{"id":"https://openalex.org/W4393066282","doi":"https://doi.org/10.1109/tetci.2024.3369485","title":"Path Planning for Unmanned Aerial Vehicle via Off-Policy Reinforcement Learning With Enhanced Exploration","display_name":"Path Planning for Unmanned Aerial Vehicle via Off-Policy Reinforcement Learning With Enhanced Exploration","publication_year":2024,"publication_date":"2024-03-22","ids":{"openalex":"https://openalex.org/W4393066282","doi":"https://doi.org/10.1109/tetci.2024.3369485"},"language":"en","primary_location":{"id":"doi:10.1109/tetci.2024.3369485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2024.3369485","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"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 Emerging Topics in Computational Intelligence","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/A5101753861","display_name":"Zhengjun Wang","orcid":"https://orcid.org/0009-0004-8238-0154"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]},{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhengjun Wang","raw_affiliation_strings":["School of Mathematics and Statistics, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China","School of System Design and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0004-8238-0154","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of System Design and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047167952","display_name":"Weifeng Gao","orcid":"https://orcid.org/0000-0003-3853-0771"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Gao","raw_affiliation_strings":["School of Mathematics and Statistics, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-3853-0771","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001176258","display_name":"Genghui Li","orcid":"https://orcid.org/0000-0002-9950-9848"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Genghui Li","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-9950-9848","affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064608174","display_name":"Zhenkun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]},{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenkun Wang","raw_affiliation_strings":["School of Mathematics and Statistics, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China","School of System Design and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen, China","Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1152-6780","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of System Design and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091227928","display_name":"Maoguo Gong","orcid":"https://orcid.org/0000-0002-0415-8556"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maoguo Gong","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Image Understanding, International Research Center for Intelligent Perception and Computation, Ministry of Education, Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-0415-8556","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Image Understanding, International Research Center for Intelligent Perception and Computation, Ministry of Education, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101753861"],"corresponding_institution_ids":["https://openalex.org/I149594827","https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":10.2652,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.98527125,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"8","issue":"3","first_page":"2625","last_page":"2639"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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":0.9986000061035156,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9915000200271606,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9830999970436096,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8730968236923218},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.8014175891876221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7220103144645691},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.7178851366043091},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6176795363426208},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5848159193992615},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5692138671875},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.481192409992218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4205673038959503},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3888319730758667},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33060628175735474},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.19217902421951294},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12605413794517517},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08094474673271179},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.07718166708946228},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0719875693321228},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.0652572512626648}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8730968236923218},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.8014175891876221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7220103144645691},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.7178851366043091},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6176795363426208},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5848159193992615},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5692138671875},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.481192409992218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4205673038959503},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3888319730758667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33060628175735474},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.19217902421951294},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12605413794517517},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08094474673271179},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.07718166708946228},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0719875693321228},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0652572512626648},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetci.2024.3369485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2024.3369485","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"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 