Pretraining Neural-Networks with Neural-Fly for Rapid Online Learning
Keywords: meta-learning, adaptive control, flight control
TL;DR: Neural-Fly can be used to pretrain neural networks to enable rapid and robust online learning.
Abstract: Executing safe and precise flight maneuvers in
dynamic high-speed winds is important for the ongoing commodi-
tization of uninhabited aerial vehicles (UAVs). However, since 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 de-
sign methods. We present Neural-Fly, a learning-based approach
that allows rapid online adaptation by incorporating pre-trained
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. This pretraining phase
enables rapid online learning through a composite adaptation law,
which only needs to update a set of linear coefficients for mixing
the basis elements to effectively correct for the wind effects.
When evaluated under challenging wind conditions generated
with the Caltech Real Weather Wind Tunnel with wind speeds
up to 43.6 km/h (12.1 m/s), 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. Finally, our control design
extrapolates to unseen wind conditions, is shown to be effective
for outdoor flights with only on-board sensors, and can transfer
across drones with minimal performance degradation.
0 Replies
Loading