A security issue with multi-sensor unmanned aerial vehicle(UAV)cyber physical systems(CPS)from the viewpoint of a false data injection(FDI)attacker is investigated in this paper.The FDI attacker can employ attacks on ...A security issue with multi-sensor unmanned aerial vehicle(UAV)cyber physical systems(CPS)from the viewpoint of a false data injection(FDI)attacker is investigated in this paper.The FDI attacker can employ attacks on feedback and feed-forward channels simultaneously with limited resource.The attacker aims at degrading the UAV CPS's estimation performance to the max while keeping stealthiness characterized by the Kullback-Leibler(K-L)divergence.The attacker is resource limited which can only attack part of sensors,and the attacked sensor as well as specific forms of attack signals at each instant should be considered by the attacker.Also,the sensor selection principle is investigated with respect to time invariant attack covariances.Additionally,the optimal switching attack strategies in regard to time variant attack covariances are modeled as a multi-agent Markov decision process(MDP)with hybrid discrete-continuous action space.Then,the multi-agent MDP is solved by utilizing the deep Multi-agent parameterized Q-networks(MAPQN)method.Ultimately,a quadrotor near hover system is used to validate the effectiveness of the results in the simulation section.展开更多
面向有人车引导的无人多车编队场景,设计并实现无人车在编队行驶中的车辆识别与轨迹跟踪控制系统,提出了一种多传感器后融合动目标检测算法,使用激光雷达、相机和毫米波雷达3种传感器作为数据源,分别使用欧式聚类、深度学习和运动学推...面向有人车引导的无人多车编队场景,设计并实现无人车在编队行驶中的车辆识别与轨迹跟踪控制系统,提出了一种多传感器后融合动目标检测算法,使用激光雷达、相机和毫米波雷达3种传感器作为数据源,分别使用欧式聚类、深度学习和运动学推理的方法对潜在目标进行检测,进而提出后融合方法将多源检测结果融合以实现对前方车辆的准确检测。基于前车轨迹生成期望路径并设计卡尔曼滤波器对期望路径进行平滑和滤波。构建车辆动力学模型、车辆道路误差模型并设计鲁棒H∞控制器进行车辆轨迹跟踪控制仿真。仿真与实车验证结果表明:在测试路段对前方车辆的平均识别准确率大于95%;实时期望路径相对于真实轨迹的均方差和轨迹平均变化率在滤波前后分别降低17.3%和48.6%;侧向控制位置误差和航向角误差相较于PID(proportional integral derivative)控制分别降低了29%和41%;车辆编队以最高54 km/h的速度实现编队整体的稳定行驶。展开更多
文摘A security issue with multi-sensor unmanned aerial vehicle(UAV)cyber physical systems(CPS)from the viewpoint of a false data injection(FDI)attacker is investigated in this paper.The FDI attacker can employ attacks on feedback and feed-forward channels simultaneously with limited resource.The attacker aims at degrading the UAV CPS's estimation performance to the max while keeping stealthiness characterized by the Kullback-Leibler(K-L)divergence.The attacker is resource limited which can only attack part of sensors,and the attacked sensor as well as specific forms of attack signals at each instant should be considered by the attacker.Also,the sensor selection principle is investigated with respect to time invariant attack covariances.Additionally,the optimal switching attack strategies in regard to time variant attack covariances are modeled as a multi-agent Markov decision process(MDP)with hybrid discrete-continuous action space.Then,the multi-agent MDP is solved by utilizing the deep Multi-agent parameterized Q-networks(MAPQN)method.Ultimately,a quadrotor near hover system is used to validate the effectiveness of the results in the simulation section.
文摘面向有人车引导的无人多车编队场景,设计并实现无人车在编队行驶中的车辆识别与轨迹跟踪控制系统,提出了一种多传感器后融合动目标检测算法,使用激光雷达、相机和毫米波雷达3种传感器作为数据源,分别使用欧式聚类、深度学习和运动学推理的方法对潜在目标进行检测,进而提出后融合方法将多源检测结果融合以实现对前方车辆的准确检测。基于前车轨迹生成期望路径并设计卡尔曼滤波器对期望路径进行平滑和滤波。构建车辆动力学模型、车辆道路误差模型并设计鲁棒H∞控制器进行车辆轨迹跟踪控制仿真。仿真与实车验证结果表明:在测试路段对前方车辆的平均识别准确率大于95%;实时期望路径相对于真实轨迹的均方差和轨迹平均变化率在滤波前后分别降低17.3%和48.6%;侧向控制位置误差和航向角误差相较于PID(proportional integral derivative)控制分别降低了29%和41%;车辆编队以最高54 km/h的速度实现编队整体的稳定行驶。
