{"id":"https://openalex.org/W2970857152","doi":"https://doi.org/10.1109/ivs.2019.8813791","title":"Addressing Inherent Uncertainty: Risk-Sensitive Behavior Generation for Automated Driving using Distributional Reinforcement Learning","display_name":"Addressing Inherent Uncertainty: Risk-Sensitive Behavior Generation for Automated Driving using Distributional Reinforcement Learning","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2970857152","doi":"https://doi.org/10.1109/ivs.2019.8813791","mag":"2970857152"},"language":"en","primary_location":{"id":"doi:10.1109/ivs.2019.8813791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ivs.2019.8813791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.03119","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Julian Bernhard","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134795","display_name":"Fortiss","ror":"https://ror.org/042x1tp92","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210134795"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julian Bernhard","raw_affiliation_strings":["Fortiss GmbH, An-Institut Technische Universit\u00e4t M\u00fcnchen, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fortiss GmbH, An-Institut Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I4210134795","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Stefan Pollok","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134795","display_name":"Fortiss","ror":"https://ror.org/042x1tp92","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210134795"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Pollok","raw_affiliation_strings":["Fortiss GmbH, An-Institut Technische Universit\u00e4t M\u00fcnchen, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fortiss GmbH, An-Institut Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I4210134795","https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":null,"display_name":"Alois Knoll","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alois Knoll","raw_affiliation_strings":["Chair of Robotics, Artificial Intelligence and Real-time Systems, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Robotics, Artificial Intelligence and Real-time Systems, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1484,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.80498786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2148","last_page":"2155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9962000250816345,"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":0.9962000250816345,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955999851226807,"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/T10524","display_name":"Traffic control and management","score":0.9941999912261963,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6794999837875366},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.6700999736785889},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5867999792098999},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.48820000886917114},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.35120001435279846},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.34119999408721924}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6794999837875366},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.6700999736785889},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5867999792098999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5630999803543091},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.48820000886917114},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43369999527931213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4291999936103821},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.39259999990463257},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.34119999408721924},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.29429998993873596},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ivs.2019.8813791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ivs.2019.8813791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.03119","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.03119","pdf_url":"https://arxiv.org/pdf/2102.03119","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":"pmh:oai:mediatum.ub.tum.de:node/1485138","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1485138","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.03119","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.03119","pdf_url":"https://arxiv.org/pdf/2102.03119","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W938188971","https://openalex.org/W1605929701","https://openalex.org/W1845972764","https://openalex.org/W2001009060","https://openalex.org/W2053984877","https://openalex.org/W2145339207","https://openalex.org/W2411577903","https://openalex.org/W2514762535","https://openalex.org/W2530849036","https://openalex.org/W2599174273","https://openalex.org/W2734346390","https://openalex.org/W2746553466","https://openalex.org/W2884674451","https://openalex.org/W2890375627","https://openalex.org/W2896856707","https://openalex.org/W2904177032","https://openalex.org/W2904263972","https://openalex.org/W2904937669","https://openalex.org/W2905427618","https://openalex.org/W2949319840","https://openalex.org/W2949556825","https://openalex.org/W2963625099","https://openalex.org/W2963804019","https://openalex.org/W6683300800","https://openalex.org/W6687681856","https://openalex.org/W6744927671","https://openalex.org/W6745500190","https://openalex.org/W6748571143","https://openalex.org/W6751629939","https://openalex.org/W6760985608"],"related_works":[],"abstract_inverted_index":{"For":[0],"highly":[1],"automated":[2],"driving":[3,28,163],"above":[4],"SAE":[5],"level":[6],"3,":[7],"behavior":[8,57,91],"generation":[9,58,92],"algorithms":[10,59],"must":[11],"reliably":[12],"consider":[13],"the":[14,18,24,37,54,119,132,138,172],"inherent":[15],"uncertainties":[16,31],"of":[17,26,64,174],"traffic":[19],"environment,":[20],"e.g.":[21,45,51],"arising":[22],"from":[23],"variety":[25],"human":[27],"styles.":[29],"Such":[30],"can":[32],"generate":[33],"ambiguous":[34,74],"decisions,":[35],"requiring":[36],"algorithm":[38],"to":[39,137],"appropriately":[40],"balance":[41],"low-probability":[42],"hazardous":[43],"events,":[44,50],"collisions,":[46],"and":[47,152],"high-probability":[48],"beneficial":[49],"quickly":[52],"crossing":[53,145],"intersection.":[55],"State-of-the-art":[56],"lack":[60],"a":[61,69,86],"distributional":[62],"treatment":[63],"decision":[65],"outcome.":[66],"This":[67],"impedes":[68],"proper":[70],"risk":[71,99,128,150],"evaluation":[72],"in":[73,108],"situations,":[75],"often":[76],"encouraging":[77],"either":[78],"unsafe":[79],"or":[80],"conservative":[81],"behavior.":[82],"Thus,":[83],"we":[84,102,147],"propose":[85],"two-step":[87],"approach":[88,156,166],"for":[89,177],"risk-sensitive":[90,121,175],"combining":[93],"offline":[94],"distribution":[95],"learning":[96],"with":[97,112],"online":[98],"assessment.":[100],"Specifically,":[101],"first":[103],"learn":[104],"an":[105,109,161],"optimal":[106,120],"policy":[107],"uncertain":[110],"environment":[111],"Deep":[113],"Distributional":[114],"Reinforcement":[115],"Learning.":[116],"During":[117],"execution,":[118],"action":[122],"is":[123],"selected":[124],"by":[125],"applying":[126],"established":[127],"criteria,":[129],"such":[130],"as":[131],"Conditional":[133],"Value":[134],"at":[135],"Risk,":[136],"learned":[139],"state-action":[140],"return":[141],"distributions.":[142],"In":[143],"intersection":[144],"scenarios,":[146],"evaluate":[148],"different":[149],"criteria":[151],"demonstrate":[153],"that":[154],"our":[155],"increases":[157],"safety,":[158],"while":[159],"maintaining":[160],"active":[162],"style.":[164],"Our":[165],"shall":[167],"encourage":[168],"further":[169],"studies":[170],"about":[171],"benefits":[173],"approaches":[176],"self-driving":[178],"vehicles.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-25T08:15:23.626066","created_date":"2019-09-05T00:00:00"}