UAV Swarm Path Planning with Reinforcement Learning for Field prospecting

TL;DR

This paper presents a reinforcement learning-based system for autonomous UAV swarm path planning that ensures full area coverage for field prospection, optimizing flight paths without prior target knowledge.

Contribution

It introduces a novel reinforcement learning approach for calculating optimal UAV swarm paths that adapt to map size and number of UAVs, improving efficiency and autonomy.

Findings

Single control for all UAVs yields shorter flight times.

Flight time increases with map size.

The system effectively covers the entire area without prior target info.

Abstract

Unmanned Aerial Vehicle (UAV) swarms adoption shows a steady growth among operators due to the benefits in time and cost arisen from their use. However, this kind of system faces an important problem which is the calculation of many optimal paths for each UAV. Solving this problem would allow a to control many UAVs without human intervention at the same time while saving battery between recharges and performing several tasks simultaneously. The main aim is to develop a system capable of calculating the optimal flight path for a UAV swarm. The aim of these paths is to achieve full coverage of a flight area for tasks such as field prospection. All this, regardless of the size of maps and the number of UAVs in the swarm. It is not necessary to establish targets or any other previous knowledge other than the given map. Experiments have been conducted to determine whether it is optimal to establish a single control for all UAVs in the swarm or a control for each UAV. The results show that it is better to use one control for all UAVs because of the shorter flight time. In addition, the flight time is greatly affected by the size of the map. The results give starting points for future research such as finding the optimal map size for each situation.