MARLander: A Local Path Planning for Drone Swarms using Multiagent Deep Reinforcement Learning

TL;DR

This paper introduces MARLander, a multi-agent deep reinforcement learning approach enabling precise, scalable drone swarm landings in complex environments, outperforming traditional control methods in accuracy and flexibility.

Contribution

The paper presents a novel MADRL-based system for drone swarm landing that eliminates centralized control, demonstrating superior accuracy and adaptability in simulation and real-world tests.

Findings

Landing accuracy of 2.26 cm on stationary targets

Landing accuracy of 3.93 cm on moving targets

Outperforms baseline PID with Artificial Potential Field method

Abstract

Achieving safe and precise landings for a swarm of drones poses a significant challenge, primarily attributed to conventional control and planning methods. This paper presents the implementation of multi-agent deep reinforcement learning (MADRL) techniques for the precise landing of a drone swarm at relocated target locations. The system is trained in a realistic simulated environment with a maximum velocity of 3 m/s in training spaces of 4 x 4 x 4 m and deployed utilizing Crazyflie drones with a Vicon indoor localization system. The experimental results revealed that the proposed approach achieved a landing accuracy of 2.26 cm on stationary and 3.93 cm on moving platforms surpassing a baseline method used with a Proportional-integral-derivative (PID) controller with an Artificial Potential Field (APF). This research highlights drone landing technologies that eliminate the need for analytical centralized systems, potentially offering scalability and revolutionizing applications in logistics, safety, and rescue missions.