To solve the problem of realizing autonomous aerial combat decision-making for unmanned combat aerial vehicles(UCAVs)rapidly and accurately in an uncertain environment,this paper proposes a decision-making method based on an improved deep reinforcement learning(DRL)algorithm:the multi-step double deep Q-network(MS-DDQN)algorithm.First,a six-degree-of-freedom UCAV model based on an aircraft control system is established on a simulation platform,and the situation assessment functions of the UCAV and its target are established by considering their angles,altitudes,environments,missile attack performances,and UCAV performance.By controlling the flight path angle,roll angle,and flight velocity,27 common basic actions are designed.On this basis,aiming to overcome the defects of traditional DRL in terms of training speed and convergence speed,the improved MS-DDQN method is introduced to incorporate the final return value into the previous steps.Finally,the pre-training learning model is used as the starting point for the second learning model to simulate the UCAV aerial combat decision-making process based on the basic training method,which helps to shorten the training time and improve the learning efficiency.The improved DRL algorithm significantly accelerates the training speed and estimates the target value more accurately during training,and it can be applied to aerial combat decision-making.

Yong-feng Li;Jing-ping Shi;Wei Jiang;Wei-guo Zhang;Yong-xi Lyu

School of Automation,Northwestern Polytechnical University,Xi'an,710129,China;Shaanxi Province Key Laboratory of Flight Control and Simulation Technology,Xi'an,710129,China

防务技术

[1]Yong-feng Li;Jing-ping Shi;Wei Jiang;Wei-guo Zhang;Yong-xi Lyu-.Autonomous maneuver decision-making for a UCAV in short-range aerial combat based on an MS-DDQN algorithm)[J].防务技术,2022(09):1697-1714

Autonomous,maneuver,decision,making,range,aerial,combat,DDQN,algorithm,To,solve,problem,realizing,autonomous,unmanned,vehicles,UCAVs,rapidly,accurately,uncertain,this,paper,proposes,method,improved,deep,reinforcement,learning,DRL,multi,double,network,First,six,degree,freedom,model,aircraft,system,established,simulation,platform,situation,assessment,functions,its,target,are,by,considering,their,angles,altitudes,environments,missile,attack,performances,By,controlling,flight,path,velocity,common,basic,actions,designed,On,basis,aiming,overcome,defects,traditional,terms,training,speed,convergence,introduced,incorporate,final,return,value,into,previous,steps,Finally,used,starting,point,second,simulate,process,which,helps,shorten,efficiency,significantly,accelerates,estimates,more,during,be,applied

0.503912