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

Ning Zhang (Corresponding Author), F.C. Nex, G. Vosselman, N. Kerle

Research output: Contribution to journalArticleAcademicpeer-review

2 Citations (Scopus)
156 Downloads (Pure)

Abstract

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.
Original languageEnglish
Article number33
Number of pages15
JournalDrones
Volume8
Issue number2
DOIs
Publication statusPublished - Feb 2024

Keywords

  • Crazyflie
  • computer vision
  • depth estimation
  • drone
  • edge computing
  • knowledge distillation
  • obstacle avoidance
  • transformer

Fingerprint

Dive into the research topics of 'End-to-End Nano-Drone Obstacle Avoidance for Indoor Exploration'. Together they form a unique fingerprint.

Cite this