{"id":"https://openalex.org/W4388737140","doi":"https://doi.org/10.1109/iecon51785.2023.10312462","title":"Risk-Aware Reward Shaping of Reinforcement Learning Agents for Autonomous Driving","display_name":"Risk-Aware Reward Shaping of Reinforcement Learning Agents for Autonomous Driving","publication_year":2023,"publication_date":"2023-10-16","ids":{"openalex":"https://openalex.org/W4388737140","doi":"https://doi.org/10.1109/iecon51785.2023.10312462"},"language":"en","primary_location":{"id":"doi:10.1109/iecon51785.2023.10312462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon51785.2023.10312462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society","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/A5112932536","display_name":"Lin-Chi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lin-Chi Wu","raw_affiliation_strings":["Eindhoven University of Technology,Department of Electrical Engineering,Netherlands","Department of Electrical Engineering, Eindhoven University of Technology, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology,Department of Electrical Engineering,Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Department of Electrical Engineering, Eindhoven University of Technology, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101743605","display_name":"Zengjie Zhang","orcid":"https://orcid.org/0000-0003-1875-1032"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Zengjie Zhang","raw_affiliation_strings":["Eindhoven University of Technology,Department of Electrical Engineering,Netherlands","Department of Electrical Engineering, Eindhoven University of Technology, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology,Department of Electrical Engineering,Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Department of Electrical Engineering, Eindhoven University of Technology, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025184822","display_name":"Sofie Haesaert","orcid":"https://orcid.org/0000-0003-4749-4688"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Sofie Haesaert","raw_affiliation_strings":["Eindhoven University of Technology,Department of Electrical Engineering,Netherlands","Department of Electrical Engineering, Eindhoven University of Technology, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology,Department of Electrical Engineering,Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Department of Electrical Engineering, Eindhoven University of Technology, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028318732","display_name":"Zhiqiang Ma","orcid":"https://orcid.org/0000-0002-6791-1162"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Ma","raw_affiliation_strings":["School of Astronautics, Northwestern Polytechnical University,Research Center for Intelligent Robotics,Xi'an,China,710072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Astronautics, Northwestern Polytechnical University,Research Center for Intelligent Robotics,Xi'an,China,710072","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100778346","display_name":"Zhiyong Sun","orcid":"https://orcid.org/0000-0002-4700-1479"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Zhiyong Sun","raw_affiliation_strings":["Eindhoven University of Technology,Department of Electrical Engineering,Netherlands","Department of Electrical Engineering, Eindhoven University of Technology, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology,Department of Electrical Engineering,Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Department of Electrical Engineering, Eindhoven University of Technology, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8832,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.72871786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9986000061035156,"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":0.9882000088691711,"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":0.9138995409011841},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.785373866558075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6538755893707275},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4961920380592346},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.4820621609687805},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43505120277404785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38495978713035583},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.3538970947265625},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19584208726882935},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.11111581325531006}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9138995409011841},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.785373866558075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6538755893707275},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4961920380592346},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.4820621609687805},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43505120277404785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38495978713035583},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3538970947265625},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19584208726882935},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.11111581325531006},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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":3,"locations":[{"id":"doi:10.1109/iecon51785.2023.10312462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon51785.2023.10312462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/e3e57e28-b350-49d8-827d-4040c67ee08f","is_oa":false,"landing_page_url":"https://www.scopus.com/pages/publications/85179509126","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wu, L-C, Zhang, Z, Haesaert, S, Ma, Z & Sun, Z 2023, Risk-Aware Reward Shaping of Reinforcement Learning Agents for Autonomous Driving. in IECON 2023 - 49th Annual Conference of the IEEE Industrial Electronics Society., 10312462, Institute of Electrical and Electronics Engineers, 49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023, Singapore, Singapore, 16/10/23. https://doi.org/10.1109/IECON51785.2023.10312462","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.tue.nl:publications/e3e57e28-b350-49d8-827d-4040c67ee08f","is_oa":false,"landing_page_url":"https://research.tue.nl/en/publications/e3e57e28-b350-49d8-827d-4040c67ee08f","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wu, L-C, Zhang, Z, Haesaert, S, Ma, Z & Sun, Z 2023, Risk-Aware Reward Shaping of Reinforcement Learning Agents for Autonomous Driving. in IECON 2023 - 49th Annual Conference of the IEEE Industrial Electronics Society., 10312462, Institute of Electrical and Electronics Engineers, 49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023, Singapore, Singapore, 16/10/23. https://doi.org/10.1109/IECON51785.2023.10312462","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2306644740","https://openalex.org/W2343568200","https://openalex.org/W2783583279","https://openalex.org/W2911281373","https://openalex.org/W2948153973","https://openalex.org/W2963679616","https://openalex.org/W2982526735","https://openalex.org/W2999862950","https://openalex.org/W3022270612","https://openalex.org/W3089594962","https://openalex.org/W3090027660","https://openalex.org/W3118868204","https://openalex.org/W3122875934","https://openalex.org/W3127561923","https://openalex.org/W3168217419","https://openalex.org/W3201032916","https://openalex.org/W3204523122","https://openalex.org/W3207654079","https://openalex.org/W4251852706","https://openalex.org/W4283379771","https://openalex.org/W4283725923","https://openalex.org/W4295993375","https://openalex.org/W4308119828","https://openalex.org/W4312721444","https://openalex.org/W4361011164","https://openalex.org/W4388737140","https://openalex.org/W6796289692"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2768698792","https://openalex.org/W4206233823","https://openalex.org/W2494202692"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"is":[3,38,43,150],"an":[4,14,34],"effective":[5],"approach":[6],"to":[7,40,45,76,81,152],"motion":[8],"planning":[9],"in":[10,91,108,127],"autonomous":[11,92,106],"driving,":[12],"where":[13],"optimal":[15],"driving":[16,55,65,107,122],"policy":[17,147],"can":[18],"be":[19,153],"automatically":[20],"learned":[21],"using":[22],"the":[23,27,30,61,68,83,96,101,131,154],"interaction":[24],"data":[25],"with":[26,160],"environment.":[28],"Nevertheless,":[29],"reward":[31,79,114,135,162],"function":[32],"for":[33,104,137],"RL":[35,89,139,156],"agent,":[36],"which":[37],"significant":[39],"its":[41],"performance,":[42],"challenging":[44],"determine.":[46],"The":[47],"conventional":[48],"work":[49],"mainly":[50],"focuses":[51],"on":[52,95],"rewarding":[53],"safe":[54],"states":[56],"but":[57],"does":[58],"not":[59],"incorporate":[60],"awareness":[62],"of":[63,67,88,133],"risky":[64,121],"behaviors":[66],"vehicles.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73,110,142],"investigate":[74],"how":[75],"use":[77],"risk-aware":[78,134,161],"shaping":[80,136],"leverage":[82],"training":[84],"and":[85,119],"test":[86],"performance":[87],"agents":[90],"driving.":[93],"Based":[94],"essential":[97],"requirements":[98],"that":[99,116,145,158],"prescribe":[100],"safety":[102],"specifications":[103],"general":[105],"practice,":[109],"propose":[111],"additional":[112],"reshaped":[113],"terms":[115],"encourage":[117],"exploration":[118],"penalize":[120],"behaviors.":[123],"A":[124],"simulation":[125],"study":[126],"OpenAI":[128],"Gym":[129],"indicates":[130],"advantage":[132],"various":[138],"agents.":[140],"Also,":[141],"point":[143],"out":[144],"proximal":[146],"optimization":[148],"(PPO)":[149],"likely":[151],"best":[155],"method":[157],"works":[159],"shaping.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}