Once we gather sensor data about the car’s surroundings and its movement, we can then use this information to improve our initial location prediction. For example, say we sense lane markers and specific terrain, and we say, hmm. Actually, we know from previously collected data that if we sense landlines close to the sides of the car, the car is probably located in the center of the lane. We also know that if we sense that our tires are pointing to the right, we’re probably on a curved section of the road. So this sensor data, combined with what we already know about the road and the car, gives us more information about where our location is most likely to be. So using the sensor information, we can improve our initial prediction and better estimate our car’s location. Bayes rule gives us a mathematical way to correct our measurements, and let’s us move from an uncertain prior belief to something more and more probable. You’ll see Bayes rule come up again and again in robotics. And in this lesson, you’ll gain a greater understanding of Bayes rule.