Robust Estimation for Linear State-Space Models with Stochastic Covariates
Preprint
Abstract
The Kalman-Bucy filter (KF) is used to estimate and predict state-space models. It frequently encounters uncertain covariates, such as those derived from noisy measurements of physical signals (e.g., sensor readings, weather data, etc.). Our aim is to account for their uncertainties and develop robust KF approaches when incorporating the uncertainties of the covariates into the model—that is, by treating them as stochastic variables with known distributions. To enhance the robustness of the KF viewed as a Bayesian method that estimates the posterior distribution of the system state conditioned on past observations, we propose two methods. The linear Bayes estimator, which yields an explicit, unbiased forecast with minimal variance. An optimal risk estimator, which is non-linear and remains robust even when the covariates are highly noisy. This second method is approximated using a sequential Monte Carlo technique.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Robust Minimum Error Entropy Based Cubature Information Filter With Non-Gaussian Measurement NoiseIEEE Signal Processing Letters, 2021
- State and parameter joint estimation of linear stochastic systems in presence of faults and non‐Gaussian noisesInternational Journal of Robust and Nonlinear Control, 2020
- Robust Power System State Estimation With Minimum Error Entropy Unscented Kalman FilterIEEE Transactions on Instrumentation and Measurement, 2020
- Distributed Kalman Filtering Under Model UncertaintyIEEE Transactions on Control of Network Systems, 2019
- A distributed maximum correntropy Kalman filterSignal Processing, 2019
- Convergence of Optimal Linear Estimator With Multiplicative and Time-Correlated Additive Measurement NoisesIEEE Transactions on Automatic Control, 2018
- The Tobit Kalman Filter: An Estimator for Censored MeasurementsIEEE Transactions on Control Systems Technology, 2015
- Robust Kalman filters for linear time-varying systems with stochastic parametric uncertaintiesIEEE Transactions on Signal Processing, 2002
- New approaches to robust minimum variance filter designIEEE Transactions on Signal Processing, 2001
- Bounds on estimation errors of discrete-time filters under modeling uncertaintyIEEE Transactions on Automatic Control, 1980