Adaptive Kalman-Informed Transformer

TL;DR

This paper introduces A-KIT, an adaptive transformer-based method that learns process noise covariance online to improve sensor fusion accuracy in navigation, outperforming traditional EKF methods in real-world underwater experiments.

Contribution

We propose A-KIT, a novel adaptive Kalman-informed transformer that dynamically estimates process noise covariance, enhancing EKF-based sensor fusion in nonlinear navigation tasks.

Findings

A-KIT reduces position error by over 49.5% compared to EKF.

A-KIT outperforms model-based adaptive EKF by an average of 35.4%.

Demonstrated effectiveness in underwater autonomous vehicle navigation.

Abstract

The extended Kalman filter (EKF) is a widely adopted method for sensor fusion in navigation applications. A crucial aspect of the EKF is the online determination of the process noise covariance matrix reflecting the model uncertainty. While common EKF implementation assumes a constant process noise, in real-world scenarios, the process noise varies, leading to inaccuracies in the estimated state and potentially causing the filter to diverge. Model-based adaptive EKF methods were proposed and demonstrated performance improvements to cope with such situations, highlighting the need for a robust adaptive approach. In this paper, we derive an adaptive Kalman-informed transformer (A-KIT) designed to learn the varying process noise covariance online. Built upon the foundations of the EKF, A-KIT utilizes the well-known capabilities of set transformers, including inherent noise reduction and the ability to capture nonlinear behavior in the data. This approach is suitable for any application involving the EKF. In a case study, we demonstrate the effectiveness of A-KIT in nonlinear fusion between a Doppler velocity log and inertial sensors. This is accomplished using real data recorded from sensors mounted on an autonomous underwater vehicle operating in the Mediterranean Sea. We show that A-KIT outperforms the conventional EKF by more than 49.5% and model-based adaptive EKF by an average of 35.4% in terms of position accuracy.