相关观测噪声下的动态定位分析

Analysis for Dynamic Positioning on Correlated Measurement Noise

对车载环境下的定位误差作时间序列分析,得到二阶马尔可夫过程的定位误差模型。将定位误差作为观测噪声,以此建立的观测方程中的观测噪声具有时间相关性。利用观测量相差法,把相邻两次观测量的相关部分消去,建立起观测噪声为白噪声的观测方程,并推导出状态估计的递推方程。避免了高阶矩阵的求逆,有效地减少了计算量,并降低了对内存的需求,提高了车载动态定位系统的实时性和定位精度。仿真结果进一步证明了算法的有效性。

The model of vehicle positioning error can be described as a 2-order Markov process, according to the results of time-series analysis. The positioning error has time-correlation, which is regarded as measurement noise in the measurement equation. The correlated portion of measurement is eliminated after the approach of measurement subtracting is proposed, and the new measurement equation is built whose noise is white. The recursive state estimation algorithm is given, by which higher-order matrix inverse is avoided. So its calculation is simplified . The simulation results show that the algorithm is effective.