基于方根分解形式的带衰减因子UKF算法应用

UKF作为一种新的非线性滤波方法已在目标跟踪问题中得到应用,在状态的时间更新阶段直接使用非线性模型,不引入线性化误差,而且不必计算Jacobians矩阵.提出了一种基于方根分解形式的带有衰减因子的UKF算法(SRDMA-UKF),算法的方根形式增加了数字稳定性和状态协方差的半正定性.通过衰减因子的引入加强对当前测量数据的利用,减小历史数据对滤波的影响.仿真实验结果表明,该算法与UKF算法相比具有更好的滤波性能.

Comparative Analysis of Unscented Kalman Filter(UKF)

As a new nonlinear filtering method,UKF(unscented Kalman filter) is applied in target tracking which directly uses nonlinear models in the time-update phase.As a result no error caused by linearization is introduced.Moreover,it is unnecessary to calculate the Jacobians matrix.The theory and algorithm of the unscented Kalman filter based on square rootdecom-position with Memory Attenuation(SRDMA-UKF) are introduced in this paper, and the square root forms have the added benefit of numerical stability and guaranteed positive semi-definiteness of the state covariances.By introducing the Memory Attenuation to enhance the use of the current measurement data,reduce the impact of historical data on the filter.The simulation results show that the estimation performance of the SRDMA-UKF is better than UKF.