EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

End-to-End Nano-Drone Obstacle Avoidance for Indoor Exploration

Ning Zhang, Francesco Nex, George Vosselman, Norman Kerle

Drones · 24.01.2024 · 8 (2) · 33

DOI: 10.3390/drones8020033 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Drones, online erschienen am 24.01.2024. Verfasst von Ning Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union’s Horizon 2020 Research and Innovation Programme, Korean Government under Grant Agreement.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Autonomous navigation of drones using computer vision has achieved promising performance. Nano-sized drones based on edge computing platforms are lightweight, flexible, and cheap; thus, they are suitable for exploring narrow spaces. However, due to their extremely limited computing power and storage, vision algorithms designed for high-performance GPU platforms cannot be used for nano-drones. To address this issue, this paper presents a lightweight CNN depth estimation network deployed on nano-drones for obstacle avoidance. Inspired by knowledge distillation (KD), a Channel-Aware Distillation Transformer (CADiT) is proposed to facilitate the small network to learn knowledge from a larger network. The proposed method is validated on the KITTI dataset and tested on a Crazyflie nano-drone with an ultra-low power microprocessor GAP8. This paper also implements a communication pipe so that the collected images can be streamed to a laptop through the on-board Wi-Fi module in real-time, enabling an offline reconstruction of the environment.

Förderung

  • European Union’s Horizon 2020 Research and Innovation Programme
  • Korean Government under Grant Agreement

Zitieren

APA

Zhang, N., Nex, F., Vosselman, G., & Kerle, N. (2024). End-to-End Nano-Drone Obstacle Avoidance for Indoor Exploration. Drones, 8(2), 33. https://doi.org/10.3390/drones8020033

Vancouver

Zhang N, Nex F, Vosselman G, Kerle N. End-to-End Nano-Drone Obstacle Avoidance for Indoor Exploration. Drones. 2024;8(2):33. doi:10.3390/drones8020033

BibTeX
@article{Zhang2024,
  author = {Zhang, Ning and Nex, Francesco and Vosselman, George and Kerle, Norman},
  title = {End-to-End Nano-Drone Obstacle Avoidance for Indoor Exploration},
  journal = {Drones},
  year = {2024},
  volume = {8},
  number = {2},
  pages = {33},
  doi = {10.3390/drones8020033}
}
Kostenlos starten →