{"id":"https://openalex.org/W2972050850","doi":"https://doi.org/10.1109/itsc.2019.8917387","title":"End-to-end Reinforcement Learning for Autonomous Longitudinal Control Using Advantage Actor Critic with Temporal Context","display_name":"End-to-end Reinforcement Learning for Autonomous Longitudinal Control Using Advantage Actor Critic with Temporal Context","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2972050850","doi":"https://doi.org/10.1109/itsc.2019.8917387","mag":"2972050850"},"language":"en","primary_location":{"id":"doi:10.1109/itsc.2019.8917387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc.2019.8917387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","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/A5028079160","display_name":"Sampo Kuutti","orcid":"https://orcid.org/0000-0002-7020-4370"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Sampo Kuutti","raw_affiliation_strings":["Connected and Autonomous Vehicles Lab, University of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Connected and Autonomous Vehicles Lab, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044490167","display_name":"Richard Bowden","orcid":"https://orcid.org/0000-0003-3285-8020"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Richard Bowden","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085529093","display_name":"Harita Joshi","orcid":null},"institutions":[{"id":"https://openalex.org/I130198913","display_name":"Jaguar Land Rover (United Kingdom)","ror":"https://ror.org/03b66v461","country_code":"GB","type":"company","lineage":["https://openalex.org/I130198913"]},{"id":"https://openalex.org/I4210127762","display_name":"Coventry (United Kingdom)","ror":"https://ror.org/030nd5313","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210127762"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Harita Joshi","raw_affiliation_strings":["Jaguar Land Rover Limited, Coventry, UK"],"affiliations":[{"raw_affiliation_string":"Jaguar Land Rover Limited, Coventry, UK","institution_ids":["https://openalex.org/I130198913","https://openalex.org/I4210127762"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029384859","display_name":"Robert de Temple","orcid":"https://orcid.org/0000-0002-4439-2339"},"institutions":[{"id":"https://openalex.org/I130198913","display_name":"Jaguar Land Rover (United Kingdom)","ror":"https://ror.org/03b66v461","country_code":"GB","type":"company","lineage":["https://openalex.org/I130198913"]},{"id":"https://openalex.org/I4210127762","display_name":"Coventry (United Kingdom)","ror":"https://ror.org/030nd5313","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210127762"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Robert de Temple","raw_affiliation_strings":["Jaguar Land Rover Limited, Coventry, UK"],"affiliations":[{"raw_affiliation_string":"Jaguar Land Rover Limited, Coventry, UK","institution_ids":["https://openalex.org/I130198913","https://openalex.org/I4210127762"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071227510","display_name":"Saber Fallah","orcid":"https://orcid.org/0000-0002-1298-1040"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Saber Fallah","raw_affiliation_strings":["Connected and Autonomous Vehicles Lab, University of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Connected and Autonomous Vehicles Lab, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028079160"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":2.7419,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.92622197,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2456","last_page":"2462"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9858999848365784,"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":0.9803000092506409,"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":0.7859091758728027},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6913154125213623},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5910952687263489},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5819061994552612},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5018713474273682},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.48404091596603394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4379734992980957},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.06921115517616272}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7859091758728027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6913154125213623},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5910952687263489},