Interacting particle filters for simultaneous state and parameter estimation

Abstract

Simultaneous state and parameter estimation arises from various applicational areas but presents a major computational challenge. Most available Markov chain or sequential Monte Carlo techniques are applicable to relatively low dimensional problems only. Alternative methods, such as the ensemble Kalman filter or other ensemble transform filters have, on the other hand, been successfully applied to high dimensional state estimation problems. In this paper, we propose an extension of these techniques to high dimensional state space models which depend on a few unknown parameters. More specifically, we combine the ensemble Kalman-Bucy filter for the continuous-time filtering problem with a generalized ensemble transform particle filter for intermittent parameter updates. We demonstrate the performance of this two stage update filter for a wave equation with unknown wave velocity parameter.

Robust Virtual Sensing of the Vehicle Sideslip Angle through the Cross-Combination of Multiple Filters Using a Decision Tree Algorithm

“…This method estimates vehicle SSA by leveraging sensor fusion using both in-vehicle sensors and a low-cost standalone global positioning system (GPS). In a similar vein, the authors of [64] proposed a double Kalman filter (DKF) for state and parameters estimation, where two estimation stages are based on cascade stability theory in the continuous time domain. The first stage ensures global convergence, while the second stage compensates for the potential loss in performance by utilizing the estimate obtained from the first stage through local linearization techniques.…”