NCS: Kalman Filtering: Difference between revisions
From Murray Wiki
Jump to navigationJump to search
No edit summary |
No edit summary |
||
Line 9: | Line 9: | ||
== Reading == | == Reading == | ||
* <p>[http://www.cs.unc.edu/~welch/ | * <p>[http://www.cs.unc.edu/~welch/media/pdf/kalman_intro.pdf An Introduction to the Kalman Filter], G. Welch and G. Bishop</p> | ||
* <p>[http://en.wikipedia.org/wiki/Kalman_filter Wikipedia: Kalman Filter]</p> | * <p>[http://en.wikipedia.org/wiki/Kalman_filter Wikipedia: Kalman Filter]</p> |
Revision as of 00:06, 16 April 2006
Prev: Alice Planner | Course Home | Next: MHE |
In this lecture, we study the Kalman filter for discrete-time linear systems. In particular, we see under what assumptions and in what senses the Kalman filter is an optimal estimator. To prove the results we use some results about conditional expectations and Gaussian probabiliy distributions. We show that the filter contains one prediction step and one correcter step that takes the most recent measurement into account. An example is used to illustrate the results.
Lecture Materials
Reading
An Introduction to the Kalman Filter, G. Welch and G. Bishop
A New Approach to Linear Filtering and Prediction Problem, R.E. Kalman. Transactions of the ASME, Series D, 1960.