Cooperative Visual Inertial Odometry for Heterogeneous Swarm of Drones Navigating in Noisy Environments

Kamil Canberk Atik, Enes Erdogan, Ahmet Yusuf Yahsi, Feyzullah Kara, Baris Yalcin, Gurkan Cetin, Nazim Kemal Ure

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents a methodology for enhancing the localization performance of drone swarms by collaborative propagation of the estimates of drones equipped with higher cost sensors to the drones with lower-cost sensors. Although recent advances in visual-inertial odometry (VIO) enabled good performance in GPS denied environments, the localization performance is still highly dependent on the accuracy of inertial sensors. Moreover, environmental effects that corrupt visual inputs also contribute to the error rate of VIO estimates thus localization in noisy environments with low-grade sensors is still widely an open problem. We show that this problem can be alleviated when drones are navigating in the form of a swarm, and the relative distance measurements between drones are available through ultra-wideband (UWB) signals. In particular, we develop a collaborative Kalman filtering and optimization framework, where the drones with lower grade sensors receive updates from drones that have access to higher-quality measurements. We validate our approach in a simulation environment with realistic visual representations and show that the proposed methodology can significantly improve the localization performance, especially for the scenarios where the camera measurements are corrupted with high noise. We further present results in simplistic flight tests to demonstrate the applicability of our approach to real hardware.

Original languageEnglish
Title of host publication2022 IEEE 31st International Symposium on Industrial Electronics, ISIE 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages727-734
Number of pages8
ISBN (Electronic)9781665482400
DOIs
Publication statusPublished - 2022
Event31st IEEE International Symposium on Industrial Electronics, ISIE 2022 - Anchorage, United States
Duration: 1 Jun 20223 Jun 2022

Publication series

NameIEEE International Symposium on Industrial Electronics
Volume2022-June

Conference

Conference31st IEEE International Symposium on Industrial Electronics, ISIE 2022
Country/TerritoryUnited States
CityAnchorage
Period1/06/223/06/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Funding

VII. ACKNOWLEDGEMENTS This work is supported by Istanbul Technical University BAP Grant NO: MOA-2019-42321 and Havelsan.

FundersFunder number
Istanbul Teknik ÜniversitesiMOA-2019-42321

    Keywords

    • localization
    • optimization
    • swarm drone
    • VIO

    Fingerprint

    Dive into the research topics of 'Cooperative Visual Inertial Odometry for Heterogeneous Swarm of Drones Navigating in Noisy Environments'. Together they form a unique fingerprint.

    Cite this