Free LSD: Prior-Free Visual Landing Site Detection for Autonomous Planes

TL;DR

This paper introduces a prior-free perception system for autonomous planes to detect safe landing sites using texture, shape, hazard assessment, and wind estimation, enabling reliable landings in unknown terrains.

Contribution

It presents a novel perception framework that detects landing sites without prior environmental knowledge, incorporating hazard detection and wind estimation for small-scale UAVs.

Findings

Successfully tested on synthetic datasets.

Effective hazard and obstacle detection.

Reliable landing site identification in real-world environments.

Abstract

Full autonomy for fixed-wing unmanned aerial vehicles (UAVs) requires the capability to autonomously detect potential landing sites in unknown and unstructured terrain, allowing for self-governed mission completion or handling of emergency situations. In this work, we propose a perception system addressing this challenge by detecting landing sites based on their texture and geometric shape without using any prior knowledge about the environment. The proposed method considers hazards within the landing region such as terrain roughness and slope, surrounding obstacles that obscure the landing approach path, and the local wind field that is estimated by the on-board EKF. The latter enables applicability of the proposed method on small-scale autonomous planes without landing gear. A safe approach path is computed based on the UAV dynamics, expected state estimation and actuator uncertainty, and the on-board computed elevation map. The proposed framework has been successfully tested on photo-realistic synthetic datasets and in challenging real-world environments.