可处理多个无序量测的前向滤波算法

Forward-filtering algorithm for dealing multiple out-of-sequence measurements

基于等价量测和前向滤波法,推导出一种单个无序量测算法Fl1,并说明了该算法与Al1算法、FPFD算法以及AA1算法之间的等价性.以Fl1算法为基础提出可以处理同时到达融合中心的多个不同单步延迟无序量测的最优算法CZ1.所提新算法的性能不依赖过程噪声的离散化模式,且无须对状态转移矩阵求逆.仿真结果表明在过程噪声DCM下CZ1算法与CA1算法的性能是相同的.

The equivalent measurement approach and forward-filtering method were used to derive an single out-of-sequence measurement processing algorithm denoted as Fl1.It was demonstrated that the algorithm was equivalent to algorithm Al1,FPFD（forward-prediction fusion and decorrelation） algorithm and algorithm AA1.Subsequently,based on algorithm Fl1,an optimal update algorithm with multiple one-step-lag out-of-sequence measurements,denoted as CZ1,was presented.The proposed algorithm did not require the inverse of the state transition matrix,and their performance was independent on the discretization form of process noise.The simulation results show that the CZ1algorithm has the same preformance as the CA1algorithm in discretized continuous-time model of the process noises.