{"id":"https://openalex.org/W3094188159","doi":"https://doi.org/10.1109/icra46639.2022.9811618","title":"Deep Surrogate Q-Learning for Autonomous Driving","display_name":"Deep Surrogate Q-Learning for Autonomous Driving","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W3094188159","doi":"https://doi.org/10.1109/icra46639.2022.9811618","mag":"3094188159"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9811618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811618","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","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/A5033350585","display_name":"Gabriel Kalweit","orcid":"https://orcid.org/0000-0003-4581-8810"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maria Kalweit","raw_affiliation_strings":["University of Freiburg,Neurorobotics Lab,Germany","Neurorobotics Lab, University of Freiburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Freiburg,Neurorobotics Lab,Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"Neurorobotics Lab, University of Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033350585","display_name":"Gabriel Kalweit","orcid":"https://orcid.org/0000-0003-4581-8810"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gabriel Kalweit","raw_affiliation_strings":["University of Freiburg,Neurorobotics Lab,Germany","Neurorobotics Lab, University of Freiburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Freiburg,Neurorobotics Lab,Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"Neurorobotics Lab, University of Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027250190","display_name":"Moritz Werling","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145546","display_name":"Baxter (Germany)","ror":"https://ror.org/05jgtkc28","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145546","https://openalex.org/I99484792"]},{"id":"https://openalex.org/I4210156768","display_name":"BMW Group (Germany)","ror":"https://ror.org/044kkbh92","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210156768"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Moritz Werling","raw_affiliation_strings":["BMWGroup,Unterschleissheim,Germany","BMWGroup, Unterschleissheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BMWGroup,Unterschleissheim,Germany","institution_ids":["https://openalex.org/I4210145546","https://openalex.org/I4210156768"]},{"raw_affiliation_string":"BMWGroup, Unterschleissheim, Germany","institution_ids":["https://openalex.org/I4210156768"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038908529","display_name":"Joschka Boedecker","orcid":"https://orcid.org/0000-0002-3486-7345"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]},{"id":"https://openalex.org/I4210098324","display_name":"Bernstein Center for Computational Neuroscience Freiburg","ror":"https://ror.org/010p50m34","country_code":"DE","type":"government","lineage":["https://openalex.org/I4210092532","https://openalex.org/I4210098324"]},{"id":"https://openalex.org/I4210113520","display_name":"Brain (Germany)","ror":"https://ror.org/01gamcy45","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210113520"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Joschka Boedecker","raw_affiliation_strings":["University of Freiburg,Neurorobotics Lab,Germany","BrainLinks-BrainTools, University of Freiburg, Germany","Neurorobotics Lab, University of Freiburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Freiburg,Neurorobotics Lab,Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"BrainLinks-BrainTools, University of Freiburg, Germany","institution_ids":["https://openalex.org/I4210098324","https://openalex.org/I161046081","https://openalex.org/I4210113520"]},{"raw_affiliation_string":"Neurorobotics Lab, University of Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3113,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.46975881,"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":"1578","last_page":"1584"},"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":0.9980999827384949,"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/T12617","display_name":"Energy, Environment, and Transportation Policies","score":0.9745000004768372,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8265615701675415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7396153211593628},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6965641975402832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5652082562446594},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5233128070831299},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5172791481018066},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49277809262275696},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48004090785980225},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.43458643555641174},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.42845243215560913},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.42584165930747986},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3806784749031067},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.12595605850219727},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10476401448249817},