Robust Approaches for Localization on Multi-camera Systems in Dynamic Environments

Marco Sewtz, Xiaozhou Luo, Johannes Landgraf, Tim Bodenmuller, Rudolph Triebel

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

10 Zitate (Scopus)

Abstract

Localization of humanoid robots in real-life scenarios has to robustly tackle dynamic environments and provide coherent data and tight integration for follow-up tasks. However state-of-the-art solutions, like ORBSlam2 [1], lack this ability. In this work we present two adaptations of ORBSlam2 for a multi-camera setup on the DLR Rollin' Justin System, one distributed multi-slam and one combined single-process system. Further, we introduce the usage of pre-recorded maps with ORBSlam2 and the alignment with semantic maps for planning. We compare performance of the adaptations against and the original approach in realistic experiments and discuss advantages and disadvantages of all methods.

OriginalspracheEnglisch
Titel2021 International Conference on Automation, Robotics and Applications, ICARA 2021
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten211-215
Seitenumfang5
ISBN (elektronisch)9780738142906
DOIs
PublikationsstatusVeröffentlicht - 4 Feb. 2021
Veranstaltung2021 International Conference on Automation, Robotics and Applications, ICARA 2021 - Virtual, Prague, Tschechische Republik
Dauer: 4 Feb. 20216 Feb. 2021

Publikationsreihe

Name2021 International Conference on Automation, Robotics and Applications, ICARA 2021

Konferenz

Konferenz2021 International Conference on Automation, Robotics and Applications, ICARA 2021
Land/GebietTschechische Republik
OrtVirtual, Prague
Zeitraum4/02/216/02/21

Fingerprint

Untersuchen Sie die Forschungsthemen von „Robust Approaches for Localization on Multi-camera Systems in Dynamic Environments“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren