MagDet:基于地磁的无人机GPS欺骗检测方法

GPS是目前最为广泛使用的基于卫星的导航和定位系统,对于无人机而言,它是一个不可或缺的组成部分,提供了关键的精确位置数据,对导航和任务的成功至关重要.然而,GPS欺骗攻击已经逐渐演变成对GPS依赖系统不断增加的威胁.目前,针对无人机的GPS欺骗检测方法大多基于仿真数据提出、依赖于多个无人机或者需要专用设备(例如,软件定义无线电平台和高清摄像头).本文提出一种新颖的基于地磁场的无人机GPS欺骗检测方法——Mag Det(Magnetic field-based Detection method),其基本思想是利用地球内部和周围金属建筑材料不均匀性引起的地磁场异常,通过真实飞行收集位置和磁场强度数据,包括正常和被攻击场景.应用各种机器学习算法来训练这些数据以选择最佳分类器,该分类器可以轻松部署在常见机载计算机中.该方法的检测率超过99.5%,平均错误率(Equal Error Rate,EER)为0.51%,优于现有检测方法.此外,评估了各种因素对Mag Det的影响,以证明其鲁棒性.即使在未访问过的地点(距离6 km),准确率也高于95%,EER为0.49%.     

基于LSTM-KF模型的无人机抗GPS欺骗方法

针对无人机 GPS 信号易受干扰、易欺骗的问题,提出一种结合深度学习和卡尔曼滤波的无人机抗GPS欺骗的检测方法,该方法通过使用长短期记忆网络从无人机飞行状态中预测得到无人机飞行的动力学模型,并利用卡尔曼滤波结合动力学模型进行动态调整来识别GPS欺骗,从而达到抵御GPS欺骗信号干扰的目的,同时该方法无须增加接收器的硬件开销,且易于实现。实验结果证明,相比同类方法,该方法对于识别GPS信号具有更高的准确率和更低的误报率,可有效增强无人机抗GPS欺骗干扰的能力。     

Elman神经网络多传感器融合技术的研究与应用

由于重力传感器容易受环境温度等各种非目标参量的影响,其输出性能大大降低,为此,采用Elman神经网络多传感器融合技术加以解决.传感器信息融合是对多种信息的获取、表示及其内在联系进行综合处理和优化的技术.多传感器信息经过融合后能够完善、准确地反映环境的特征.采用Elman神经网络补偿由系统的非线性和外界干扰引起的误差.仿真试验表明,该算法计算量小、拟合程度好、精确度高.     

基于加速度信息修正的四旋翼位置估计算法研究

针对单一的微传感器无法准确进行四旋翼无人机空间定位的问题,设计了一种多元信息融合的互补滤波算法用于无人机空间位置估计。该算法的核心思想为利用一类通用的辅助传感器如气压传感器,全球定位系统（GPS）以及微基站的测量信息对加速度传感器的测量信息进行实时修正,然后利用修正后的加速度信息积分估计四旋翼无人机的空间位置。本文在自主研制的飞行控制平台上验证了这种互补滤波算法的有效性。通过对比实验验证,利用本文设计的互补滤波算法可以使得无人机运动速度估计值以及空间位置估计值无偏差的收敛。飞行实验证明,将该互补滤波算法输出的速度以及位置估计信息应用于位置控制器中,可以实现无人机稳定的位置控制。     

基于力传感的系留无人机定位方法研究

在无GPS或弱GPS环境下,系留无人机通常采用激光雷达或视觉进行定位,由于受距离和光线的影响,无法实现精准定位。针对该问题,提出了一种基于力传感的系留无人机绳缆定位方法。系留无人机在室内飞行时,绳缆的状态可等效于悬链线,通过建立系留无人机悬链线模型,可有效估计无人机所处空间位置。使用基于力传感器的无人机、硅胶绳缆、绕线机搭建测试平台,绳缆定位数据与MarveImind的Indoor“GPS”标定无人机的位置做误差对比分析。实验结果表明:基于力传感的系留无人机定位方法,相较于Fotokite Pro无人机绳缆定位方法,定位精度提升了70.86%。该定位方法的提出,有利于系留无人机在无GPS环境下的稳定飞行。     

