Unscented filter with non-zero process noise

[dgondelach]

I created a post on an extension of this discussion, namely on how to add the process noise:

Unscented Kalman Filter: process noise sigma point augmentation

\newcommand{\bm}{\boldsymbol} Hi everyone, I was looking at the Hipparchus implementation of the Unscented Kalman Filter and came across a potential limitation in how the process noise is added to the sigma points after prediction. The notation here is based on Table 7.3 in Wan and Merwe [1], where the UKF is formulated for zero-mean process- and measurement noise. Below, I abbreviate the sampling of sigma points as UT : \hspace{1cm} \bm{\mathcal{X}} = \left[\begin{matrix} \bm x & \bm x …