Meta-Learning-Based Robust Adaptive Flight Control Under Uncertain Wind Conditions
Abstract
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.
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.Attached Files
Submitted - 2103.01932v1.pdf
Files
Name | Size | Download all |
---|---|---|
md5:5cc1b2b8af2ba40c435805d502b0df1d
|
3.6 MB | Preview Download |
Additional details
- Eprint ID
- 99547
- DOI
- 10.48550/arXiv.2103.01932
- Resolver ID
- CaltechAUTHORS:20191029-154625952
- Center for Autonomous Systems and Technologies
- Raytheon Company
- Created
-
2019-10-29Created from EPrint's datestamp field
- Updated
-
2023-06-02Created from EPrint's last_modified field
- Caltech groups
- GALCIT, Center for Autonomous Systems and Technologies (CAST)