利用地面景象信息辅助的无人机自主定位技术

针对无人机自主定位过程中GPS定位系统失效的问题,提出了一种利用地面景象信息辅助的无人机自主定位技术,首先利用无人机所拍摄的实时航拍图像,与预先储存在无人机计算机中地面景象的数字化地形图进行匹配,从匹配结果中提取一个同名像点,结合地面景象数字化地形图所提供的数据信息获取此同名像点的地理位置坐标,根据同名像点位置与无人机位置间的几何关系,结合机载光电测量系统的坐标转换过程,实现无人机的自主定位过程。利用已知的地面同名像点的地理位置信息,反推出无人机的地理位置信息具有一定的创新性。由于整个定位过程存在实际误差,因此利用无人机飞行时记录的数据,采用蒙特卡罗法对定位误差进行仿真试验。试验结果表明该技术能够在误差允许范围内,在GPS定位系统失效的情况下完成无人机的自主定位     

基于优化异质BP神经网络信息融合的清洁机器人定位研究

清洁机器人的移动定位是个复杂的非线性定位的问题,精密机械结构与路径规划无法补偿定位不精确造成的移动误差,提出一种基于异质RBF神经网络信息融合的清洁机器人定位技术,设计了智能机器人的控制系统、移动系统和感知系统,设计多个位姿传感器后,实时采集位置信息,在主控芯片中使用粒子群优化神经网络技术对多传感器的信息进行融合,计算清洁机器人的位置信息,解决了位置因素非线性强,定位误差大的问题,并且有效提高了神经网络的局部收敛能力;使用机器人多传感器的实验平台测试证明,这种方法下清洁机器人的移动中定位准确率较传统方法提高13%,具有很强的可靠性与实用性。     

基于径向基神经网络的称重设备传感器故障检测方法

在对称重设备数字化改造的过程中,有些研究人员提出了对某一特定传感器的故障诊断方法,但对于非指定传感器或者两个传感器同时发生故障的情况却没有检测方法.为此,本文提出了一种基于径向基神经网络预测的任意一个或两个称重传感器的故障检测方法.本文首先建立单个传感器的预测模型和任意两个传感器的预测模型,然后通过这两个预测模型计算出任意一个称重传感器的预测值和任意两个传感器的预测值,根据预测值与实际值之间的差值判断称重传感器故障个数、位置、类型等信息.实验表明,当称重传感器的输出误差大于0.3 t时使用此方法可以准确检测出称重传感器的故障信息.     

无人驾驶飞机精确定位方法研究

GPS技术已广泛应用于无人驾驶飞机的空间定位和导航,但在战时、困难地区的应用会受到限制。文章提出了一种利用多点约束的影像匹配技术实现无人机精确定位的方法,该方法基于多点约束的思想提高了影像匹配的可靠性,同时利用匹配获取的多个同名点解决了由于无人机空中姿态变化引起的单点无法精确定位问题。该方法首先对无人机获取的实时影像和基准影像进行小波变换处理,以便从实时影像上获得足够的明显特征点,然后利用影像匹配和匹配点之间的位置约束关系获取基准影像上的同名点位,使用这些同名点,可以得到精确的无人机空间位置。     

基于Elman递归神经网络的汽车牌照定位方法研究

该文提出了一种新的基于Elman递归神经网络的汽车牌照定位方法。Elman递归神经网络具有上下文层 ,它将隐含层前一时刻的输出反馈到当前时刻的输入 ,这种反馈连接使Elman网络能够检测随时间变化的序列信息。该文的牌照定位方法利用Elman神经网络的反馈连接特性以及牌照区的水平和垂直两个方向的梯度特征不同于图像中的其它区域的特点 ,以一个小窗体 (12× 12 )内图像在两个方向的梯度值 ,对神经网络进行训练 ,然后在同样的梯度图上滑动该小窗体 ,让训练后的神经网络判断小窗体内的区域是否为牌照区的一部分 ,并结合汽车牌照的几何特征来实现牌照定位。实验结果表明该方法的准确定位率高     

