2
$\begingroup$

Usually I find that if I understand the etymology, I better understand the algorithm is doing/trying to convey. I've never found where the name for this transform comes from.

$\endgroup$
  • $\begingroup$ I knew nothing about this but I looked it up on wikipedia. It has to do with the extended Kalman filter which linearizes a nonlinear function. Jeffrey Uhlmann coined the term in his PhD thesis in the 1990s. Wikipedia describes how he came up with the term,and provides a motivating example. It helps if you know something about Kalman filters as the article is largely technical.. $\endgroup$ – Michael R. Chernick Dec 20 '16 at 2:21
4
$\begingroup$

The Wikipedia page for Unscented transform links to an interview with its creator Jeffrey Uhlmann, which includes the following explanation:

What’s with the Name “Unscented”?

Initially I only referred to it as the “new filter.” Needing a more specific name, people in my lab began referring to it as the “Uhlmann filter,” which obviously isn’t a name that I could use, so I had to come up with an official term. One evening everyone else in the lab was at the Royal Opera House, and as I was working I noticed someone’s deodorant on a desk. The word “unscented” caught my eye as the perfect technical term. At first people in the lab thought it was absurd—which is okay because absurdity is my guiding principle—and that it wouldn’t catch on. My claim was that people simply accept technical terms as technical terms: for example, does anyone think about why a tree is called a tree?

Sorry if this is anticlimactic!

The interview also says:

What’s the appeal of the Unscented Transform?

What was most striking to people about the UT was not the accuracy so much as the ease with which it could be implemented. There was no longer a need to derive a linearized approximation which would then have to be coded up for use in the filter.

So it may be that he associated the alternative with "code smell"?

$\endgroup$
  • $\begingroup$ I like the comparison to the 'code smell' of the EKF. I'll definitely remember that now! $\endgroup$ – noname Dec 20 '16 at 3:55
  • $\begingroup$ I read some of this also without following the link to the interview. It is difficult to see whether or not this helps the OP without knowing his background. I worked with Kalman Filters when I was working on orbit determination problems in the Aerospace industry. I have also seen them used in time series analysis. The interview is interesting but why is it satisfactory? $\endgroup$ – Michael R. Chernick Dec 20 '16 at 11:25

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.