{"id":"https://openalex.org/W2966735560","doi":"https://doi.org/10.1609/aaai.v33i01.33013387","title":"End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks","display_name":"End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2966735560","doi":"https://doi.org/10.1609/aaai.v33i01.33013387","mag":"2966735560"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33013387","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013387","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4213/4091","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4213/4091","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089532118","display_name":"Richard Cheng","orcid":"https://orcid.org/0000-0001-8301-9169"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Richard Cheng","raw_affiliation_strings":["California Institute of Technology"],"affiliations":[{"raw_affiliation_string":"California Institute of Technology","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043415749","display_name":"G\u00e1bor Orosz","orcid":"https://orcid.org/0000-0002-9000-3736"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G\u00e1bor Orosz","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068600217","display_name":"Richard M. Murray","orcid":"https://orcid.org/0000-0002-5785-7481"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard M. Murray","raw_affiliation_strings":["California Institute of Technology"],"affiliations":[{"raw_affiliation_string":"California Institute of Technology","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002930599","display_name":"Joel W. Burdick","orcid":"https://orcid.org/0000-0002-3091-540X"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joel W. Burdick","raw_affiliation_strings":["California Institute of Technology"],"affiliations":[{"raw_affiliation_string":"California Institute of Technology","institution_ids":["https://openalex.org/I122411786"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089532118"],"corresponding_institution_ids":["https://openalex.org/I122411786"],"apc_list":null,"apc_paid":null,"fwci":122.2044,"has_fulltext":true,"cited_by_count":520,"citation_normalized_percentile":{"value":1.0,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"33","issue":"01","first_page":"3387","last_page":"3395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9519000053405762,"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":0.9519000053405762,"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/T12810","display_name":"Real-time simulation and control systems","score":0.9510999917984009,"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/T12095","display_name":"Vehicle emissions and performance","score":0.9300000071525574,"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":0.8431131839752197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7179959416389465},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.7073547840118408},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6657299995422363},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5776670575141907},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.5140055418014526},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33218222856521606},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32812798023223877},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.2872878313064575}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8431131839752197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7179959416389465},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.7073547840118408},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6657299995422363},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5776670575141907},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5140055418014526},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33218222856521606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32812798023223877},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2872878313064575},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v33i01.33013387","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013387","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4213/4091","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33013387","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013387","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4213/4091","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5199999809265137,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2966735560.pdf","grobid_xml":"https://content.openalex.org/works/W2966735560.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1580216809","https://openalex.org/W1771410628","https://openalex.org/W1845972764","https://openalex.org/W1963790880","https://openalex.org/W1999874108","https://openalex.org/W2098432798","https://openalex.org/W2125612430","https://openalex.org/W2130178506","https://openalex.org/W2134122536","https://openalex.org/W2134491302","https://openalex.org/W2158323882","https://openalex.org/W2164479831","https://openalex.org/W2342662072","https://openalex.org/W2586823359","https://openalex.org/W2618318883","https://openalex.org/W2735010720","https://openalex.org/W2785364612","https://openalex.org/W2788084076","https://openalex.org/W2791704483","https://openalex.org/W2886262373","https://openalex.org/W2887709062","https://openalex.org/W2963148914","https://openalex.org/W2963525569","https://openalex.org/W2963575966","https://openalex.org/W2963864421","https://openalex.org/W3098925401","https://openalex.org/W4211049957","https://openalex.org/W4243363090","https://openalex.org/W4293545785","https://openalex.org/W4294555834","https://openalex.org/W4294562617","https://openalex.org/W4297780563","https://openalex.org/W4302570325","https://openalex.org/W4321151576","https://openalex.org/W6629804754","https://openalex.org/W6638018090","https://openalex.org/W6674995601","https://openalex.org/W6684037837","https://openalex.org/W6684205842"],"related_works":["https://openalex.org/W962423920","https://openalex.org/W2387968248","https://openalex.org/W2350715914","https://openalex.org/W2120821724","https://openalex.org/W2379529020","https://openalex.org/W2101175215","https://openalex.org/W2893549521","https://openalex.org/W2330311678","https://openalex.org/W2352322616","https://openalex.org/W2598699656"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"algorithms":[3,89,187],"have":[4],"found":[5],"limited":[6],"success":[7,86],"beyond":[8],"simulated":[9],"applications,":[10],"and":[11,65,101,123,147,164,172,188],"one":[12],"main":[13],"reason":[14],"is":[15],"the":[16,22,70,85,95,103,108,120,138,143,192],"absence":[17],"of":[18,69,87,110,142,160],"safety":[19,78,100,133,190],"guarantees":[20,132],"during":[21,79,137,191],"learning":[23,68,104,139,183,194],"process.":[24,195],"Real":[25],"world":[26],"systems":[27],"would":[28],"realistically":[29],"fail":[30],"or":[31],"break":[32],"before":[33],"an":[34,161],"optimal":[35],"controller":[36,47,55,128],"can":[37],"be":[38],"learned.":[39],"To":[40],"address":[41],"this":[42],"issue,":[43],"we":[44],"propose":[45],"a":[46,52],"architecture":[48],"that":[49,174],"combines":[50],"(1)":[51,158],"model-free":[53],"RL-based":[54],"with":[56,134,168],"(2)":[57,165],"model-based":[58],"controllers":[59,97],"utilizing":[60],"control":[61,159],"barrier":[62],"functions":[63],"(CBFs)":[64],"(3)":[66],"online":[67],"unknown":[71],"system":[72,121],"dynamics,":[73],"in":[74,182],"order":[75],"to":[76,90,118],"ensure":[77],"learning.":[80],"Our":[81,126],"general":[82],"framework":[83],"leverages":[84],"RL":[88,144],"learn":[91],"high-performance":[92],"controllers,":[93],"while":[94],"CBF-based":[96],"both":[98],"guarantee":[99],"guide":[102],"process":[105],"by":[106],"constraining":[107],"set":[109],"explorable":[111],"polices.":[112],"We":[113,153],"utilize":[114],"Gaussian":[115],"Processes":[116],"(GPs)":[117],"model":[119],"dynamics":[122],"its":[124],"uncertainties.":[125],"novel":[127],"synthesis":[129],"algorithm,":[130],"RL-CBF,":[131],"high":[135],"probability":[136],"process,":[140],"regardless":[141],"algorithm":[145,156,176],"used,":[146],"demonstrates":[148],"greater":[149,179],"policy":[150],"exploration":[151],"efficiency.":[152],"test":[154],"our":[155,175],"on":[157],"inverted":[162],"pendulum":[163],"autonomous":[166],"carfollowing":[167],"wireless":[169],"vehicle-to-vehicle":[170],"communication,":[171],"show":[173],"attains":[177],"much":[178],"sample":[180],"efficiency":[181],"than":[184],"other":[185],"state-of-the-art":[186],"maintains":[189],"entire":[193]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":67},{"year":2024,"cited_by_count":67},{"year":2023,"cited_by_count":95},{"year":2022,"cited_by_count":81},{"year":2021,"cited_by_count":114},{"year":2020,"cited_by_count":71},{"year":2019,"cited_by_count":12}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}