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5819061994552612},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5018713474273682},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.48404091596603394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4379734992980957},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.06921115517616272},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/itsc.2019.8917387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc.2019.8917387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","raw_type":"proceedings-article"},{"id":"pmh:oai:epubs.surrey.ac.uk:852359","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/852359/1/Kuutti%20-%202019%20-%20End-to-end%20Reinforcement%20Learning%20for%20Autonomous%20Longitudinal%20Control%20Using%20Advantage%20Actor%20Critic%20with%20%20%281%29.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1547105496","https://openalex.org/W1573205248","https://openalex.org/W1646707810","https://openalex.org/W2009303086","https://openalex.org/W2046376809","https://openalex.org/W2060277733","https://openalex.org/W2064675550","https://openalex.org/W2121092017","https://openalex.org/W2121806728","https://openalex.org/W2129660761","https://openalex.org/W2136602922","https://openalex.org/W2136767008","https://openalex.org/W2140135625","https://openalex.org/W2146737184","https://openalex.org/W2155027007","https://openalex.org/W2406067508","https://openalex.org/W2523413845","https://openalex.org/W2556958149","https://openalex.org/W2560647685","https://openalex.org/W2606548817","https://openalex.org/W2751621024","https://openalex.org/W2791639158","https://openalex.org/W2809717747","https://openalex.org/W2844672055","https://openalex.org/W2869375357","https://openalex.org/W2962938178","https://openalex.org/W2963095800","https://openalex.org/W2963679616","https://openalex.org/W2964043796","https://openalex.org/W3000508506","https://openalex.org/W6677939520","https://openalex.org/W6680194329","https://openalex.org/W6680327459","https://openalex.org/W6680657880","https://openalex.org/W6683204974","https://openalex.org/W6692846177","https://openalex.org/W6730111887","https://openalex.org/W6743671064","https://openalex.org/W6752315495","https://openalex.org/W6753127035"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W4384574988","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W1528400370"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,21,40,67,145,156,161,173],"has":[2,133],"been":[3],"used":[4],"widely":[5],"for":[6,130,143],"autonomous":[7],"longitudinal":[8],"control":[9,87],"algorithms.":[10],"However,":[11],"many":[12],"existing":[13],"algorithms":[14,53],"suffer":[15],"from":[16,180],"sample":[17,109],"inefficiency":[18,110],"in":[19,55,95,155,182],"reinforcement":[20,39,144,160],"as":[22,24,127,138,158],"well":[23],"the":[25,30,77,81,104,120,131,141,148,170,186],"jerky":[26],"driving":[27],"behaviour":[28],"of":[29,51,103,188],"learned":[31,82],"systems.":[32],"In":[33],"this":[34,56],"paper,":[35],"we":[36],"propose":[37],"a":[38,43,124,128,152],"algorithm":[41,105],"and":[42,93,157,163],"training":[44,102,137],"framework":[45],"to":[46,72,84,97,118,136,146,194],"address":[47],"these":[48],"two":[49],"disadvantages":[50],"previous":[52,91],"proposed":[54,59],"field.":[57],"The":[58],"system":[60,68,83],"uses":[61],"an":[62,195],"Advantage":[63],"Actor":[64],"Critic":[65],"(A2C)":[66],"with":[69],"recurrent":[70,190,198],"layers":[71],"introduce":[73],"temporal":[74],"context":[75],"within":[76],"network.":[78],"This":[79],"allows":[80],"evaluate":[85],"continuous":[86],"actions":[88,94],"based":[89],"on":[90,169],"states":[92],"addition":[96],"current":[98],"states.":[99],"Moreover,":[100],"slow":[101],"caused":[106],"by":[107,113],"its":[108],"is":[111,151,175],"addressed":[112],"utilising":[114],"another":[115],"neural":[116,125],"network":[117,126,162,165],"approximate":[119],"vehicle":[121],"dynamics.":[122],"Using":[123],"proxy":[129,164],"simulator":[132],"significant":[134],"benefit":[135],"it":[139],"reduces":[140],"requirement":[142],"query":[147],"simulation":[149],"(which":[150],"major":[153],"bottleneck)":[154],"both":[159],"can":[166],"be":[167],"deployed":[168],"same":[171],"GPU,":[172],"speed":[174],"considerably":[176],"improved.":[177],"Simulation":[178],"results":[179],"testing":[181],"IPG":[183],"CarMaker":[184],"show":[185],"effectiveness":[187],"our":[189],"A2C":[191,196],"algorithm,":[192],"compared":[193],"without":[197],"layers.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}