Reinforcement Learning Compensated Extended Kalman Filter for Attitude Estimation

TL;DR

This paper introduces a reinforcement learning-based approach to enhance the extended Kalman filter for attitude estimation, addressing issues like initial inaccuracies and non-Gaussian noise, validated through simulations and real data.

Contribution

It proposes a novel reinforcement learning method to adaptively learn filter gains, improving attitude estimation accuracy over traditional EKF methods.

Findings

Improved attitude estimation accuracy demonstrated in simulations.

Effective compensation for non-Gaussian noise in real data.

Convergence analysis of the proposed reinforcement learning EKF.

Abstract

Inertial measurement units are widely used in different fields to estimate the attitude. Many algorithms have been proposed to improve estimation performance. However, most of them still suffer from 1) inaccurate initial estimation, 2) inaccurate initial filter gain, and 3) non-Gaussian process and/or measurement noise. In this paper, we leverage reinforcement learning to compensate for the classical extended Kalman filter estimation, i.e., to learn the filter gain from the sensor measurements. We also analyse the convergence of the estimate error. The effectiveness of the proposed algorithm is validated on both simulated data and real data.