lecture25

lecture25 - 16.322 Stochastic Estimation and Control, Fall...

Info iconThis preview shows pages 1–4. Sign up to view the full content.

View Full Document Right Arrow Icon
16.322 Stochastic Estimation and Control, Fall 2004 Prof. Vander Velde Page 1 of 9 Lecture 25 Last time: () 1 2 TT KP H H P HR −− =+ If kk zx v , 1 2 HI PR = Then if ± , 1 2 R Alternatively, if R P ± , 2 KI The effect is that ˆˆ ˆ x xK z H x +− The quantity 2 K is known as the Kalman gain . It is the optimum gain in the mean squared error sense. Substitute it into the expression for P + . () () 1 T T T T T T T T T T P I KH P I KH KRK I KHP I KHPHK K R K IK HP PHK K H PHK K R K HP PHK KH PH RK I KH P P H K P H HP H R HP H R K HP PHK PHK HP =− + + + + + + + + + + The form at the top is true for any choice of K . The last form is true only for the Kalman gain . The first form is better behaved numerically if you process a measurement which is very accurate relative to your prior information. So the measurement update step is:
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
16.322 Stochastic Estimation and Control, Fall 2004 Prof. Vander Velde Page 2 of 9 () 1 ˆˆ ˆ TT KPHH PH R xxK z H x PI K H P −− +− =+ =− The filter operates by alternating time propagation and measurement update steps. The results were derived here on the basis of preserving zero mean errors and minimizing the error variances. If all errors and noises are assumed normally distributed , so the probability density functions can be manipulated, one can derive the same results using the conditional mean approach : define x at every stage to be the mean of the distribution of x conditioned on all the measurements available up to that stage. Example: Conversion of continuous dynamics to discrete time form N 12 2 10 2 01 0 0 00 2 B A xx xn x = = ⎡⎤ ⎢⎥ ⎣⎦ ± ± ± ²³´³µ We could do time propagation by integration ( ) 1 N = : xA x PA PP A B B = + ± ± 2 2 1 ... 2 At eI A t A t Φ= = + ∆ + + 2 0 01 0 0000 A == If this does not work, expand A φ = ± , (0) I = ( ) 2 t ∆ = :
Background image of page 2
16.322 Stochastic Estimation and Control, Fall 2004 Prof. Vander Velde Page 3 of 9 [] 11 0 01 12 0 10 k k t IA t H ⎡⎤ Φ= + ∆= ⎢⎥ ⎣⎦ = = () ( ) 2 0 2, 2, 2, 2 0 02 T T k QB
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 4
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 11/07/2011 for the course AERO 16.322 taught by Professor Wallacevandervelde during the Fall '04 term at MIT.

Page1 / 9

lecture25 - 16.322 Stochastic Estimation and Control, Fall...

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online