A Novel a Priori State Computation Strategy for the Unscented Kalman Filter to Improve Computational Efficiency

DOI10.1109/TAC.2016.2599291zbMATH Open1366.93650arXiv1608.05497OpenAlexW3104033897MaRDI QIDQ5282428FDOQ5282428

Andrew G. Dempster, S. K. Biswas, Li Qiao

Publication date: 27 July 2017

Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)

Abstract: A priori state vector and error covariance computation for the Unscented Kalman Filter (UKF) is described. The original UKF propagates multiple sigma points to compute the a priori mean state vector and the error covariance, resulting in a higher computational time compared to the Extended Kalman Filter (EKF). In the proposed method, the posterior mean state vector is propagated and then the sigma points at the current time step are calculated using the first-order Taylor Series approximation. This reduces the computation time significantly, as demonstrated using two example applications which show improvements of 90.5% and 92.6%. This method shows the estimated state vector and the error covariance are accurate to the first-order Taylor series terms. A second method using Richardson Extrapolation improves prediction accuracy to the second-order Taylor series terms. This is implemented on the two examples, improving efficiency by 85.5% and 86.8%.

Full work available at URL: https://arxiv.org/abs/1608.05497

Mathematics Subject Classification ID

Inference from stochastic processes and prediction (62M20) Filtering in stochastic control theory (93E11) Signal detection and filtering (aspects of stochastic processes) (60G35)

Cited In (4)

• A quantified approach of predicting suitability of using the unscented Kalman filter in a non-linear application
• A marginalized unscented Kalman filter for efficient parameter estimation with applications to finite element models
• A modified fractional-order unscented Kalman filter for nonlinear fractional-order systems
• Conditionally minimax nonlinear filter and unscented Kalman filter: empirical analysis and comparison

This page was built for publication: A Novel a Priori State Computation Strategy for the Unscented Kalman Filter to Improve Computational Efficiency

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5282428)