{"id":"https://openalex.org/W4401417394","doi":"https://doi.org/10.1109/icra57147.2024.10610272","title":"Uncertainty-aware Reinforcement Learning for Autonomous Driving with Multimodal Digital Driver Guidance","display_name":"Uncertainty-aware Reinforcement Learning for Autonomous Driving with Multimodal Digital Driver Guidance","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401417394","doi":"https://doi.org/10.1109/icra57147.2024.10610272"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610272","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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":"https://openalex.org/A5103974420","display_name":"Wenhui Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wenhui Huang","raw_affiliation_strings":["Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043334142","display_name":"Zitong Shan","orcid":"https://orcid.org/0000-0001-8903-9259"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4392738231","display_name":"State Key Laboratory of Automotive Simulation and Control","ror":"https://ror.org/00b67z867","country_code":null,"type":"facility","lineage":["https://openalex.org/I194450716","https://openalex.org/I4392738231"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zitong Shan","raw_affiliation_strings":["Jilin University,State Key Laboratory of Automotive Simulation and Control,Changchun,China,130022"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University,State Key Laboratory of Automotive Simulation and Control,Changchun,China,130022","institution_ids":["https://openalex.org/I194450716","https://openalex.org/I4392738231"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081071311","display_name":"Shanhe Lou","orcid":"https://orcid.org/0000-0001-5984-9517"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shanhe Lou","raw_affiliation_strings":["Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072073374","display_name":"Chen Lv","orcid":"https://orcid.org/0000-0001-6897-4512"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Lv","raw_affiliation_strings":["Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"18355","last_page":"18361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9986000061035156,"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":0.9986000061035156,"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":0.998199999332428,"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":0.9980000257492065,"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":0.8112823963165283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7004191279411316},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5431267023086548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34586265683174133}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8112823963165283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7004191279411316},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5431267023086548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34586265683174133}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610272","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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":43,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2539402368","https://openalex.org/W2761873684","https://openalex.org/W2901453561","https://openalex.org/W2947433239","https://openalex.org/W2950673314","https://openalex.org/W2962730596","https://openalex.org/W2963238274","https://openalex.org/W2964469479","https://openalex.org/W2966994213","https://openalex.org/W2968983352","https://openalex.org/W2991604980","https://openalex.org/W3004264147","https://openalex.org/W3006408506","https://openalex.org/W3038618902","https://openalex.org/W3093963693","https://openalex.org/W3121045039","https://openalex.org/W3132408792","https://openalex.org/W3182474098","https://openalex.org/W4226257065","https://openalex.org/W4282944694","https://openalex.org/W4285278949","https://openalex.org/W4293775587","https://openalex.org/W4386824909","https://openalex.org/W4387303358","https://openalex.org/W4387415195","https://openalex.org/W4389044710","https://openalex.org/W6683397050","https://openalex.org/W6685444567","https://openalex.org/W6730042731","https://openalex.org/W6734517396","https://openalex.org/W6735374517","https://openalex.org/W6745935785","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6754005058","https://openalex.org/W6756482612","https://openalex.org/W6763291628","https://openalex.org/W6766242139","https://openalex.org/W6771763659","https://openalex.org/W6802251749","https://openalex.org/W6810152107","https://openalex.org/W6838855248"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109","https://openalex.org/W4362501864","https://openalex.org/W2001405890"],"abstract_inverted_index":{"While":[0],"existing":[1],"Learning":[2],"from":[3,86],"intervention":[4,120],"(LfI)":[5],"methods":[6],"within":[7],"the":[8,17,59,69,79,87,100,107,111,119,127,132,135,143,160,190],"human-in-the-loop":[9],"reinforcement":[10,146],"learning":[11,58,147,198],"(HiL-RL)":[12],"paradigm":[13],"mainly":[14],"operate":[15],"on":[16],"assumption":[18],"that":[19],"human":[20,30,42,66,83],"policies":[21],"are":[22,33,207],"homogeneous":[23],"and":[24,38,138,181,186,200,204],"deterministic":[25],"with":[26,35],"low":[27],"variance,":[28],"natural":[29],"driving":[31,116,174,201],"behaviors":[32,67],"multimodal":[34,65],"intrinsic":[36],"uncertainties,":[37],"hence,":[39],"accommodating":[40],"diverse":[41,115],"capabilities":[43],"is":[44,121,167],"significant":[45],"for":[46,57],"its":[47,95],"practical":[48],"applications.":[49],"This":[50],"work":[51],"proposes":[52],"an":[53],"enhanced":[54],"LfI":[55,179],"approach":[56],"optimal":[60],"RL":[61,112,133],"policy":[62,97],"by":[63],"leveraging":[64],"in":[68,106,159,170,195],"setting":[70],"of":[71,82,110,183,192,197],"N-driver":[72],"concurrent":[73],"interventions.":[74],"Specifically,":[75],"we":[76,130],"first":[77],"learn":[78],"N":[80],"number":[81],"digital":[84],"drivers":[85,102],"multi-human":[88],"demonstration":[89],"dataset,":[90],"wherein":[91],"each":[92],"driver":[93],"possesses":[94],"own":[96],"distribution.":[98],"Then,":[99],"post-trained":[101],"will":[103],"be":[104],"kept":[105],"training":[108],"loop":[109],"algorithms,":[113],"providing":[114],"guidance":[117],"whenever":[118],"required.":[122],"Additionally,":[123],"to":[124,141],"better":[125],"utilize":[126],"provided":[128],"guidance,":[129],"augment":[131],"regarding":[134],"fundamental":[136],"architecture":[137],"optimization":[139],"objectives":[140],"facilitate":[142],"proposed":[144,151],"uncertainty-aware":[145],"(UnaRL)":[148],"algorithm.":[149],"The":[150],"approach,":[152],"which":[153],"won":[154],"2<sup":[155],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[156,209],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">nd</sup>":[157],"place":[158],"Alibaba":[161],"Future":[162],"Car":[163],"Innovation":[164],"Challenge":[165],"2022,":[166],"solidly":[168],"compared":[169],"two":[171],"challenging":[172],"autonomous":[173],"scenarios":[175],"against":[176],"state-of-the-art":[177],"(SOTA)":[178],"baselines,":[180],"results":[182],"both":[184],"simulation":[185],"real-world":[187],"experiment":[188],"confirm":[189],"superiority":[191],"our":[193],"method":[194],"terms":[196],"robustness":[199],"performance.":[202],"Videos":[203],"source":[205],"code":[206],"provided.<sup":[208],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}