{"id":"https://openalex.org/W7118191230","doi":"https://doi.org/10.1109/jiot.2025.3650490","title":"Federated Deep Reinforcement Learning for Safe Multi-UAV Cooperative Control in IoT Communications","display_name":"Federated Deep Reinforcement Learning for Safe Multi-UAV Cooperative Control in IoT Communications","publication_year":2026,"publication_date":"2026-01-05","ids":{"openalex":"https://openalex.org/W7118191230","doi":"https://doi.org/10.1109/jiot.2025.3650490"},"language":null,"primary_location":{"id":"doi:10.1109/jiot.2025.3650490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3650490","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","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/A5082625689","display_name":"Jian Gu","orcid":"https://orcid.org/0000-0001-7309-1896"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Gu","raw_affiliation_strings":["School of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7309-1896","affiliations":[{"raw_affiliation_string":"School of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100529837","display_name":"Yin Wang","orcid":"https://orcid.org/0000-0002-6811-4798"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Wang","raw_affiliation_strings":["School of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-6811-4798","affiliations":[{"raw_affiliation_string":"School of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121926165","display_name":"Wen Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Ji","raw_affiliation_strings":["National Maglev Transportation Engineering Research and Development Center, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6464-6121","affiliations":[{"raw_affiliation_string":"National Maglev Transportation Engineering Research and Development Center, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01727373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"9","first_page":"18392","last_page":"18403"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11133","display_name":"UAV Applications and Optimization","score":0.8224999904632568,"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"}},"topics":[{"id":"https://openalex.org/T11133","display_name":"UAV Applications and Optimization","score":0.8224999904632568,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.02290000021457672,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T14413","display_name":"Advanced Technologies in Various Fields","score":0.018699999898672104,"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":0.8062000274658203},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5953999757766724},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47859999537467957},{"id":"https://openalex.org/keywords/wireless-sensor-network","display_name":"Wireless sensor network","score":0.44839999079704285},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4318000078201294},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41909998655319214},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4036000072956085},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.39309999346733093},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.3919000029563904}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8065000176429749},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8062000274658203},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5953999757766724},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47859999537467957},{"id":"https://openalex.org/C24590314","wikidata":"https://www.wikidata.org/wiki/Q336038","display_name":"Wireless sensor network","level":2,"score":0.44839999079704285},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4318000078201294},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4171999990940094},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4036000072956085},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C47796450","wikidata":"https://www.wikidata.org/wiki/Q508378","display_name":"Intelligent transportation system","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C82327864","wikidata":"https://www.wikidata.org/wiki/Q835100","display_name":"Intelligent control","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.34389999508857727},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3431999981403351},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C81860439","wikidata":"https://www.wikidata.org/wiki/Q251212","display_name":"Internet of Things","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C155386361","wikidata":"https://www.wikidata.org/wiki/Q1649571","display_name":"Process control","level":3,"score":0.3041999936103821},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C2775907273","wikidata":"https://www.wikidata.org/wiki/Q7805281","display_name":"Time constraint","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C176563091","wikidata":"https://www.wikidata.org/wiki/Q669238","display_name":"Intelligent sensor","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2025.3650490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3650490","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4156673550605774}],"awards":[{"id":"https://openalex.org/G7803051127","display_name":null,"funder_award_id":"12102178","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,22,53,166],"cooperative":[1,23,220],"control":[2,24,68,127,192,221],"of":[3,26,37,55,76,142,189,205,218],"UAVs":[4,28,46],"in":[5,15,74,253,275],"a":[6,61,117,130],"complex":[7],"environment":[8,39,49],"is":[9,29,83,108,158],"the":[10,27,35,38,42,45,48,67,81,105,124,139,154,161,171,185,190,199,203,206,215,226,238,256],"key":[11],"and":[12,18,47,78,95,148,182,187,213,271],"fundamental":[13],"problem":[14],"intelligent":[16,126],"transportation":[17],"IoT":[19,51,232,254],"communication":[20],"systems.":[21],"policy":[25,69],"challenging":[30],"to":[31,34,65,85,92,100,123],"determine":[32],"due":[33,91],"non-stationarity":[36],"caused":[40],"by":[41],"interactions":[43],"between":[44],"under":[50,231],"communication.":[52,233],"use":[54],"deep":[56,119],"learning":[57,106,121,176],"algorithms":[58],"based":[59],"on":[60,151],"digital":[62],"twin(DT)":[63],"system":[64,152],"optimize":[66],"has":[70],"shown":[71,197],"significant":[72],"benefits":[73],"terms":[75],"efficiency":[77],"flexibility.":[79],"However,":[80],"DT":[82],"prone":[84],"being":[86],"inconsistent":[87],"with":[88,129,250],"real-world":[89],"applications":[90],"sensor":[93,146],"errors":[94,147],"data":[96,149],"delays,":[97],"which":[98],"lead":[99],"incorrect":[101],"policy,":[102],"even":[103],"if":[104],"process":[107],"convergent.":[109],"To":[110,136],"address":[111],"this":[112,114],"issue,":[113],"paper":[115],"proposes":[116],"federated":[118,174],"reinforcement":[120,175],"solution":[122,201,240],"multi-UAV":[125,219],"problem,":[128],"newly":[131],"developed":[132],"constrained":[133,172],"optimization":[134],"framework.":[135],"effectively":[137,208],"eliminate":[138],"negative":[140],"impact":[141],"uncertainties":[143],"such":[144],"as":[145,223,225],"delays":[150],"performance,":[153],"safety":[155,186,204],"constraint":[156],"function":[157,163],"integrated":[159],"into":[160],"objective":[162],"for":[164],"optimization.":[165],"model":[167],"undergoes":[168],"training":[169],"through":[170],"distributed":[173],"framework,":[177],"avoiding":[178],"potentially":[179],"dangerous":[180,211],"behavior":[181],"thereby":[183],"improving":[184],"robustness":[188],"resulting":[191],"strategies.":[193],"Experimental":[194,234],"results":[195,235],"have":[196],"that":[198,237],"proposed":[200,239],"ensures":[202],"strategy,":[207],"avoids":[209],"potential":[210],"behaviors,":[212],"improves":[214],"success":[216,266],"rate":[217,267],"tasks":[222],"well":[224],"average":[227],"task":[228,276],"completion":[229,277],"time":[230],"demonstrate":[236],"achieves":[241],"substantial":[242],"performance":[243],"improvements":[244],"while":[245],"ensuring":[246],"operational":[247],"safety.":[248],"Compared":[249],"baseline":[251],"methods":[252],"environments,":[255],"algorithm":[257],"exhibits":[258],"min":[259,263,272],"26.7%":[260],"faster":[261],"convergence,":[262],"1.8%":[264],"higher":[265],"across":[268],"swarm":[269],"sizes,":[270],"12.3%":[273],"reduction":[274],"time.":[278]},"counts_by_year":[],"updated_date":"2026-04-25T06:01:18.069262","created_date":"2026-01-05T00:00:00"}