Skip to main content

W06. State 02

Today we will learn how to apply Bayes filters to object detection. The Bayes Filter is just an iterated version of Bayes' Theorem. By repeatedly applying Bayes' Theorem, we can converge to a particular measurement with a high likelihood of being correct. This should make sense intuitively: if we repeatedly measure that we're at 10cm, we're probably pretty close to being at 10cm.

Pre-readings and Videos​

It may seem like detection should "just work" if you get the right threshold, but usually there's so much uncertainty in the measurement and error in the robot movement that we need to use a process to iterate towards a probable state. Iterating measurements allows us to converge to a detection.

Particle Filter Demo​

This demo of particle filters gives a basic motivation for why we would even care to use something like the Bayes Filter.

Bayes Filter Overview​

This video is a brief explanation of the Bayes filter, and compares to other concepts. It's not important to understand every term and detail of this video, but it does set the stage for why the Bayes Filter is helpful.

Summary of the Day​

Learning Goals​

  1. Be able to implement a Bayes Filter on your lab robot.
  2. Be able to apply the Bayes Filter concept to general detection problems.
  3. Motivate the need for particle filters for detection in terms of robot error.