Kalman Filter, Live
Chapter 1 · Lesson 1 · Random variables · Gaussians · fusion

Noise and data fusion

By the end of this lesson you can
  • Fuse two noisy sensors into one estimate that beats both
  • Read a sensor's quality from its variance
  • Say how far off a reading can be with the 68-95 rule

Why no sensor tells the truth, how the Gaussian describes its noise, and how to fuse two noisy readings into one better estimate. 6 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.

Start the lesson →

Slides

Lesson 1The Kalman filterWhat the Kalman filter does: truth plus noiseOpen slide →01 · Lesson 1 · What is the Kalman filter?

What Is the Kalman Filter? A Friendly Introduction

The Kalman filter in plain words: every sensor reads truth plus noise, and the filter fuses them by predicting and correcting. With Python you can run.

Lesson 1Random variablesRandom variables: mean, variance and standard deviationOpen slide →02 · Lesson 1 · Random variables

Random Variables, Mean and Variance for Sensor Noise

Why a sensor reading is a random variable, and how to measure its noise with the mean, variance and standard deviation, by hand and in Python.

Lesson 1The GaussianThe Gaussian bell curve and the 68-95 ruleOpen slide →03 · Lesson 1 · The Gaussian

Normal (Gaussian) Distribution and Sensor Noise

The bell curve in plain words: mean and variance, the 68-95 rule, and why adding or scaling Gaussians is so easy. Worked examples and live Python.

Lesson 1Sensor qualityVariance as sensor quality: which sensor to trustOpen slide →04 · Lesson 1 · Variance and sensor quality

Variance and Sensor Quality: Which Sensor to Trust

A sensor's noise variance tells you how much to trust it. Two sensors centred on the truth, the 68-95 rule, averaging, and Python to compare them.

Lesson 1Data fusionData fusion: combining two sensors with the gain KOpen slide →05 · Lesson 1 · Data fusion

Sensor Fusion: Combining Two Noisy Sensors

Fuse two noisy sensors with a weighted average, the gain K and the fused variance. Two thermometers, worked examples and Python you can run.

Lesson 1RecapLesson 1 recap: noise, the bell curve and data fusionOpen slide →06 · Recap · Reading

Lesson 1 Recap: Sensor Noise, Gaussians and Data Fusion

Lesson 1 in one page: truth plus noise, mean and variance, the Gaussian and its 68-95 rule, variance as sensor quality, and the fusion rule with gain K.

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