{"id":"https://openalex.org/W4416513228","doi":"https://doi.org/10.1109/tcomm.2025.3635773","title":"Deep Transfer Reinforcement Learning-Based Exploration Enhanced Multi-UAV Trajectory Planning","display_name":"Deep Transfer Reinforcement Learning-Based Exploration Enhanced Multi-UAV Trajectory Planning","publication_year":2025,"publication_date":"2025-11-21","ids":{"openalex":"https://openalex.org/W4416513228","doi":"https://doi.org/10.1109/tcomm.2025.3635773"},"language":null,"primary_location":{"id":"doi:10.1109/tcomm.2025.3635773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcomm.2025.3635773","pdf_url":null,"source":{"id":"https://openalex.org/S196647941","display_name":"IEEE Transactions on Communications","issn_l":"0090-6778","issn":["0090-6778","1558-0857"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316002","host_organization_name":"IEEE Communications Society","host_organization_lineage":["https://openalex.org/P4310316002","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Communications Society","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 Communications","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/A5000816439","display_name":"Wenke Yuan","orcid":"https://orcid.org/0009-0006-1573-5845"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenke Yuan","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0006-1573-5845","affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gaoxiang Cao","orcid":"https://orcid.org/0009-0006-6673-6573"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaoxiang Cao","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0006-6673-6573","affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102803853","display_name":"Yunpeng Hou","orcid":"https://orcid.org/0000-0001-7216-9022"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunpeng Hou","raw_affiliation_strings":["Hefei Comprehensive National Science Center, Institute of Artificial Intelligence, Hefei, China","Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7216-9022","affiliations":[{"raw_affiliation_string":"Hefei Comprehensive National Science Center, Institute of Artificial Intelligence, Hefei, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021207234","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0002-4487-8400"},"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":"Jian Wang","raw_affiliation_strings":["College of Electronic Engineering, National University of Defense Technology, Hefei, China","College of Electronic Engineering, National University of Defense Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic Engineering, National University of Defense Technology, Hefei, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Electronic Engineering, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045720734","display_name":"Shuangwu Chen","orcid":"https://orcid.org/0000-0003-2817-9738"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuangwu Chen","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2817-9738","affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047787436","display_name":"Huasen He","orcid":"https://orcid.org/0000-0001-9963-019X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huasen He","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9963-019X","affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083577000","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0002-7329-4738"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7329-4738","affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"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":0.32470652,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"74","issue":null,"first_page":"1577","last_page":"1593"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.5257999897003174,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.5257999897003174,"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/T11133","display_name":"UAV Applications and Optimization","score":0.24779999256134033,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.08420000225305557,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7732999920845032},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6244999766349792},{"id":"https://openalex.org/keywords/trajectory-optimization","display_name":"Trajectory optimization","score":0.5184000134468079},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.43959999084472656},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.43070000410079956},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4043000042438507},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.3977999985218048},{"id":"https://openalex.org/keywords/unexpected-events","display_name":"Unexpected events","score":0.35510000586509705}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7732999920845032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6711999773979187},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6244999766349792},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.5184000134468079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5024999976158142},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.43959999084472656},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.43070000410079956},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3977999985218048},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.34709998965263367},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29679998755455017},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.288100004196167},{"id":"https://openalex.org/C104060986","wikidata":"https://www.wikidata.org/wiki/Q180046","display_name":"Space