{"id":"https://openalex.org/W2967081385","doi":"https://doi.org/10.1109/icra.2019.8794189","title":"Early Failure Detection of Deep End-to-End Control Policy by Reinforcement Learning","display_name":"Early Failure Detection of Deep End-to-End Control Policy by Reinforcement Learning","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2967081385","doi":"https://doi.org/10.1109/icra.2019.8794189","mag":"2967081385"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2019.8794189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794189","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":"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/A5046628126","display_name":"Keuntaek Lee","orcid":"https://orcid.org/0000-0001-5955-5965"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Keuntaek Lee","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017764509","display_name":"Kamil Saigol","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726763","display_name":"Lyft (United States)","ror":"https://ror.org/01nhtcw46","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726763"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kamil Saigol","raw_affiliation_strings":["Lyft Inc, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Lyft Inc, San Francisco, CA, USA","institution_ids":["https://openalex.org/I4401726763"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044505993","display_name":"Evangelos A. Theodorou","orcid":"https://orcid.org/0000-0002-0834-5738"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evangelos A. Theodorou","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046628126"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.7001,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77930819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"8543","last_page":"8549"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9962000250816345,"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":0.9962000250816345,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9947999715805054,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9864000082015991,"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/observability","display_name":"Observability","score":0.8520359992980957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7090173363685608},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.683763325214386},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6509321928024292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6301369667053223},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.45372557640075684},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4434620141983032},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.43738389015197754},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.42950600385665894},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3596900403499603},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11828795075416565}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.8520359992980957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7090173363685608},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.683763325214386},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6509321928024292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6301369667053223},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.45372557640075684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4434620141983032},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.43738389015197754},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.42950600385665894},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3596900403499603},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11828795075416565},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2019.8794189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794189","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W582134693","https://openalex.org/W1522301498","https://openalex.org/W1567512734","https://openalex.org/W1686810756","https://openalex.org/W1723619723","https://openalex.org/W1904365287","https://openalex.org/W1931877416","https://openalex.org/W2109944946","https://openalex.org/W2132083787","https://openalex.org/W2164411961","https://openalex.org/W2600383743","https://openalex.org/W2611430843","https://openalex.org/W2752013927","https://openalex.org/W2757751962","https://openalex.org/W2806163172","https://openalex.org/W2962871846","https://openalex.org/W2962957031","https://openalex.org/W2963392613","https://openalex.org/W2964059111","https://openalex.org/W2964121744","https://openalex.org/W4300172425","https://openalex.org/W6617145748","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6640174482","https://openalex.org/W6676444349","https://openalex.org/W6684488266","https://openalex.org/W6743806954","https://openalex.org/W6745714403","https://openalex.org/W6752742761"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2765830098","https://openalex.org/W2967463586","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W4206221578","https://openalex.org/W3029572990","https://openalex.org/W2615757685"],"abstract_inverted_index":{"We":[0,101,123],"propose":[1],"the":[2,21,37,61,65,81,91,96],"use":[3],"of":[4,23,64,78,93],"Bayesian":[5,120],"networks,":[6],"which":[7,30],"provide":[8],"both":[9],"a":[10,31,52,58,76],"mean":[11],"value":[12],"and":[13,45,107,113],"an":[14],"uncertainty":[15,63,97,131],"estimate":[16],"as":[17,55,57,75,137,139],"output,":[18],"to":[19,49,80,130],"enhance":[20],"safety":[22],"learned":[24,66],"control":[25,53,79],"policies":[26],"under":[27],"circumstances":[28],"in":[29],"test-time":[32],"input":[33],"differs":[34],"significantly":[35],"from":[36,133,140],"training":[38],"set.":[39],"Our":[40],"algorithm":[41],"combines":[42],"reinforcement":[43],"learning":[44,48],"end-to-end":[46],"imitation":[47],"simultaneously":[50],"learn":[51],"policy":[54],"well":[56,138],"threshold":[59,98],"over":[60],"predictive":[62,83],"model,":[67],"with":[68],"no":[69],"hand-tuning":[70],"required.":[71],"Corrective":[72],"action,":[73],"such":[74],"return":[77],"model":[82],"controller":[84],"or":[85],"human":[86],"expert,":[87],"is":[88,99,128],"taken":[89],"before":[90],"failure":[92],"tasks,":[94],"when":[95],"exceeded.":[100],"validate":[102],"our":[103,126],"method":[104,127],"on":[105],"fully-observable":[106],"vision-based":[108],"partially-observable":[109],"systems":[110],"using":[111,117],"cart-pole":[112],"autonomous":[114],"driving":[115],"simulations":[116],"deep":[118],"convolutional":[119],"neural":[121],"networks.":[122],"demonstrate":[124],"that":[125],"robust":[129],"resulting":[132],"varying":[134],"system":[135],"dynamics":[136],"partial":[141],"state":[142],"observability.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}