{"id":"https://openalex.org/W4412159393","doi":"https://doi.org/10.1002/aisy.202500208","title":"Multiple Unmanned Aerial Vehicle Formation Control through Deep Reinforcement Learning with Offline Sample Correction","display_name":"Multiple Unmanned Aerial Vehicle Formation Control through Deep Reinforcement Learning with Offline Sample Correction","publication_year":2025,"publication_date":"2025-07-10","ids":{"openalex":"https://openalex.org/W4412159393","doi":"https://doi.org/10.1002/aisy.202500208"},"language":"en","primary_location":{"id":"doi:10.1002/aisy.202500208","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202500208","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/aisy.202500208","source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/aisy.202500208","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103080774","display_name":"Zhongkai Chen","orcid":"https://orcid.org/0000-0003-3275-6542"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongkai Chen","raw_affiliation_strings":["College of Intelligence Science and Technology National University of Defense Technology  Changsha 410073 China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology National University of Defense Technology  Changsha 410073 China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031130592","display_name":"Han Zhou","orcid":"https://orcid.org/0000-0002-8367-7695"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Zhou","raw_affiliation_strings":["College of Intelligence Science and Technology National University of Defense Technology  Changsha 410073 China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology National University of Defense Technology  Changsha 410073 China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035598117","display_name":"Chao Yan","orcid":"https://orcid.org/0000-0002-9995-4239"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]},{"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":true,"raw_author_name":"Chao Yan","raw_affiliation_strings":["College of Automation Engineering Nanjing University of Aeronautics and Astronautics  Nanjing 211106 China","College of Intelligence Science and Technology National University of Defense Technology  Changsha 410073 China"],"raw_orcid":"https://orcid.org/0000-0002-9995-4239","affiliations":[{"raw_affiliation_string":"College of Automation Engineering Nanjing University of Aeronautics and Astronautics  Nanjing 211106 China","institution_ids":["https://openalex.org/I9842412"]},{"raw_affiliation_string":"College of Intelligence Science and Technology National University of Defense Technology  Changsha 410073 China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048578575","display_name":"Yihao Sun","orcid":"https://orcid.org/0000-0002-3997-1272"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihao Sun","raw_affiliation_strings":["College of Intelligence Science and Technology National University of Defense Technology  Changsha 410073 China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology National University of Defense Technology  Changsha 410073 China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027437343","display_name":"Xiaojia Xiang","orcid":"https://orcid.org/0000-0002-1525-6231"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojia Xiang","raw_affiliation_strings":["College of Intelligence Science and Technology National University of Defense Technology  Changsha 410073 China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology National University of Defense Technology  Changsha 410073 China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5035598117"],"corresponding_institution_ids":["https://openalex.org/I170215575","https://openalex.org/I9842412"],"apc_list":{"value":2750,"currency":"USD","value_usd":2750},"apc_paid":{"value":2750,"currency":"USD","value_usd":2750},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16524812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"12","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":1.0,"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":1.0,"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":0.9993000030517578,"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":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7319862842559814},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6503230333328247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4865052103996277},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4826677143573761},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.44245392084121704},{"id":"https://openalex.org/keywords/aeronautics","display_name":"Aeronautics","score":0.43322402238845825},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4148145914077759},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22094020247459412},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.09092915058135986},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.0468277633190155}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7319862842559814},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