{"id":"https://openalex.org/W3209213339","doi":"https://doi.org/10.1109/tits.2021.3115235","title":"Policy-Based Reinforcement Learning for Training Autonomous Driving Agents in Urban Areas With Affordance Learning","display_name":"Policy-Based Reinforcement Learning for Training Autonomous Driving Agents in Urban Areas With Affordance Learning","publication_year":2021,"publication_date":"2021-11-02","ids":{"openalex":"https://openalex.org/W3209213339","doi":"https://doi.org/10.1109/tits.2021.3115235","mag":"3209213339"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2021.3115235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2021.3115235","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Transportation Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Policy-Based_Reinforcement_Learning_for_Training_Autonomous_Driving_Agents_in_Urban_Areas_With_Affordance_Learning/20639289","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":true,"raw_author_name":"Marwa Ahmed","raw_affiliation_strings":["Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Waurn Ponds, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Waurn Ponds, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088397310","display_name":"Ahmed Abobakr","orcid":"https://orcid.org/0000-0002-6664-2335"},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Ahmed Abobakr","raw_affiliation_strings":["Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Egypt"],"affiliations":[{"raw_affiliation_string":"Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Egypt","institution_ids":["https://openalex.org/I145487455"]}]},{"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, Waurn Ponds, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Waurn Ponds, VIC, 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, Waurn Ponds, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Waurn Ponds, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101463981"],"corresponding_institution_ids":["https://openalex.org/I149704539"],"apc_list":null,"apc_paid":null,"fwci":1.3944,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.80734229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"23","issue":"8","first_page":"12562","last_page":"12571"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9945999979972839,"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/T10524","display_name":"Traffic control and management","score":0.9940000176429749,"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/affordance","display_name":"Affordance","score":0.9497277140617371},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7465661764144897},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6794716119766235},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6491125822067261},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6236934065818787},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5490914583206177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5429679155349731},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48892346024513245},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4715965688228607},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.43669945001602173},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4250423014163971},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32887500524520874},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20683959126472473},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10187968611717224}],"concepts":[{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.9497277140617371},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7465661764144897},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6794716119766235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6491125822067261},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6236934065818787},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5490914583206177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5429679155349731},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48892346024513245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4715965688228607},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.43669945001602173},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4250423014163971},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32887500524520874},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20683959126472473},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10187968611717224},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tits.2021.3115235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2021.3115235","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Transportation