Reinforcement Learning for Shared Autonomy Drone Landings

TL;DR

This paper presents a reinforcement learning-based shared autonomy system that assists novice pilots in safely landing UAVs under challenging conditions, significantly improving success rates and performance.

Contribution

It introduces a novel shared autonomy approach using RL trained in simulation to assist human pilots in UAV landings without prior knowledge of human intent or environment.

Findings

Success rate increased from 51.4% to 98.2% with assistance.

Participants performed better than experienced pilots when aided.

The system was effective despite being trained only on simulated user data.

Abstract

Novice pilots find it difficult to operate and land unmanned aerial vehicles (UAVs), due to the complex UAV dynamics, challenges in depth perception, lack of expertise with the control interface and additional disturbances from the ground effect. Therefore we propose a shared autonomy approach to assist pilots in safely landing a UAV under conditions where depth perception is difficult and safe landing zones are limited. Our approach comprises of two modules: a perception module that encodes information onto a compressed latent representation using two RGB-D cameras and a policy module that is trained with the reinforcement learning algorithm TD3 to discern the pilot's intent and to provide control inputs that augment the user's input to safely land the UAV. The policy module is trained in simulation using a population of simulated users. Simulated users are sampled from a parametric model with four parameters, which model a pilot's tendency to conform to the assistant, proficiency, aggressiveness and speed. We conduct a user study (n = 28) where human participants were tasked with landing a physical UAV on one of several platforms under challenging viewing conditions. The assistant, trained with only simulated user data, improved task success rate from 51.4% to 98.2% despite being unaware of the human participants' goal or the structure of the environment a priori. With the proposed assistant, regardless of prior piloting experience, participants performed with a proficiency greater than the most experienced unassisted participants.