{"id":"https://openalex.org/W3010600586","doi":"https://doi.org/10.1145/3374587.3374599","title":"A Reinforcement Learning-based Decentralized Method of Avoiding Multi-UAV Collision in 3-D Airspace","display_name":"A Reinforcement Learning-based Decentralized Method of Avoiding Multi-UAV Collision in 3-D Airspace","publication_year":2019,"publication_date":"2019-12-06","ids":{"openalex":"https://openalex.org/W3010600586","doi":"https://doi.org/10.1145/3374587.3374599","mag":"3010600586"},"language":"en","primary_location":{"id":"doi:10.1145/3374587.3374599","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3374587.3374599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Computer Science and Artificial Intelligence","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/A5113747188","display_name":"Jian Sun","orcid":"https://orcid.org/0000-0002-1111-7891"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jian Sun","raw_affiliation_strings":["Bell Honors School, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Bell Honors School, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048600272","display_name":"Yingzhou Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingzhou Zhang","raw_affiliation_strings":["College of Computer, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113747188"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.3537,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65886324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"82"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.8419876098632812},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.8212335109710693},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7082828879356384},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.5710538029670715},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5708343982696533},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5555845499038696},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5217496156692505},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.48603159189224243},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.4367881417274475},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.42591604590415955},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.41473495960235596},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.32249557971954346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24479824304580688},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.1756230890750885}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8419876098632812},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.8212335109710693},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7082828879356384},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.5710538029670715},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5708343982696533},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5555845499038696},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5217496156692505},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.48603159189224243},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.4367881417274475},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.42591604590415955},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.41473495960235596},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.32249557971954346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24479824304580688},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.1756230890750885},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3374587.3374599","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3374587.3374599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Computer Science and Artificial Intelligence","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":15,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1771410628","https://openalex.org/W1958637628","https://openalex.org/W2066520471","https://openalex.org/W2147967553","https://openalex.org/W2248010213","https://openalex.org/W2462226675","https://openalex.org/W2485734267","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2753049553","https://openalex.org/W2766376871","https://openalex.org/W2785624097","https://openalex.org/W2807781934","https://openalex.org/W2963821308"],"related_works":["https://openalex.org/W2930076404","https://openalex.org/W4253519380","https://openalex.org/W2071957557","https://openalex.org/W2596413128","https://openalex.org/W4391249562","https://openalex.org/W2356867392","https://openalex.org/W2913749762","https://openalex.org/W2321940404","https://openalex.org/W2782776446","https://openalex.org/W3043170174"],"abstract_inverted_index":{"Recently,":[0],"large-scale":[1,168],"multi-UAV":[2,26,169],"collaboration":[3],"system":[4],"have":[5],"been":[6],"proposed":[7],"for":[8,24,136,166],"mobile":[9],"sensor":[10],"network":[11],"applications":[12],"and":[13,64,67,80,87,149],"the":[14,18,21,47,58,75,84,88,99,154],"collision":[15,32,76],"avoidance":[16,33],"becomes":[17],"core":[19],"of":[20,35,78,90,115],"scalable":[22],"control":[23],"any":[25],"system.":[27],"We":[28,56],"present":[29],"a":[30,52,69,112,127,137,151,167],"decentralized":[31],"mechanism":[34],"cooperative":[36],"unmanned":[37],"aerial":[38],"vehicles":[39],"(UAVs)":[40],"in":[41,145],"three-dimensional":[42],"airspace,":[43],"which":[44,110],"directly":[45],"maps":[46],"observed":[48],"environment":[49],"information":[50],"to":[51,73,119,132,162],"UAV's":[53],"steer":[54],"commands.":[55],"solve":[57],"problem":[59],"on":[60,98],"continuous":[61],"state":[62],"space":[63,66],"action":[65],"design":[68],"multi-module":[70],"reward":[71],"function":[72],"decrease":[74],"rate":[77],"UAV-UAV":[79],"UAV-obstacle,":[81],"deviation":[82],"from":[83],"planned":[85],"trajectory":[86],"cost":[89],"turning":[91],"angular":[92],"velocity.":[93],"Our":[94],"method":[95,144,159],"is":[96,111,160],"based":[97],"Distributed":[100],"Proximal":[101],"Policy":[102],"Optimization":[103],"(DPPO)":[104],"algorithm":[105,118],"with":[106],"asynchronous":[107],"training":[108,130],"framework,":[109],"policy":[113,165],"gradient":[114],"Reinforcement":[116],"Learning":[117],"learn":[120],"an":[121],"optimal":[122],"policy.":[123],"Subsequently,":[124],"we":[125],"propose":[126],"multi-scenario":[128],"multi-stage":[129],"process":[131],"our":[133,143,158],"experiment":[134],"as":[135],"good":[138],"convergence":[139],"solution.":[140],"After":[141],"testing":[142],"non-stationary":[146],"stochastic":[147],"environments":[148],"conducting":[150],"contrast":[152],"experiment,":[153],"result":[155],"shows":[156],"that":[157],"able":[161],"find":[163],"collision-free":[164],"swarm.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}