Neural Moving Horizon Estimation for Robust Flight Control

TL;DR

This paper introduces NeuroMHE, a neural network-based moving horizon estimator that automatically tunes parameters for robust quadrotor flight control, outperforming existing methods in simulations and real-world tests.

Contribution

We develop NeuroMHE, a novel neural moving horizon estimator that integrates analytical gradients and a recursive Kalman filter for efficient learning and adaptation in flight scenarios.

Findings

NeuroMHE reduces force estimation errors by up to 76.7%.

It outperforms state-of-the-art neural estimators with fewer parameters.

Effective in both simulations and physical quadrotor experiments.

Abstract

Estimating and reacting to disturbances is crucial for robust flight control of quadrotors. Existing estimators typically require significant tuning for a specific flight scenario or training with extensive ground-truth disturbance data to achieve satisfactory performance. In this paper, we propose a neural moving horizon estimator (NeuroMHE) that can automatically tune its key parameters modeled by a neural network and adapt to different flight scenarios. We achieve this by deriving the analytical gradients of the MHE estimates with respect to the MHE weighting matrices, which enables a seamless embedding of the MHE as a learnable layer into the neural network for highly effective learning. Interestingly, we show that the gradients can be computed efficiently using a Kalman filter in a recursive form. Moreover, we develop a model-based policy gradient algorithm to train NeuroMHE directly from the quadrotor trajectory tracking error without needing the ground-truth disturbance data. The effectiveness of NeuroMHE is verified extensively via both simulations and physical experiments on quadrotors in various challenging flights. Notably, NeuroMHE outperforms a state-of-the-art neural network-based estimator, reducing force estimation errors by up to 76.7%, while using a portable neural network that has only 7.7% of the learnable parameters of the latter. The proposed method is general and can be applied to robust adaptive control of other robotic systems.