- #1
the_dialogue
- 79
- 0
Kalman Filter - Covariance Matrix
Kalman Filter Problem
I have the following expectation formula:
[tex]P_k=E\{\left[(x_k-\hat{x}^-_k)-K_k(H_k x_k+v_k-H_k \hat{x}^-_k)\right]\left[(x_k-\hat{x}^-_k)-K_k(H_k x_k+v_k-H_k \hat{x}^-_k)\right]\}[/tex]2. The attempt at a solution
I'm told the solution is:
[tex]P_k=(I-K_k H_k)P^-_k (I-K_k H_k)^T + K_k R_k K^T_k[/tex]
where [tex]P_k[/tex] is the covariance matrix, and [tex]P^-_k[/tex] is the estimate of the covariance matrix; [tex]R_k[/tex] is the covariance of [tex]v_k[/tex], and [tex]K_k[/tex] is the "blending factor" used in the following equation:
[tex]\hat{x}_k=\hat{x}^-_k+K_k (z_k-H_k \hat{x}^-_k)[/tex], where z_k is the measurement.
I'm not sure how this derivation is obtained. I know that at some point I have to use the fact that [tex](x_k-\hat{x}^-_k)[/tex] is uncorrelated with [tex]v_k[/tex], but I can't seem to get to the point where I have to use this assumption. All I get is a bunch of ugly expansions!
Any help getting started would be appreciated.
Kalman Filter Problem
Homework Statement
I have the following expectation formula:
[tex]P_k=E\{\left[(x_k-\hat{x}^-_k)-K_k(H_k x_k+v_k-H_k \hat{x}^-_k)\right]\left[(x_k-\hat{x}^-_k)-K_k(H_k x_k+v_k-H_k \hat{x}^-_k)\right]\}[/tex]2. The attempt at a solution
I'm told the solution is:
[tex]P_k=(I-K_k H_k)P^-_k (I-K_k H_k)^T + K_k R_k K^T_k[/tex]
where [tex]P_k[/tex] is the covariance matrix, and [tex]P^-_k[/tex] is the estimate of the covariance matrix; [tex]R_k[/tex] is the covariance of [tex]v_k[/tex], and [tex]K_k[/tex] is the "blending factor" used in the following equation:
[tex]\hat{x}_k=\hat{x}^-_k+K_k (z_k-H_k \hat{x}^-_k)[/tex], where z_k is the measurement.
I'm not sure how this derivation is obtained. I know that at some point I have to use the fact that [tex](x_k-\hat{x}^-_k)[/tex] is uncorrelated with [tex]v_k[/tex], but I can't seem to get to the point where I have to use this assumption. All I get is a bunch of ugly expansions!
Any help getting started would be appreciated.
Last edited: