A detection-estimation approach to filtering for Gaussian systems with intermittent observations

In this paper we consider the problem of state estimation for linear discrete-time Gaussian systems with intermittent observations. Intermittent observations result from packet dropouts when data travel along unreliable communication channels, as in the case of wireless sensor networks, or networked control systems. We assume that the receiver does not know the sequence of packet dropouts, which is a common situation, e.g., in wireless sensor networks or in networks that cannot rely on protocols that provide information on packet loss. In this paper we propose a detection-estimation approach to the problem of state estimation. The estimator consists of two stages: the first is a nonlinear optimal detector, which decides if a packet dropout has occurred, and the second is a time-varying Kalman filter, which is fed with both the observations and the decisions from the first stage. The overall estimator has finite memory and the tradeoff between performance and computational complexity can be easily controlled. Simulation results highlight the effectiveness of the proposed approach, which outperforms the linear optimal filter of Nahi. Finally, the method is amenable to generalization.

[1]  Raquel Caballero-Águila,et al.  Linear and quadratic estimation using uncertain observations from multiple sensors with correlated uncertainty , 2011, Signal Process..

[2]  C. Striebel,et al.  On the maximum likelihood estimates for linear dynamic systems , 1965 .

[3]  H. Vincent Poor,et al.  An Introduction to Signal Detection and Estimation , 1994, Springer Texts in Electrical Engineering.

[4]  H. Vincent Poor,et al.  An introduction to signal detection and estimation (2nd ed.) , 1994 .

[5]  James C. Spall,et al.  Validation of state-space models from a single realization of non-Gaussian measurements , 1985 .

[6]  Alfredo Germani,et al.  Reduced-Order Quadratic Kalman-Like Filtering of Non-Gaussian Systems , 2012, IEEE Transactions on Automatic Control.

[7]  Seiichi Nakamori,et al.  Second-order polynomial estimators from uncertain observations using covariance information , 2003, Appl. Math. Comput..

[8]  F. Carravetta,et al.  Polynomial Filtering for Linear Discrete Time Non-Gaussian Systems , 1996 .

[9]  Y. Ho,et al.  A Bayesian approach to problems in stochastic estimation and control , 1964 .

[10]  James C. Spa.  Estimation via Markov Chain Monte Carlo , 2002 .

[11]  Mohamed T. Hadidi,et al.  Linear recursive state estimators under uncertain observations , 1978 .

[12]  Charles R. Johnson,et al.  Topics in Matrix Analysis , 1991 .

[13]  Seiichi Nakamori,et al.  Design of Quadratic Estimators using Covariance Information in Linear Discrete-Time Stochastic Systems , 2008 .

[14]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[15]  M. Zakai.  On the optimal filtering of diffusion processes , 1969 .

[16]  Nasser E. Nahi,et al.  Optimal recursive estimation with uncertain observation , 1969, IEEE Trans. Inf. Theory.

[17]  Alfredo Germani,et al.  Reduced-order quadratic Kalman-like filtering for non-Gaussian systems , 2012, 2012 IEEE 51st IEEE Conference on Decision and Control (CDC).

[18]  J. Spall,et al.  Asymptotic distribution theory for the kalman filter state estimator , 1984 .

[19]  H. Akaike,et al.  Comment on "An innovations approach to least-squares estimation, part I: Linear filtering in additive white noise" , 1970 .

[20]  A. Hermoso-Carazo,et al.  Least-squares Polynomial Estimation from Observations Featuring Correlated Random Delays , 2010 .

[21]  Martin P. Clark.  Data Networks, IP and the Internet , 1977 .

[22]  Seiichi Nakamori,et al.  New design of estimators using covariance information with uncertain observations in linear discrete-time systems , 2003, Appl. Math. Comput..

[23]  Xiao Ma,et al.  Optimal Filtering Over Uncertain Wireless Communication Channels , 2011, IEEE Signal Processing Letters.

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

[25]  A. Germani,et al.  Optimal quadratic filtering of linear discrete-time non-Gaussian systems , 1995, IEEE Trans. Autom. Control..

[26]  Guanrong Chen,et al.  Suboptimal Kalman Filtering for Linear Systems with Non-Gaussian Noise , 1993 .

[27]  João Pedro Hespanha,et al.  A Survey of Recent Results in Networked Control Systems , 2007, Proceedings of the IEEE.