Reinforcement Learning Compensated Extended Kalman Filter for Attitude Estimation
This addresses attitude estimation issues in fields using inertial measurement units, but it is incremental as it builds on the extended Kalman filter with reinforcement learning compensation.
The paper tackled the problem of inaccurate initial estimation, filter gain, and non-Gaussian noise in attitude estimation using inertial measurement units by leveraging reinforcement learning to compensate for the classical extended Kalman filter, learning the filter gain from sensor measurements, and validated the algorithm on simulated and real data.
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.