Introduction

• Kalman filter is an algorithm that uses a series of

data observed over time, which contains noise and
other inaccuracies, to estimate unknown variable
EN5101 Digital Control Systems accurately.
• It was proposed by R E Kalman in 1960, and became
Kalman Filter a standard approach for optimal estimation
• KF is a real-time, recursive, efficient estimation
algorithm in standard (KF), extended (EKF), an
Prof. Rohan Munasinghe unscented (UKF) forms
Dept of Electronic and
Telecommunication Engineering
University of Moratuwa
1 2

KF Highlights Preliminaries: Definitions and Identities

3 4
5 6

Kalman Filter- Priliminaries

7 8
 Kalman Filter Equations Kalman: Predictor Corrector
--- (1) by definition

--- (2)
Eq (1) Eq (2) Eq (4) Eq (5)

--- (3)

-(4)

-- (5) 9 10

(c)
Kalman Filter Derivation (6)

Step 1 : State Ref (1)

Extrapolation

--- (6)

11 12
 Step 2 : Covariance Extrapolation

13 14

(c),
Step 3: Kalman Gain Calculation

(d)K’k+1 (1)

15 16
17 18

Step 4: State Update

(d)K’k+1

Step 5: Covariance Update

19 20
 Assignment

21