Toward Appearance-based Autonomous Landing Site Identification for Multirotor Drones in Unstructured Environments

TL;DR

This paper presents a pipeline for automatically generating synthetic datasets to train appearance-based terrain classifiers, enabling autonomous landing site identification for multirotor drones in unstructured environments.

Contribution

It introduces a novel method to generate training data automatically, reducing the need for manual labeling and improving real-time landing site detection.

Findings

The U-Net trained on synthetic data performs well on real-world images.

The approach enables real-time landing site classification on drone platforms.

Synthetic data generation reduces manual effort in dataset creation.

Abstract

A remaining challenge in multirotor drone flight is the autonomous identification of viable landing sites in unstructured environments. One approach to solve this problem is to create lightweight, appearance-based terrain classifiers that can segment a drone's RGB images into safe and unsafe regions. However, such classifiers require data sets of images and masks that can be prohibitively expensive to create. We propose a pipeline to automatically generate synthetic data sets to train these classifiers, leveraging modern drones' ability to survey terrain automatically and the ability to automatically calculate landing safety masks from terrain models derived from such surveys. We then train a U-Net on the synthetic data set, test it on real-world data for validation, and demonstrate it on our drone platform in real-time.