Understanding Kalman Filters

Discover real-world situations in which you can use Kalman filters. Kalman filters are often used to optimally estimate the internal states of a system in the presence of uncertain and indirect measurements. Learn the working principles behind Kalman filters by watching the following introductory examples.

You will explore the situations where Kalman filters are commonly used. When the state of a system can only be measured indirectly, you can use a Kalman filter to optimally estimate the states of that system. And when measurements from different sensors are available but subject to noise, you can use a Kalman filter to combine sensory data from various sources (known as sensor fusion) to find the best estimate of the parameter of interest.

You will also learn about state observers by walking through a few examples that include simple math. This will help you understand what a Kalman filter is and how it works. At a high level, Kalman filters are a type of optimal state estimator. The videos also include a discussion of nonlinear state estimators, such as extended and unscented Kalman filters.

Finally, an example demonstrates how the states of a linear system can be estimated using Kalman filters, MATLAB^®, and Simulink^®.