All self-driving cars go through the same series of steps to safely navigate through the world. You’ve been working on the first step, localization. Before cars can safely navigate, they first use sensors and other collected data to best estimate where they are in the world. In this lesson, we’ll be talking about representing and predicting car movement. But before we do, let’s review all the steps that a common filter takes to localize a car. First, we start with an initial prediction of our cars location and the probability distribution that describes our uncertainty about that prediction. Here’s a one-dimensional example in which we know that our car is on this one lane road but we don’t know its exact location. And so, our prior probability distribution is uniform. We then sense the world around the car. This is called the measurement update step in which we gather more information about the car’s surroundings and refine our location prediction. Say we measure that we’re about two grid cells in front of the stop sign. Our measurement isn’t perfect but we have a much better idea of our car’s location. The next step is moving, also called the time update or prediction step. We predict where the car will move based on the knowledge we have about its velocity and current position and we shift our probability distribution to reflect this movement. This example shows a one-cell movement to the right and this gives us a new state estimate for the position of the car. The Kalman Filter simply repeats the sense and move measurement and prediction steps to localize the car as it’s moving. The beauty of Kalman Filters is that they combine somewhat inaccurate sensor measurements with somewhat inaccurate predictions of motion to get a filtered location estimate that’s better than any estimates that come from only sensor readings or only knowledge about movement. This is why a common filter is such a powerful localization method.