{"id":"https://openalex.org/W3024219488","doi":"https://doi.org/10.1109/iv47402.2020.9304593","title":"From Simulation to Real World Maneuver Execution using Deep Reinforcement Learning","display_name":"From Simulation to Real World Maneuver Execution using Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-10-19","ids":{"openalex":"https://openalex.org/W3024219488","doi":"https://doi.org/10.1109/iv47402.2020.9304593","mag":"3024219488"},"language":"en","primary_location":{"id":"doi:10.1109/iv47402.2020.9304593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv47402.2020.9304593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.07023","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Alessandro Paolo Capasso","orcid":null},"institutions":[{"id":"https://openalex.org/I124601658","display_name":"University of Parma","ror":"https://ror.org/02k7wn190","country_code":"IT","type":"education","lineage":["https://openalex.org/I124601658"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Paolo Capasso","raw_affiliation_strings":["University of Parma - VisLab, Parma, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Parma - VisLab, Parma, Italy","institution_ids":["https://openalex.org/I124601658"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Giulio Bacchiani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giulio Bacchiani","raw_affiliation_strings":["VisLab srl, an Am-barella Inc. company, Parma, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VisLab srl, an Am-barella Inc. company, Parma, Italy","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Alberto Broggi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alberto Broggi","raw_affiliation_strings":["VisLab srl, an Am-barella Inc. company, Parma, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VisLab srl, an Am-barella Inc. company, Parma, Italy","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6771,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.76174251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1570","last_page":"1575"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9980999827384949,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8208000063896179},{"id":"https://openalex.org/keywords/roundabout","display_name":"Roundabout","score":0.6865000128746033},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5967000126838684},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5371999740600586},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.48980000615119934},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4699000120162964},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.3384000062942505},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.32899999618530273}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8208000063896179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6912000179290771},{"id":"https://openalex.org/C109157449","wikidata":"https://www.wikidata.org/wiki/Q7371221","display_name":"Roundabout","level":2,"score":0.6865000128746033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6276999711990356},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5967000126838684},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5371999740600586},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4699000120162964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39320001006126404},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.3018999993801117},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.28220000863075256},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iv47402.2020.9304593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv47402.2020.9304593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.07023","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.07023","pdf_url":"https://arxiv.org/pdf/2005.07023","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.07023","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.07023","pdf_url":"https://arxiv.org/pdf/2005.07023","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1978161072","https://openalex.org/W2062868933","https://openalex.org/W2096719600","https://openalex.org/W2145339207","https://openalex.org/W2766447205","https://openalex.org/W2789184669","https://openalex.org/W2891315523","https://openalex.org/W2964047820","https://openalex.org/W2964248288","https://openalex.org/W2968095971","https://openalex.org/W2998004995","https://openalex.org/W3100366369","https://openalex.org/W6636881020","https://openalex.org/W6674966245","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6744128076","https://openalex.org/W6745935785","https://openalex.org/W6746316224","https://openalex.org/W6746495208","https://openalex.org/W6750629867","https://openalex.org/W6756103505","https://openalex.org/W6756840741","https://openalex.org/W6760279721"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"has":[3],"proved":[4],"to":[5,8,36],"be":[6],"able":[7],"solve":[9],"many":[10],"control":[11],"tasks":[12],"in":[13,29,65,89,101],"different":[14,102],"fields,":[15],"but":[16],"the":[17,37,49,66,96,99,111,122,126],"behavior":[18,97],"of":[19,39,51,98,125],"these":[20,63],"systems":[21],"is":[22,33],"not":[23],"always":[24],"as":[25],"expected":[26],"when":[27],"deployed":[28],"real-world":[30,45,116,132],"scenarios.":[31,103,133],"This":[32],"mainly":[34],"due":[35],"lack":[38],"domain":[40],"adaptation":[41],"between":[42,53,113],"simulated":[43,114],"and":[44,55,115,131],"data":[46,117],"together":[47],"with":[48],"absence":[50],"distinction":[52],"train":[54],"test":[56],"datasets.":[57],"In":[58,79],"this":[59,120],"work,":[60],"we":[61,81,105],"investigate":[62],"problems":[64],"autonomous":[67],"driving":[68],"field,":[69],"especially":[70],"for":[71,76],"a":[72,83],"maneuver":[73],"planning":[74],"module":[75],"roundabout":[77],"insertions.":[78],"particular,":[80],"present":[82],"system":[84,127],"based":[85],"on":[86,129],"multiple":[87],"environments":[88],"which":[90],"agents":[91],"are":[92],"trained":[93],"simultaneously,":[94],"evaluating":[95],"model":[100],"Finally,":[104],"analyze":[106],"techniques":[107],"aimed":[108],"at":[109],"reducing":[110],"gap":[112],"showing":[118],"that":[119],"increased":[121],"generalization":[123],"capabilities":[124],"both":[128],"unseen":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2020-05-21T00:00:00"}