观测滞后系统协方差交叉融合Kalman滤波器  

Covariance Intersection Fusion Kalman Filter for Systems with Delayed Measurements

作　　者：齐文娟[1] 高媛[1] 邓自立[1] 

机构地区：[1]黑龙江大学自动化系,哈尔滨150080

出　　处：《科学技术与工程》2011年第3期448-451,共4页Science Technology and Engineering

基　　金：国家自然科学基金(60874063);黑龙江大学自动控制重点实验室项目资助

摘　　要：对观测滞后和带未知互协方差的两传感器线性离散定常随机系统,提出了一种协方差交叉(CI)融合稳态Kalman滤波器。它给出了不依赖于未知互协方差的实际融合误差方差阵的一个公共的上界,因而具有一致性和鲁棒性。证明了其精度高于每个局部Kalman滤波器的精度,且低于当互协方差已知时的最优矩阵加权融合Kalman滤波器的精度。一个跟踪系统的MonteCarlo仿真例子说明了其有效性。For the linear discrete time-invariant stochastic systems with two sensors and with delayed measurements and unknown cross-covariance,a covariance intersection（CI）fusion steady-state Kalman filter is proceed.It gives a common upper bound of the actual CI fused error variance,which independent of unknown cross-covariance,so that it has consistency and robustness.It is proved that its accuracy is higher than that of each local Kalman filter,and is lower than that of the optimal fusion Kalman filter with known cross-covariance.A Monte-Carlo simulation example for a tracking system shows its effectiveness.

关 键 词：滞后观测 未知互协方差 协方差交叉融合 KALMAN滤波器 一致性 鲁棒性 

分 类 号：O211.64[理学—概率论与数理统计]