Neural-Fly enables rapid learning for agile flight in strong winds

TLDR

Executing safe and precise flight maneuvers in dynamic high‑speed winds is important for the ongoing commoditization of UAVs, yet the relationship between wind conditions and aircraft maneuverability is poorly understood. Neural‑Fly is a learning‑based approach that enables rapid online adaptation by incorporating pretrained representations through deep learning. Neural‑Fly learns a shared aerodynamic representation via domain adversarially invariant meta‑learning using only 12 minutes of flight data, then adapts linear coefficients for mixing basis elements with a composite adaptation law. In the Caltech Real Weather Wind Tunnel, Neural‑Fly achieves precise flight control with substantially smaller tracking error than state‑of‑the‑art nonlinear and adaptive controllers, provides exponential stability for robustness guarantees, and generalizes to unseen wind conditions, outdoor flights, and across drones with minimal performance loss.

Abstract

Executing safe and precise flight maneuvers in dynamic high-speed winds is important for the ongoing commoditization of uninhabited aerial vehicles (UAVs). However, because the relationship between various wind conditions and its effect on aircraft maneuverability is not well understood, it is challenging to design effective robot controllers using traditional control design methods. We present Neural-Fly, a learning-based approach that allows rapid online adaptation by incorporating pretrained representations through deep learning. Neural-Fly builds on two key observations that aerodynamics in different wind conditions share a common representation and that the wind-specific part lies in a low-dimensional space. To that end, Neural-Fly uses a proposed learning algorithm, domain adversarially invariant meta-learning (DAIML), to learn the shared representation, only using 12 minutes of flight data. With the learned representation as a basis, Neural-Fly then uses a composite adaptation law to update a set of linear coefficients for mixing the basis elements. When evaluated under challenging wind conditions generated with the Caltech Real Weather Wind Tunnel, with wind speeds up to 43.6 kilometers/hour (12.1 meters/second), Neural-Fly achieves precise flight control with substantially smaller tracking error than state-of-the-art nonlinear and adaptive controllers. In addition to strong empirical performance, the exponential stability of Neural-Fly results in robustness guarantees. Last, our control design extrapolates to unseen wind conditions, is shown to be effective for outdoor flights with only onboard sensors, and can transfer across drones with minimal performance degradation.