Kalman Filter, Live
Chapter 3 · Lesson 3 · Covariance · state space · the full filter · Free preview

The matrix Kalman filter

By the end of this lesson you can
  • Track position and velocity in 2D with the matrix Kalman filter
  • Read correlation from a covariance matrix and its ellipse
  • Write F, H, Q and R for a moving object

Many variables at once: correlation and the covariance matrix, how uncertainty moves through a model, state space, and the full matrix filter on a rocket. 7 short slides, then worked examples and problems. Each slide has an everyday picture, a worked example and Python you can run right on the page.

Free preview: most of every slide is yours to read, with its Python lab. Members get the full text, every example with its solution, and five extra problems per lesson.

Start the lesson →

Slides

Free previewLesson 3CorrelationCorrelation and covariance: when two numbers move togetherOpen slide →01 · Lesson 3 · Correlation

Correlation and Covariance, Explained with Examples

What correlation means, and covariance as the average product of deviations, worked by hand on ice cream, hot chocolate and coffee sales, with live Python.

Free previewLesson 3Covariance matrixThe covariance matrix and its ellipseOpen slide →02 · Lesson 3 · The covariance matrix

The Covariance Matrix and the 2σ Uncertainty Ellipse

Variances on the diagonal, covariance off it: read a covariance matrix, find the correlation ρ and draw its 2σ ellipse. Worked examples and live Python.

Free previewLesson 3APAᵀTransforming covariance: the rule A P AᵀOpen slide →03 · Lesson 3 · Transforming covariance

How a Covariance Matrix Transforms: A P Aᵀ Explained

If y = Ax + b, the mean becomes Aμ + b and the covariance becomes A P Aᵀ. The matrix version of a²σ², worked by hand and drawn live in Python.

Free previewLesson 3State spaceState-space models: the state, F, B and HOpen slide →04 · Lesson 3 · State space

State Space Models Explained: x = Fx + Bu and z = Hx

What the state is, and how F, B and H describe motion, inputs and sensors. Position and velocity with friction and a motor push, simulated in Python.

Free previewLesson 3The matrix filterThe matrix Kalman filter: predict and correct with matricesOpen slide →05 · Lesson 3 · The matrix filter

Kalman Filter Equations in Matrix Form, with a Worked Example

The five Kalman filter equations in matrix form next to the 1D ones, where each comes from, and one full predict-correct cycle worked in numbers.

Free previewLesson 3Rocket trackingRocket tracking: a 4-number Kalman filter in 2DOpen slide →06 · Lesson 3 · Rocket tracking

Kalman Filter Example: Tracking a Rocket with Noisy GPS

A full 2D Kalman filter: state x, y, vx, vy, the matrices F, H, Q and R, covariance ellipses, and tuning Q against R on a rocket flying to Mars, in Python.

Free previewLesson 3RecapLesson 3 recap: the matrix Kalman filterOpen slide →07 · Recap · Reading

Lesson 3 Recap: Covariance and the Matrix Kalman Filter

The matrix Kalman filter on one page: covariance, the 2σ ellipse, A P Aᵀ, state-space models with F, B and H, and the five predict-correct equations.

The full course

From noisy sensors to the EKF, by running it

Lessons 1 and 2 are free. Finish all four and you will be able to:

You get: all 4 lessons with Python labs · every worked example and solution · 5 extra problems per lesson · your progress tracked · Steppe, your AI tutor inside every lesson, day or night · every future update.

$20 once · lifetime access · 14-day money-back guarantee
Continue to checkout →

Already a member? Log in to the course