Emerging Topics in Computational Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G1917244243","display_name":null,"funder_award_id":"62276202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5966497531","display_name":null,"funder_award_id":"62106186","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8132092863","display_name":null,"funder_award_id":"QTZX22047","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W131069610","https://openalex.org/W1854270966","https://openalex.org/W1969483458","https://openalex.org/W1988648633","https://openalex.org/W1997840820","https://openalex.org/W2009525320","https://openalex.org/W2103120971","https://openalex.org/W2128990851","https://openalex.org/W2133833812","https://openalex.org/W2141664020","https://openalex.org/W2163178194","https://openalex.org/W2169528473","https://openalex.org/W2201581102","https://openalex.org/W2343616166","https://openalex.org/W2728420778","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2751627329","https://openalex.org/W2887439418","https://openalex.org/W2896112628","https://openalex.org/W2907217398","https://openalex.org/W2938321354","https://openalex.org/W2963523627","https://openalex.org/W2964884740","https://openalex.org/W2971481292","https://openalex.org/W2973229164","https://openalex.org/W3029271058","https://openalex.org/W3034257692","https://openalex.org/W3034563340","https://openalex.org/W3049557657","https://openalex.org/W3088197938","https://openalex.org/W3118513984","https://openalex.org/W3129584569","https://openalex.org/W3132442447","https://openalex.org/W3138639222","https://openalex.org/W3174337303","https://openalex.org/W3193130279","https://openalex.org/W3193878267","https://openalex.org/W3208032334","https://openalex.org/W3210448484","https://openalex.org/W4200589899","https://openalex.org/W4206919818","https://openalex.org/W4210616537","https://openalex.org/W4214717370","https://openalex.org/W4226396566","https://openalex.org/W4236251699","https://openalex.org/W4283800386","https://openalex.org/W4287827583","https://openalex.org/W4298857966","https://openalex.org/W4323339346","https://openalex.org/W4364857867","https://openalex.org/W6605295560","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6680235470","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6717230150","https://openalex.org/W6735033012","https://openalex.org/W6741002519","https://openalex.org/W6748839928","https://openalex.org/W6767226293","https://openalex.org/W6771843596","https://openalex.org/W6803800456"],"related_works":["https://openalex.org/W3094054656","https://openalex.org/W4285676344","https://openalex.org/W2123270665","https://openalex.org/W4382584175","https://openalex.org/W2359600231","https://openalex.org/W2380019117","https://openalex.org/W3138952546","https://openalex.org/W1660309994","https://openalex.org/W2369187583","https://openalex.org/W3197207153"],"abstract_inverted_index":{"Unmanned":[0],"aerial":[1],"vehicles":[2],"(UAVs)":[3],"are":[4],"widely":[5],"used":[6],"in":[7,54,95,98],"urban":[8],"search":[9],"and":[10,41,78,111,155],"rescue,":[11],"where":[12],"path":[13,48],"planning":[14,49,149],"plays":[15],"a":[16,67],"critical":[17],"role.":[18],"This":[19],"paper":[20],"proposes":[21],"an":[22,30],"approach":[23],"using":[24,106],"off-policy":[25,89,128,139],"reinforcement":[26],"learning":[27],"(RL)":[28],"with":[29,100],"improved":[31],"exploration":[32,43],"mechanism":[33],"(IEM)":[34],"based":[35,70],"on":[36,71],"prioritized":[37],"experience":[38],"replay":[39],"(PER)":[40],"curiosity-driven":[42],"to":[44,59,73,115,136],"address":[45,84],"the":[46,61,75,85,107,123,137,142,148,157],"time-constrained":[47],"problem":[50],"for":[51,152],"UAVs":[52],"operating":[53],"complex":[55],"unknown":[56],"environments.":[57],"Firstly,":[58],"meet":[60],"task's":[62],"time":[63,110,150],"constraints,":[64],"we":[65,83,119],"design":[66],"rollout":[68],"algorithm":[69],"PER":[72],"optimize":[74],"behavior":[76],"policy":[77],"enhance":[79],"sampling":[80,124],"efficiency.":[81],"Additionally,":[82],"issue":[86],"that":[87],"certain":[88],"RL":[90,129,140],"algorithms":[91,143],"often":[92],"get":[93],"trapped":[94,162],"local":[96],"optima":[97],"environments":[99],"sparse":[101],"rewards":[102,114],"by":[103],"measuring":[104],"curiosity":[105],"states'":[108],"unvisited":[109],"generating":[112],"intrinsic":[113],"encourage":[116],"exploration.":[117],"Lastly,":[118],"introduce":[120],"IEM":[121,145],"into":[122],"stage":[125],"of":[126,159],"various":[127],"algorithms.":[130],"Simulation":[131],"experiments":[132],"demonstrate":[133],"that,":[134],"compared":[135],"original":[138],"algorithms,":[141],"incorporating":[144],"can":[146],"reduce":[147],"required":[151],"rescuing":[153,160],"paths":[154],"achieve":[156],"goal":[158],"all":[161],"individuals.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}