多模型多传感器信息融合Kalman平滑器

基于标量加权的线性最小方差最优信息融合算法,对多模型多传感器离散线性随机系统,给出了一种分布式标量加权信息融合固定滞后Kalman平滑器.它只需计算加权标量系数,可减小在融合中心的计算负担.当各子系统存在稳态滤波时,又给出了标量加权信息融合稳态平滑器,它计算量小,便于实时应用.并给出了两个子系统之间的平滑误差互协方差阵的计算公式.仿真例子验证了其有效性.

Multi-model and multi-sensor information fusion Kalman smoother

Based on the optimal information fusion algorithm weighted by scalars in the linear minimum variance sense,a distributed information fusion fixed-lag Kalman smoother weighted by scalars is given for discrete linear stochastic system with multiple model and multiple sensors.It only requires the computation of scalar weights,so that the calculated burden in the fusion center can be reduced.The information fusion steady-state smoother weighted by scalars is also given when all subsystems have steady-state filtering.It has a small calculation and is convenient to apply in real time.The computation formula for the smoothing error cross-covariance matrix is given between any two subsystems.A simulation example shows its effectiveness.