{"id":"https://openalex.org/W7141056504","doi":"https://doi.org/10.1109/lra.2026.3678458","title":"<b>ROAD</b> : <b>R</b> esponsibility- <b>O</b> riented Reward Design for Reinforcement Learning in <b>A</b> utonomous <b>D</b> riving","display_name":"<b>ROAD</b> : <b>R</b> esponsibility- <b>O</b> riented Reward Design for Reinforcement Learning in <b>A</b> utonomous <b>D</b> riving","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7141056504","doi":"https://doi.org/10.1109/lra.2026.3678458"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3678458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3678458","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5122947218","display_name":"Yongming Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongming Chen","raw_affiliation_strings":["Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045321240","display_name":"M Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I52158045","display_name":"China Agricultural University","ror":"https://ror.org/04v3ywz14","country_code":"CN","type":"education","lineage":["https://openalex.org/I52158045"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miner Chen","raw_affiliation_strings":["College of Information and Electrical Engineering, China Agricultural University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information and Electrical Engineering, China Agricultural University, Beijing, China","institution_ids":["https://openalex.org/I52158045"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029622642","display_name":"Qunyi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qunyi Zhang","raw_affiliation_strings":["Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010199786","display_name":"Liewen Liao","orcid":"https://orcid.org/0000-0002-4679-2440"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liewen Liao","raw_affiliation_strings":["Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002118929","display_name":"Mingyang Jiang","orcid":"https://orcid.org/0000-0002-3277-9536"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyang Jiang","raw_affiliation_strings":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112673067","display_name":"Xiang Zuo","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Zuo","raw_affiliation_strings":["School of Aeronautics and Astronautic, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautic, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028926935","display_name":"Hengrui Zhang","orcid":"https://orcid.org/0000-0002-0989-5803"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengrui Zhang","raw_affiliation_strings":["Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130760742","display_name":"Yuchen Xi","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Xi","raw_affiliation_strings":["Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045427668","display_name":"Songan Zhang","orcid":"https://orcid.org/0000-0002-3238-5406"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songan Zhang","raw_affiliation_strings":["Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101414911","display_name":"Ming Yang","orcid":"https://orcid.org/0000-0001-6107-6226"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Yang","raw_affiliation_strings":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002740588","display_name":"H. Eric Tseng","orcid":"https://orcid.org/0000-0001-5087-9592"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongtei Eric Tseng","raw_affiliation_strings":["Department of Electrical Engineering, The University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35894185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8503999710083008,"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":0.8503999710083008,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.018300000578165054,"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":0.016599999740719795,"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":0.45809999108314514},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.37070000171661377},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3068000078201294},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.2939000129699707},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.2599000036716461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5170999765396118},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.45809999108314514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4246000051498413},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3402999937534332},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3678458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3678458","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcementlearning":[0],"(RL)":[1],"in":[2,11,33,69,129],"autonomous":[3],"driving":[4,102],"employs":[5],"a":[6,43,60,86,98,140],"trial-and-error":[7],"mechanism,":[8],"enhancing":[9],"robustness":[10],"unpredictable":[12],"environments.":[13],"However,":[14],"crafting":[15],"effective":[16],"reward":[17,45,74,131,141],"functions":[18],"remains":[19],"challenging,":[20],"as":[21],"conventional":[22],"approaches":[23],"rely":[24],"heavily":[25],"on":[26,134],"manual":[27],"design":[28],"and":[29,72,80,104,143,173],"demonstrate":[30],"limited":[31],"efficacy":[32],"complex":[34],"scenarios.":[35],"To":[36,76],"address":[37],"this":[38,40,203],"issue,":[39],"study":[41],"introduces":[42],"responsibility-oriented":[44],"function":[46,142],"that":[47,92,153,163],"explicitly":[48],"incorporates":[49],"traffic":[50,70,95,158],"regulations":[51],"into":[52,97],"the":[53,67,110,126,130,148,178,181,190],"RL":[54],"framework.":[55],"Specifically,":[56],"we":[57,84,138],"first":[58],"use":[59],"vision":[61],"language":[62],"model":[63],"(VLM)":[64],"to":[65,115,124,146,157],"determine":[66],"liability":[68,105],"collisions":[71],"propose":[73,85],"signals.":[75],"mitigate":[77],"VLM":[78],"hallucination":[79],"ensure":[81],"regulatory":[82,112],"grounding,":[83],"Traffic":[87],"Regulation":[88],"Knowledge":[89],"Graph":[90],"(TRKG)":[91],"structures":[93],"unstructured":[94],"laws":[96],"queryable":[99],"ontology":[100],"of":[101,170],"scenarios":[103],"standards.":[106],"This":[107],"mechanism":[108],"retrieves":[109],"precise":[111],"context":[113],"required":[114],"quantify":[116],"accident":[117],"responsibility":[118],"(primary/shared/secondary),":[119],"which":[120],"is":[121,205],"then":[122],"used":[123],"modulate":[125],"crash":[127],"penalty":[128],"function.":[132],"Building":[133],"these":[135],"liability-informed":[136],"signals,":[137],"construct":[139],"employ":[144],"it":[145],"train":[147],"agent,":[149],"thereby":[150],"encouraging":[151],"behavior":[152],"more":[154],"faithfully":[155],"adheres":[156],"regulations.":[159],"Experimental":[160],"validations":[161],"show":[162],"our":[164],"approach":[165],"achieves":[166],"task":[167],"success":[168,182],"rates":[169],"73.2%":[171],"(intersection)":[172],"54.0%":[174],"(roundabout).":[175],"Compared":[176],"with":[177],"original":[179],"policy,":[180],"rate":[183],"improves":[184],"by":[185,196],"+8.2":[186],"pp/+11.2":[187],"pp,":[188],"while":[189],"ego":[191],"vehicle's":[192],"primary-liability":[193],"share":[194],"decreases":[195],"13.5":[197],"pp/5.7":[198],"pp.":[199],"The":[200],"code":[201],"for":[202],"work":[204],"available":[206],"at":[207],"<uri":[208],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[209],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/Songan-Lab/ROAD</uri>.":[210]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-03-28T00:00:00"}
