Obstacle Detection for BVLOS Drones

TL;DR

This paper explores deep learning-based obstacle detection for BVLOS drones, comparing models and techniques to improve safety, but highlights the need for more data for real-world deployment.

Contribution

It introduces a module for obstacle detection in BVLOS drones using deep learning, comparing different models and data augmentation methods.

Findings

Deep learning shows promise for obstacle detection

YOLOv3 and YOLOv5 are evaluated for performance

More data is needed for real-world application

Abstract

With the introduction of new regulations in the European Union, the future of Beyond Visual Line Of Sight (BVLOS) drones is set to bloom. This led to the creation of the theBEAST project, which aims to create an autonomous security drone, with focus on those regulations and on safety. This technical paper describes the first steps of a module within this project, which revolves around detecting obstacles so they can be avoided in a fail-safe landing. A deep learning powered object detection method is the subject of our research, and various experiments are held to maximize its performance, such as comparing various data augmentation techniques or YOLOv3 and YOLOv5. According to the results of the experiments, we conclude that although object detection is a promising approach to resolve this problem, more volume of data is required for potential usage in a real-life application.