Autonomous maneuver decision-making for a UCAV in short-range aerial combat based on an MS-DDQN algorithm

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.     

密集环境中无人机协同机动飞行运动规划方法综述

从单无人机机动飞行向多机协同扩展的通用规划框架出发,介绍了其中各模块相关研究的基本原理、代表性方法和前沿研究,主要包括用于环境障碍感知的实时导航地图构建、离散空间的路径规划、连续空间的轨迹规划、基于离散连续混合空间的规划、多航迹或轨迹的协同规划。综合无人机通用规划框架的关键技术,提出了无人机协同机动规划下一步需要重点研究的方向。     

高空长航时无人机编队协同侦察任务规划

针对高空长航时无人机侦察任务规划特点,分析了高空长航时无人机执行侦察任务过程中的飞行航线约束和通信条件约束,以最小化无人机总飞行航程和最终编队飞行时间为优化目标,建立无人机编队协同侦察任务规划问题模型。同以往的通用侦察任务模型相比,该模型突出考虑了高空长航时无人机执行侦察任务过程的特点。以基本粒子群算法为基础,通过粒子群离散化和结合遗传算法进行改进,使其适用于求解复杂组合优化问题。仿真结果验证了算法求解复杂任务规划问题的有效性。     

Outflanking missile defences: the Nuclear Non-proliferation Treaty,nuclear weapons and terrorism

Ian Bellany, an Emeritus Professor of Politics at Lancaster University, died in July 2011 at the age of 70, after a long and painful struggle with myelofibrosis, a rare and invariably terminal blood cancer. Between early 2009 and August 2010, under contract to Hurst & Co., he worked intermittently on a book about nuclear terrorism, which he provisionally entitled Before the Storm. The editor and I are grateful to Michael Dwyer at Hurst & Co. for releasing the draft. What is published here is an edited version of that draft. It may seem presumptuous to speak for Ian, but I am sure he would also have liked to thank the doctors and nurses of the NHS Morecambe Bay Universities Hospital Trust, whose skill, knowledge, and flair for improvisation kept him alive and writing for much longer than anyone expected. Alastair Bellany, Rutgers University, New Jersey, USA.

In the past, terrorists have tended to eschew acts of extreme violence for fear of alienating those whom they wish to persuade and attract to their cause. The first to discard this philosophy was the Aum group in Japan, which sought to use anthrax and acquire a nuclear weapon. Since then, attitudes have changed, spurred on by the impact on public perception of the successful Al Qaeda 9/11 attack on New York and Washington. By crossing the line between moderation and extreme violence, terrorist groups retain one valuable capability: they are much less easily deterred and have few inhibitions. This article considers the three nuclear options open to terrorists – produce a radiological contaminant bomb; build a nuclear bomb; or steal or get given a nuclear device. It examines the possibilities and probabilities of each option and considers how the implementation of the Nuclear Non-proliferation Treaty (NPT) provisions might impose some constraints on terrorists’ nuclear ambitions. By examining the doubtful nuclear security practices of different states and providing statistical evidence of an increase in levels of international terrorist violence, this article points to determined terrorists in time acquiring the means to acquire one or other variants of a nuclear weapon. It concludes that it is not a matter of “if” but “when.”     

融合地面多传感器信息引导无人机着陆

针对无人机自主着陆过程中卫星导航系统易被干扰的问题,提出了一种基于地基多传感器融合的无人机自主着陆引导方法。采用主动式激光照射的方式,获取机载反射棱镜的近红外成像,在红外图像中对无人机目标进行识别;通过坐标转换将识别结果映射到可见光图像中,在可见光图像中选择的感兴趣区域进行可见光目标识别,从而在降低计算量的基础上获得更加精确的无人机相对角度信息;利用距离测量信息和引导系统角度信息可以获得精确的无人机相对位置。无人机着陆引导试验结果表明,该方法能够提供精确的无人机位置信息,能有效适应于复杂背景下的无人机自主着陆引导。     

机翼变形的临近空间太阳能飞行器平稳升空方案

临近空间太阳能飞行器由于苛刻的能源平衡约束,往往具有大展弦比轻质结构,使得其在低空飞行时空速过低,飞行安全性受到了显著的挑战。为了实现该类飞行器在临近空间工作点与中低空爬升过程的气动性能匹配,提出了基于主动变形的太阳能飞行器升空方案。针对性地研究了可变形飞行器的气动和推进系统建模方法,在此基础上定量分析了不同飞行器构型俯仰、滚转和偏航三个通道稳定性和操纵性。给出了从地面到高空机翼逐渐展平的升空方案,并对升空过程中各高度所需平飞推力和功率进行了校核。结果显示,该方案可以有效提升飞行器中低空稳定性和操纵性,代价是增加了功率消耗。     

有人/无人机协同作战指挥界面设计

分析了近期内有人/无人机协同作战的体系结构及作战模式,基于三代战机座舱普遍装备的多功能显示器,展开有人/无人机指挥控制界面的设计;基于人机工程学观点和飞行员的视觉习惯,从缓解飞行员的心理和生理疲劳的角度出发布置无人机编队的飞行参数,设计了有人/无人机执行协同对地攻击任务时包含巡航队形、战斗队形、任务类型、导航点切换等功能的指挥控制界面。为未来短期内有人/无人机协同作战指挥控制系统研究提供参考。     

基于扩展卡尔曼滤波的雷达无源定位方法

提出了基于扩展卡尔曼滤波的雷达无源定位技术。利用多无人机平台对雷达网进行航迹欺骗,需要对网内的雷达进行定位以达到精确欺骗干扰的目的。但飞行器在飞行过程量测噪声较高,传统的时差定位方法无法满足定位精度的要求。对于时差定位的非线性时变模型,提出了利用时变扩展卡尔曼滤波对雷达位置进行跟踪定位的方法。仿真结果显示,利用扩展卡尔滤波进行无源定位可以在高噪声背景下有较好的定位精度。     

一种基于单幅跑道图像的无人机降落位姿测量新方法

提出了一种在无人机降落并接近跑道的过程中,在已知跑道宽度的前提下,基于单幅跑道图像测量其位姿参数的新方法.通过分析跑道消影点与无人机位姿的关系,得到消影点的图像坐标与姿态角的关系.依据摄像机共线方程,推导出了无人机位姿与跑道的世界坐标方程系数及像直线方程系数的关系.通过合理假设,对位姿参数进行了简化,求解出无人机降落过程中的位姿状态.仿真实验结果证明,方法易于实现,可满足无人机自主降落导航的应用需求.     

雷达哨舰在编队对空预警中的前出阵位研究

针对现代海战中空袭目标的特点,确定雷达哨舰在编队对空预警中的前出阵位。论述了雷达哨舰在编队对空预警中的使用原则,分析了影响雷达哨舰前出阵位的各因素,建立了雷达哨舰阵位配置和预警机动区的数学模型,采用MATLAB7.0工具仿真计算了模型中各参数对哨舰前出距离和预警机动区面积的影响,得到了雷达哨舰配置的约束条件,可为对编队组织对空预警提供参考。