The "Blob" Filter: Gaussian Mixture Nonlinear Filtering with Re-Sampling for Mixand Narrowing

M.L. Psiaki

Abstract: A new Gaussian mixture filter has been developed, one that uses a re-sampling step in order to limit the covariances of its individual Gaussian components. The new filter has been designed to produce accurate solutions of difficult nonlinear/non-Bayesian estimation problems. It uses static multiple-model filter calculations and Extended Kalman Filter (EKF) approximations for each Gaussian mixand in order to perform dynamic propagation and measurement update. The re-sampling step uses a newly designed algorithm that employs linear matrix inequalities in order to bound each mixand's covariance. Re-sampling occurs between the dynamic propagation and the measurement update in order to ensure bounded covariance in both of these operations. The resulting filter has been tested on a difficult 7-state nonlinear filtering problem. It achieves significantly better accuracy than a simple EKF, an Unscented Kalman Filter, a Moving-Horizon Estimator/Backwards-Smoothing EKF, and a regularized Particle Filter.
Published in: Proceedings of IEEE/ION PLANS 2014
May 5 - 8, 2014
Hyatt Regency Hotel
Monterey, CA
Pages: 393 - 406
Cite this article: Psiaki, M.L., "The "Blob" Filter: Gaussian Mixture Nonlinear Filtering with Re-Sampling for Mixand Narrowing," Proceedings of IEEE/ION PLANS 2014, Monterey, CA, May 2014, pp. 393-406.
Full Paper: ION Members/Non-Members: 1 Download Credit
Sign In