Differentiable Moving Horizon Estimation for Robust Flight Control

TL;DR

This paper introduces a data-efficient, differentiable moving horizon estimation method that automatically tunes parameters online, improving robust quadrotor control in challenging scenarios through end-to-end learning and recursive gradient computation.

Contribution

It presents a novel differentiable MHE algorithm that enables online auto-tuning and adaptation without extensive data or ground truth, integrating seamlessly with neural networks.

Findings

Effective in simulation and real quadrotor experiments

Handles sudden payload changes and downwash disturbances

Achieves robust trajectory tracking with minimal tuning

Abstract

Estimating and reacting to external disturbances is of fundamental importance for robust control of quadrotors. Existing estimators typically require significant tuning or training with a large amount of data, including the ground truth, to achieve satisfactory performance. This paper proposes a data-efficient differentiable moving horizon estimation (DMHE) algorithm that can automatically tune the MHE parameters online and also adapt to different scenarios. We achieve this by deriving the analytical gradient of the estimated trajectory from MHE with respect to the tuning parameters, enabling end-to-end learning for auto-tuning. Most interestingly, we show that the gradient can be calculated efficiently from a Kalman filter in a recursive form. Moreover, we develop a model-based policy gradient algorithm to learn the parameters directly from the trajectory tracking errors without the need for the ground truth. The proposed DMHE can be further embedded as a layer with other neural networks for joint optimization. Finally, we demonstrate the effectiveness of the proposed method via both simulation and experiments on quadrotors, where challenging scenarios such as sudden payload change and flying in downwash are examined.