{"id":"https://openalex.org/W4414605660","doi":"https://doi.org/10.1109/qrs65678.2025.00068","title":"A Reinforcement Learning Algorithm for Safety Decision Making in Autonomous Driving Systems with Reward Machine Guidance","display_name":"A Reinforcement Learning Algorithm for Safety Decision Making in Autonomous Driving Systems with Reward Machine Guidance","publication_year":2025,"publication_date":"2025-07-16","ids":{"openalex":"https://openalex.org/W4414605660","doi":"https://doi.org/10.1109/qrs65678.2025.00068"},"language":"en","primary_location":{"id":"doi:10.1109/qrs65678.2025.00068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/qrs65678.2025.00068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 25th International Conference on Software Quality, Reliability and Security (QRS)","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Junge Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I118574674","display_name":"Jiangsu Normal University","ror":"https://ror.org/051hvcm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I118574674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junge Huang","raw_affiliation_strings":["School of Computer Science and Technology, Jiangsu Normal University,Xuzhou,Jiangsu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Jiangsu Normal University,Xuzhou,Jiangsu,China","institution_ids":["https://openalex.org/I118574674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009184834","display_name":"Yi Zhu","orcid":"https://orcid.org/0000-0003-3045-2588"},"institutions":[{"id":"https://openalex.org/I118574674","display_name":"Jiangsu Normal University","ror":"https://ror.org/051hvcm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I118574674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhu","raw_affiliation_strings":["School of Computer Science and Technology, Jiangsu Normal University,Xuzhou,Jiangsu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Jiangsu Normal University,Xuzhou,Jiangsu,China","institution_ids":["https://openalex.org/I118574674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100690701","display_name":"Jinyong Wang","orcid":"https://orcid.org/0000-0002-5205-1649"},"institutions":[{"id":"https://openalex.org/I124841900","display_name":"Xuzhou University of Technology","ror":"https://ror.org/02315by94","country_code":"CN","type":"education","lineage":["https://openalex.org/I124841900"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyong Wang","raw_affiliation_strings":["School of Information Engineering, Xuzhou University of Technology,Xuzhou,Jiangsu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Xuzhou University of Technology,Xuzhou,Jiangsu,China","institution_ids":["https://openalex.org/I124841900"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101888222","display_name":"Ying Zhao","orcid":"https://orcid.org/0000-0003-0096-5614"},"institutions":[{"id":"https://openalex.org/I118574674","display_name":"Jiangsu Normal University","ror":"https://ror.org/051hvcm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I118574674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zhao","raw_affiliation_strings":["School of Computer Science and Technology, Jiangsu Normal University,Xuzhou,Jiangsu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Jiangsu Normal University,Xuzhou,Jiangsu,China","institution_ids":["https://openalex.org/I118574674"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108991949","display_name":"Miaoer Li","orcid":null},"institutions":[{"id":"https://openalex.org/I118574674","display_name":"Jiangsu Normal University","ror":"https://ror.org/051hvcm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I118574674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miaoer Li","raw_affiliation_strings":["School of Computer Science and Technology, Jiangsu Normal University,Xuzhou,Jiangsu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Jiangsu Normal University,Xuzhou,Jiangsu,China","institution_ids":["https://openalex.org/I118574674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"634","last_page":"643"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.8704000115394592,"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":0.8704000115394592,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8632000088691711},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8432000279426575},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.5946999788284302},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5648999810218811},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4674000144004822},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46389999985694885},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.3644999861717224},{"id":"https://openalex.org/keywords/advanced-driver-assistance-systems","display_name":"Advanced driver assistance systems","score":0.3531999886035919}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8632000088691711},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8432000279426575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6714000105857849},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.5946999788284302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5656999945640564},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5648999810218811},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5336999893188477},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46389999985694885},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C9628104","wikidata":"https://www.wikidata.org/wiki/Q788009","display_name":"Autonomous system (mathematics)","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.3163999915122986},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.3028999865055084},{"id":"https://openalex.org/C127757376","wikidata":"https://www.wikidata.org/wiki/Q2056514","display_name":"Active safety","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C2986897749","wikidata":"https://www.wikidata.org/wiki/Q231761","display_name":"Potential field","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/qrs65678.2025.00068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/qrs65678.2025.00068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 25th International Conference on Software Quality, Reliability and Security (QRS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1877157977","display_name":null,"funder_award_id":"62077029,62277030","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2873068653","display_name":null,"funder_award_id":"NJ2020022","funder_id":"https://openalex.org/F4320334859","funder_display_name":"Foundation of the Graduate Innovation Center, Nanjing University of Aeronautics and Astronautics"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334859","display_name":"Foundation of the Graduate Innovation Center, Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W828139470","https://openalex.org/W1512310098","https://openalex.org/W1755189310","https://openalex.org/W1962072139","https://openalex.org/W1994350081","https://openalex.org/W2101508170","https://openalex.org/W2121553911","https://openalex.org/W2127240436","https://openalex.org/W2233387800","https://openalex.org/W2785931971","https://openalex.org/W2953303875","https://openalex.org/W3090425956","https://openalex.org/W3092156990","https://openalex.org/W3116073702","https://openalex.org/W3127561923","https://openalex.org/W4283821610","https://openalex.org/W4312835009","https://openalex.org/W4312844584","https://openalex.org/W4394963598","https://openalex.org/W4400189254","https://openalex.org/W4412692910"],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,25,34,74,87,93,101,110,116,121,130,150],"field":[2],"of":[3,30,36,89,95,103,109,125,134,143],"autonomous":[4,66,104,145],"driving,":[5],"safe":[6],"and":[7,27,123,132],"efficient":[8],"decision-making":[9,111],"through":[10,139],"deep":[11],"reinforcement":[12,39,53,154],"learning":[13,40,54,155],"remains":[14],"a":[15,52,61,79,140],"significant":[16],"challenge.":[17],"Existing":[18],"methods":[19],"often":[20],"struggle":[21],"to":[22,24,71,85,99],"adapt":[23],"dynamic":[26],"complex":[28,160],"conditions":[29],"urban":[31],"environments,":[32],"while":[33],"lack":[35],"interpretability":[37],"in":[38,159],"algorithms":[41],"raises":[42],"safety":[43,102,133],"concerns.":[44],"To":[45],"address":[46],"these":[47],"issues,":[48],"this":[49,135],"paper":[50],"proposes":[51],"method":[55,136],"guided":[56],"by":[57],"reward":[58,62,152],"machine.":[59],"Firstly,":[60],"machine":[63],"tailored":[64],"for":[65],"driving":[67,105,146],"scenarios":[68],"is":[69,83,113],"constructed":[70],"better":[72],"guide":[73],"agent's":[75],"behavior":[76],"selection.":[77],"Then,":[78],"time":[80],"sensitivity":[81],"factor":[82],"proposed":[84,151],"adjust":[86],"generation":[88],"counterfactual":[90],"experiences,":[91],"optimizing":[92],"effectiveness":[94,131],"policy":[96],"learning.":[97],"Furthermore,":[98],"improve":[100],"decisions,":[106],"formal":[107],"verification":[108],"process":[112],"conducted":[114],"via":[115],"UPPAAL":[117],"model":[118],"checker,":[119],"enabling":[120],"identification":[122],"handling":[124],"potential":[126],"hazardous":[127],"states.":[128],"Finally,":[129],"are":[137],"validated":[138],"case":[141],"study":[142],"an":[144],"system,":[147],"demonstrating":[148],"that":[149],"machine-guided":[153],"algorithm":[156],"performs":[157],"well":[158],"road":[161],"scenarios.":[162]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}