Path: Common/Estimation
% Extended Kalman Filter measurement update step.
All inputs are after the predict state (see EKFPredict). The h
data field may contain either a function name for computing
the estimated measurements or an m by n matrix. If h is a function
name you must include hX which is a function to compute the m by n
matrix is a linearized version of the function h.
--------------------------------------------------------------------------
Form:
d = EKFUpdate( d )
--------------------------------------------------------------------------
------
Inputs
------
d (1,1) EKF data structure
.m (n,1) Mean
.p (n,n) Covariance
.h (m,n) Either matrix or name of function
.hX (1,:) Name of Jacobian for h
.y (m,1) Measurement vector
.r (m,m) Measurement covariance vector
.hData (1,1) Datastructure for the h and hX functions
-------
Outputs
-------
d (1,1) EKF data structure
.m (n,1) Mean
.p (n,n) Covariance
.v (m,1) Residuals
--------------------------------------------------------------------------
Back to the Common Module page