Stochastic Integration Filter

Jindřich Duník, Ondřej Straka, Miroslav Ŝimandl

IEEE Transactions on Automatic Control · 2013 · 107 citations · 15 references

Concepts

TL;DR

State estimation of nonlinear stochastic dynamic systems is typically performed with filters such as the EKF, UKF, or CKF that use computationally efficient but approximate integral evaluations, while Monte Carlo Kalman filters achieve asymptotically exact integrals at high computational cost. This note introduces a new local filter that employs stochastic integration methods to achieve asymptotically exact integral evaluation with computational complexity comparable to traditional filters. The proposed filter is demonstrated through a numerical example.

Abstract

The technical note deals with state estimation of nonlinear stochastic dynamic systems. Traditional filters providing local estimates of the state, such as the extended Kalman filter, unscented Kalman filter, or the cubature Kalman filter, are based on computationally efficient but approximate integral evaluations. On the other hand, the Monte Carlo based Kalman filter takes an advantage of asymptotically exact integral evaluations but at the expense of substantial computational demands. The aim of the technical note is to propose a new local filter that utilises stochastic integration methods providing the asymptotically exact integral evaluation with computational complexity similar to the traditional filters. The technical note will demonstrate that the unscented and cubature Kalman filters are special cases of the proposed stochastic integration filter. The proposed filter is illustrated by a numerical example.

References

15