{"id":"https://openalex.org/W2898045695","doi":"https://doi.org/10.1109/icra.2019.8793611","title":"Safe Reinforcement Learning With Model Uncertainty Estimates","display_name":"Safe Reinforcement Learning With Model Uncertainty Estimates","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2898045695","doi":"https://doi.org/10.1109/icra.2019.8793611","mag":"2898045695"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2019.8793611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8793611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1810.08700","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017253556","display_name":"Bj\u00f6rn L\u00fctjens","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bjorn Lutjens","raw_affiliation_strings":["Aerospace Controls Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Controls Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064513857","display_name":"Michael Everett","orcid":"https://orcid.org/0000-0001-9377-6745"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Everett","raw_affiliation_strings":["Aerospace Controls Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Controls Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011665886","display_name":"Jonathan P. How","orcid":"https://orcid.org/0000-0001-8576-1930"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan P. How","raw_affiliation_strings":["Aerospace Controls Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Controls Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8662","last_page":"8668"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9994999766349792,"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":0.9994999766349792,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.998199999332428,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7767935991287231},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7153937220573425},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.6627781391143799},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.6495345234870911},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.6472176909446716},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.6427128314971924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6271215677261353},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.560695230960846},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.558483362197876},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.47198396921157837},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.43632322549819946},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4128112196922302},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.29480308294296265},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12636995315551758},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11275750398635864}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7767935991287231},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7153937220573425},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.6627781391143799},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.6495345234870911},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.6472176909446716},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.6427128314971924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6271215677261353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.560695230960846},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.558483362197876},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.47198396921157837},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.43632322549819946},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4128112196922302},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.29480308294296265},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12636995315551758},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11275750398635864},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icra.2019.8793611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8793611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1810.08700","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.08700","pdf_url":"https://arxiv.org/pdf/1810.08700","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2898045695","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1810.08700.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:dspace.mit.edu:1721.1/125488","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/125488","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv","raw_type":"http://purl.org/eprint/type/ConferencePaper"},{"id":"doi:10.48550/arxiv.1810.08700","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1810.08700","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1810.08700","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.08700","pdf_url":"https://arxiv.org/pdf/1810.08700","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307103","display_name":"Ford Motor