{"id":"https://openalex.org/W3002936144","doi":"https://doi.org/10.1109/robio49542.2019.8961480","title":"Learning Adaptive Driving Behavior Using Recurrent Deterministic Policy Gradients","display_name":"Learning Adaptive Driving Behavior Using Recurrent Deterministic Policy Gradients","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3002936144","doi":"https://doi.org/10.1109/robio49542.2019.8961480","mag":"3002936144"},"language":"en","primary_location":{"id":"doi:10.1109/robio49542.2019.8961480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio49542.2019.8961480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5102721416","display_name":"Kaustubh Mani","orcid":"https://orcid.org/0009-0007-9467-3159"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["IN","US"],"is_corresponding":true,"raw_author_name":"Kaustubh Mani","raw_affiliation_strings":["IIIT-Hyderabad,Robotics Research Center","Robotics Research Center, IIIT-Hyderabad"],"affiliations":[{"raw_affiliation_string":"IIIT-Hyderabad,Robotics Research Center","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"Robotics Research Center, IIIT-Hyderabad","institution_ids":["https://openalex.org/I4210116723","https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012183445","display_name":"Meha Kaushik","orcid":"https://orcid.org/0000-0002-8257-6171"},"institutions":[{"id":"https://openalex.org/I4210153468","display_name":"Microsoft (Canada)","ror":"https://ror.org/04xhxg104","country_code":"CA","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210153468"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Meha Kaushik","raw_affiliation_strings":["Microsoft Canada Development Center"],"affiliations":[{"raw_affiliation_string":"Microsoft Canada Development Center","institution_ids":["https://openalex.org/I4210153468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028845933","display_name":"Nirvan Singhania","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]},{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Nirvan Singhania","raw_affiliation_strings":["IIIT-Hyderabad,Robotics Research Center","Robotics Research Center, IIIT-Hyderabad"],"affiliations":[{"raw_affiliation_string":"IIIT-Hyderabad,Robotics Research Center","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"Robotics Research Center, IIIT-Hyderabad","institution_ids":["https://openalex.org/I4210116723","https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075816776","display_name":"K. Madhava Krishna","orcid":"https://orcid.org/0000-0001-7846-7901"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"K. Madhava Krishna","raw_affiliation_strings":["IIIT-Hyderabad,Robotics Research Center","Robotics Research Center, IIIT-Hyderabad"],"affiliations":[{"raw_affiliation_string":"IIIT-Hyderabad,Robotics Research Center","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"Robotics Research Center, IIIT-Hyderabad","institution_ids":["https://openalex.org/I4210116723","https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102721416"],"corresponding_institution_ids":["https://openalex.org/I4210116723","https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":0.42,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72573171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2092","last_page":"2098"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9937999844551086,"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":0.9922000169754028,"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":0.8006340265274048},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7602223753929138},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.5978319048881531},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.48526498675346375},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4659012258052826},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4377509653568268},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.41723763942718506},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.37845394015312195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34902554750442505},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.1897495687007904},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12874263525009155}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8006340265274048},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7602223753929138},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.5978319048881531},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.48526498675346375},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4659012258052826},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4377509653568268},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.41723763942718506},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.37845394015312195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34902554750442505},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.1897495687007904},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12874263525009155},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio49542.2019.8961480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio49542.2019.8961480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2017957151","https://openalex.org/W2111901564","https://openalex.org/W2156737235","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2291973609","https://openalex.org/W2462906003","https://openalex.org/W2530849036","https://openalex.org/W2563338958","https://openalex.org/W2615547864","https://openalex.org/W2727840223","https://openalex.org/W2749747771","https://openalex.org/W2896066033","https://openalex.org/W2900477380","https://openalex.org/W2913811934","https://openalex.org/W2962867954","https://openalex.org/W2963864421","https://openalex.org/W2968983352","https://openalex.org/W4295719664","https://openalex.org/W4297781990","https://openalex.org/W4301501993","https://openalex.org/W4302570325","https://openalex.org/W6683195989","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6696783566","https://openalex.org/W6718836005","https://openalex.org/W6731187701","https://openalex.org/W6737769214","https://openalex.org/W6745935785","https://openalex.org/W6752818208","https://openalex.org/W6756559057","https://openalex.org/W6759494603"],"related_works":["https://openalex.org/W2286391053","https://openalex.org/W2982600058","https://openalex.org/W1963486701","https://openalex.org/W2312483540","https://openalex.org/W4249477090","https://openalex.org/W191745111","https://openalex.org/W1522083559","https://openalex.org/W2007570603","https://openalex.org/W2808224918","https://openalex.org/W2773679836"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,43,133],"propose":[4],"adaptive":[5],"driving":[6,26],"behaviors":[7],"for":[8,99],"simulated":[9,29],"cars":[10],"using":[11],"continuous":[12],"control":[13],"deep":[14],"reinforcement":[15],"learning.":[16],"Deep":[17],"Deterministic":[18,51,114],"Policy":[19,52,115],"Gradient(DDPG)":[20],"is":[21,66,95],"known":[22],"to":[23,38,59,77,82,90],"give":[24],"smooth":[25],"maneuvers":[27],"in":[28,71,88],"environments.":[30],"Unfortunately,":[31],"simple":[32],"feedforward":[33],"networks,":[34],"lack":[35],"the":[36,60,63,72,93,100],"capability":[37],"contain":[39],"temporal":[40],"information,":[41],"hence":[42],"have":[44],"used":[45],"its":[46],"Recurrent":[47,50,113],"variant":[48],"called":[49,126],"Gradients.":[53,116],"Our":[54],"trained":[55],"agent":[56],"adapts":[57],"itself":[58],"velocity":[61],"of":[62,68,74,112,143],"traffic.":[64],"It":[65],"capable":[67],"slowing":[69],"down":[70],"presence":[73],"dense":[75],"traffic,":[76],"prevent":[78],"collisions":[79],"as":[80,103],"well":[81,104],"speed":[83],"up":[84],"and":[85,128,138],"change":[86],"lanes":[87],"order":[89],"overtake":[91],"when":[92],"traffic":[94],"sparse.":[96],"The":[97],"reasons":[98],"above":[101],"behavior,":[102],"as,":[105],"our":[106],"main":[107],"contributions":[108],"are:":[109],"1.":[110],"Application":[111],"2.":[117],"Novel":[118],"reward":[119],"function":[120],"formulation.":[121],"3.":[122],"Modified":[123],"Replay":[124,130],"Buffer":[125],"Near":[127],"Far":[129],"Buffers,":[131],"wherein":[132],"maintain":[134],"two":[135],"replay":[136],"buffers":[137],"sample":[139],"equally":[140],"from":[141],"both":[142],"them.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}