{"id":"https://openalex.org/W4404925130","doi":"https://doi.org/10.1145/3696271.3696284","title":"Deep Reinforcement Learning for Autonomous Driving with Multi-Scenario Fusion: A Unified Reward Function Approach","display_name":"Deep Reinforcement Learning for Autonomous Driving with Multi-Scenario Fusion: A Unified Reward Function Approach","publication_year":2024,"publication_date":"2024-08-02","ids":{"openalex":"https://openalex.org/W4404925130","doi":"https://doi.org/10.1145/3696271.3696284"},"language":"en","primary_location":{"id":"doi:10.1145/3696271.3696284","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696271.3696284","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Machine Learning and Machine Intelligence (MLMI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3696271.3696284","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101852463","display_name":"Dongkun Han","orcid":"https://orcid.org/0000-0003-0336-9818"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dongkun Han","raw_affiliation_strings":["Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0003-0336-9818","affiliations":[{"raw_affiliation_string":"Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111875641","display_name":"Sen Shen","orcid":"https://orcid.org/0009-0001-8653-2483"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Sen Shen","raw_affiliation_strings":["Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0009-0001-8653-2483","affiliations":[{"raw_affiliation_string":"Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.2986,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66920722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"78","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9611999988555908,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.960099995136261,"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":0.8751662969589233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6875178813934326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5488860011100769},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5417355895042419},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4854505658149719},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.329099178314209}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8751662969589233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6875178813934326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5488860011100769},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5417355895042419},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4854505658149719},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.329099178314209},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":1,"locations":[{"id":"doi:10.1145/3696271.3696284","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696271.3696284","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Machine Learning and Machine Intelligence (MLMI)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3696271.3696284","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696271.3696284","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Machine Learning and Machine Intelligence (MLMI)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2008515416","https://openalex.org/W2271840356","https://openalex.org/W2560647685","https://openalex.org/W2913433017","https://openalex.org/W3020741887","https://openalex.org/W3127561923","https://openalex.org/W3216772467","https://openalex.org/W4285278949","https://openalex.org/W4285279465","https://openalex.org/W4298857966","https://openalex.org/W4304780885","https://openalex.org/W4312435357","https://openalex.org/W4390666697","https://openalex.org/W6637967152"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Autonomous":[0,53],"driving":[1,115],"is":[2,105],"a":[3,38,58,66,71,79,89],"hot":[4],"yet":[5],"challenging":[6],"issue":[7],"due":[8],"to":[9,18,82,97,130],"its":[10],"variability":[11],"and":[12,23,60,69,86],"the":[13,109,126],"ongoing":[14],"fast":[15],"development":[16],"related":[17],"tasks":[19],"like":[20],"vehicle":[21],"control":[22],"scene":[24],"recognition.":[25],"Nonetheless,":[26],"advancements":[27],"in":[28,44,101,134],"deep":[29],"representation":[30],"learning":[31],"have":[32],"transformed":[33],"Reinforcement":[34],"Learning":[35],"(RL)":[36],"into":[37],"framework":[39],"of":[40],"mastering":[41],"intricate":[42],"strategies":[43],"complex":[45],"environments.":[46],"This":[47],"study":[48],"focuses":[49],"on":[50,57,84],"situations":[51],"involving":[52],"Vehicles":[54],"(AVs)":[55],"navigating":[56],"highway":[59,110],"merging":[61],"onto":[62,88],"an":[63,83],"on-ramp":[64],"entering":[65],"parking":[67,80],"lot":[68,81],"finding":[70],"spot":[72],"as":[73],"scenarios":[74,135],"where":[75],"it":[76,99],"travels":[77],"from":[78],"ramp":[85],"merges":[87],"highway.":[90],"The":[91,103],"reward":[92],"system":[93],"will":[94],"be":[95,119],"adjusted":[96],"make":[98],"applicable":[100],"scenarios.":[102],"research":[104],"carried":[106],"out":[107],"using":[108],"env":[111],"simulator,":[112],"which":[113],"provides":[114],"conditions":[116],"that":[117,125],"can":[118],"customized.":[120],"Our":[121],"test":[122],"results":[123],"show":[124],"AI":[127],"successfully":[128],"learns":[129],"achieve":[131],"training":[132],"goals":[133],"with":[136,140],"both":[137],"simple":[138],"interactions,":[139],"other":[141],"vehicles.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}