CaltechAUTHORS
  A Caltech Library Service

Neural Lander: Stable Drone Landing Control using Learned Dynamics

Shi, Guanya and Shi, Xichen and O'Connell, Michael and Yu, Rose and Azizzadenesheli, Kamyar and Anandkumar, Animashree and Yue, Yisong and Chung, Soon-Jo (2018) Neural Lander: Stable Drone Landing Control using Learned Dynamics. . (Submitted) http://resolver.caltech.edu/CaltechAUTHORS:20190205-100744248

[img] PDF - Submitted Version
See Usage Policy.

1549Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20190205-100744248

Abstract

Precise trajectory control near ground is difficult for multi-rotor drones, due to the complex ground effects caused by interactions between multi-rotor airflow and the environment. Conventional control methods often fail to properly account for these complex effects and fall short in accomplishing smooth landing. In this paper, we present a novel deep-learning-based robust nonlinear controller (Neural-Lander) that improves control performance of a quadrotor during landing. Our approach blends together a nominal dynamics model coupled with a Deep Neural Network (DNN) that learns the high-order interactions. We employ a novel application of spectral normalization to constrain the DNN to have bounded Lipschitz behavior. Leveraging this Lipschitz property, we design a nonlinear feedback linearization controller using the learned model and prove system stability with disturbance rejection. To the best of our knowledge, this is the first DNN-based nonlinear feedback controller with stability guarantees that can utilize arbitrarily large neural nets. Experimental results demonstrate that the proposed controller significantly outperforms a baseline linear proportional-derivative (PD) controller in both 1D and 3D landing cases. In particular, we show that compared to the PD controller, Neural-Lander can decrease error in z direction from 0.13m to zero, and mitigate average x and y drifts by 90% and 34% respectively, in 1D landing. Meanwhile, Neural-Lander can decrease z error from 0.12m to zero, in 3D landing. We also empirically show that the DNN generalizes well to new test inputs outside the training domain.


Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription
https://arxiv.org/abs/1811.08027arXivDiscussion Paper
ORCID:
AuthorORCID
Chung, Soon-Jo0000-0002-6657-3907
Additional Information:The authors thank Joel Burdick, Mory Gharib and Daniel Pastor Moreno. The work is funded in part by Caltech’s Center for Autonomous Systems and Technologies and Raytheon Company.
Group:GALCIT
Funders:
Funding AgencyGrant Number
CaltechUNSPECIFIED
Raytheon CompanyUNSPECIFIED
Record Number:CaltechAUTHORS:20190205-100744248
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20190205-100744248
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:92658
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:05 Feb 2019 19:10
Last Modified:05 Feb 2019 19:10

Repository Staff Only: item control page