Course overview
You've just heard a lot of terms, and chances are they're unfamiliar. In this course, you will get an initial introduction to many concepts and tools that you will come across as you become a self-driving car engineer.
At the end of this course, you will be required to demonstrate your mastery of basic linear algebra. You need to write your own class matrix and use this class to write a fully functional "Kalman filter" (we will learn this later).
course
1. Introduction to Kalman Filter
Kalman filter is an algorithm. It uses noise sensor measurements (and Bayes' theorem) to make reliable estimates of unknown quantities (eg, the likely position of a vehicle in 3 seconds).
In this lesson, you need to learn the basics required for the Kalman filter.
2. State and Object Oriented Programming
What is the "state" of a driverless car? What quantities do we need to track when programming our vehicles for autonomous driving?
In this lesson, you need to understand how roboticists understand "state" and learn how to manage this "state" using a programming tool called object-oriented programming.
3. Matrices and Transformations
Matrix math is the most powerful mathematical tool for self-driving car engineers. If a problem can be solved using a matrix language, we can usually find an efficient and fast programming solution.
This class will teach you how to apply matrix mathematics from a practical/non-theoretical perspective.