6503230333328247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4865052103996277},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4826677143573761},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44245392084121704},{"id":"https://openalex.org/C178802073","wikidata":"https://www.wikidata.org/wiki/Q8421","display_name":"Aeronautics","level":1,"score":0.43322402238845825},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4148145914077759},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22094020247459412},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09092915058135986},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0468277633190155},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1002/aisy.202500208","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202500208","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/aisy.202500208","source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f7bf5424061d491b997778464d2642c4","is_oa":true,"landing_page_url":"https://doaj.org/article/f7bf5424061d491b997778464d2642c4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Advanced Intelligent Systems, Vol 7, Iss 12, Pp n/a-n/a (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1002/aisy.202500208","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202500208","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/aisy.202500208","source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2578841985","display_name":null,"funder_award_id":"62403240","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5205714092","display_name":null,"funder_award_id":"BK20241396","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412159393.pdf","grobid_xml":"https://content.openalex.org/works/W4412159393.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1517023801","https://openalex.org/W2068394052","https://openalex.org/W2099175737","https://openalex.org/W2119959427","https://openalex.org/W2150312211","https://openalex.org/W2746553466","https://openalex.org/W3023942433","https://openalex.org/W3033034581","https://openalex.org/W3036610339","https://openalex.org/W3039584914","https://openalex.org/W3043763914","https://openalex.org/W3153657716","https://openalex.org/W3183210514","https://openalex.org/W3213750164","https://openalex.org/W3214814008","https://openalex.org/W4248542902","https://openalex.org/W4307647390","https://openalex.org/W4312332347","https://openalex.org/W4313472056","https://openalex.org/W4319460065","https://openalex.org/W4320176201","https://openalex.org/W4321608219","https://openalex.org/W4321780014","https://openalex.org/W4323767825","https://openalex.org/W4384207644","https://openalex.org/W4386900525","https://openalex.org/W4387146027","https://openalex.org/W4388430494","https://openalex.org/W4388838093","https://openalex.org/W4390755075","https://openalex.org/W4392449656","https://openalex.org/W4392543764","https://openalex.org/W4396741054","https://openalex.org/W4398200204","https://openalex.org/W4400510777"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Multiple":[0],"unmanned":[1],"aerial":[2],"vehicle":[3],"(multi\u2010UAV)":[4],"formation":[5,23,44,51,83],"plays":[6],"a":[7,39,55],"pivotal":[8],"role":[9],"in":[10],"both":[11],"military":[12],"and":[13,33,122,135,142,155],"civilian":[14],"applications.":[15],"However,":[16],"enabling":[17],"multi\u2010UAV":[18,43,50],"to":[19,29,59,80,94],"efficiently":[20],"acquire":[21],"collaborative":[22],"policies":[24,124],"is":[25,47,66,86,93],"challenging,":[26],"primarily":[27],"due":[28],"the":[30,61,82,96,108,112,116,119,137,145],"complex":[31],"kinematics":[32],"dynamic":[34],"environmental":[35],"factors":[36],"involved.":[37],"Herein,":[38],"deep":[40],"reinforcement":[41],"learning\u2010based":[42],"control":[45,52,84],"approach":[46,147],"proposed.":[48,87],"The":[49,88,140],"problem":[53],"as":[54],"Markov":[56],"decision":[57],"process":[58,65],"capture":[60],"inherent":[62],"sequential":[63],"decision\u2010making":[64],"first":[67],"modeled.":[68],"Furthermore,":[69],"an":[70],"enhanced":[71],"actor\u2010critic":[72,78],"algorithm":[73],"called":[74],"offline":[75,103],"sample":[76],"correction":[77],"(OSCAC)":[79],"learn":[81],"policy":[85,121],"core":[89],"insight":[90],"behind":[91],"OSCAC":[92,106],"optimize":[95],"utilization":[97],"of":[98,111,132,144],"historical":[99],"data":[100],"through":[101,150],"correcting":[102],"samples.":[104],"Specifically,":[105],"adjusts":[107],"importance":[109],"weights":[110],"samples":[113],"based":[114],"on":[115],"discrepancies":[117],"between":[118],"current":[120],"previous":[123],"during":[125],"each":[126],"update":[127],"step,":[128],"making":[129],"better":[130],"use":[131],"past":[133],"experience":[134],"improving":[136],"learning":[138],"performance.":[139],"effectiveness":[141],"reliability":[143],"proposed":[146],"are":[148],"validated":[149],"numerical":[151],"simulations,":[152,154],"software\u2010in\u2010the\u2010loop":[153],"real\u2010world":[156],"experiments.":[157]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
