Path: Common/Estimation
% Interactive Multiple Models update step.
The inputs and outputs only show data structure fields used in this
function.
All inputs are after the prediction of the state (see IMMPredict).
IMMUpdate is called after IMMPredict. A complete IMM implementation is
IMMPredict( d )
IMMUpdate( d )
--------------------------------------------------------------------------
Form:
d = IMMUpdate( d )
--------------------------------------------------------------------------
------
Inputs
------
d (1,1) IMM data structure
.use (1,1) 'KF' 'EKF' 'UKF' Only KF is implemented
.cHatJ (1,n) Scaling factor
.mPI (m,n) Mean vectors for each model
.pPI {n} Covariance matrix for each model
.y (p,1) Measurements
.h (p,m) Measurement matrix
.r (p,p) Measurement noise covariance
-------
Outputs
-------
d (1,1) IMM data structure
.m (n,1) Aggregate mean
.p (n,n) Aggregate covariance
.mI (m,1) Model mean
.pI {n}(m,m) Model covariance
--------------------------------------------------------------------------
Common: Estimation/KFUpdate Math: Probability/NormalDistribution
Back to the Common Module page