Systems","raw_type":"journal-article"},{"id":"pmh:oai:figshare.com:article/20639289","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Policy-Based_Reinforcement_Learning_for_Training_Autonomous_Driving_Agents_in_Urban_Areas_With_Affordance_Learning/20639289","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":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/20639289","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Policy-Based_Reinforcement_Learning_for_Training_Autonomous_Driving_Agents_in_Urban_Areas_With_Affordance_Learning/20639289","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":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1544016679","https://openalex.org/W1563795667","https://openalex.org/W1947481528","https://openalex.org/W1952057695","https://openalex.org/W1969483458","https://openalex.org/W1986014385","https://openalex.org/W2032924574","https://openalex.org/W2102104695","https://openalex.org/W2108598243","https://openalex.org/W2119112357","https://openalex.org/W2192586580","https://openalex.org/W2194775991","https://openalex.org/W2479866714","https://openalex.org/W2563338958","https://openalex.org/W2570343428","https://openalex.org/W2582616844","https://openalex.org/W2603203130","https://openalex.org/W2727840223","https://openalex.org/W2752236613","https://openalex.org/W2761873684","https://openalex.org/W2777795072","https://openalex.org/W2885060261","https://openalex.org/W2893501195","https://openalex.org/W2896066033","https://openalex.org/W2945935438","https://openalex.org/W2962887844","https://openalex.org/W2962894046","https://openalex.org/W2963322416","https://openalex.org/W2963864421","https://openalex.org/W2968806961","https://openalex.org/W2996896271","https://openalex.org/W3009593063","https://openalex.org/W3010904226","https://openalex.org/W3034445502","https://openalex.org/W3040318838","https://openalex.org/W3100366369","https://openalex.org/W3102270594","https://openalex.org/W4210543899","https://openalex.org/W4246193833","https://openalex.org/W4295719664","https://openalex.org/W4299805595","https://openalex.org/W6631190155","https://openalex.org/W6633802082","https://openalex.org/W6684921986","https://openalex.org/W6731187701","https://openalex.org/W6745935785","https://openalex.org/W6752781648","https://openalex.org/W6755170904","https://openalex.org/W6770856692","https://openalex.org/W6772033386"],"related_works":["https://openalex.org/W1972718289","https://openalex.org/W1791514435","https://openalex.org/W2346831895","https://openalex.org/W2248634132","https://openalex.org/W2295809616","https://openalex.org/W3049116993","https://openalex.org/W2070708245","https://openalex.org/W1541884709","https://openalex.org/W2053445884","https://openalex.org/W2101105382"],"abstract_inverted_index":{"Learning":[0],"to":[1,41,76,111,175],"drive":[2],"in":[3,21,98,145,153,192,196],"urban":[4,45,147],"areas":[5],"is":[6,74,133],"an":[7,49,146],"open":[8],"challenge":[9],"for":[10,47],"autonomous":[11],"vehicles":[12],"(AVs),":[13],"as":[14],"complex":[15],"decision":[16],"making":[17],"requirements":[18],"are":[19],"needed":[20],"multi-task":[22],"co-ordinations":[23],"environments.":[24],"In":[25,207],"this":[26],"paper,":[27],"we":[28],"propose":[29],"a":[30,34,54,70,89,112,117,129,154,193],"hybrid":[31],"framework":[32],"with":[33,53,109,177,202,212,231],"new":[35],"perception":[36,103,126],"model":[37,122,210],"involving":[38],"affordance":[39,83],"learning":[40,72],"simplify":[42],"the":[43,58,78,96,99,125,137,141,151,209],"surrounding":[44,93],"scenes":[46,94,214],"training":[48],"AV":[50,97,199],"agent,":[51],"along":[52],"planned":[55],"trajectory":[56],"and":[57,149,164,181,228,234],"associated":[59],"driving":[60,143,200],"measurements.":[61],"Our":[62,184],"proposed":[63,138,170,185],"solution":[64,139,171,186],"encompasses":[65],"two":[66],"main":[67],"aspects.":[68],"Firstly,":[69],"supervised":[71],"network":[73],"used":[75],"map":[77],"input":[79],"sensory":[80],"data":[81],"into":[82,128],"predictions.":[84],"The":[85,162],"predicted":[86],"affordances":[87],"provide":[88],"low-dimensional":[90],"representation":[91],"of":[92,95,101,131,205],"form":[100],"key":[102],"indicators,":[104],"e.g.,":[105],"true":[106],"or":[107],"false":[108],"respect":[110],"traffic":[113,179,233],"light":[114],"signal.":[115],"Secondly,":[116],"deep":[118],"deterministic":[119],"policy":[120],"gradient":[121],"that":[123,168],"maps":[124],"information":[127],"series":[130],"actions":[132],"devised.":[134],"We":[135],"evaluate":[136,150],"using":[140],"CARLA":[142],"simulator":[144],"town":[148,157],"performance":[152],"new,":[155],"unseen":[156],"under":[158],"different":[159,178,203],"weather":[160,235],"conditions.":[161,183,236],"quantitative":[163],"qualitative":[165],"results":[166,218],"indicate":[167],"our":[169],"can":[172],"generalize":[173],"well":[174],"cope":[176],"solutions":[180],"environmental":[182],"also":[187],"outperforms":[188],"other":[189],"baseline":[190],"methods":[191],"comparative":[194],"study":[195],"handling":[197],"various":[198],"tasks":[201],"levels":[204],"difficulty.":[206],"addition,":[208],"trained":[211],"simulated":[213],"yields":[215],"promising":[216],"prediction":[217],"when":[219],"testing":[220],"on":[221,225],"recorded":[222],"video":[223],"streams":[224],"real-world":[226],"highway":[227],"suburb":[229],"environments":[230],"varying":[232]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}