{"id":"https://openalex.org/W4285818823","doi":"https://doi.org/10.1109/lra.2022.3192205","title":"Safe Reinforcement Learning Using Black-Box Reachability Analysis","display_name":"Safe Reinforcement Learning Using Black-Box Reachability Analysis","publication_year":2022,"publication_date":"2022-07-19","ids":{"openalex":"https://openalex.org/W4285818823","doi":"https://doi.org/10.1109/lra.2022.3192205"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3192205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3192205","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5046206548","display_name":"Mahmoud Selim","orcid":"https://orcid.org/0000-0002-9499-6480"},"institutions":[{"id":"https://openalex.org/I107720978","display_name":"Ain Shams University","ror":"https://ror.org/00cb9w016","country_code":"EG","type":"education","lineage":["https://openalex.org/I107720978"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Mahmoud Selim","raw_affiliation_strings":["Ain Shams University, Cairo, Egypt"],"affiliations":[{"raw_affiliation_string":"Ain Shams University, Cairo, Egypt","institution_ids":["https://openalex.org/I107720978"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102709386","display_name":"Amr Alanwar","orcid":"https://orcid.org/0000-0003-2941-519X"},"institutions":[{"id":"https://openalex.org/I193619901","display_name":"Constructor University","ror":"https://ror.org/02yrs2n53","country_code":"DE","type":"education","lineage":["https://openalex.org/I193619901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Amr Alanwar","raw_affiliation_strings":["Jacobs University, Bremen, Germany"],"affiliations":[{"raw_affiliation_string":"Jacobs University, Bremen, Germany","institution_ids":["https://openalex.org/I193619901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019247599","display_name":"Shreyas Kousik","orcid":"https://orcid.org/0000-0003-1348-7463"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shreyas Kousik","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069625302","display_name":"Grace Gao","orcid":"https://orcid.org/0000-0002-1807-8637"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grace Gao","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050003000","display_name":"Marco Pavone","orcid":"https://orcid.org/0000-0002-0206-4337"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marco Pavone","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045975901","display_name":"Karl Henrik Johansson","orcid":"https://orcid.org/0000-0001-9940-5929"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Karl H. Johansson","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5046206548"],"corresponding_institution_ids":["https://openalex.org/I107720978"],"apc_list":null,"apc_paid":null,"fwci":3.8611,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.94170033,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"7","issue":"4","first_page":"10665","last_page":"10672"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9958999752998352,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8052483797073364},{"id":"https://openalex.org/keywords/reachability","display_name":"Reachability","score":0.7638533115386963},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7131038904190063},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6988389492034912},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6039979457855225},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.5753706097602844},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49563920497894287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48004257678985596},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.4590938985347748},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.13915351033210754},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10438317060470581}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8052483797073364},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.7638533115386963},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7131038904190063},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6988389492034912},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6039979457855225},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5753706097602844},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49563920497894287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48004257678985596},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.4590938985347748},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.13915351033210754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10438317060470581},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2022.3192205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3192205","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315934","display_name":"Toyota