Intercepting unauthorized aerial robots in controlled airspace using reinforcement learning

• A novel approach utilizing Reinforcement Learning (RL) to train fixed-wing UAV pursuer agents for intercepting dynamic evader targets is presented. • The study compares the performance of model-based RL algorithm DreamerV3 and model-free algorithms Truncated Quantile Critics (TQC) and Soft Actor-Critic (SAC). • High-fidelity flight dynamics simulations are used to create realistic training environments and evaluate the algorithms. • The system’s robustness is validated through various scenarios, including unseen evasion strategies, wind disturbances, and sensor noise. • DreamerV3 demonstrated superior generalization and robustness capabilities against unseen target behaviors and environmental perturbations compared to TQC and SAC. 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.