基于NARX神经网络辅助组合导航方法研究

为解决短时全球导航卫星系统(GNSS)失效造成车载组合导航系统导航精度下降的问题,提出一种NARX神经网络辅助的组合导航方法。对神经网络辅助导航的原理进行了分类,并分析了神经网络可利用的输入输出信息,提出一种根据惯性测量单位(IMU)测量信息和惯性导航解算信息对GNSS位置速度增量进行预测的方法。通过实测数据实验验证了方法的有效性,GNSS失效60 s期间,导航最大位置误差5.1 m、最大速度误差0.15 m/s。     

基于MLP神经网络改进组合导航算法

为解决GPS信号失锁条件下,GPS/INS(inertial navigation system)组合导航系统解算精度降低甚至发散的问题,提出采用多层感知机神经网络(multilayer perceptron neural networks,MLPNN)来辅助组合导航系统.在GPS信号有效时对神经网络进行训练,在GPS...     

Spoofing Signal Generation Based on Manipulation of Code Delay and Doppler Frequency of Authentic GPS Signal

We propose an efficient spoofing signal generation method that uses the processing results of a global positioning system (GPS) receiver for authentic GPS signals. Conventional methods of generating spoofing signals use expensive GPS simulators because the structures of the spoofing signals must be almost identical to those of the GPS signals. Simulators require GPS ephemeris at a specific time and target position. Subsequently, a complicated process is used to generate navigation data using the ephemeris and model error sources such as the satellite clock bias and ionospheric delay. In contrast, the proposed method can generate spoofing signals for the desired target position without requiring GPS simulators; it does so by adjusting the signal processing results of the receiver. Using the navigation results of the receiver, such as position and velocity, the pseudorange delay and spoofing Doppler frequency between the estimated position of the receiver and the target spoofing position are obtained; these are then applied to shift the signal-tracking results of the receiver to create a new signal for the target spoofing position. Our experimental results indicate that the proposed algorithm can effectively generate spoofing signals with characteristics highly similar to those of authentic GPS signals. In addition, we confirmed that the spoofing signals generated by the proposed method are difficult to be detected using conventional spoofing detection techniques.

     

A New Approach to Estimate True Position of Unmanned Aerial Vehicles in an INS/GPS Integration System in GPS Spoofing Attack Conditions

This paper presents a new approach to estimate the true position of an unmanned aerial vehicle (UAV) in the conditions of spoofing attacks on global positioning system (GPS) receivers. This approach consists of two phases, the spoofing detection phase which is accomplished by hypothesis test and the trajectory estimation phase which is carried out by applying the adapted particle filters to the integrated inertial navigation system (INS) and GPS. Due to nonlinearity and unfavorable impacts of spoofing signals on GPS receivers, deviation in position calculation is modeled as a cumulative uniform error. This paper also presents a procedure of applying adapted particle swarm optimization filter (PSOF) to the INS/GPS integration system as an estimator to compensate spoofing attacks. Due to memory based nature of PSOF and benefits of each particle’s experiences, application of PSOF algorithm in the INS/GPS integration system leads to more precise positioning compared with general particle filter (PF) and adaptive unscented particle filer (AUPF) in the GPS spoofing attack scenarios. Simulation results show that the adapted PSOF algorithm is more reliable and accurate in estimating the true position of UAV in the condition of spoofing attacks. The validation of the proposed method is done by root mean square error (RMSE) test.     

组合导航系统离线信息融合算法

获得高精度的载体实际飞行轨迹,是组合导航系统性能评测的重要手段.从组合导航系统研究出发,针对惯性导航系统、姿态(非姿态)型GPS和大气数据计算机多传感器组合导航方式,实现多传感器信息离线融合算法.同类型导航传感器数据采用加权最小二乘算法,并利用开环卡尔曼滤波实现组合导航的信息融合,在此基础上再进行最优固定区间平滑滤波.仿真实验结果表明,经过上述3步信息融合之后,得到的导航结果精度不仅高于任一个传感器精度,而且高于单独采用卡尔曼滤波的导航参数精度.     

