768","https://openalex.org/W1965455100","https://openalex.org/W1987108535","https://openalex.org/W2022189869","https://openalex.org/W2054161738","https://openalex.org/W2088413745","https://openalex.org/W2097545165","https://openalex.org/W2101075098","https://openalex.org/W2105934661","https://openalex.org/W2120846115","https://openalex.org/W2153323685","https://openalex.org/W2243721295","https://openalex.org/W2294439372","https://openalex.org/W2296360731","https://openalex.org/W2334470880","https://openalex.org/W2344396459","https://openalex.org/W2496718517","https://openalex.org/W2555811267","https://openalex.org/W2571817908","https://openalex.org/W2580495915","https://openalex.org/W2611622123","https://openalex.org/W2754105315","https://openalex.org/W2783780731","https://openalex.org/W2801197440","https://openalex.org/W2808549908","https://openalex.org/W2814753043","https://openalex.org/W2827360073","https://openalex.org/W2875946885","https://openalex.org/W2888989468","https://openalex.org/W2926935974","https://openalex.org/W2931490213","https://openalex.org/W2931813256","https://openalex.org/W2933551834","https://openalex.org/W2952720101","https://openalex.org/W2956142922","https://openalex.org/W2956281179","https://openalex.org/W2956363187","https://openalex.org/W2957117296","https://openalex.org/W2957219263","https://openalex.org/W2957547836","https://openalex.org/W2957644857","https://openalex.org/W2957824261","https://openalex.org/W2958319445","https://openalex.org/W2958962614","https://openalex.org/W2959737159","https://openalex.org/W2959807635","https://openalex.org/W2960009422","https://openalex.org/W2960762614","https://openalex.org/W2961839807","https://openalex.org/W2962399339","https://openalex.org/W2962476921","https://openalex.org/W2962481867","https://openalex.org/W2962513890","https://openalex.org/W2963575966","https://openalex.org/W2963604565","https://openalex.org/W2963625099","https://openalex.org/W2963804019","https://openalex.org/W2964048876","https://openalex.org/W2965287542","https://openalex.org/W2966239323","https://openalex.org/W2967661800","https://openalex.org/W2967733758","https://openalex.org/W2968486209","https://openalex.org/W2968827403","https://openalex.org/W3106238320","https://openalex.org/W3150280064","https://openalex.org/W3152138688","https://openalex.org/W4244577181","https://openalex.org/W4297780563","https://openalex.org/W4301501993","https://openalex.org/W6600644339","https://openalex.org/W6631209646","https://openalex.org/W6639086533","https://openalex.org/W6639175102","https://openalex.org/W6678168664","https://openalex.org/W6731804457"],"related_works":["https://openalex.org/W4296209631","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2561617217","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2348909947","https://openalex.org/W3049728571"],"abstract_inverted_index":{"There":[0],"have":[1],"been":[2],"numerous":[3],"advances":[4],"in":[5,23,30],"reinforcement":[6,32],"learning,":[7],"but":[8,41],"the":[9,14,18,48],"typically":[10],"unconstrained":[11],"exploration":[12],"of":[13,20,52],"learning":[15,33],"process":[16],"prevents":[17],"adoption":[19],"these":[21,42],"methods":[22],"many":[24],"safety":[25],"critical":[26],"applications.":[27],"Recent":[28],"work":[29],"safe":[31],"uses":[34],"idealized":[35],"models":[36,43],"to":[37,66,76],"achieve":[38],"their":[39],"guarantees,":[40],"do":[44],"not":[45],"easily":[46],"accommodate":[47],"stochasticity":[49],"or":[50],"high-dimensionality":[51],"real":[53],"world":[54],"systems.":[55],"We":[56],"investigate":[57],"how":[58,71],"prediction":[59],"provides":[60],"a":[61],"general":[62],"and":[63,69],"intuitive":[64],"framework":[65],"constraint":[67],"exploration,":[68],"show":[70],"it":[72],"can":[73],"be":[74],"used":[75],"safely":[77],"learn":[78],"intersection":[79],"handling":[80],"behaviors":[81],"on":[82],"an":[83],"autonomous":[84],"vehicle.":[85]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}