Hacker News Reader

Comment by tnecniv | Hacker News Reader

Yes, they are a staple of modern robotics and other fields. If the Kalman filter assumptions about the system hold (linear model, Gaussian noise), the Kalman filter is an optimal filter and you can't do better. There are also more complicated variants like the extended Kalman filter and the unscented Kalman that can do better when the assumptions of the Kalman filter are not accurate.

It's also worth noting that the Kalman filter follows the EM pattern of many ML / statistical models.

View on HN

In practical robotics, how often do the assumptions hold? Is it really usually true that the variables have only a linear relationship?

No, but nonlinear systems can be linearized about any particular operating point very easily, and the linearized system is often reasonably close to the whole nonlinear one.

People are generally happy with the Gaussian noise assumption. In some cases, there are acceptable linearizations of the dynamical model. One example is linearizing the quadrotor dynamics about the hover state (no roll or pitch). This approximation works well enough for basic flying, but you won't be able to pull off any flashy maneuvers because any hard bank will move you too far away from the linearization point for it to hold. A better choice would be a more complicated KF (I've used an error-state KF in the past).

The real draw of these filters, though, is that they are very fast. In my experience, most of the compute time every update cycle is spent on sensing because your sensors dump a ton of data that you need to process as part of your CV / SLAM / whatever pipeline (the outputs of these then go into your KF). The dream is to get a 10ms update loop so your control algorithms can do a good job, but this is easier said than done.

KF has absolutely nothing to do with EM; no latent variables, no Jensen, no surrogate... nada.

Please stop saying that.

Can a KF be implemented in or explained as a RNN?

No.

Reply on news.ycombinator.com