Learned Uncertainty Calibration for Visual Inertial Localization

TL;DR

This paper introduces a learned approach to improve the covariance estimates of the Extended Kalman Filter in visual inertial localization, addressing systematic inaccuracies through a nonlinear calibration map.

Contribution

It proposes a method to learn a nonlinear map that calibrates EKF covariance estimates, enhancing their accuracy in visual inertial localization tasks.

Findings

Learned calibration reduces covariance estimation errors.

Applicable to both simulation and real-world data.

Improves reliability of uncertainty estimates in visual inertial systems.

Abstract

The widely-used Extended Kalman Filter (EKF) provides a straightforward recipe to estimate the mean and covariance of the state given all past measurements in a causal and recursive fashion. For a wide variety of applications, the EKF is known to produce accurate estimates of the mean and typically inaccurate estimates of the covariance. For applications in visual inertial localization, we show that inaccuracies in the covariance estimates are \emph{systematic}, i.e. it is possible to learn a nonlinear map from the empirical ground truth to the estimated one. This is demonstrated on both a standard EKF in simulation and a Visual Inertial Odometry system on real-world data.