@inproceedings{Ge:2016:10.1109/CDC.2016.7798564,
author = {Ge, M and Kerrigan, EC},
doi = {10.1109/CDC.2016.7798564},
publisher = {IEEE},
title = {Relations between Full Information and Kalman-Based Estimation},
url = {http://dx.doi.org/10.1109/CDC.2016.7798564},
year = {2016}
}

Download

TY  - CPAPER
AB  - For nonlinear state space systems with additivenoises, sometimes the number of process noise signals couldbe less than the dimension of the state space. In order toimprove the accuracy and stability of nonlinear state estimation,this paper provides for the first time the derivation of thefull information estimator (FIE) for such nonlinear systems.We verify our derivation of the FIE by firstly proving theunbiasedness and minimum-variance of the FIE for linear timevarying (LTV) systems, then showing the equivalence betweenthe Kalman filter/smoother and the FIE for LTV systems.Finally, we prove that the FIE will provide more accurate stateestimates than the extended Kalman filter (EKF) and smoother(EKS) for nonlinear systems.
AU  - Ge,M
AU  - Kerrigan,EC
DO  - 10.1109/CDC.2016.7798564
PB  - IEEE
PY  - 2016///
TI  - Relations between Full Information and Kalman-Based Estimation
UR  - http://dx.doi.org/10.1109/CDC.2016.7798564
UR  - http://hdl.handle.net/10044/1/40568
ER  - 

Download