{"id":"https://openalex.org/W2991126425","doi":"https://doi.org/10.1109/itsc.2019.8917002","title":"Lane-Merging Using Policy-based Reinforcement Learning and Post-Optimization","display_name":"Lane-Merging Using Policy-based Reinforcement Learning and Post-Optimization","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2991126425","doi":"https://doi.org/10.1109/itsc.2019.8917002","mag":"2991126425"},"language":"en","primary_location":{"id":"doi:10.1109/itsc.2019.8917002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc.2019.8917002","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.03168","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Patrick Hart","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I4210134795","display_name":"Fortiss","ror":"https://ror.org/042x1tp92","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210134795"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Patrick Hart","raw_affiliation_strings":["fortiss GmbH, An-Institut Technische Universit\u00e4t M\u00fcnchen, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"fortiss GmbH, An-Institut Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I4210134795","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Leonard Rychly","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I4210134795","display_name":"Fortiss","ror":"https://ror.org/042x1tp92","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210134795"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Leonard Rychly","raw_affiliation_strings":["fortiss GmbH, An-Institut Technische Universit\u00e4t M\u00fcnchen, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"fortiss GmbH, An-Institut Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I4210134795","https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":null,"display_name":"Alois Knoll","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alois Knoll","raw_affiliation_strings":["Chair of Robotics, Artificial Intelligence and Real-time Systems, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Robotics, Artificial Intelligence and Real-time Systems, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210134795","https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":1.4003,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.8322203,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3176","last_page":"3181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9986000061035156,"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":0.9986000061035156,"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":0.998199999332428,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9905999898910522,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.878600001335144},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5873000025749207},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.49570000171661377},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4519999921321869},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.38089999556541443},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.3553999960422516}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.878600001335144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6956999897956848},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5873000025749207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5584999918937683},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.49570000171661377},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3772999942302704},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.2946000099182129},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/itsc.2019.8917002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc.2019.8917002","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:arXiv.org:2003.03168","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.03168","pdf_url":"https://arxiv.org/pdf/2003.03168","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"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1525640","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1525640","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.03168","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.03168","pdf_url":"https://arxiv.org/pdf/2003.03168","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":17,"referenced_works":["https://openalex.org/W1568248713","https://openalex.org/W1888497568","https://openalex.org/W1965455100","https://openalex.org/W2530849036","https://openalex.org/W2897066388","https://openalex.org/W2904263972","https://openalex.org/W3100789280","https://openalex.org/W6638018090","https://openalex.org/W6675999342","https://openalex.org/W6678545291","https://openalex.org/W6684921986","https://openalex.org/W6734523390","https://openalex.org/W6740222838","https://openalex.org/W6741002519","https://openalex.org/W6746404916","https://openalex.org/W6747473740","https://openalex.org/W6747924173"],"related_works":[],"abstract_inverted_index":{"Many":[0],"current":[1],"behavior":[2],"generation":[3],"methods":[4],"struggle":[5],"to":[6,38,54,84],"handle":[7],"real-world":[8],"traffic":[9],"situations":[10],"as":[11,33,125],"they":[12],"do":[13],"not":[14],"scale":[15],"well":[16],"with":[17,51,147],"complexity.":[18],"However,":[19],"behaviors":[20],"can":[21,108,117,133],"be":[22,109,134],"learned":[23],"off-line":[24],"using":[25,144],"data-driven":[26],"approaches.":[27],"Especially,":[28],"reinforcement":[29,49,66,105],"learning":[30,50,67],"is":[31],"promising":[32],"it":[34,107],"implicitly":[35],"learns":[36],"how":[37],"behave":[39],"utilizing":[40],"collected":[41],"experiences.":[42],"In":[43],"this":[44],"work,":[45],"we":[46],"combine":[47],"policy-based":[48,65],"local":[52],"optimization":[53],"foster":[55],"and":[56,73,114,128],"synthesize":[57],"the":[58,61,77,80,97,102,115,129,141],"best":[59],"of":[60,96,151],"two":[62],"methodologies.":[63],"The":[64,121],"algorithm":[68],"provides":[69],"an":[70],"initial":[71],"solution":[72],"guiding":[74],"reference":[75],"for":[76,111,119],"post-optimization.":[78],"Therefore,":[79],"optimizer":[81,116],"only":[82],"has":[83],"compute":[85],"a":[86,126,148],"single":[87],"homotopy":[88],"class,":[89],"e.g.":[90],"drive":[91],"behind":[92],"or":[93],"in":[94,136],"front":[95],"other":[98],"vehicle.":[99],"By":[100],"storing":[101],"state-history":[103],"during":[104],"learning,":[106],"used":[110],"constraint":[112],"checking":[113],"account":[118],"interactions.":[120],"post-optimization":[122],"additionally":[123],"acts":[124],"safety-layer":[127],"novel":[130],"method,":[131],"thus,":[132],"applied":[135],"safety-critical":[137],"applications.":[138],"We":[139],"evaluate":[140],"proposed":[142],"method":[143],"lane-change":[145],"scenarios":[146],"varying":[149],"number":[150],"vehicles.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-12-05T00:00:00"}