123.1 Where to from here
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis sagittis posuere ligula sit amet lacinia. Duis dignissim pellentesque magna, rhoncus congue sapien finibus mollis. Ut eu sem laoreet, vehicula ipsum in, convallis erat. Vestibulum magna sem, blandit pulvinar augue sit amet, auctor malesuada sapien. Nullam faucibus leo eget eros hendrerit, non laoreet ipsum lacinia. Curabitur cursus diam elit, non tempus ante volutpat a. Quisque hendrerit blandit purus non fringilla. Integer sit amet elit viverra ante dapibus semper. Vestibulum viverra rutrum enim, at luctus enim posuere eu. Orci varius natoque penatibus et magnis dis parturient montes, nascetur ridiculus mus.
123.1.1 Summary of this week
At the end of every week, we quickly summarize progress made during the week and preview upcoming topics.
This week, we introduced the purpose and basic features of Kalman filters.
- You learned that the purpose of a KF is to estimate the state of a dynamic system.
- You learned that the KF requires a model of system dynamics and noises.
- You learned that the KF repeatedly performs two steps: prediction and correction.
- You learned that the output of a KF is an estimate of the model’s state as well as the uncertainty of the estimate.
- You learned some example application categories that use KF.
123.2 Where to from here?
You are now ready to study the background topics that are necessary to be able to understand more deeply how a KF works, and to implement it for your application.
Next week, we focus on learning about state-space models.
- Why do we need to know about them?
- What are some example model types that we might want touse for some applications?
- How do we think about the time-domain response of a state-space model?
- How do we convert a continuous-time model to a discrete-time model, and how do we simulate them?
- Can the model tell us if it is even possible for a KF to estimate its state?