{"id":"https://openalex.org/W4386065468","doi":"https://doi.org/10.1109/tiv.2023.3307134","title":"Robust Multi-Agent Reinforcement Learning Method Based on Adversarial Domain Randomization for Real-World Dual-UAV Cooperation","display_name":"Robust Multi-Agent Reinforcement Learning Method Based on Adversarial Domain Randomization for Real-World Dual-UAV Cooperation","publication_year":2023,"publication_date":"2023-08-22","ids":{"openalex":"https://openalex.org/W4386065468","doi":"https://doi.org/10.1109/tiv.2023.3307134"},"language":"en","primary_location":{"id":"doi:10.1109/tiv.2023.3307134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tiv.2023.3307134","pdf_url":null,"source":{"id":"https://openalex.org/S4210199657","display_name":"IEEE Transactions on Intelligent Vehicles","issn_l":"2379-8858","issn":["2379-8858","2379-8904"],"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 Intelligent Vehicles","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/A5101639628","display_name":"Shutong Chen","orcid":"https://orcid.org/0009-0009-8094-889X"},"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":"Shutong Chen","raw_affiliation_strings":["Department of Computer Science, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-8094-889X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072386697","display_name":"Guanjun Liu","orcid":"https://orcid.org/0000-0002-7523-4827"},"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":"Guanjun Liu","raw_affiliation_strings":["Department of Computer Science, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7523-4827","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043926144","display_name":"Ziyuan Zhou","orcid":"https://orcid.org/0000-0002-2649-8666"},"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":"Ziyuan Zhou","raw_affiliation_strings":["Department of Computer Science, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2649-8666","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009120365","display_name":"Kaiwen Zhang","orcid":"https://orcid.org/0000-0003-4573-8968"},"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":"Kaiwen Zhang","raw_affiliation_strings":["Department of Computer Science, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4573-8968","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108025258","display_name":"Jiacun Wang","orcid":"https://orcid.org/0000-0001-6601-3515"},"institutions":[{"id":"https://openalex.org/I141450709","display_name":"Monmouth University","ror":"https://ror.org/01d6qxv05","country_code":"US","type":"education","lineage":["https://openalex.org/I141450709"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiacun Wang","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Monmouth University, West Long Branch, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0001-6601-3515","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Monmouth University, West Long Branch, NJ, USA","institution_ids":["https://openalex.org/I141450709"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8738,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.96988693,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"9","issue":"1","first_page":"1615","last_page":"1627"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9921000003814697,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8048031330108643},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7052887082099915},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6473398208618164},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6456454396247864},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.531396746635437},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5182285308837891},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47086301445961},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.47067198157310486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.431352823972702},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41265174746513367},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15189054608345032}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8048031330108643},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7052887082099915},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6473398208618164},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6456454396247864},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.531396746635437},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5182285308837891},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47086301445961},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.47067198157310486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.431352823972702},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41265174746513367},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15189054608345032},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tiv.2023.3307134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tiv.2023.3307134","pdf_url":null,"source":{"id":"https://openalex.org/S4210199657","display_name":"IEEE Transactions on Intelligent Vehicles","issn_l":"2379-8858","issn":["2379-8858","2379-8904"],"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 Intelligent