Nonlinear State Estimation with Unscented Kalman Filter - Matlab
Show older comments
I am following the procedure proposed in Nonlinear State Estimation Using Unscented Kalman Filter and Particle Filter - MATLAB & Simulink (mathworks.com) in order to build an UKF, but I obtain a graph where there is no difference between the UKF estimate and the Measurements.

I have additive noise both in the process and in the meaurements. So, as suggested in the provided procedure, I didn't add the noise in the State-Transition function and in the Measurement function, because the additive noise should be provided by default.
The variables involved in the graph are xCorrectedUKF (UKF estimate) and yMeas (Measured), so I think that something went wrong during their definition on in their relationship. However, xCorrectedUKF is only defined in the for loop, so I have only to define yMeas before.
In the solution provided by Mathworks, the Measurements (yMeas) are defined in the following way (it is assumed to be non-additive noise in the example):
rng(1); % Fix the random number generator for reproducible results
yTrue = xTrue(:,1);
yMeas = yTrue .* (1+sqrt(R)*randn(size(yTrue))); % sqrt(R): Standard deviation of noise
Anyway, I don't know how to deal with the definition of yMeas in my case.
How can I write yMeas considering the presence of the additive noise?
1 Comment
Andrea Mancini
on 8 Dec 2020
Answers (0)
Categories
Find more on State Estimation in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!