exploration","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2833999991416931},{"id":"https://openalex.org/C146481406","wikidata":"https://www.wikidata.org/wiki/Q105131","display_name":"Hotspot (geology)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25619998574256897},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcomm.2025.3635773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcomm.2025.3635773","pdf_url":null,"source":{"id":"https://openalex.org/S196647941","display_name":"IEEE Transactions on Communications","issn_l":"0090-6778","issn":["0090-6778","1558-0857"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316002","host_organization_name":"IEEE Communications Society","host_organization_lineage":["https://openalex.org/P4310316002","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Communications Society","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 Communications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4736320777","display_name":null,"funder_award_id":"U23A20275","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7553321691","display_name":null,"funder_award_id":"62201543","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":39,"referenced_works":["https://openalex.org/W1969791930","https://openalex.org/W2031834036","https://openalex.org/W2131959252","https://openalex.org/W2137983211","https://openalex.org/W2788862220","https://openalex.org/W2897895275","https://openalex.org/W2964051877","https://openalex.org/W3006499227","https://openalex.org/W3039263585","https://openalex.org/W3051352583","https://openalex.org/W3091526482","https://openalex.org/W3131765381","https://openalex.org/W3167450743","https://openalex.org/W3171715134","https://openalex.org/W3172086257","https://openalex.org/W3172786112","https://openalex.org/W3175611345","https://openalex.org/W3183579868","https://openalex.org/W3183773409","https://openalex.org/W3199843466","https://openalex.org/W3200237136","https://openalex.org/W4206111066","https://openalex.org/W4210611093","https://openalex.org/W4226457030","https://openalex.org/W4285229436","https://openalex.org/W4297499129","https://openalex.org/W4312877079","https://openalex.org/W4312943725","https://openalex.org/W4313593056","https://openalex.org/W4316468203","https://openalex.org/W4364374682","https://openalex.org/W4365128504","https://openalex.org/W4383112908","https://openalex.org/W4385245566","https://openalex.org/W4386453810","https://openalex.org/W4387441444","https://openalex.org/W4391019655","https://openalex.org/W4391547575","https://openalex.org/W4401325873"],"related_works":[],"abstract_inverted_index":{"Motivated":[0],"by":[1,212,230],"the":[2,24,84,104,127,133,162,179,205,209,223],"intelligent":[3],"decision-making":[4],"ability,":[5],"Deep":[6],"Reinforcement":[7],"Learning":[8,79],"(DRL)":[9],"has":[10],"been":[11],"extensively":[12],"applied":[13],"in":[14,28,33],"multi-Unmanned":[15],"Aerial":[16],"Vehicle":[17],"(UAV)":[18],"trajectory":[19,31,150,218],"planning.":[20],"This":[21],"article":[22],"investigates":[23],"application":[25],"of":[26,61,108,136,208],"DRL":[27,182],"Three-Dimensional":[29],"(3D)":[30],"planning":[32,151,219],"environments":[34,98],"with":[35,73],"obstacles,":[36],"where":[37],"multiple":[38,154],"UAVs":[39,137],"act":[40],"as":[41],"aerial":[42],"Base":[43],"Stations":[44],"(BSs)":[45],"to":[46,49,66,87,96,125,166,185],"provide":[47],"services":[48],"ground":[50],"user":[51],"hotspots.":[52,169],"The":[53,214],"existing":[54],"DRL-based":[55],"algorithms":[56],"require":[57],"a":[58,110,172,187],"significant":[59],"amount":[60],"trial":[62],"and":[63,99,118,160,176,181,191,216,226],"error":[64],"iterations":[65],"obtain":[67,126],"sufficiently":[68],"high-performing":[69],"agents.":[70],"To":[71],"cope":[72],"this":[74],"drawback,":[75],"we":[76,144],"introduce":[77],"Transfer":[78],"(TL)":[80],"into":[81],"DRL,":[82],"enabling":[83],"UAV":[85,210],"agent":[86],"possess":[88],"prior":[89],"knowledge":[90],"upon":[91],"initialization,":[92],"thereby":[93],"quickly":[94],"adapting":[95],"unfamiliar":[97],"significantly":[100,221],"improving":[101],"performance.":[102],"Considering":[103],"limited":[105],"local":[106],"observations":[107,124],"UAVs,":[109,155],"multi-modal":[111],"fusion":[112,129],"autoencoder":[113],"is":[114],"proposed":[115,198],"for":[116,153],"extracting":[117],"compressing":[119],"cross-modal":[120],"features":[121],"from":[122],"global":[123,128],"state,":[130],"which":[131,156],"enhances":[132,161],"perception":[134,215],"capabilities":[135,165],"without":[138],"incurring":[139],"excessive":[140],"communication":[141],"overhead.":[142],"Finally,":[143],"propose":[145],"an":[146],"exploration":[147,164,224],"novelty-driven":[148],"collaborative":[149],"algorithm":[152,220],"ensures":[157],"obstacle":[158],"avoidance":[159],"UAVs\u2019":[163],"cover":[167],"all":[168],"We":[170],"adopt":[171],"probabilistic":[173],"channel":[174],"model":[175],"discretize":[177],"both":[178],"time":[180],"action":[183],"space":[184],"achieve":[186],"balance":[188],"between":[189],"practicality":[190],"tractability.":[192],"Extensive":[193],"experiments":[194],"demonstrate":[195],"that":[196],"our":[197],"transfer":[199],"reinforcement":[200],"learning":[201],"method":[202],"can":[203],"improve":[204],"initial":[206],"performance":[207],"agents":[211],"76%.":[213],"exploration-enhanced":[217],"increased":[222],"efficiency":[225],"improved":[227],"hotspot":[228],"coverage":[229],"50%.":[231]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-23T00:00:00"}