{"id":"https://openalex.org/W4406612132","doi":"https://doi.org/10.1109/smc54092.2024.10832016","title":"Deep Attention Driven Reinforcement Learning (DAD-RL) for Autonomous Decision-Making in Dynamic Environment","display_name":"Deep Attention Driven Reinforcement Learning (DAD-RL) for Autonomous Decision-Making in Dynamic Environment","publication_year":2024,"publication_date":"2024-10-06","ids":{"openalex":"https://openalex.org/W4406612132","doi":"https://doi.org/10.1109/smc54092.2024.10832016"},"language":"en","primary_location":{"id":"doi:10.1109/smc54092.2024.10832016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10832016","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 Systems, Man, and Cybernetics (SMC)","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/A5017692956","display_name":"Jayabrata Chowdhury","orcid":"https://orcid.org/0000-0003-1534-6066"},"institutions":[{"id":"https://openalex.org/I4210091347","display_name":"Robert Bosch (China)","ror":"https://ror.org/00cedkn40","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091347","https://openalex.org/I889804353"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jayabrata Chowdhury","raw_affiliation_strings":["Indian Institute of Science,Robert Bosch Centre for Cyber-Physical Systems,Bangalore"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Robert Bosch Centre for Cyber-Physical Systems,Bangalore","institution_ids":["https://openalex.org/I4210091347"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093478166","display_name":"Venkataramanan Shivaraman","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Venkataramanan Shivaraman","raw_affiliation_strings":["Indian Institute of Science,Department of Aerospace Engineering,Bangalore"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Department of Aerospace Engineering,Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111258276","display_name":"Sumit Dangi","orcid":null},"institutions":[{"id":"https://openalex.org/I288749910","display_name":"Indian Institute of Science Education and Research, Bhopal","ror":"https://ror.org/02rb21j89","country_code":"IN","type":"education","lineage":["https://openalex.org/I288749910"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sumit Dangi","raw_affiliation_strings":["Indian Institute of Science Education and Research,Department of Data Science & Engineering and Electrical Engineering & Computer Sci-ence,Bhopal"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science Education and Research,Department of Data Science & Engineering and Electrical Engineering & Computer Sci-ence,Bhopal","institution_ids":["https://openalex.org/I288749910"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Suresh Sundaram","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Suresh Sundaram","raw_affiliation_strings":["Indian Institute of Science,Department of Aerospace Engineering,Bangalore"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Department of Aerospace Engineering,Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014252229","display_name":"P. B. Sujit","orcid":"https://orcid.org/0000-0002-7297-1493"},"institutions":[{"id":"https://openalex.org/I288749910","display_name":"Indian Institute of Science Education and Research, Bhopal","ror":"https://ror.org/02rb21j89","country_code":"IN","type":"education","lineage":["https://openalex.org/I288749910"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"P B Sujit","raw_affiliation_strings":["Indian Institute of Science Education and Research,Department of Data Science & Engineering and Electrical Engineering & Computer Sci-ence,Bhopal"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science Education and Research,Department of Data Science & Engineering and Electrical Engineering & Computer Sci-ence,Bhopal","institution_ids":["https://openalex.org/I288749910"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017692956"],"corresponding_institution_ids":["https://openalex.org/I4210091347"],"apc_list":null,"apc_paid":null,"fwci":1.598,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84579332,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3863","last_page":"3868"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.12449999898672104,"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"}},"topics":[{"id":"https://openalex.org/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.12449999898672104,"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":0.8885265588760376},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7392910122871399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5338566899299622},{"id":"https://openalex.org/keywords/dynamic-decision-making","display_name":"Dynamic