Sensor Integration for Satellite-Based Vehicular Navigation Using Neural Networks

Land vehicles rely mainly on global positioning system (GPS) to provide their position with consistent accuracy. However, GPS receivers may encounter frequent GPS outages within urban areas where satellite signals are blocked. In order to overcome this problem, GPS is usually combined with inertial sensors mounted inside the vehicle to obtain a reliable navigation solution, especially during GPS outages. This letter proposes a data fusion technique based on radial basis function neural network (RBFNN) that integrates GPS with inertial sensors in real time. A field test data was used to examine the performance of the proposed data fusion module and the results discuss the merits and the limitations of the proposed technique     

组合导航中低成本磁航向系统的神经网络补偿

根据组合导航的特点,设计了低成本磁航向系统神经网络补偿方法。研究了磁航向系统的误差和补偿技术;在全球定位系统信号良好情况下,以捷联惯导/全球定位组合导航系统的航向信息为参考,使用卡尔曼滤波作为学习算法,建立多层前向神经网络模型补偿磁航向系统。实验结果表明,神经网络补偿方法将磁航向系统的航向角误差由±15°减小到约±1°,取得了明显的效果。     

基于SLAM的旋翼无人机组合导航算法研究

在旋翼无人机组合导航中,针对缺乏GPS作为导航信号源的室内飞行环境,为了达到精确定位的目的,提出一种基于SLAM（simultaneous localization and mapping）的旋翼无人机组合导航算法。首先,引入双线性插值算法,实现基于扫描匹配的即时定位与地图构建;其次,对陀螺仪、加速度计和磁罗盘建立捷联惯导系统误差模型,针对旋翼无人机的使用环境对误差模型进行简化;最后,应用联邦卡尔曼滤波算法,设计组合导航系统模型,将SLAM算法和捷联惯导系统估计出的位置数据进行融合。仿真结果表明所设计基于SLAM的旋翼无人机组合导航算法能够进一步提高组合导航系统对旋翼无人机位姿估计的精度。     

Optimizing neuro-fuzzy modules for data fusion of vehicular navigation systems using temporal cross-validation

The last two decades have shown an increasing trend in the use of positioning and navigation technologies in land vehicles. Most of the present navigation systems incorporate global positioning system (GPS) and inertial navigation system (INS), which are integrated using Kalman filtering (KF) to provide reliable positioning information. Due to several inadequacies related to KF-based INS/GPS integration, artificial intelligence (AI) methods have been recently suggested to replace KF. Various neural network and neuro-fuzzy methods for INS/GPS integration were introduced. However, these methods provided relatively poor positioning accuracy during long GPS outages. Moreover, the internal system parameters had to be tuned over time of the navigation mission to reach the desired positioning accuracy. In order to overcome these limitations, this study optimizes the AI-based INS/GPS integration schemes utilizing adaptive neuro-fuzzy inference system (ANFIS) by implementing, a temporal window-based cross-validation approach during the update procedure. The ANFIS-based system considers a non-overlap moving window instead of the commonly used sliding window approach. The proposed system is tested using differential GPS and navigational grade INS field test data obtained from a land vehicle experiment. The results showed that the proposed system is a reliable modeless system and platform independent module that requires no priori knowledge of the navigation equipment utilized. In addition, significant accuracy improvement was achieved during long GPS outages.     

Improving positioning accuracy of vehicular navigation system during GPS outages utilizing ensemble learning algorithm

Recently, methods based on Artificial Intelligence (AI) have been widely used to improve positioning accuracy for land vehicle navigation by integrating the Global Positioning System (GPS) with the Strapdown Inertial Navigation System (SINS). In this paper, we propose the ensemble learning algorithm instead of traditional single neural network to overcome the limitations of complex and dynamic data cased by vehicle irregular movement. The ensemble learning algorithm (LSBoost or Bagging), similar to the neural network, can build the SINS/GPS position model based on current and some past samples of SINS velocity, attitude and IMU output information. The performance of the proposed algorithm has been experimentally verified using GPS and SINS data of different trajectories collected in some land vehicle navigation tests. The comparison results between the proposed model and traditional algorithms indicate that the proposed algorithm can improve the positioning accuracy for cases of SINS and specific GPS outages.