Scribd Logo
Upload

Welcome to Scribd!

  • 19 views

    CT Kalman Filter Outline: KF State Equation. Kalman Gain. Error Covariance. Riccati Equation

    Uploaded by

    Ashutosh Ashu
    This document outlines the continuous-time Kalman filter (CT KF). It discusses the KF state equation, Kalman gain, error covariance, and Riccati equation that describe the filter dynamics. It also covers solving the KF equations, applying the orthogonality principle to minimize estimation error, differentiating the error covariance, and deriving the continuous-time Riccati equation. As an example, it presents the steady-state solution of the algebraic Riccati equation for a simple linear system with process and measurement noise.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    CT Kalman Filter Outline: KF State Equation. Kalman Gain. Error Covariance. Riccati Equation

    Uploaded by

    Ashutosh Ashu
    19 views6 pages
    This document outlines the continuous-time Kalman filter (CT KF). It discusses the KF state equation, Kalman gain, error covariance, and Riccati equation that describe the filter dynamics. It also covers solving the KF equations, applying the orthogonality principle to minimize estimation error, differentiating the error covariance, and deriving the continuous-time Riccati equation. As an example, it presents the steady-state solution of the algebraic Riccati equation for a simple linear system with process and measurement noise.

    Original Title

    ContKF

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document outlines the continuous-time Kalman filter (CT KF). It discusses the KF state equation, Kalman gain, error covariance, and Riccati equation that describe the filter dynamics. It also covers solving the KF equations, applying the orthogonality principle to minimize estimation error, differentiating the error covariance, and deriving the continuous-time Riccati equation. As an example, it presents the steady-state solution of the algebraic Riccati equation for a simple linear system with process and measurement noise.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    19 views6 pages

    CT Kalman Filter Outline: KF State Equation. Kalman Gain. Error Covariance. Riccati Equation

    Uploaded by

    Ashutosh Ashu
    This document outlines the continuous-time Kalman filter (CT KF). It discusses the KF state equation, Kalman gain, error covariance, and Riccati equation that describe the filter dynamics. It also covers solving the KF equations, applying the orthogonality principle to minimize estimation error, differentiating the error covariance, and deriving the continuous-time Riccati equation. As an example, it presents the steady-state solution of the algebraic Riccati equation for a simple linear system with process and measurement noise.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 6

    Outline

    CT Kalman Filter  KF state equation.


     Kalman gain.
     Error covariance.
    M. Sami Fadali
     Riccati equation.
    Professor of Electrical
    Engineering
    University of Nevada

    1 2

    CT Model Filter Dynamics

    • Data: 3 4
    Orthogonality Principle Apply Orthogonality

    For minimum mean-square error


    estimation, the estimation error is
    orthogonal to the data  Error

    5
     Evaluate the RHS next 6

    Solve KF Equation Error Orthogonal to Estimate

     Solution
     Multiply by

     Mean error is zero for an unbiased estimator.


     Error is orthogonal to measurements for minimum
    7
    mean-square error. 8
    Kalman Gain Autocorrelation of Output

    , for
    Orthogonality

    9 10

    Differentiate Output Covariance


    ,
    ,

    ,0 0 ,0 , ,

    ,0 0 ,0 , ,

    ,0 0 ,0 , ,

    11 12
    Error Dynamics Error Covariance: Lyapunov Eq.

     Apply the output covariance result to the error

    P t   Fo (t ) Pt   Pt Fo (t )  G (t )Q G T (t )


    T

    P t   F (t )  K (t ) H (t )Pt 
     Pt F (t )  K (t ) H (t )
    T

     G (t )QG T (t )  K (t ) RK T (t )

    13 14

    Riccati Equation Summary of CT KF


     Substitute for the Kalman gain

    15 16
    Steady-state Filter Example: Steady-state Filter
     Consider the equation of motion

     Under certain condition, the steady-  State-space model


    state solution of the ARE exists.
     x1  0 1  x1  0
     Unique positive definite solution.  x   0 0  x   1u (t )
     Use steady-state filter for simpler  2   2   
    implementation (suboptimal) x 
    z (t )  1 0 1   v(t )
    17  x2  18

    Algebraic Riccati Equation Kalman Gain


     Solve the algebraic Riccati equation

    0 1  p1 p2   p1 p2  0 0 0 ⁄
            q0 1
    0 0  p2 p3   p2 p3  1 0 1 ⁄
     p p2  1 1   p1 p2 
     1     1 0 
     The term is needed to calculate the
     p2 p3  0 r   p2 p3  steady-state square error (trace of )
    0  2 p2  p12 r , 0  p3  p1 p2 r
    0  q  p22 r
    19 20
    Reference

     J.B. Burl, Linear Optimal Control:


    and Methods, Addison Wesley
    Longman, Menlo Park, CA 1999.

    21

    You might also like