CaltechAUTHORS
  A Caltech Library Service

Learning Pose Estimation for UAV Autonomous Navigation and Landing Using Visual-Inertial Sensor Data

Baldini, Francesca and Anandkumar, Animashree and Murray, Richard M. (2020) Learning Pose Estimation for UAV Autonomous Navigation and Landing Using Visual-Inertial Sensor Data. In: 2020 American Control Conference (ACC). IEEE , Piscataway, NJ, pp. 2961-2966. ISBN 9781538682661. https://resolver.caltech.edu/CaltechAUTHORS:20200108-154918519

[img] PDF - Submitted Version
See Usage Policy.

5Mb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200108-154918519

Abstract

In this work, we propose a robust network-in-the-loop control system for autonomous navigation and landing of an Unmanned-Aerial-Vehicle (UAV). To estimate the UAV’s absolute pose, we develop a deep neural network (DNN) architecture for visual-inertial odometry, which provides a robust alternative to traditional methods. We first evaluate the accuracy of the estimation by comparing the prediction of our model to traditional visual-inertial approaches on the publicly available EuRoC MAV dataset. The results indicate a clear improvement in the accuracy of the pose estimation up to 25% over the baseline. Finally, we integrate the data-driven estimator in the closed-loop flight control system of Airsim, a simulator available as a plugin for Unreal Engine, and we provide simulation results for autonomous navigation and landing.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.23919/ACC45564.2020.9147400DOIArticle
https://arxiv.org/abs/1912.04527arXivDiscussion Paper
ORCID:
AuthorORCID
Murray, Richard M.0000-0002-5785-7481
Additional Information:© 2020 AACC. F. Baldini is supported in part by Darpa PAI grant HR0011-18-9-0035. A. Anandkumar is supported in part by Darpa PAI grant HR0011-18-9-0035, Bren Endowed Chair, Microsoft Faculty Fellowship, Google Faculty Award, Adobe Grant.
Funders:
Funding AgencyGrant Number
Defense Advanced Research Projects Agency (DARPA)HR0011-18-9-0035
Bren Professor of Computing and Mathematical SciencesUNSPECIFIED
Microsoft Faculty FellowshipUNSPECIFIED
GoogleUNSPECIFIED
AdobeUNSPECIFIED
Record Number:CaltechAUTHORS:20200108-154918519
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20200108-154918519
Official Citation:F. Baldini, A. Anandkumar and R. M. Murray, "Learning Pose Estimation for UAV Autonomous Navigation and Landing Using Visual-Inertial Sensor Data," 2020 American Control Conference (ACC), Denver, CO, USA, 2020, pp. 2961-2966, doi: 10.23919/ACC45564.2020.9147400
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:100568
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:08 Jan 2020 23:58
Last Modified:31 Jul 2020 16:50

Repository Staff Only: item control page