Interpretable and Secure Trajectory Optimization for UAV-Assisted Communication

TL;DR

This paper introduces an interpretable UAV-assisted communication scheme that combines deep reinforcement learning and Monte Carlo tree search to optimize trajectory, power, and collision avoidance, ensuring reliable, efficient, and trustworthy UAV operations.

Contribution

It presents a novel interpretable AI framework integrating D3QN and MCTS for UAV trajectory and communication optimization, emphasizing transparency and safety.

Findings

Outperforms existing methods in performance and generalization

Enhances reliability and safety of UAV communication systems

Provides explainable AI for UAV trajectory and communication decisions

Abstract

Unmanned aerial vehicles (UAVs) have gained popularity due to their flexible mobility, on-demand deployment, and the ability to establish high probability line-of-sight wireless communication. As a result, UAVs have been extensively used as aerial base stations (ABSs) to supplement ground-based cellular networks for various applications. However, existing UAV-assisted communication schemes mainly focus on trajectory optimization and power allocation, while ignoring the issue of collision avoidance during UAV flight. To address this issue, this paper proposes an interpretable UAV-assisted communication scheme that decomposes reliable UAV services into two sub-problems. The first is the constrained UAV coordinates and power allocation problem, which is solved using the Dueling Double DQN (D3QN) method. The second is the constrained UAV collision avoidance and trajectory optimization problem, which is addressed through the Monte Carlo tree search (MCTS) method. This approach ensures both reliable and efficient operation of UAVs. Moreover, we propose a scalable interpretable artificial intelligence (XAI) framework that enables more transparent and reliable system decisions. The proposed scheme's interpretability generates explainable and trustworthy results, making it easier to comprehend, validate, and control UAV-assisted communication solutions. Through extensive experiments, we demonstrate that our proposed algorithm outperforms existing techniques in terms of performance and generalization. The proposed model improves the reliability, efficiency, and safety of UAV-assisted communication systems, making it a promising solution for future UAV-assisted communication applications