FoundLoc: Vision-based Onboard Aerial
Localization in the Wild

Yao He*1, Ivan Cisneros*1, Nikhil Keetha1, Jay Patrikar1,
Zelin Ye1, Ian Higgins1, Yaoyu Hu1 Parv Kapoor1 Sebastian Scherer1
1Carnegie Mellon University
* denotes equal contribution
Paper arXiv

FoundLoc enables Unmanned Aerial Vehicle global localization in the wild using only a low-cost onboard vision-based system without relying on external GNSS signals.

Abstract

Robust and accurate localization for Unmanned Aerial Vehicles (UAVs) is an essential capability to achieve autonomous and long-range flights. Current methods rely heavily on GNSS, which is vulnerable to jamming, spoofing, and environmental interference. In this paper, we develop a GNSS-denied localization approach for UAVs that harnesses both Visual-Inertial Odometry (VIO) and Visual Place Recognition (VPR) using a foundation model. This paper presents a novel vision-based pipeline that works exclusively with a nadir-facing camera, an Inertial Measurement Unit (IMU), and pre-existing satellite imagery for robust and accurate localization in varied environments and conditions. Our system demonstrated average localization accuracy within a 20-meter range, with a minimum error below 1 meter, under real-world conditions marked by drastic changes in environmental appearance and with no assumption of the vehicle's initial pose. The method is proven to be effective and robust, addressing the crucial need for reliable UAV localization in GNSS-denied environments, while also being computationally efficient enough to be deployed on resource-constrained platforms.

Demo: FoundLoc on Nardo-Air

Demo: FoundLoc on large-scale ALTO

BibTeX


      @article{yao2023foundloc,
        title={FoundLoc: Vision-based Onboard Aerial Localization in the Wild},
        author={Yao He and Ivan Cisneros and Nikhil Keetha and Jay Patrikar and Zelin Ye and Ian Higgins and Yaoyu Hu and Parv Kapoor and Sebastian Scherer},
        journal={arXiv preprint arXiv:2310.16299},
        year={2023}
      }