{"id":"https://openalex.org/W4416750631","doi":"https://doi.org/10.1109/iros60139.2025.11246043","title":"Risk-Aware Reinforcement Learning with Group Opinion for Autonomous Driving","display_name":"Risk-Aware Reinforcement Learning with Group Opinion for Autonomous Driving","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750631","doi":"https://doi.org/10.1109/iros60139.2025.11246043"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5100628454","display_name":"Guanyi Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Guanyi Zhao","raw_affiliation_strings":["City University of Hong Kong,Department of Computer Science,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,Department of Computer Science,Hong Kong,China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100771701","display_name":"Meng Xu","orcid":"https://orcid.org/0000-0003-4857-5439"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Meng Xu","raw_affiliation_strings":["City University of Hong Kong,Department of Computer Science,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,Department of Computer Science,Hong Kong,China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101700401","display_name":"Zihao Wen","orcid":"https://orcid.org/0000-0002-5401-5393"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zihao Wen","raw_affiliation_strings":["City University of Hong Kong,Department of Computer Science,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,Department of Computer Science,Hong Kong,China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107093999","display_name":"Jianping Wang","orcid":"https://orcid.org/0000-0002-8729-9185"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jianping Wang","raw_affiliation_strings":["City University of Hong Kong,Department of Computer Science,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,Department of Computer Science,Hong Kong,China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100628454"],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42806223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15254","last_page":"15261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.6668999791145325,"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":0.6668999791145325,"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":0.12520000338554382,"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":0.05889999866485596,"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":0.8356000185012817},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.7749000191688538},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4875999987125397},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.40709999203681946},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.3774999976158142}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8356000185012817},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.7749000191688538},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5138000249862671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49639999866485596},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47620001435279846},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.40709999203681946},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3165000081062317},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.2662000060081482}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2023993734","https://openalex.org/W2223108412","https://openalex.org/W2514940730","https://openalex.org/W2739476658","https://openalex.org/W2968008415","https://openalex.org/W2970231061","https://openalex.org/W2977843878","https://openalex.org/W3007866289","https://openalex.org/W3037429136","https://openalex.org/W3038712064","https://openalex.org/W3096609285","https://openalex.org/W3119746519","https://openalex.org/W3119924655","https://openalex.org/W3127561923","https://openalex.org/W3213157846","https://openalex.org/W4220902452","https://openalex.org/W4311416660","https://openalex.org/W4312550876","https://openalex.org/W4366483297","https://openalex.org/W4384519037","https://openalex.org/W4388265616","https://openalex.org/W4388737140","https://openalex.org/W4391940985","https://openalex.org/W4400524848","https://openalex.org/W4400577150","https://openalex.org/W4401415366"],"related_works":[],"abstract_inverted_index":{"To":[0,65],"avoid":[1],"dangerous":[2,56],"situations,":[3],"such":[4,183],"as":[5,111,122,152,184],"collisions":[6],"in":[7,102,140,165,179,188],"dynamic":[8],"environments,":[9],"autonomous":[10],"vehicles":[11],"must":[12],"predict":[13],"the":[14,17,52,123,133],"risks":[15],"of":[16,54,96,136,190],"current":[18],"scene":[19],"to":[20,50,59,99,121,156],"take":[21],"safe":[22],"actions.":[23],"Traditional":[24],"rule-based":[25],"risk":[26,101,117,124,145],"prediction":[27,118,125],"methods":[28,178],"and":[29,61,143,186,192],"existing":[30],"reinforcement":[31],"learning":[32],"(RL)":[33],"approaches,":[34],"which":[35],"typically":[36],"rely":[37],"on":[38],"manually":[39],"designed":[40],"driving":[41,63,84,104,163],"decision":[42],"rules":[43],"or":[44],"heuristic":[45],"reward":[46,154,191],"functions,":[47],"often":[48],"fail":[49],"capture":[51],"complexity":[53],"real-world":[55,89,103],"scenarios,":[57,138,182],"leading":[58],"suboptimal":[60],"unsafe":[62],"decisions.":[64],"address":[66],"this":[67],"limitation,":[68],"we":[69,92,114],"develop":[70],"a":[71,116,128,153],"novel":[72],"RL":[73,159],"method,":[74],"called":[75],"Group":[76],"Opinion":[77],"Risk-Aware":[78],"Reinforcement":[79],"Learning":[80],"(GORA-RL),":[81],"for":[82,161],"safer":[83],"decisions":[85,164],"that":[86,131,171],"align":[87],"with":[88,127],"conditions.":[90],"Specifically,":[91],"first":[93],"introduce":[94],"surveys":[95],"human":[97],"drivers":[98],"assess":[100],"situations.":[105],"Using":[106],"these":[107,137],"real":[108],"group":[109],"opinions":[110],"training":[112],"data,":[113],"train":[115,157],"model,":[119],"referred":[120],"model":[126,148],"Transformer":[129],"(RPT),":[130],"captures":[132],"crucial":[134],"characteristics":[135],"resulting":[139],"more":[141],"realistic":[142],"reliable":[144],"predictions.":[146],"This":[147],"is":[149],"then":[150],"integrated":[151],"function":[155],"an":[158],"algorithm":[160],"making":[162],"various":[166],"scenarios.":[167],"The":[168],"experiments":[169],"validate":[170],"our":[172],"approach":[173],"outperforms":[174],"two":[175],"state-of-the-art":[176],"(SOTA)":[177],"challenging":[180],"congested":[181],"merging":[185],"intersections,":[187],"terms":[189],"several":[193],"other":[194],"metrics.":[195],"Project":[196],"site:":[197],"https://github.com/naiyisiji/RPT.":[198]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}