中文说明：无迹卡尔曼滤波UKF摒弃了对非线性函数进行线性化的传统做法，采用卡尔曼线性滤波框架，对于一步预测方程，使用无迹变换UT来处理均值和协方差的非线性传递问题。UKF算法是对非线性函数的概率密度分布进行近似，用一系列确定样本来逼近状态的后验概率密度，而不是对非线性函数进行近似，不需要对Jacobian矩阵进行求导。UKF没有把高阶项忽略，因此对于非线性分布的娃统计量有较高的计算精度，有效地克服了扩展卡尔曼滤波的估计精度低、稳定性差的缺陷。
English Description：
Unscented Kalman filter (UKF) abandons the traditional method of linearization of nonlinear function, adopts the framework of Kalman linear filter, and uses unscented transform ut to deal with the nonlinear transfer problem of mean and covariance for one-step prediction equation. UKF algorithm is to approximate the probability density distribution of nonlinear function, using a series of determined samples to approximate the posterior probability density of the state, rather than approximate the nonlinear function, so it does not need to seek the derivative of Jacobian matrix. UKF does not ignore the high-order term, so it has high accuracy for the nonlinear distribution statistics, and effectively overcomes the shortcomings of the extended Kalman filter, such as low estimation accuracy and poor stability.