自主机器人作业的关键问题是自身的定位问题。卡尔曼滤波可用于对系统位置进行估计。首先介绍了移动机器人同步定位与地图构建(Simultaneous Localization and Mapping,SLAM)的一般模型及关键技术,然后介绍了扩展卡尔曼滤波(Extended Ka...自主机器人作业的关键问题是自身的定位问题。卡尔曼滤波可用于对系统位置进行估计。首先介绍了移动机器人同步定位与地图构建(Simultaneous Localization and Mapping,SLAM)的一般模型及关键技术,然后介绍了扩展卡尔曼滤波(Extended Kalman Filter,EKF)的原理,通过分析粗差对EKF模型的影响,提出了抗差EKF模型。该模型根据多余观测分量及预测残差统计,构造抗差等价EKF增益矩阵,通过迭代解算给出抗差解。最后分别实现了加入粗差后的标准EKF-SLAM解决方案以及加入粗差后的抗差EKF-SLAM解决方案;模拟了自主机器人运动轨迹,并对比了两种模型对机器人定位的精确度,结果显示了抗差EKF模型的优越性。展开更多
When a pico satellite is under normal operational condi- tions, whether it is extended or unscented, a conventional Kalman filter gives sufficiently good estimation results. However, if the measurements are not reliab...When a pico satellite is under normal operational condi- tions, whether it is extended or unscented, a conventional Kalman filter gives sufficiently good estimation results. However, if the measurements are not reliable because of any kind of malfunc- tions in the estimation system, the Kalman filter gives inaccurate results and diverges by time. This study compares two different robust Kalman filtering algorithms, robust extended Kalman filter （REKF） and robust unscented Kalman filter （RUKF）, for the case of measurement malfunctions. In both filters, by the use of de- fined variables named as the measurement noise scale factor, the faulty measurements are taken into the consideration with a small weight, and the estimations are corrected without affecting the characteristic of the accurate ones. The proposed robust Kalman filters are applied for the attitude estimation process of a pico satel- lite, and the results are compared.展开更多
文摘When a pico satellite is under normal operational condi- tions, whether it is extended or unscented, a conventional Kalman filter gives sufficiently good estimation results. However, if the measurements are not reliable because of any kind of malfunc- tions in the estimation system, the Kalman filter gives inaccurate results and diverges by time. This study compares two different robust Kalman filtering algorithms, robust extended Kalman filter （REKF） and robust unscented Kalman filter （RUKF）, for the case of measurement malfunctions. In both filters, by the use of de- fined variables named as the measurement noise scale factor, the faulty measurements are taken into the consideration with a small weight, and the estimations are corrected without affecting the characteristic of the accurate ones. The proposed robust Kalman filters are applied for the attitude estimation process of a pico satel- lite, and the results are compared.