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.09074345231056213}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8265615701675415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7396153211593628},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6965641975402832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5652082562446594},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5233128070831299},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5172791481018066},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49277809262275696},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48004090785980225},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.43458643555641174},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.42845243215560913},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.42584165930747986},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3806784749031067},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.12595605850219727},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10476401448249817},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.09074345231056213},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra46639.2022.9811618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811618","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:freidok.uni-freiburg.de:227084","is_oa":false,"landing_page_url":"https://freidok.uni-freiburg.de/data/227084","pdf_url":null,"source":{"id":"https://openalex.org/S4306401057","display_name":"FreiDok plus (Universit\u00e4tsbibliothek Freiburg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I161046081","host_organization_name":"University of Freiburg","host_organization_lineage":["https://openalex.org/I161046081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2022 IEEE International Conference on Robotics and Automation (ICRA). , 2022. - 1578-1584, ISBN: 978-1-7281-9681-7","raw_type":"article_in_conference_proceedings"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1522301498","https://openalex.org/W1869778509","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2784064751","https://openalex.org/W2787196707","https://openalex.org/W2787938642","https://openalex.org/W2890375627","https://openalex.org/W2896066033","https://openalex.org/W2896642734","https://openalex.org/W2904263972","https://openalex.org/W2907953482","https://openalex.org/W2963430173","https://openalex.org/W2963923407","https://openalex.org/W2964007901","https://openalex.org/W2964121744","https://openalex.org/W2964161785","https://openalex.org/W3001665214","https://openalex.org/W3085121432","https://openalex.org/W3091528360","https://openalex.org/W3100247915","https://openalex.org/W3100349024","https://openalex.org/W3102797050","https://openalex.org/W4287692910","https://openalex.org/W6631190155","https://openalex.org/W6639086533","https://openalex.org/W6682849425","https://openalex.org/W6687681856","https://openalex.org/W6744580074","https://openalex.org/W6747574793","https://openalex.org/W6748571143","https://openalex.org/W6748839928","https://openalex.org/W6773165671","https://openalex.org/W6781315541","https://openalex.org/W6783084392"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"Open":[0],"challenges":[1],"for":[2,28,134],"deep":[3,124],"reinforcement":[4],"learning":[5,25],"systems":[6],"are":[7],"their":[8,14],"adaptivity":[9],"to":[10,88,131],"changing":[11],"environments":[12],"and":[13,19,106,153],"efficiency":[15],"w.r.t.":[16],"computational":[17],"resources":[18],"data.":[20],"In":[21,54],"the":[22,31,51,55,62,74,90,103,108,129,148,160],"application":[23],"of":[24,33,47,128,138],"lane-change":[26],"behavior":[27],"autonomous":[29],"driving,":[30],"number":[32,137],"required":[34,109],"transitions":[35],"imposes":[36],"a":[37,121,135],"bottleneck,":[38],"since":[39],"test":[40],"drivers":[41,85],"cannot":[42],"perform":[43],"an":[44,116],"arbitrary":[45],"amount":[46],"lane":[48],"changes":[49],"in":[50,73,140,147],"real":[52,161],"world.":[53],"off-policy":[56],"setting,":[57],"additional":[58],"information":[59],"on":[60,120,159],"solving":[61],"task":[63],"can":[64],"be":[65],"gained":[66],"by":[67],"observing":[68],"actions":[69],"from":[70],"others.":[71],"While":[72],"classical":[75],"RL":[76],"setup":[77],"this":[78],"knowledge":[79],"remains":[80],"unused,":[81],"we":[82],"use":[83],"other":[84],"as":[86],"surrogates":[87],"learn":[89,154],"agent's":[91],"value":[92],"function":[93],"more":[94],"efficiently.":[95],"We":[96,113,143],"propose":[97,115],"Surrogate":[98],"Q-learning":[99],"that":[100],"deals":[101],"with":[102],"aforementioned":[104],"problems":[105],"reduces":[107],"driving":[110,157],"time":[111],"drastically.":[112],"further":[114],"efficient":[117],"implementation":[118],"based":[119],"permutation":[122],"equivariant":[123],"neural":[125],"network":[126],"architecture":[127],"Q-function":[130],"estimate":[132],"action-values":[133],"variable":[136],"vehicles":[139],"sensor":[141],"range.":[142],"evaluate":[144],"our":[145],"method":[146],"open":[149],"traffic":[150],"simulator":[151],"SUMO":[152],"well":[155],"performing":[156],"policies":[158],"highD":[162],"dataset.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}