This paper proposes SafeGPT, a two-tiered framework that integrates generative pretrained transformers (GPTs) with reinforcement learning (RL) for efficient and reliable unmanned aerial vehicle (UAV) last-mile deliveries. In the proposed design, a Global GPT module assigns high-level tasks such as sector allocation, while an On-Device GPT manages real-time local route planning. An RL-based safety filter monitors each GPT decision and overrides unsafe actions that could lead to battery depletion or duplicate visits, effectively mitigating hallucinations. Furthermore, a dual replay buffer mechanism helps both the GPT modules and the RL agent refine their strategies over time. Simulation results demonstrate that SafeGPT achieves higher delivery success rates compared to a GPT-only baseline, while substantially reducing battery consumption and travel distance. These findings validate the efficacy of combining GPT-based semantic reasoning with formal safety guarantees, contributing a viable solution for robust and energy-efficient UAV logistics.
Cite
@article{arxiv.2504.10831,
title = {Hallucination-Aware Generative Pretrained Transformer for Cooperative Aerial Mobility Control},
author = {Hyojun Ahn and Seungcheol Oh and Gyu Seon Kim and Soyi Jung and Soohyun Park and Joongheon Kim},
journal= {arXiv preprint arXiv:2504.10831},
year = {2025}
}