[MUSIC] Welcome to week two of The Estimation and Learning Module in the Robotics Specialization. This week, with Steve Miguel, we will be learning about the Kalman Filter. First of all, we'll be exploring how we use the Kalman Filter to model Linear Dynamical Systems, and to track their uncertainty over time. Then, we'll learn about how to do estimation using posterior distributions and Maximum-A-Posterior Estimation, for these distributions. And than finally we'll explore how to generalize these Kalman Filters, the handle nonlineraities, using different types of algorithms and models. To summarize, this week we'll learn how to track the uncertainty of estimating Dynamical Systems over time, using the Kalman Filter to perform these estimates. >> Hello, my name is Stephen McGill. I'm a doctoral candidate at the University of Pennsylvania. My research focuses on humanoid robots, especially as it relates to human robot interaction. I like seeing how a human can help to develop control algorithms to control a high dimensional system. I will try to talk to you about Kalman Filters and localization in these coming weeks, especially as it relate to my experience in Robo Cup, and DARPA Robotics Challenge.