Kalman Filter - Gaussian representation

1. What Gaussian for Kalman filter?
2. Is Kalman filter a Gaussian process?
3. Is Kalman filter Bayesian?
4. What is covariance matrix in Kalman filter?

What Gaussian for Kalman filter?

Traditional Kalman filtering assumes white i.i.d. Gaussian measurement noise, and as such is not optimal for these applications. To address this gap, we propose using general (non-white) Gaussian Processes (GPs) as a non-parametric noise model that can capture the correlation present in these perception systems.

Is Kalman filter a Gaussian process?

Despite the fact that Kalman filters (KF) can be seen as a special case of Gaussian processes (GPs) [9] they differ in the way the models need to be thought about (i.e. physical state- based versus covariance function) that describe the underly- ing process.

Is Kalman filter Bayesian?

Kalman filter is the analytical implementation of Bayesian filtering recursions for linear Gaussian state space models. For this model class the filtering density can be tracked in terms of finite-dimensional sufficient statistics which do not grow in time∗.

What is covariance matrix in Kalman filter?

This uncertainty can be represented by a matrix known as the state covariance matrix, P. The state covariance matrix consists of the variances associated with each of the state estimates as well as the correlation between the errors in the state estimates.