{"id":"https://openalex.org/W4285813110","doi":"https://doi.org/10.1109/iv51971.2022.9827367","title":"Solving the Deadlock Problem with Deep Reinforcement Learning Using Information from Multiple Vehicles","display_name":"Solving the Deadlock Problem with Deep Reinforcement Learning Using Information from Multiple Vehicles","publication_year":2022,"publication_date":"2022-06-05","ids":{"openalex":"https://openalex.org/W4285813110","doi":"https://doi.org/10.1109/iv51971.2022.9827367"},"language":"en","primary_location":{"id":"doi:10.1109/iv51971.2022.9827367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv51971.2022.9827367","pdf_url":null,"source":{"id":"https://openalex.org/S4363605370","display_name":"2022 IEEE Intelligent Vehicles Symposium (IV)","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 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102486779","display_name":"Tsuyoshi Goto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsuyoshi Goto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011232754","display_name":"Hidenori Itaya","orcid":"https://orcid.org/0000-0002-4647-2586"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hidenori Itaya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089532441","display_name":"Tsubasa Hirakawa","orcid":"https://orcid.org/0000-0003-3851-5221"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsubasa Hirakawa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062009349","display_name":"Takayoshi Yamashita","orcid":"https://orcid.org/0000-0003-2631-9856"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takayoshi Yamashita","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5011810133","display_name":"Hironobu Fujiyoshi","orcid":"https://orcid.org/0000-0001-7391-4725"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hironobu Fujiyoshi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1026","last_page":"1032"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9941999912261963,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9812999963760376,"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/deadlock","display_name":"Deadlock","score":0.8236375451087952},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8137561082839966},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7602800726890564},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6295444369316101},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.6016390323638916},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.596431314945221},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5106239914894104},{"id":"https://openalex.org/keywords/deadlock-prevention-algorithms","display_name":"Deadlock prevention algorithms","score":0.494625061750412},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4867284595966339},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48102790117263794},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.35092997550964355},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3337250351905823},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.2034304440021515},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11070537567138672},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07071343064308167}],"concepts":[{"id":"https://openalex.org/C159023740","wikidata":"https://www.wikidata.org/wiki/Q623276","display_name":"Deadlock","level":2,"score":0.8236375451087952},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8137561082839966},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7602800726890564},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6295444369316101},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.6016390323638916},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.596431314945221},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5106239914894104},{"id":"https://openalex.org/C113429609","wikidata":"https://www.wikidata.org/wiki/Q4060699","display_name":"Deadlock prevention algorithms","level":3,"score":0.494625061750412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4867284595966339},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48102790117263794},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35092997550964355},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3337250351905823},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2034304440021515},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11070537567138672},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07071343064308167},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iv51971.2022.9827367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv51971.2022.9827367","pdf_url":null,"source":{"id":"https://openalex.org/S4363605370","display_name":"2022 IEEE Intelligent Vehicles Symposium (IV)","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 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W2124394479","https://openalex.org/W2145339207","https://openalex.org/W2156737235","https://openalex.org/W2195446438","https://openalex.org/W2257979135","https://openalex.org/W2575705757","https://openalex.org/W2736601468","https://openalex.org/W2761873684","https://openalex.org/W2904907999","https://openalex.org/W2914351253","https://openalex.org/W2964043796","https://openalex.org/W2964338167","https://openalex.org/W2970517549","https://openalex.org/W2995937146","https://openalex.org/W3106247689","https://openalex.org/W3204551200","https://openalex.org/W6638018090","https://openalex.org/W6683195989","https://openalex.org/W6687590523","https://openalex.org/W6692846177","https://openalex.org/W6713411898","https://openalex.org/W6741002519","https://openalex.org/W6758763022","https://openalex.org/W6768539364","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2379911191","https://openalex.org/W2380314807","https://openalex.org/W3140720071","https://openalex.org/W1776252073","https://openalex.org/W2589418455","https://openalex.org/W4252845830","https://openalex.org/W2993626413","https://openalex.org/W2388652903","https://openalex.org/W4313533643","https://openalex.org/W2163554925"],"abstract_inverted_index":{"Autonomous":[0],"driving":[1,147],"system":[2],"controls":[3],"a":[4,15,23,80,99,109,117,142,150],"vehicle":[5,16],"using":[6],"path":[7,34],"planning.":[8],"Path":[9],"planning":[10,35],"for":[11,41,112],"automated":[12],"vehicles":[13,47],"observes":[14],"and":[17,21,103,130],"the":[18,26,32,65,91,120,127,131,134,158,163],"surrounding":[19],"information":[20],"plans":[22],"trajectory":[24,40],"on":[25],"basis":[27],"of":[28,98,133,145],"rule-based":[29,33],"approach.":[30],"However,":[31],"cannot":[36],"generate":[37,87,167],"an":[38,52],"appropriate":[39,88],"complex":[42,58],"scenes,":[43],"such":[44],"as":[45],"two":[46],"passes":[48],"each":[49],"other":[50],"at":[51,90,119],"intersection":[53],"without":[54],"traffic":[55],"lights.":[56],"Such":[57],"scene":[59],"is":[60,68],"called":[61],"deadlock.":[62],"For":[63,136],"avoiding":[64,169],"deadlock,":[66],"it":[67],"very":[69],"costly":[70],"to":[71,86],"create":[72],"rules":[73],"manually.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78,107,124,140],"propose":[79],"multi-agent":[81],"deep":[82],"reinforcement":[83],"learning":[84],"method":[85,96,165],"trajectories":[89,168],"deadlock":[92,152],"scenes.":[93],"The":[94,154],"proposed":[95,164],"consists":[97],"single":[100],"feature":[101],"extractor":[102],"actor-critic":[104],"branches.":[105],"Moreover,":[106],"introduce":[108],"mask-attention":[110],"mechanism":[111],"visual":[113],"explanation.":[114],"By":[115],"taking":[116],"look":[118],"obtained":[121,128],"attention":[122],"maps,":[123],"can":[125,166],"confirm":[126],"agent":[129],"reason":[132],"behavior.":[135],"evaluating":[137],"our":[138],"method,":[139],"develop":[141],"simulator":[143],"environment":[144,160],"autonomous":[146],"that":[148,162],"produces":[149],"certain":[151],"scene.":[153],"experimental":[155],"results":[156],"with":[157],"developed":[159],"show":[161],"deadlocks.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}