Intercepting Unauthorized Aerial Robots in Controlled Airspace Using Reinforcement Learning

TL;DR

This paper introduces a reinforcement learning-based method for training UAV pursuers to intercept unauthorized drones in controlled airspace, demonstrating adaptability and effectiveness in complex, dynamic scenarios.

Contribution

It presents a novel RL approach using DreamerV3, TQC, and SAC algorithms for UAV interception, tested in high-fidelity simulations with diverse conditions.

Findings

RL-trained UAV pursuers successfully intercept dynamic targets.

The approach adapts to unseen evasion tactics and environmental disturbances.

High-fidelity simulations validate the effectiveness of RL methods in UAV interception.

Abstract

The proliferation of unmanned aerial vehicles (UAVs) in controlled airspace presents significant risks, including potential collisions, disruptions to air traffic, and security threats. Ensuring the safe and efficient operation of airspace, particularly in urban environments and near critical infrastructure, necessitates effective methods to intercept unauthorized or non-cooperative UAVs. This work addresses the critical need for robust, adaptive systems capable of managing such threats through the use of Reinforcement Learning (RL). We present a novel approach utilizing RL to train fixed-wing UAV pursuer agents for intercepting dynamic evader targets. Our methodology explores both model-based and model-free RL algorithms, specifically DreamerV3, Truncated Quantile Critics (TQC), and Soft Actor-Critic (SAC). The training and evaluation of these algorithms were conducted under diverse scenarios, including unseen evasion strategies and environmental perturbations. Our approach leverages high-fidelity flight dynamics simulations to create realistic training environments. This research underscores the importance of developing intelligent, adaptive control systems for UAV interception, significantly contributing to the advancement of secure and efficient airspace management. It demonstrates the potential of RL to train systems capable of autonomously achieving these critical tasks.