{"id":"https://openalex.org/W2942497147","doi":"https://doi.org/10.1109/besc.2018.8697262","title":"Ship Collision Avoidance Using Constrained Deep Reinforcement Learning","display_name":"Ship Collision Avoidance Using Constrained Deep Reinforcement Learning","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2942497147","doi":"https://doi.org/10.1109/besc.2018.8697262","mag":"2942497147"},"language":"en","primary_location":{"id":"doi:10.1109/besc.2018.8697262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/besc.2018.8697262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 5th International Conference on Behavioral, Economic, and Socio-Cultural Computing (BESC)","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/A5100422124","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0003-0392-8210"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["Hubei Key Laboratory of Transportation, Wuhan University of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Transportation, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112719601","display_name":"Xiao Wang","orcid":"https://orcid.org/0000-0002-0008-0659"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Wang","raw_affiliation_strings":["School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088177440","display_name":"Kezhong Liu","orcid":"https://orcid.org/0000-0002-1085-7556"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kezhong Liu","raw_affiliation_strings":["Hubei Key Laboratory of Transportation, Wuhan University of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Transportation, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035966314","display_name":"Xiaolie Wu","orcid":"https://orcid.org/0000-0003-1534-7552"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolie Wu","raw_affiliation_strings":["School of Navigation, Wuhan University of Technology Wuhan 434070, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Navigation, Wuhan University of Technology Wuhan 434070, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039388570","display_name":"Tianyou Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyou Lu","raw_affiliation_strings":["School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010830153","display_name":"Zhaohui Chao","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhaohui","raw_affiliation_strings":["School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I196699116"],"apc_list":null,"apc_paid":null,"fwci":0.4883,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.69527616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"abs 1604 7316","issue":null,"first_page":"115","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11622","display_name":"Maritime Navigation and Safety","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/T11622","display_name":"Maritime Navigation and Safety","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9857000112533569,"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":0.9815000295639038,"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":0.9363017082214355},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.8661530017852783},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7070391774177551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.532551646232605},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5015826225280762},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.48440414667129517},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.472445547580719},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4590602517127991},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.44659772515296936},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.17885208129882812},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07654589414596558},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07577008008956909}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9363017082214355},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.8661530017852783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7070391774177551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.532551646232605},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5015826225280762},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.48440414667129517},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.472445547580719},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4590602517127991},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.44659772515296936},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.17885208129882812},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07654589414596558},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07577008008956909},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/besc.2018.8697262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/besc.2018.8697262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 5th International Conference on Behavioral, Economic, and Socio-Cultural Computing (BESC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2121615981","https://openalex.org/W2139603520","https://openalex.org/W2145339207","https://openalex.org/W2173248099","https://openalex.org/W2259075191","https://openalex.org/W2342840547","https://openalex.org/W2484617215","https://openalex.org/W2547705816","https://openalex.org/W2548693551","https://openalex.org/W2583993537","https://openalex.org/W2604173613","https://openalex.org/W2604847142","https://openalex.org/W2606508169","https://openalex.org/W2733160965","https://openalex.org/W2740828027","https://openalex.org/W2962977206","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W3100944043","https://openalex.org/W6678317597","https://openalex.org/W6684921986","https://openalex.org/W6692580597","https://openalex.org/W6692846177","https://openalex.org/W6704559304","https://openalex.org/W6735738130","https://openalex.org/W6735993925","https://openalex.org/W6741471465"],"related_works":["https://openalex.org/W2889566344","https://openalex.org/W4317634134","https://openalex.org/W2981729160","https://openalex.org/W4310743282","https://openalex.org/W2743212448","https://openalex.org/W1819938260","https://openalex.org/W2340892746","https://openalex.org/W2742483371","https://openalex.org/W3005999311","https://openalex.org/W2029648619"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"the":[3,53,81,105,119],"rapid":[4],"development":[5],"of":[6,56,86],"mobile":[7,23],"technology":[8,24],"and":[9,18,22,41,73,84,102,121,124,138],"application":[10],"platforms":[11],"has":[12,45],"provided":[13],"better":[14],"services":[15],"for":[16],"life":[17],"work.":[19],"Artificial":[20],"intelligence":[21,34],"have":[25],"made":[26],"traffic":[27],"ever":[28],"more":[29,136],"convenient.":[30],"As":[31],"an":[32],"artificial":[33],"method":[35],"that":[36,78,133],"intersects":[37],"with":[38,99],"multiple":[39],"disciplines":[40],"fields,":[42],"reinforcement":[43,87,93],"learning":[44,94],"been":[46],"proved":[47],"to":[48,95,117],"be":[49],"highly":[50],"effective":[51],"in":[52,64,140],"automatic":[54],"driving":[55],"vehicles.":[57],"However,":[58],"there":[59],"are":[60],"still":[61],"many":[62],"difficulties":[63],"ship":[65,96],"collision":[66,97],"avoidance,":[67],"because":[68],"it":[69],"involves":[70],"continuous":[71,142],"actions":[72,83,103],"complicated":[74],"regulations.":[75,130],"We":[76],"find":[77],"by":[79],"constraining":[80],"states,":[82],"regulation":[85],"learning,":[88],"we":[89,109],"can":[90],"well":[91],"apply":[92],"avoidance":[98],"vast":[100],"states":[101],"at":[104],"same":[106],"time.":[107],"Hence,":[108],"propose":[110],"Constrained-DQN(Deep":[111],"Q":[112],"Network),":[113],"which":[114],"is":[115,135],"used":[116],"limit":[118],"state":[120],"action":[122],"set,":[123],"separate":[125],"reward":[126],"value":[127],"via":[128],"different":[129],"Experiments":[131],"show":[132],"Constrained-DQN":[134],"stable":[137],"adaptive":[139],"handling":[141],"space":[143],"than":[144],"traditional":[145],"path":[146],"planning":[147],"algorithms.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}