Company","ror":"https://ror.org/00g2tkw06"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2898045695.pdf","grobid_xml":"https://content.openalex.org/works/W2898045695.grobid-xml"},"referenced_works_count":69,"referenced_works":["https://openalex.org/W192919555","https://openalex.org/W1567512734","https://openalex.org/W1585575029","https://openalex.org/W1590642498","https://openalex.org/W1845972764","https://openalex.org/W1995945562","https://openalex.org/W2039522160","https://openalex.org/W2056257343","https://openalex.org/W2062561016","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2108677974","https://openalex.org/W2164411961","https://openalex.org/W2164479831","https://openalex.org/W2165489953","https://openalex.org/W2167052694","https://openalex.org/W2169206416","https://openalex.org/W2233908551","https://openalex.org/W2294678926","https://openalex.org/W2302053044","https://openalex.org/W2424778531","https://openalex.org/W2462906003","https://openalex.org/W2531327146","https://openalex.org/W2556372419","https://openalex.org/W2600383743","https://openalex.org/W2604216058","https://openalex.org/W2606757878","https://openalex.org/W2615735215","https://openalex.org/W2767449908","https://openalex.org/W2799977193","https://openalex.org/W2800978878","https://openalex.org/W2807662017","https://openalex.org/W2887927966","https://openalex.org/W2950751653","https://openalex.org/W2951266961","https://openalex.org/W2963238274","https://openalex.org/W2963472564","https://openalex.org/W2963590277","https://openalex.org/W2963809389","https://openalex.org/W2963938771","https://openalex.org/W2964010366","https://openalex.org/W2964016190","https://openalex.org/W2964059111","https://openalex.org/W2964319688","https://openalex.org/W3106889297","https://openalex.org/W3125893104","https://openalex.org/W6617021176","https://openalex.org/W6617145748","https://openalex.org/W6674330103","https://openalex.org/W6676315081","https://openalex.org/W6684037837","https://openalex.org/W6695011786","https://openalex.org/W6697126365","https://openalex.org/W6697490744","https://openalex.org/W6718836005","https://openalex.org/W6727645556","https://openalex.org/W6728622933","https://openalex.org/W6730042731","https://openalex.org/W6730269975","https://openalex.org/W6733118196","https://openalex.org/W6735443497","https://openalex.org/W6736680870","https://openalex.org/W6737757103","https://openalex.org/W6745560713","https://openalex.org/W6745640914","https://openalex.org/W6748381273","https://openalex.org/W6753624969","https://openalex.org/W6764214684","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2964059111","https://openalex.org/W2145339207","https://openalex.org/W3198148650","https://openalex.org/W2893463703","https://openalex.org/W2979906247","https://openalex.org/W3169290870","https://openalex.org/W2904875922","https://openalex.org/W2970859221","https://openalex.org/W2945100890","https://openalex.org/W3208983194","https://openalex.org/W3012980652","https://openalex.org/W3033673001","https://openalex.org/W3010624034","https://openalex.org/W3037788110","https://openalex.org/W3130238021","https://openalex.org/W2992671401","https://openalex.org/W3162470651","https://openalex.org/W3082923719","https://openalex.org/W2884412095","https://openalex.org/W3188049289"],"abstract_inverted_index":{"Many":[0],"current":[1],"autonomous":[2],"systems":[3],"are":[4,45,83,104],"being":[5],"designed":[6],"with":[7],"a":[8,107,121],"strong":[9],"reliance":[10],"on":[11,28],"black":[12],"box":[13],"predictions":[14,27,43],"from":[15],"deep":[16],"neural":[17,81],"networks":[18,82],"(DNNs).":[19],"However,":[20],"DNNs":[21],"tend":[22],"to":[23,47,69,86,94,112,146,150],"be":[24,67,147],"overconfident":[25],"in":[26,106,144],"unseen":[29,71,138],"data":[30],"and":[31,92,98,132,153],"can":[32,66],"give":[33,95],"unpredictable":[34],"results":[35],"for":[36,53],"far-from-distribution":[37],"test":[38],"data.":[39],"The":[40,102,118,140],"importance":[41],"of":[42,63],"that":[44,125,136],"robust":[46,149],"this":[48],"distributional":[49],"shift":[50],"is":[51,120,142],"evident":[52],"safety-critical":[54],"applications,":[55],"such":[56,78],"as":[57,79],"collision":[58,122],"avoidance":[59,123],"around":[60,116],"pedestrians.":[61,117],"Measures":[62],"model":[64],"uncertainty":[65,100],"used":[68],"identify":[70],"data,":[72],"but":[73],"the":[74],"state-of-the-art":[75],"extraction":[76],"methods":[77,103],"Bayesian":[80],"mostly":[84],"intractable":[85],"compute.":[87],"This":[88],"paper":[89],"uses":[90],"MC-Dropout":[91],"Bootstrapping":[93],"computationally":[96],"tractable":[97],"parallelizable":[99],"estimates.":[101],"embedded":[105],"Safe":[108],"Reinforcement":[109],"Learning":[110],"framework":[111],"form":[113],"uncertainty-aware":[114],"navigation":[115],"result":[119],"policy":[124,141],"knows":[126],"what":[127],"it":[128],"does":[129],"not":[130],"know":[131],"cautiously":[133],"avoids":[134],"pedestrians":[135],"exhibit":[137],"behavior.":[139],"demonstrated":[143],"simulation":[145],"more":[148],"novel":[151],"observations":[152],"take":[154],"safer":[155],"actions":[156],"than":[157],"an":[158],"uncertainty-unaware":[159],"baseline.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}