{"id":"https://openalex.org/W4285119242","doi":"https://doi.org/10.1109/tvt.2022.3184043","title":"Oracle-Guided Deep Reinforcement Learning for Large-Scale Multi-UAVs Flocking and Navigation","display_name":"Oracle-Guided Deep Reinforcement Learning for Large-Scale Multi-UAVs Flocking and Navigation","publication_year":2022,"publication_date":"2022-06-20","ids":{"openalex":"https://openalex.org/W4285119242","doi":"https://doi.org/10.1109/tvt.2022.3184043"},"language":"en","primary_location":{"id":"doi:10.1109/tvt.2022.3184043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvt.2022.3184043","pdf_url":null,"source":{"id":"https://openalex.org/S10936095","display_name":"IEEE Transactions on Vehicular Technology","issn_l":"0018-9545","issn":["0018-9545","1939-9359"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Vehicular Technology","raw_type":"journal-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/A5066352851","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-9215-5530"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9215-5530","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456470","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0001-5444-748X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5444-748X","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100649670","display_name":"Junfeng Wu","orcid":"https://orcid.org/0000-0002-9418-4562"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Wu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055923466","display_name":"Xianping Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianping Tao","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034214957","display_name":"Haijun Wu","orcid":"https://orcid.org/0000-0003-1787-5973"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijun Wu","raw_affiliation_strings":["National Experimental Teaching Demonstration Center of Computer Science Technology and Software Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Experimental Teaching Demonstration Center of Computer Science Technology and Software Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":5.4775,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.96266619,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"71","issue":"10","first_page":"10280","last_page":"10292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9998000264167786,"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":0.9998000264167786,"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/T11133","display_name":"UAV Applications and Optimization","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/flocking","display_name":"Flocking (texture)","score":0.9074944257736206},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8986972570419312},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.7544269561767578},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6856545209884644},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6854208111763},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6607194542884827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5329122543334961},{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.48589128255844116},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.43986719846725464},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4259437918663025},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38990628719329834},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3164643943309784},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.08713248372077942}],"concepts":[{"id":"https://openalex.org/C2781220375","wikidata":"https://www.wikidata.org/wiki/Q814208","display_name":"Flocking (texture)","level":2,"score":0.9074944257736206},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8986972570419312},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7544269561767578},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6856545209884644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6854208111763},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6607194542884827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5329122543334961},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.48589128255844116},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.43986719846725464},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4259437918663025},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38990628719329834},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3164643943309784},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.08713248372077942},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvt.2022.3184043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvt.2022.3184043","pdf_url":null,"source":{"id":"https://openalex.org/S10936095","display_name":"IEEE Transactions on Vehicular Technology","issn_l":"0018-9545","issn":["0018-9545","1939-9359"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Vehicular Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1486437991","https://openalex.org/W1522301498","https://openalex.org/W1590980054","https://openalex.org/W1947715781","https://openalex.org/W1996813585","https://openalex.org/W2009622829","https://openalex.org/W2076337359","https://openalex.org/W2145339207","https://openalex.org/W2150312211","https://openalex.org/W2733312032","https://openalex.org/W2736601468","https://openalex.org/W2768629321","https://openalex.org/W2792734461","https://openalex.org/W2884236119","https://openalex.org/W2889919447","https://openalex.org/W2907916537","https://openalex.org/W2912444619","https://openalex.org/W2918849077","https://openalex.org/W2950292737","https://openalex.org/W2962890638","https://openalex.org/W2963658727","https://openalex.org/W2969275160","https://openalex.org/W2973229164","https://openalex.org/W2988592481","https://openalex.org/W2999672258","https://openalex.org/W2999934039","https://openalex.org/W3006499227","https://openalex.org/W3025756803","https://openalex.org/W3025789438","https://openalex.org/W3035458768","https://openalex.org/W3037515790","https://openalex.org/W3044274646","https://openalex.org/W3091778231","https://openalex.org/W3094019951","https://openalex.org/W3098060190","https://openalex.org/W3102483098","https://openalex.org/W3113092951","https://openalex.org/W3126889909","https://openalex.org/W3168104141","https://openalex.org/W3183210514","https://openalex.org/W3193740671","https://openalex.org/W3212600915","https://openalex.org/W4299802797","https://openalex.org/W6631190155","https://openalex.org/W6638018090","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6747941106","https://openalex.org/W6748839928","https://openalex.org/W6779828175"],"related_works":["https://openalex.org/W2002188687","https://openalex.org/W2142589698","https://openalex.org/W2794811781","https://openalex.org/W4327740834","https://openalex.org/W4387445286","https://openalex.org/W4389665619","https://openalex.org/W2166744572","https://openalex.org/W2138105113","https://openalex.org/W1596835606","https://openalex.org/W2182108128"],"abstract_inverted_index":{"The":[0],"flocking":[1,33,54],"and":[2,34,46,55,68,90,102,132,161,163,190],"navigation":[3,35,56],"control":[4,36,57],"of":[5,16,24,58,94],"large-scale":[6],"Unmanned":[7],"Aerial":[8],"Vehicle":[9],"(UAV)":[10],"swarms":[11],"have":[12,41],"received":[13],"a":[14,63,165],"lot":[15],"research":[17],"interest":[18],"due":[19],"to":[20,30,74,106,118,170,187],"the":[21,53,59,76,87,91,99,108,113,119,123,137,141,146,149,153,158,177,192],"wide":[22],"applications":[23],"UAVs":[25,189],"in":[26,43],"many":[27],"fields.":[28],"Compared":[29],"traditional":[31],"non-learning-based":[32],"methods,":[37],"reinforcement":[38,71,85,115],"learning-based":[39],"methods":[40,73],"advantages":[42],"model-free,":[44],"flexibility,":[45],"adaptability.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,126],"formulate":[52],"UAV":[60],"swarm":[61],"as":[62],"Markov":[64],"Decision":[65],"Process":[66],"(MDP)":[67],"use":[69],"multi-agent":[70,120],"learning":[72,101,116],"solve":[75],"problem.":[77],"There":[78],"are":[79],"two":[80],"significant":[81],"challenges":[82],"introduced":[83],"by":[84],"learning:":[86],"scalability":[88,109],"issue":[89],"partial":[92,124],"observations":[93,160],"each":[95],"UAV.":[96],"We":[97,156],"adopt":[98],"independent":[100],"parameter":[103],"sharing":[104],"scheme":[105],"tackle":[107],"issue,":[110],"which":[111,135],"extends":[112],"single-agent":[114],"algorithms":[117],"scenario.":[121],"For":[122],"observations,":[125],"propose":[127],"an":[128],"oracle-guided":[129,159],"two-stage":[130],"training":[131,142],"execution":[133,154],"scheme,":[134],"utilizes":[136],"flock":[138,150],"center":[139,151],"during":[140,152],"phase":[143],"but":[144],"avoids":[145],"dependence":[147],"on":[148],"phase.":[155],"design":[157],"rewards":[162],"build":[164],"highly":[166],"efficient":[167],"simulation":[168],"environment":[169],"conduct":[171],"experiments.":[172],"Simulation":[173],"results":[174],"show":[175],"that":[176],"policy":[178,193],"trained":[179,194],"with":[180,185,195],"our":[181],"method":[182],"performs":[183],"well":[184],"up":[186],"thirty-two":[188],"outperforms":[191],"local":[196],"observations.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":8}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}