Cooperative Search and Track of Rogue Drones using Multiagent Reinforcement Learning

TL;DR

This paper presents a multiagent reinforcement learning approach for cooperative search and tracking of rogue drones to enhance security around critical infrastructure, addressing a gap in current interception methods.

Contribution

It introduces a novel multiagent reinforcement learning scheme for UAV teams to effectively locate and track multiple rogue drones in realistic scenarios.

Findings

High detection and tracking success rates in simulations

Scalable performance with increasing number of agents

Effective coordination among UAVs in complex environments

Abstract

This work considers the problem of intercepting rogue drones targeting sensitive critical infrastructure facilities. While current interception technologies focus mainly on the jamming/spoofing tasks, the challenges of effectively locating and tracking rogue drones have not received adequate attention. Solving this problem and integrating with recently proposed interception techniques will enable a holistic system that can reliably detect, track, and neutralize rogue drones. Specifically, this work considers a team of pursuer UAVs that can search, detect, and track multiple rogue drones over a sensitive facility. The joint search and track problem is addressed through a novel multiagent reinforcement learning scheme to optimize the agent mobility control actions that maximize the number of rogue drones detected and tracked. The performance of the proposed system is investigated under realistic settings through extensive simulation experiments with varying number of agents demonstrating both its performance and scalability.