Autonomous Quadrotor Landing using Deep Reinforcement Learning

TL;DR

This paper presents a deep reinforcement learning approach for autonomous quadrotor landing using only low-resolution downward images, achieving performance comparable to state-of-the-art methods and human pilots.

Contribution

It introduces a hierarchical Deep Q-Network framework that enables UAVs to land on ground markers using minimal sensor data, with extensive training and testing in diverse environments.

Findings

Performance comparable to state-of-the-art algorithms

Effective use of domain randomization for training

Successful real-world deployment of the method

Abstract

Landing an unmanned aerial vehicle (UAV) on a ground marker is an open problem despite the effort of the research community. Previous attempts mostly focused on the analysis of hand-crafted geometric features and the use of external sensors in order to allow the vehicle to approach the land-pad. In this article, we propose a method based on deep reinforcement learning that only requires low-resolution images taken from a down-looking camera in order to identify the position of the marker and land the UAV on it. The proposed approach is based on a hierarchy of Deep Q-Networks (DQNs) used as high-level control policy for the navigation toward the marker. We implemented different technical solutions, such as the combination of vanilla and double DQNs, and a partitioned buffer replay. Using domain randomization we trained the vehicle on uniform textures and we tested it on a large variety of simulated and real-world environments. The overall performance is comparable with a state-of-the-art algorithm and human pilots.