Geek asks and answers

Kalman filter with a complete data set?

I am looking for a way to combine data with a compass and a gyroscope to determine the relationship after the fact. I will work with a complete data set in which the data of a three-dimensional compass and gyroscope are recorded at regular intervals, but I want to restore the estimate of the relationship in post-processing.

I just looked at using the Kalman filter, as they are so well documented, but would rather use something more suitable for the case where the complete data set is known. I have a feeling that the solution is "just" the least-squares problem, but I hope someone here can point me towards a paper or two dedicated to this problem (or such problems).

At this moment, I’m not even sure that this filter will be called, so it’s hard for me to find useful search terms. Any help would be appreciated.

Many thanks!

+3
source share
1 answer

If you understand the Kalman filter in detail, you can also implement the so-called “smooth” Kalman, which works with a complete data set.

However, let me warn you about one thing. For programmers, there is no Kalman filter . The Kalman filter is hard to understand. You cannot implement and use it correctly if you do not understand it.

- , . , . manuscript, . , , - 29-32 . , .

+4

More articles:


All Articles