欢迎访问《兵工学报》官方网站,今天是 分享到:

兵工学报 ›› 2020, Vol. 41 ›› Issue (8): 1613-1622.doi: 10.3969/j.issn.1000-1093.2020.08.016

• 论文 • 上一篇    下一篇

基于深度神经网络的无人作战飞机自主空战机动决策

张宏鹏1, 黄长强1, 轩永波2, 唐上钦1   

  1. (1.空军工程大学 航空工程学院, 陕西 西安 710038; 2.空军研究院 航空兵研究所, 北京 100085)
  • 收稿日期:2019-10-14 修回日期:2019-10-14 上线日期:2020-09-23
  • 通讯作者: 黄长强(1961—),男,教授,博士生导师 E-mail:hcqxian@163.com
  • 作者简介:张宏鹏(1996—),男,硕士研究生。E-mail:1152951370@qq.com
  • 基金资助:
    国家自然科学基金项目(51579209)

Maneuver Decision of Autonomous Air Combat of Unmanned Combat Aerial Vehicle Based on Deep Neural Network

ZHANG Hongpeng1, HUANG Changqiang1, XUAN Yongbo2, TANG Shangqin1   

  1. (1.Aeronautics Engineering College, Air Force Engineering University, Xi'an 710038, Shaanxi, China; 2.Aviation Research Institute, Air Force Research Institute, Beijing 100085, China)
  • Received:2019-10-14 Revised:2019-10-14 Online:2020-09-23

摘要: 机动决策是决定无人作战飞机空战成败的关键因素。为提高空战获胜概率,提出用深度神经网络进行决策。构建了36种机动动作,通过飞行仿真,得到由当前态势、控制量和未来态势构成的样本;用样本训练深度神经网络,使其能够根据当前信息快速准确预测未来态势,设计了决策目标函数和态势评估函数,空战过程中,利用训练好的网络预测所有动作对应的未来态势,根据决策目标函数从中选出最优动作;在不同初始条件下,分别与采用简单机动和自主机动的敌机进行空战仿真,并对空战态势进行评估。结果表明,所提方法在均势时能通过较少的动作获得空战胜利,在劣势时能通过一系列机动获得优势,且决策用时缩短了9 ms.

关键词: 无人作战飞机, 机动决策, 深度神经网络, 空战态势, 飞行仿真

Abstract: Maneuver decision is a critical factor which determines the success and failure of air combat for unmanned combat aerial vehicle. In order to increase the probability of wining air combat, a deep neural network (DNN) is proposed for maneuver decision. 36 kinds of maneuvers were constructed, and the samples of current situation, control quantity and future situation were acquired through flight simulations. The DNN is trained with the samples, making it capable of predicting future situation according to current information. Decision target function and situation assessment function were designed. In the process of air combat, the trained DNN is used to predict the future situations corresponding to all maneuvers, and the best maneuver is selected from all the maneuvers according to decision target function. The enemy planes which simply and autonomously maneuver were simulated, respectively, under different initial conditions, and the air combat situations were also assessed. The results show that the proposed decision method can be used to win air combat with less actions at balanced situation, and gain an edge through a series of actions at adverse situation, and the decision-making time is reduced by 9 ms.

Key words: unmannedcombataerialvehicle, maneuverdecision, deepneuralnetwork, aircombatsituation, flightsimulation

中图分类号: