Today

Bayesian filtering and the particle filter

For Next Time

Work on the Robot Localization project. For the next class you should have done the part of the “Implementation Plan” part of the assignment.

Bayesian Filtering and the Particle Filter

Notes from Today on Bayes’ filter
Notes from Previous Years on Bayes’ filter and how it applies to robot localization are here.

I will lead a walkthrough of the derivation in-class. You are welcome to hangout in the room and listen (and hopefully ask questions), you can go right now and work with friends, you can leave once you have the basic idea, etc.

Proposed Model for Working through this Derivation

With your partner and another team, work through the notes. Here are some guidelines.

Make sure everyone understands each step before moving onto the next one.
If there is a persistent issue that cannot be resolved, call a member of the teaching team over and ask us for help. If for some reason this is not easy to do at the time, make a note of it so you can return to it later.
If you need more help at any point in the derivation, don’t hesitate to call a member of the teaching team over and ask for help.
Stop when you get to the section labeled “Scalability.”

The Particle Filter Algorithm (together as a class)

As a class, let’s go through the basic steps of the particle filter algorithm and the issues around scalability of the Bayes filter.