{"id":"https://openalex.org/W4206391787","doi":"https://doi.org/10.1109/smc52423.2021.9658892","title":"A Deep Q-Network Reinforcement Learning-Based Model for Autonomous Driving","display_name":"A Deep Q-Network Reinforcement Learning-Based Model for Autonomous Driving","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W4206391787","doi":"https://doi.org/10.1109/smc52423.2021.9658892"},"language":"en","primary_location":{"id":"doi:10.1109/smc52423.2021.9658892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc52423.2021.9658892","pdf_url":null,"source":{"id":"https://openalex.org/S4363607761","display_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/A_Deep_Q-Network_Reinforcement_Learning-Based_Model_for_Autonomous_Driving/20618457","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101463981","display_name":"Marwa Ahmed","orcid":"https://orcid.org/0000-0002-6927-9543"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Marwa Ahmed","raw_affiliation_strings":["Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072923302","display_name":"Chee Peng Lim","orcid":"https://orcid.org/0000-0003-4191-9083"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chee Peng Lim","raw_affiliation_strings":["Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015293969","display_name":"Saeid Nahavandi","orcid":"https://orcid.org/0000-0002-0360-5270"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Saeid Nahavandi","raw_affiliation_strings":["Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149704539"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"739","last_page":"744"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9998000264167786,"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":0.9998000264167786,"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/T10524","display_name":"Traffic control and management","score":0.9983000159263611,"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"}},{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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":0.8785947561264038},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7711240649223328},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.5604506731033325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5221458077430725},{"id":"https://openalex.org/keywords/brake","display_name":"Brake","score":0.5049362778663635},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4982771873474121},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3570515513420105},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12299168109893799},{"id":"https://openalex.org/keywords/automotive-engineering","display_name":"Automotive engineering","score":0.10673314332962036}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8785947561264038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7711240649223328},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.5604506731033325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5221458077430725},{"id":"https://openalex.org/C2780999251","wikidata":"https://www.wikidata.org/wiki/Q17022503","display_name":"Brake","level":2,"score":0.5049362778663635},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4982771873474121},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3570515513420105},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12299168109893799},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.10673314332962036},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/smc52423.2021.9658892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc52423.2021.9658892","pdf_url":null,"source":{"id":"https://openalex.org/S4363607761","display_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/20618457","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/A_Deep_Q-Network_Reinforcement_Learning-Based_Model_for_Autonomous_Driving/20618457","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/20618457","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/A_Deep_Q-Network_Reinforcement_Learning-Based_Model_for_Autonomous_Driving/20618457","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2257979135","https://openalex.org/W2531409750","https://openalex.org/W2563338958","https://openalex.org/W2567061106","https://openalex.org/W2582616844","https://openalex.org/W2604283518","https://openalex.org/W2727840223","https://openalex.org/W2744369598","https://openalex.org/W2752236613","https://openalex.org/W2783963507","https://openalex.org/W2945935438","https://openalex.org/W2950471160","https://openalex.org/W2963322416","https://openalex.org/W2963864421","https://openalex.org/W2963881378","https://openalex.org/W3102270594","https://openalex.org/W4295719664","https://openalex.org/W6684921986","https://openalex.org/W6696324988","https://openalex.org/W6728184133","https://openalex.org/W6731156920","https://openalex.org/W6731187701","https://openalex.org/W6736622323","https://openalex.org/W6745935785"],"related_works":["https://openalex.org/W2953205341","https://openalex.org/W235065745","https://openalex.org/W2029935773","https://openalex.org/W2787754950","https://openalex.org/W1572215850","https://openalex.org/W1985775355","https://openalex.org/W2352115286","https://openalex.org/W2084793300","https://openalex.org/W2476350415","https://openalex.org/W2050406034"],"abstract_inverted_index":{"Learning":[0],"to":[1,38,108,113],"drive":[2],"in":[3,55,63,77,116,160,169,197,201,213],"highly":[4],"crowded":[5],"urban":[6,82],"areas":[7],"with":[8,103,162,173],"multi-agent":[9],"interaction":[10],"is":[11],"a":[12,53,70,74,95,104,126,170,174,202,206],"challenging":[13],"task.":[14],"Most":[15],"of":[16,128],"the":[17,23,27,41,48,64,110,136,145,151,164,190,194,199,210],"current":[18,65],"methods":[19],"rely":[20],"on":[21],"hand-crafting":[22],"policy":[24,43],"required":[25],"for":[26],"decision-making":[28],"process.":[29],"In":[30,84],"contrast,":[31],"reinforcement":[32],"learning":[33],"(RL)":[34],"offers":[35],"proper":[36,165],"methodologies":[37],"automatically":[39],"formulate":[40],"best":[42],"without":[44],"manual":[45],"intervention.":[46],"However,":[47],"baseline":[49],"RL":[50,111],"algorithms":[51],"face":[52],"challenge":[54],"handling":[56],"simulated":[57],"driving":[58,62,92,115,179,184],"situations":[59],"(e.g.,":[60],"keep":[61,69],"lane":[66,203],"center,":[67],"and":[68,80,99,141,154,177],"safe":[71,207],"distance":[72,208],"from":[73,135,144,181,209],"leading":[75,211],"vehicle)":[76],"high":[78],"fidelity":[79],"complex":[81,117],"areas.":[83],"this":[85],"study,":[86],"we":[87],"propose":[88],"an":[89,182],"end-to-end":[90],"autonomous":[91,183,195],"system":[93],"using":[94],"Deep":[96],"Q-Network":[97],"(DQN)":[98],"long-short-term":[100],"memory":[101],"(LSTM)":[102],"new":[105],"observation":[106,123],"input":[107,124],"enable":[109],"agent":[112,196],"learn":[114],"environments":[118],"i.e.":[119],"CARLA":[120],"simulator.":[121],"The":[122,148,186],"comprises":[125,150],"tuple":[127],"RGB":[129],"(Red,":[130],"Green,":[131],"Blue)":[132],"image":[133],"data":[134],"forward-facing":[137],"camera,":[138],"vehicle":[139,142,200,212],"speed,":[140],"angle":[143],"road":[146,216],"center.":[147],"output":[149],"steering,":[152],"brake,":[153],"acceleration":[155],"commands.":[156],"Our":[157],"proposed":[158],"model,":[159],"conjunction":[161],"formulating":[163],"reward":[166],"function,":[167],"results":[168,187],"rapid":[171],"convergence":[172],"better":[175],"performance":[176],"safer":[178],"behaviors":[180],"agent.":[185],"indicate":[188],"that":[189],"LSTM-DQN":[191],"model":[192],"enables":[193],"controlling":[198],"while":[204],"keeping":[205],"varied":[214],"unseen":[215],"conditions.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}