# Asymptotic Optimality of the Minimum-Variance Fixed-Interval Smoother

@article{Einicke2007AsymptoticOO,
title={Asymptotic Optimality of the Minimum-Variance Fixed-Interval Smoother},
author={Garry A. Einicke},
journal={IEEE Transactions on Signal Processing},
year={2007},
volume={55},
pages={1543-1547}
}
• G. Einicke
• Published 1 April 2007
• Mathematics
• IEEE Transactions on Signal Processing
This correspondence investigates the asymptotic performance of the discrete-time and continuous-time, time-varying, minimum-variance, fixed-interval smoothers. Comparison theorems are generalized to provide sufficient conditions for the monotonic convergence of the underlying Riccati equations. Under these conditions, the energy of the estimation errors asymptotically approach a lower bound and attain lscr2 /L2 stability

## Tables from this paper

Asymptotic convergence of Riccati equation and smoother solutions
• G. Einicke
• Mathematics
2007 46th IEEE Conference on Decision and Control
• 2007
It is shown that when the Riccati equation solutions converge, the time-varying, minimum-variance, fixed-interval smoothers provide optimal performance.
Properties of a continuous-time H∞ fixed-interval smoother
• G. Einicke
• Mathematics
2007 46th IEEE Conference on Decision and Control
• 2007
It is shown that the smoother exhibits an increase in mean-square-error, the error is bounded, and the upper error bound is greater than that for the Hinfin filter.
A Solution to the Continuous-Time H ∞ Fixed-Interval Smoother Problem
—The minimum-variance fixed-interval smoother is a state-space realization of the Wiener solution generalized for time-varying problems. It involves forward and adjoint Wiener-Hopf factor inverses in
A Solution to the Continuous-Time ${\rm H}_{\infty}$ Fixed-Interval Smoother Problem
• G. Einicke
• Mathematics
IEEE Transactions on Automatic Control
• 2009
It is shown that the smoother exhibits an increase in mean-square-error, the error is bounded, and the upper error bound is greater than that for the H∞ filter.
About the true type of smoothers
• Mathematics
ArXiv
• 2008
The variational formulation and the Euler-Lagrange equations are used to study the steady-state error in linear non-causal estimators (smoothers) and reveal a significant advantage of smoothing over filtering with respect to robustness to model uncertainty.
Iterative Smoother-Based Variance Estimation
• Mathematics
IEEE Signal Processing Letters
• 2012
The minimum-variance smoother solution for input estimation is described and it is shown that the resulting estimates are unbiased. The smoothed input and state estimates are used to iteratively
Longwall mining automation an application of minimum-variance smoothing [Applications of Control]
• Mathematics
IEEE Control Systems
• 2008
This article reviews the development of the minimum-variance smoother and describes its use in longwall automation. We describe both continuous- and discrete-time smoother solutions. It is shown,
Riccati Equation and EM Algorithm Convergence for Inertial Navigation Alignment
• Mathematics
IEEE Transactions on Signal Processing
• 2009
This correspondence investigates the convergence of a Kalman filter-based expectation-maximization (EM) algorithm for estimating variances. It is shown that if the variance estimates and the error
The use of energy constraints within filtering and smoothing
• G. Einicke
• Mathematics
IEEE Conference on Decision and Control and European Control Conference
• 2011
A low-cost filtering procedure is proposed in which the input measurements are constrained by nonlinear censuring functions and the resulting estimates are unbiased, and the estimation errors are bounded.
EM algorithm convergence for inertial navigation system alignment
• G. Einicke
• Mathematics
2008 47th IEEE Conference on Decision and Control
• 2008
The convergence of a Kalman filter-based EM algorithm for estimating variances is investigated. It is established that if the variance estimates and the error covariances are initialized

## References

SHOWING 1-10 OF 18 REFERENCES
Optimal and robust noncausal filter formulations
• G. Einicke
• Mathematics
IEEE Transactions on Signal Processing
• 2006
The paper describes an optimal minimum-variance noncausal filter or fixed-interval smoother that involves a cascade of a KalMan predictor and an adjoint Kalman predictor and demonstrates that optimal, robust, and extended Kalman smoothers can provide performance benefits.
H/sub infinity /-minimum error state estimation of linear stationary processes
A state estimator is derived which minimizes the H/sub infinity /-norm of the estimation error power spectrum matrix. Two approaches are presented. The first achieves the optimal estimator in the
Convergence properties of the Riccati difference equation in optimal filtering of nonstabilizable systems
• Mathematics
• 1984
This paper studies the convergence and properties of the solutions of the Riccati difference equation. Special emphasis is given to systems which are not necessarily stabilizable (in the filtering
Linear estimation of boundary value stochastic processes--Part II: 1-D smoothing problems
• Mathematics
• 1984
This paper addresses the fixed-interval smoothing problem for linear two-point boundary value stochastic processes of the type introduced by Krener [5]. As these models are not Markovian, Kalman
Estimation theory with applications to communications and control
• Mathematics
• 1979
This text provides a comprehensive treatment of estimation theory which should be suitable for graduate level engineers and is suitable for students studying estimation theory.
The set of positive semidefinite solutions of the algebraic Riccati equation of discrete-time optimal control
• H. Wimmer
• Mathematics
IEEE Trans. Autom. Control.
• 1996
In this paper the algebraic Riccati equation (ARE) of the discrete-time linear-quadratic (LQ) optimal control problem and its set of positive semidefinite solutions is studied under the most general
The optimum linear smoother as a combination of two optimum linear filters
• Mathematics
• 1969
A solution to the optimum linear smoothing problem is presented in which the smoother is interpreted as a combination of two optimum linear filters. This result is obtained from the well-known
Adaptive &Optimal Control for SISO Plant
An adaptive minimax control problem is stated for a general SISO plant in which the disturbance is assumed to belong to a given convex set of sequences and arbitrary otherwise. Unlike the standard
Two filter smoothing formulae by diagonalization of the Hamiltonian equations
• Mathematics
• 1982
We present a new approach to two filter smoothing formulae via diagonalization of the general time variant hamiltonian equations of the linear estimation problem. This approach shows the special role