{"id":"https://openalex.org/W4221150980","doi":"https://doi.org/10.1109/itsc55140.2022.9922345","title":"How to Learn from Risk: Explicit Risk-Utility Reinforcement Learning for Efficient and Safe Driving Strategies","display_name":"How to Learn from Risk: Explicit Risk-Utility Reinforcement Learning for Efficient and Safe Driving Strategies","publication_year":2022,"publication_date":"2022-10-08","ids":{"openalex":"https://openalex.org/W4221150980","doi":"https://doi.org/10.1109/itsc55140.2022.9922345"},"language":"en","primary_location":{"id":"doi:10.1109/itsc55140.2022.9922345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc55140.2022.9922345","pdf_url":null,"source":{"id":"https://openalex.org/S4363607737","display_name":"2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.08409","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028058149","display_name":"Lukas M. Schmidt","orcid":"https://orcid.org/0000-0003-2182-4263"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Lukas M. Schmidt","raw_affiliation_strings":["Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS,Nuremberg,Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS,Nuremberg,Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074880700","display_name":"Sebastian Rietsch","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Rietsch","raw_affiliation_strings":["Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS,Nuremberg,Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS,Nuremberg,Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005165731","display_name":"Axel Plinge","orcid":"https://orcid.org/0000-0001-7757-2953"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Axel Plinge","raw_affiliation_strings":["Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS,Nuremberg,Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS,Nuremberg,Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014144494","display_name":"Bjoern M. Eskofier","orcid":"https://orcid.org/0000-0002-0417-0336"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bjoern M. Eskofier","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Erlangen,Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Erlangen,Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023277657","display_name":"Christopher Mutschler","orcid":"https://orcid.org/0000-0001-8108-0230"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christopher Mutschler","raw_affiliation_strings":["Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS,Nuremberg,Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS,Nuremberg,Germany","institution_ids":["https://openalex.org/I4210124274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028058149"],"corresponding_institution_ids":["https://openalex.org/I4210124274"],"apc_list":null,"apc_paid":null,"fwci":0.2153,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.27290323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1913","last_page":"1920"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.7039999961853027,"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":0.7039999961853027,"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":0.15219999849796295,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.03759999945759773,"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":0.8933518528938293},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6873703598976135},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6429907083511353},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.5199538469314575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4767678380012512},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41065219044685364},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3882741332054138},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15916121006011963},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.09120669960975647}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8933518528938293},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6873703598976135},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6429907083511353},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.5199538469314575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4767678380012512},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41065219044685364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3882741332054138},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15916121006011963},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.09120669960975647},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/itsc55140.2022.9922345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc55140.2022.9922345","pdf_url":null,"source":{"id":"https://openalex.org/S4363607737","display_name":"2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2203.08409","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.08409","pdf_url":"https://arxiv.org/pdf/2203.08409","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:publica.fraunhofer.de:publica/445676","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/445676","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"},{"id":"doi:10.48550/arxiv.2203.08409","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.08409","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.08409","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.08409","pdf_url":"https://arxiv.org/pdf/2203.08409","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/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320330033","display_name":"ADA Lovelace Center for Analytics, Data, Applications","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4221150980.pdf","grobid_xml":"https://content.openalex.org/works/W4221150980.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2101075098","https://openalex.org/W2145339207","https://openalex.org/W2493343568","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2795064979","https://openalex.org/W2903709398","https://openalex.org/W2904263972","https://openalex.org/W2962790223","https://openalex.org/W2963575966","https://openalex.org/W2989958156","https://openalex.org/W3101981467","https://openalex.org/W3116043511","https://openalex.org/W3117013454","https://openalex.org/W3118172322","https://openalex.org/W3209881631","https://openalex.org/W4308068584","https://openalex.org/W6734194636","https://openalex.org/W6737893269","https://openalex.org/W6751725685","https://openalex.org/W6780587392","https://openalex.org/W6784643869"],"related_works":["https://openalex.org/W1353223","https://openalex.org/W17336456","https://openalex.org/W17081961","https://openalex.org/W8801238","https://openalex.org/W6915741","https://openalex.org/W15411808","https://openalex.org/W18501828","https://openalex.org/W16046748","https://openalex.org/W14942622","https://openalex.org/W13846533"],"abstract_inverted_index":{"Autonomous":[0],"driving":[1,128],"has":[2],"the":[3,18,60,89,108,112],"potential":[4],"to":[5,80],"revolutionize":[6],"mobility":[7],"and":[8,29,44,68,95,111,126,133,143],"is":[9,47,63,77],"hence":[10],"an":[11,103],"active":[12],"area":[13],"of":[14,20,91,114],"research.":[15],"In":[16],"practice,":[17],"behavior":[19,62,90],"autonomous":[21,92],"vehicles":[22,93],"must":[23],"be":[24],"acceptable,":[25],"i.e.,":[26],"efficient,":[27],"safe,":[28],"interpretable.":[30],"While":[31],"vanilla":[32],"reinforcement":[33],"learning":[34,76],"(RL)":[35],"finds":[36,124],"performant":[37],"behavioral":[38],"strategies,":[39],"they":[40,54],"are":[41],"often":[42],"unsafe":[43],"uninterpretable.":[45],"Safety":[46],"introduced":[48],"through":[49],"Safe":[50],"RL":[51],"approaches,":[52],"but":[53],"still":[55,98],"mostly":[56],"remain":[57],"un-interpretable":[58],"as":[59],"learned":[61],"jointly":[64],"optimized":[65],"for":[66,130],"safety":[67],"performance":[69],"without":[70],"modeling":[71],"them":[72],"separately.":[73],"Interpretable":[74],"machine":[75],"rarely":[78],"applied":[79],"RL.":[81],"This":[82],"work":[83],"proposes":[84],"SafeDQN,":[85],"which":[86],"allows":[87],"making":[88],"safe":[94,127],"interpretable":[96,125],"while":[97,116],"being":[99,117],"efficient.":[100],"SafeDQN":[101,123],"offers":[102],"understandable,":[104],"semantic":[105],"trade-off":[106],"between":[107],"expected":[109],"risk":[110,142],"utility":[113],"actions":[115],"algorithmically":[118],"transparent.":[119],"We":[120],"show":[121],"that":[122],"policies":[129],"various":[131],"scenarios":[132],"demonstrate":[134],"how":[135],"state-of-the-art":[136],"saliency":[137],"techniques":[138],"can":[139],"help":[140],"assess":[141],"utility.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2022-04-03T00:00:00"}