A Caltech Library Service

Meta-Learning-Based Robust Adaptive Flight Control Under Uncertain Wind Conditions

O'Connell, Michael and Shi, Guanya and Shi, Xichen and Chung, Soon-Jo (2019) Meta-Learning-Based Robust Adaptive Flight Control Under Uncertain Wind Conditions. . (Unpublished)

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


Realtime model learning proves challenging for complex dynamical systems, such as drones flying in variable wind conditions. Machine learning technique such as deep neural networks have high representation power but is often too slow to update onboard. On the other hand, adaptive control relies on simple linear parameter models can update as fast as the feedback control loop. We propose an online composite adaptation method that treats outputs from a deep neural network as a set of basis functions capable of representing different wind conditions. To help with training, meta-learning techniques are used to optimize the network output useful for adaptation. We validate our approach by flying a drone in an open air wind tunnel under varying wind conditions and along challenging trajectories. We compare the result with other adaptive controller with different basis function sets and show improvement over tracking and prediction errors.

Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription Paper
Shi, Guanya0000-0002-9075-3705
Chung, Soon-Jo0000-0002-6657-3907
Additional Information:We thank Yisong Yue, Animashree Anandkumar, Kamyar Azizzadenesheli, Joel Burdick, Mory Gharib, Daniel Pastor Moreno, and Anqi Liu for helpful discussions. The work is funded in part by Caltech’s Center for Autonomous Systems and Technologies and Raytheon Company.
Group:GALCIT, Center for Autonomous Systems and Technologies (CAST)
Funding AgencyGrant Number
Center for Autonomous Systems and TechnologiesUNSPECIFIED
Raytheon CompanyUNSPECIFIED
Record Number:CaltechAUTHORS:20191029-154625952
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:99547
Deposited By: Tony Diaz
Deposited On:29 Oct 2019 22:58
Last Modified:04 Mar 2021 00:18

Repository Staff Only: item control page