Analysis of discrete-time Kalman filtering under incorrect noise covariances

Analysis tools are developed that can be effectively used to study the performance degradation of a filter when incorrect models of the state and measurement noise covariances are used. For a linear time-variant system with stationary noise processes, it is shown that under certain stability conditions on the system model, the one-step prediction error covariance matrix will converge to a steady-state solution even when the filter gain is not optimal. On the other hand, if the state transition matrix has an unreachable mode outside a unit circle, then the modeling errors in the noise covariances may cause the filter to diverge. Bounds on the asymptotic filter performance are computed when the range of errors in the noise covariance matrices are known. Using simple examples, insights into the behavior of a Kalman filter under nonideal conditions are provided. >

[1]  R. E. Kalman,et al.  A New Approach to Linear Filtering and Prediction Problems , 2002 .

[2]  T. Nishimura,et al.  On the a priori information in sequential estimation problems , 1965 .

[3]  H. Heffes.  The effect of erroneous models on the Kalman filter response , 1966 .

[4]  Tosio Kato.  Perturbation theory for linear operators , 1966 .

[5]  S. Neal.  Linear estimation in the presence of errors in assumed plant dynamics , 1967, IEEE Transactions on Automatic Control.

[6]  N. F. Toda,et al.  Divergence in the Kalman Filter , 1967 .

[7]  T. Kailath,et al.  An innovations approach to least-squares estimation--Part II: Linear smoothing in additive white noise , 1968 .

[8]  C. Price.  An analysis of the divergence problem in the Kalman filter , 1968 .

[9]  A. Sage,et al.  Sensitivity analysis of discrete filtering and smoothing algorithms , 1969 .

[10]  F. L. Sims,et al.  Sensitivity analysis of discrete Kalman filters. , 1970 .

[11]  R. Mehra.  On the identification of variances and adaptive Kalman filtering , 1970 .

[12]  A. Jazwinski.  Stochastic Processes and Filtering Theory , 1970 .

[13]  C. Desoer.  Slowly varying discrete system xi+1=Aixi , 1970 .

[14]  D. Mayne,et al.  On the discrete time matrix Riccati equation of optimal control , 1970 .

[15]  David Q. Mayne,et al.  “On the discrete time matrix Riccati equation of optimal control-a correction” , 1971 .

[16]  A.P. Sage,et al.  Analysis of Modeling and Bias Errors in Discrete-Time State Estimation , 1971, IEEE Transactions on Aerospace and Electronic Systems.

[17]  R. Fitzgerald.  Divergence of the Kalman filter , 1971 .

[18]  D. Alspach.  Comments on "On the identification of variances and adaptive Kalman filtering" , 1972 .

[19]  T. Kailath,et al.  Initial-condition robustness of linear least squares filtering algorithms , 1974 .

[20]  S. Iglehart,et al.  Estimation of a dispersion parameter in discrete Kalman filtering , 1974 .

[21]  B. Molinari.  The stabilizing solution of the discrete algebraic riccati equation , 1975 .

[22]  R. K. Mehra.  Optimization of measurement schedules and sensor designs for linear dynamic systems , 1976 .

[23]  B. Anderson,et al.  Detectability and Stabilizability of Time-Varying Discrete-Time Linear Systems , 1981 .

[24]  Bernard Friedland.  Estimating Noise Variances by Using Multiple Observers , 1982, IEEE Transactions on Aerospace and Electronic Systems.

[25]  D. Luenberger,et al.  Estimation of structured covariance matrices , 1982, Proceedings of the IEEE.

[26]  G. Goodwin,et al.  Convergence properties of the Riccati difference equation in optimal filtering of nonstabilizable systems , 1984 .

[27]  G. Goodwin,et al.  Riccati equations in optimal filtering of nonstabilizable systems having singular state transition matrices , 1986 .

[28]  Cornelius T. Leondes,et al.  On the sensitivity of a discrete-time Kalman filter to plant-dynamics modelling errors , 1986 .

[29]  Suwanchai Sangsuk-Iam,et al.  Behavior of the discrete-time Kalman filter under incorrect noise covariances , 1987, 26th IEEE Conference on Decision and Control.

[30]  Suwanchai Sangsuk-Iam,et al.  Analysis of continuous-time Kalman filtering under incorrect noise covariances , 1988, Autom..