典型文献
Safe Navigation for UAV-Enabled Data Dissemination by Deep Reinforcement Learning in Unknown Environments
文献摘要：
Unmanned aerial vehicles (UAVs) are increasingly considered in safe autonomous naviga-tion systems to explore unknown environments where UAVs are equipped with multiple sensors to perceive the surroundings.However,how to achieve UAV-enabled data dissemination and also ensure safe nav-igation synchronously is a new challenge.In this pa-per,our goal is minimizing the whole weighted sum of the UAV's task completion time while satisfying the data transmission task requirement and the UAV's fea-sible flight region constraints.However,it is unable to be solved via standard optimization methods mainly on account of lacking a tractable and accurate sys-tem model in practice.To overcome this tough issue,we propose a new solution approach by utilizing the most advanced dueling double deep Q network (duel-ing DDQN) with multi-step learning.Specifically,to improve the algorithm,the extra labels are added to the primitive states.Simulation results indicate the va-lidity and performance superiority of the proposed al-gorithm under different data thresholds compared with two other benchmarks.
文献关键词：
中图分类号：
作者姓名：
Fei Huang;Guangxia Li;Shiwei Tian;Jin Chen;Guangteng Fan;Jinghui Chang
作者机构：
College of Communications Engineering,Army Engineering University,Nanjing 210007,China;The National Innovation Institute of Defense Technology,Chinese Academy of Military Sciences,Beijing 100071,China;The Satellite Communication Center,Beijing 102300,China
文献出处：
引用格式：
[1]Fei Huang;Guangxia Li;Shiwei Tian;Jin Chen;Guangteng Fan;Jinghui Chang-.Safe Navigation for UAV-Enabled Data Dissemination by Deep Reinforcement Learning in Unknown Environments)[J].中国通信（英文版）,2022(01):202-217
A类：
duel,lidity
B类：
Safe,Navigation,Enabled,Data,Dissemination,by,Deep,Reinforcement,Learning,Unknown,Environments,Unmanned,aerial,vehicles,UAVs,increasingly,considered,safe,autonomous,naviga,systems,explore,unknown,environments,where,equipped,multiple,sensors,perceive,surroundings,However,how,achieve,enabled,data,dissemination,also,ensure,synchronously,new,challenge,In,this,our,goal,minimizing,whole,weighted,sum,task,completion,while,satisfying,transmission,requirement,fea,sible,flight,region,constraints,unable,solved,via,standard,optimization,methods,mainly,account,lacking,tractable,accurate,model,practice,To,overcome,tough,issue,solution,approach,utilizing,most,advanced,dueling,double,deep,network,DDQN,step,learning,Specifically,improve,algorithm,extra,labels,added,primitive,states,Simulation,results,indicate,performance,superiority,proposed,under,different,thresholds,compared,other,benchmarks
AB值：
0.67534
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
