If you have no idea where a car is located in the world the probability distribution for its location will look completely flat. The probability of it being anywhere say in San Francisco or in Tokyo will be the exact same. The probability that the car will be at any particular location will be a constant value that’s the same at every location. So the probability distribution can be represented by a constant horizontal line on a graph, that shows the probability of all of these outcomes. But as we gather more information, this distribution will change. Say we get a GPS sensor reading that tells us that we’re a lot closer to San Francisco than to Tokyo. The location probability goes up near the GPS measurement and the probability goes down in regions far from the GPS measurement. And even though the GPS signal isn’t perfect you have more information about the likely location of your car. The vehicle is never 100 percent sure of its location, yet through sensing the vehicle increases its certainty. The shape of the probability distribution tells you the most likely locations and the least likely locations of the vehicle. Probability distributions are really useful ways to visualize and represent uncertainty, not just in single vehicle localization but also in tracking the locations of pedestrians, bicycles and other moving vehicles around a car. These distributions are also used in representing uncertainty in sensor measurements. Remember that autonomous vehicles are robots on wheels. So everything from sensing, measuring and moving will involve some uncertainty. So, in this lesson you’re going to learn how to draw and interpret probability distributions. This will prepare you for vehicle localization and object-.