decision-making","score":0.47546833753585815},{"id":"https://openalex.org/keywords/autonomous-learning","display_name":"Autonomous learning","score":0.41979730129241943},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34972813725471497},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3381044864654541},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12592488527297974},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.057074517011642456}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8885265588760376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7392910122871399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5338566899299622},{"id":"https://openalex.org/C174988536","wikidata":"https://www.wikidata.org/wiki/Q5318965","display_name":"Dynamic decision-making","level":2,"score":0.47546833753585815},{"id":"https://openalex.org/C2983271839","wikidata":"https://www.wikidata.org/wiki/Q29644074","display_name":"Autonomous learning","level":2,"score":0.41979730129241943},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34972813725471497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3381044864654541},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12592488527297974},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.057074517011642456}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc54092.2024.10832016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10832016","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 Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W3003329097","https://openalex.org/W3089736706","https://openalex.org/W3093963693","https://openalex.org/W3127561923","https://openalex.org/W3128395826","https://openalex.org/W3134848271","https://openalex.org/W3181068094","https://openalex.org/W3191652410","https://openalex.org/W3208122016","https://openalex.org/W4214496626","https://openalex.org/W4285102480","https://openalex.org/W4309592030","https://openalex.org/W4312974600","https://openalex.org/W4383108453","https://openalex.org/W4385245566","https://openalex.org/W4388286274","https://openalex.org/W4392449656","https://openalex.org/W4393156515","https://openalex.org/W6796289742","https://openalex.org/W6804244202","https://openalex.org/W6838061527"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Autonomous":[0],"Vehicle":[1],"(AV)":[2],"decision-making":[3,86],"in":[4,30,47,182],"ur-ban":[5],"environments":[6],"is":[7,138],"inherently":[8],"challenging":[9],"due":[10],"to":[11,39,117,160],"the":[12,24,63,77,83,99,141,148,152,173,176],"dynamic":[13,100],"interactions":[14,29,41,101],"with":[15,102,127],"surrounding":[16,80,104],"vehicles.":[17,105],"For":[18],"safe":[19],"planning,":[20],"AV/ego":[21],"must":[22],"understand":[23,107],"weightage":[25],"of":[26,79,175],"various":[27],"spatiotemporal":[28,57,92,124,179],"a":[31,114,131],"scene.":[32],"Contemporary":[33],"works":[34],"use":[35],"colos-sal":[36],"transformer":[37],"architectures":[38],"encode":[40],"mainly":[42],"for":[43,97],"trajectory":[44],"prediction,":[45],"resulting":[46,136],"increased":[48],"computational":[49],"complexity.":[50],"To":[51,106],"address":[52],"this":[53],"issue":[54],"without":[55,157],"compromising":[56],"understanding":[58],"and":[59,75,109,178],"performance,":[60],"we":[61,112],"propose":[62],"simple":[64],"Deep":[65],"Attention":[66],"Driven":[67],"Reinforcement":[68],"Learning":[69],"(DAD-RL)":[70],"framework,":[71],"which":[72],"dynamically":[73],"assigns":[74],"incorporates":[76],"significance":[78],"vehicles":[81],"into":[82],"ego's":[84],"RL-driven":[85],"process.":[87],"We":[88,146],"introduce":[89],"an":[90,169],"AV-centric":[91],"attention":[93,180],"encoding":[94,129],"(STAE)":[95],"mechanism":[96],"learning":[98],"different":[103],"map":[108],"route":[110],"context,":[111],"employ":[113],"context":[115,121],"encoder":[116,181],"extract":[118],"features":[119],"from":[120],"maps.":[122],"The":[123,135],"representations":[125],"combined":[126],"contextual":[128],"provide":[130],"comprehensive":[132],"state":[133],"representation.":[134],"model":[137],"trained":[139],"using":[140],"Soft-Actor":[142],"Critic":[143],"(SAC)":[144],"algorithm.":[145],"evaluate":[147],"proposed":[149],"framework":[150],"on":[151],"SMARTS":[153],"urban":[154],"benchmarking":[155],"scenarios":[156],"traffic":[158],"signals":[159],"demonstrate":[161],"that":[162],"DAD-RL":[163],"outperforms":[164],"recent":[165],"state-of-the-art":[166],"methods.":[167],"Furthermore,":[168],"ablation":[170],"study":[171],"underscores":[172],"importance":[174],"context-encoder":[177],"achieving":[183],"superior":[184],"performance.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}