Vehicles","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4971678349","display_name":null,"funder_award_id":"22511105500","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G5788605144","display_name":null,"funder_award_id":"62172299","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7465024212","display_name":null,"funder_award_id":"2023-4-YB-05","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8592490694","display_name":null,"funder_award_id":"62032019","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"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1907356258","https://openalex.org/W2141559645","https://openalex.org/W2201581102","https://openalex.org/W2605102758","https://openalex.org/W2793398421","https://openalex.org/W2896720518","https://openalex.org/W2907916537","https://openalex.org/W2946901134","https://openalex.org/W2954559956","https://openalex.org/W2964536243","https://openalex.org/W2987256267","https://openalex.org/W2990747716","https://openalex.org/W2995092355","https://openalex.org/W3006868075","https://openalex.org/W3007547569","https://openalex.org/W3021399679","https://openalex.org/W3042466401","https://openalex.org/W3084343743","https://openalex.org/W3086351065","https://openalex.org/W3088310808","https://openalex.org/W3090573937","https://openalex.org/W3118300017","https://openalex.org/W3120778962","https://openalex.org/W3126300335","https://openalex.org/W3166228843","https://openalex.org/W3203069471","https://openalex.org/W4226223832","https://openalex.org/W4285132117","https://openalex.org/W4293525115","https://openalex.org/W4297996976","https://openalex.org/W4312403563","https://openalex.org/W4312616886","https://openalex.org/W4320005669","https://openalex.org/W4321461140","https://openalex.org/W4367016573","https://openalex.org/W4367663420","https://openalex.org/W4376456516","https://openalex.org/W4377111731","https://openalex.org/W4377712795","https://openalex.org/W4379051467","https://openalex.org/W4385068279","https://openalex.org/W4387171533","https://openalex.org/W6687681856","https://openalex.org/W6738796088","https://openalex.org/W6749557584","https://openalex.org/W6761443123","https://openalex.org/W6763177082","https://openalex.org/W6764943343","https://openalex.org/W6771704696","https://openalex.org/W6774026654","https://openalex.org/W6779402086","https://openalex.org/W6780559895","https://openalex.org/W6785517317","https://openalex.org/W6846044417","https://openalex.org/W6852997558"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4288019534","https://openalex.org/W4310988119"],"abstract_inverted_index":{"A":[0],"control":[1,71],"system":[2],"of":[3,29,197,204,216],"multiple":[4],"unmanned":[5],"aerial":[6],"vehicles":[7],"(multi-UAV)":[8],"is":[9,73,101],"generally":[10],"very":[11],"complex":[12,42,175],"when":[13],"they":[14],"complete":[15],"a":[16,19,27,36,41,52,70,76,83,90,98,110,123,156,161,198,213],"task":[17,215],"in":[18,55,75,122,133],"closely-cooperative":[20],"manner,":[21],"e.g.":[22],"two":[23],"UAVs":[24],"cooperatively":[25],"transport":[26],"package":[28],"goods.":[30],"Multi-agent":[31],"reinforcement":[32],"learning":[33],"(MARL)":[34],"offers":[35],"promising":[37],"solution":[38],"for":[39],"such":[40],"control.":[43],"However,":[44],"MARL":[45],"heavily":[46],"relies":[47],"on":[48],"trial-and-error":[49],"explorations,":[50],"facing":[51],"big":[53],"challenge":[54],"gathering":[56],"real-world":[57,84,214],"training":[58,125,164,199],"data.":[59],"Simulation":[60],"environments":[61],"are":[62],"commonly":[63],"used":[64,121],"to":[65,113,159,212,226],"overcome":[66],"this":[67,115,142],"challenge,":[68],"i.e.,":[69],"policy":[72,124,171],"trained":[74,169,206],"simulation":[77,93],"environment":[78,165],"and":[79,94,96,131,220],"then":[80],"transferred":[81],"into":[82],"system.":[85],"But":[86],"there":[87],"often":[88,126],"exists":[89],"gap":[91],"between":[92],"reality":[95],"thus":[97],"successful":[99],"transfer":[100],"not":[102],"guaranteed":[103],"easily.":[104],"The":[105],"domain":[106,147],"randomization":[107,148],"method":[108,184,211],"provides":[109],"workable":[111],"way":[112],"bridge":[114],"gap.":[116],"Nevertheless,":[117],"the":[118,168,180,194,202,205],"traditional":[119,227],"one":[120],"suffers":[127],"from":[128],"slow":[129],"convergence":[130,195],"results":[132],"an":[134,145,152],"unstable":[135],"decision":[136,170],"policy.":[137,207],"To":[138],"address":[139],"these":[140],"issues,":[141],"article":[143],"proposes":[144],"adversarial":[146,153],"method.":[149],"It":[150],"utilizes":[151],"generator":[154],"as":[155],"\u201cnature":[157],"player\u201d":[158],"generate":[160],"more":[162],"reasonable":[163],"so":[166],"that":[167],"can":[172,188],"deal":[173],"with":[174],"situations.":[176],"Additionally,":[177],"we":[178,187],"improve":[179],"prioritized":[181],"experience":[182],"replay":[183],"by":[185],"which":[186],"sample":[189],"those":[190],"critical":[191],"experiences,":[192],"increasing":[193],"speed":[196],"without":[200],"decreasing":[201],"performance":[203],"We":[208],"apply":[209],"our":[210],"dual-UAV":[217],"cooperative":[218],"transportation,":[219],"experiments":[221],"illustrate":[222],"its":[223],"effectiveness":[224],"compared":[225],"ones.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":15}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}