TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

How Kalman Filters Work

377 pointsby slackpadabout 9 years ago

12 comments

aethertapabout 9 years ago
I spent quite a bit of time working through the Kalman filter content in Sebastian Thrun&#x27;s book &quot;Probabilistic Robotics&quot;[1] a while back. I ended up making some notes [2] of the process that might be of interest to others if you&#x27;re trying to get a grasp of everything that&#x27;s going on with that process. One other person on the Internet that I know of thought they were useful, so I&#x27;ll post the link here. This was part of a project I was working on to build a K-8 robotics curriculum (no, not teaching the kids Kalman filters, but <i>I</i> wanted to know how it all worked before starting to make a curriculum). The book is really good if you&#x27;re wanting to make robots that can navigate uncertain environments.<p>Edit: I wish I&#x27;d had access to this article when I was going through that process. This is really well done.<p>1. <a href="http:&#x2F;&#x2F;amzn.com&#x2F;0262201623" rel="nofollow">http:&#x2F;&#x2F;amzn.com&#x2F;0262201623</a><p>2. <a href="https:&#x2F;&#x2F;github.com&#x2F;aethertap&#x2F;probabilistic-robotics" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;aethertap&#x2F;probabilistic-robotics</a>
评论 #11562009 未加载
评论 #11562577 未加载
评论 #11564409 未加载
评论 #11565821 未加载
kxyvrabout 9 years ago
The best presentation that I&#x27;ve ever seen on what a Kalman filter really is comes from a SIAM Review article, &quot;A Fresh Look at the Kalman Filter&quot; by Jeffrey Humpherys, Preston Redd, and Jeremy West<p><a href="http:&#x2F;&#x2F;epubs.siam.org&#x2F;doi&#x2F;abs&#x2F;10.1137&#x2F;100799666" rel="nofollow">http:&#x2F;&#x2F;epubs.siam.org&#x2F;doi&#x2F;abs&#x2F;10.1137&#x2F;100799666</a><p>It sets up the discrete-time linear system and then uses a minimization principle to show what&#x27;s going on. I can highly recommend it especially for people coming to Kalman filters from a math or optimization background.
评论 #11563059 未加载
rboydabout 9 years ago
I&#x27;d like to add Roger Labbe&#x27;s free book &quot;Kalman and Bayesian Filters in Python&quot; to the mix. Along with Thrun (which he cited to point me at), this is the resource that finally drove it home for me.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;rlabbe&#x2F;Kalman-and-Bayesian-Filters-in-Python" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;rlabbe&#x2F;Kalman-and-Bayesian-Filters-in-Pyt...</a><p>For people wondering about application, one of the popular recent uses is for sensor fusion in virtual reality.
评论 #11562645 未加载
kshitijlabout 9 years ago
For people familiar with Gaussian Processes, it may help to think of Kalman filters as a special case of GPs where you can construct the inverse of the covariance matrix directly, and this inverse has a tridiagonal structure.<p>Thus, a really efficient Bayesian regression algorithm.
评论 #11563099 未加载
danpalmerabout 9 years ago
What&#x27;s even more interesting is that there is some experimental evidence to suggest that the human brain uses Kalman filters for certain things. I <i>think</i> this was one of the papers about it: <a href="http:&#x2F;&#x2F;papers.nips.cc&#x2F;paper&#x2F;3665-a-neural-implementation-of-the-kalman-filter.pdf" rel="nofollow">http:&#x2F;&#x2F;papers.nips.cc&#x2F;paper&#x2F;3665-a-neural-implementation-of-...</a>
platzabout 9 years ago
I find it odd that nowhere in the 3-part series is discussed the relationship between kalman filters and hidden markov models.
评论 #11566550 未加载
fuzzythinkerabout 9 years ago
Another nice explanation, a bit more visual.<p><a href="http:&#x2F;&#x2F;www.bzarg.com&#x2F;p&#x2F;how-a-kalman-filter-works-in-pictures&#x2F;" rel="nofollow">http:&#x2F;&#x2F;www.bzarg.com&#x2F;p&#x2F;how-a-kalman-filter-works-in-pictures...</a>
rsp1984about 9 years ago
What many don&#x27;t know about Kalman Filters (and took me a while to realize as well) is that it&#x27;s just recursive least squares.<p>It is just formulated a bit differently such that incremental update complexity depends of the dimensionality of the observation, not the dimensionality of the estimated state. Depending on the dimensions this can be a lot more efficient.
aswansonabout 9 years ago
Best breakdown from a conceptual as well as mathematically precise description I have ever read.
tnecnivabout 9 years ago
Nice writeup. I use these filters quite often (especially the particle filter). Very powerful tools.
评论 #11562075 未加载
univalentabout 9 years ago
Adaptive Filter Theory by Simon Haykin is the single best engineering book I used. <a href="http:&#x2F;&#x2F;www.amazon.com&#x2F;Adaptive-Filter-Theory-Simon-Haykin&#x2F;dp&#x2F;013267145X" rel="nofollow">http:&#x2F;&#x2F;www.amazon.com&#x2F;Adaptive-Filter-Theory-Simon-Haykin&#x2F;dp...</a> Covers Kalman filters in great detail. Did anyone else us it?
andhessabout 9 years ago
Awesome to see some Kalman filters! Takes me back to my undergrad :-)