Research Institute","ror":null},{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1424654272","https://openalex.org/W1515851193","https://openalex.org/W1585575029","https://openalex.org/W1845972764","https://openalex.org/W1991579213","https://openalex.org/W1996625075","https://openalex.org/W2101075098","https://openalex.org/W2136074593","https://openalex.org/W2221045814","https://openalex.org/W2300621294","https://openalex.org/W2560882727","https://openalex.org/W2604216058","https://openalex.org/W2750147881","https://openalex.org/W2781726626","https://openalex.org/W2784465508","https://openalex.org/W2804791273","https://openalex.org/W2887154784","https://openalex.org/W2892521964","https://openalex.org/W2911618937","https://openalex.org/W2962954724","https://openalex.org/W2963428623","https://openalex.org/W2963809389","https://openalex.org/W2963821308","https://openalex.org/W2966735560","https://openalex.org/W2967193622","https://openalex.org/W2973229164","https://openalex.org/W2990212897","https://openalex.org/W3008953696","https://openalex.org/W3029901419","https://openalex.org/W3080564557","https://openalex.org/W3081975785","https://openalex.org/W3086849158","https://openalex.org/W3096954237","https://openalex.org/W3112005744","https://openalex.org/W3115737827","https://openalex.org/W3133498163","https://openalex.org/W3135301907","https://openalex.org/W3162902207","https://openalex.org/W3185128647","https://openalex.org/W3215339089","https://openalex.org/W4206058163","https://openalex.org/W4206497039","https://openalex.org/W4287065532","https://openalex.org/W4287829052","https://openalex.org/W4293545785","https://openalex.org/W4297780563","https://openalex.org/W6668095294","https://openalex.org/W6677959772","https://openalex.org/W6682367392","https://openalex.org/W6685043521","https://openalex.org/W6687063787","https://openalex.org/W6734122017","https://openalex.org/W6737893269","https://openalex.org/W6743558609","https://openalex.org/W6747473740","https://openalex.org/W6747790125","https://openalex.org/W6751494529","https://openalex.org/W6751535212","https://openalex.org/W6751725685","https://openalex.org/W6759111761","https://openalex.org/W6774406872","https://openalex.org/W6774521036","https://openalex.org/W6784643869","https://openalex.org/W6785757768","https://openalex.org/W6796910599","https://openalex.org/W6798650984","https://openalex.org/W6798979448","https://openalex.org/W6801971982"],"related_works":["https://openalex.org/W2127267268","https://openalex.org/W2136512912","https://openalex.org/W2067910792","https://openalex.org/W2156446763","https://openalex.org/W2150194458","https://openalex.org/W2143461633","https://openalex.org/W2889071233","https://openalex.org/W4321471459","https://openalex.org/W4221156924","https://openalex.org/W2380814829"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"is":[3],"capable":[4],"of":[5,82,137],"sophisticated":[6],"motion":[7],"planning":[8],"and":[9,29,77,87,98,124],"control":[10],"for":[11,63],"robots":[12,38],"in":[13,127],"uncertain":[14],"environments.":[15],"However,":[16],"state-of-the-art":[17,110],"deep":[18],"RL":[19,112],"approaches":[20],"typically":[21],"lack":[22],"safety":[23,41],"guarantees,":[24],"especially":[25],"when":[26],"the":[27,95,135],"robot":[28,66],"environment":[30],"models":[31],"are":[32],"unknown.":[33],"To":[34],"justify":[35],"widespread":[36],"deployment,":[37],"must":[39],"respect":[40],"constraints":[42],"without":[43],"sacrificing":[44],"performance.":[45],"Thus,":[46],"we":[47],"propose":[48],"a":[49,64,69,89,115,118,120,125],"Black-box":[50],"Reachability-based":[51],"Safety":[52],"Layer":[53],"(BRSL)":[54],"with":[55,129],"three":[56],"main":[57],"components:":[58],"(1)":[59],"data-driven":[60],"reachability":[61],"analysis":[62],"black-box":[65],"model,":[67],"(2)":[68],"trajectory":[70],"rollout":[71],"planner":[72],"that":[73,100],"predicts":[74],"future":[75],"actions":[76],"observations":[78],"using":[79],"an":[80,130],"ensemble":[81],"neural":[83],"networks":[84],"trained":[85],"online,":[86],"(3)":[88],"differentiable":[90],"polytope":[91],"collision":[92],"check":[93],"between":[94],"reachable":[96],"set":[97,132],"obstacles":[99],"enables":[101],"correcting":[102],"unsafe":[103,131],"actions.":[104],"In":[105],"simulation,":[106],"BRSL":[107],"outperforms":[108],"other":[109],"safe":[111],"methods":[113],"on":[114],"Turtlebot":[116],"3,":[117],"quadrotor,":[119],"trajectory-tracking":[121],"point":[122],"mass,":[123],"hexarotor":[126],"wind":[128],"adjacent":[133],"to":[134],"area":[136],"highest":[138],"reward.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}