-
Notifications
You must be signed in to change notification settings - Fork 6
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Matlab forward innovation model Kalman gain -> filter Kalman gain #2
Comments
The steady state matlab Kalman gain identified by Besides this larger issue, the Kalman gain for the 'innovations form' of the Kalman filter is slightly different from the normal Kalman gain: K_matlab = A*K This particular change has been accounted for already. But the apparent sign mismatch is persistent. Matlab defines the error as |
It is not just the wrong sign. The forward innovations form conversion to the filter update form above ( From Katayama 2005, p. 120:
I did some testing and found that if I used van Overschee's matlab toolbox for SSID that accompanies van Overschee et de Moor 1996, but manually zero out this cross term, the Kalman gain is consistent with I now need to circle back to matlab's n4sid results but there is actually not an option to force |
I have used Matlab's Using this matlab function with What remains, however, is that the Kalman gains fit by |
This is an issue carried forward from when this was hosted on the github.gatech.edu domain. In the interest of resolving it, I will past my comments below.
The text was updated successfully, but these errors were encountered: