发表机构
Jiangsu Second Normal University（江苏第二师范学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出用决策Transformer优化无人机轨迹、姿态与RIS相位，在动态D2D通信中最大化平均总速率，实现跨场景零样本迁移并优于直接DRL。
AI 中文摘要
本文研究了具有随机链路激活的无人机（UAV）搭载可重构智能表面（RIS）辅助的设备到设备（D2D）通信。它建模了无人机运动和姿态、时变莱斯角以及角度相关的RIS反射。提出了一种无人机轨迹、姿态和RIS相位的联合优化，以在移动性、能量和硬件约束下最大化平均总速率。该问题通过深度强化学习和在多个场景的专家轨迹上训练的决策Transformer来解决。结果表明有效的跨场景泛化，零样本迁移优于直接DRL迁移，在线微调以更少的交互达到竞争性能。
英文摘要
This paper studies unmanned aerial vehicle (UAV)-mouted reconfigurable intelligent surface (RIS)-assisted device-to-device (D2D) communication with stochastic link activation. It models UAV motion and attitude, time-varying Rician angles, and angle-dependent RIS reflection. A joint optimization of UAV trajectory, attitude, and RIS phases is formulated to maximize average sum rate under mobility, energy, and hardware constraints. The problem is addressed using deep reinforcement learning and a Decision Transformer trained on expert trajectories from multiple scenarios. Results demonstrate effective cross-scenario generalization, with zero-shot transfer outperforming direct DRL transfer and online fine-tuning achieving competitive performance with fewer interactions.
