Learning to Assist Drone Landings

TL;DR

This paper introduces a shared autonomy system that helps novice drone pilots perform safe landings in obstacle-rich environments, achieving performance comparable to or better than experienced pilots through perceptual and policy modules.

Contribution

It presents a novel shared autonomy approach combining perceptual encoding and reinforcement learning for assisting drone landings, outperforming human pilots in a user study.

Findings

Participants outperformed experienced pilots when assisted.

The system successfully generalizes to unknown platforms.

Novice pilots achieved safe landings comparable to experts.

Abstract

Unmanned aerial vehicles (UAVs) are often used for navigating dangerous terrains, however they are difficult to pilot. Due to complex input-output mapping schemes, limited perception, the complex system dynamics and the need to maintain a safe operation distance, novice pilots experience difficulties in performing safe landings in obstacle filled environments. In this work we propose a shared autonomy approach that assists novice pilots to perform safe landings on one of several elevated platforms at a proficiency equal to or greater than experienced pilots. Our approach consists of two modules, a perceptual module and a policy module. The perceptual module compresses high dimensionality RGB-D images into a latent vector trained with a cross-modal variational auto-encoder. The policy module provides assistive control inputs trained with the reinforcement algorithm TD3. We conduct a user study (n=33) where participants land a simulated drone with and without the use of the assistant. Despite the goal platform not being known to the assistant, participants of all skill levels were able to outperform experienced participants while assisted in the task.