Autonomous UAV Navigation Using Reinforcement Learning

TL;DR

This paper presents a reinforcement learning framework enabling UAVs to autonomously navigate unknown environments, demonstrated through simulation and real-world experiments, with potential applications in wildfire monitoring and search and rescue.

Contribution

It introduces a novel reinforcement learning approach tailored for UAV navigation in unknown environments, including implementation details and validation.

Findings

UAVs successfully learned to navigate in unknown environments

Reinforcement learning was effectively applied to UAV flight control

The approach is viable for real-world UAV applications

Abstract

Unmanned aerial vehicles (UAV) are commonly used for missions in unknown environments, where an exact mathematical model of the environment may not be available. This paper provides a framework for using reinforcement learning to allow the UAV to navigate successfully in such environments. We conducted our simulation and real implementation to show how the UAVs can successfully learn to navigate through an unknown environment. Technical aspects regarding to applying reinforcement learning algorithm to a UAV system and UAV flight control were also addressed. This will enable continuing research using a UAV with learning capabilities in more important applications, such as wildfire monitoring, or search and rescue missions.