Multi-Sized AI Models Assisted Low-Altitude UAV Delivery With RAN Optimization

With the development of Artificial Intelligence (AI) 1technology and wireless communication technology, Uncrewed Aerial Vehicles (UAVs)-based low-altitude applications have become increasingly attractive for accurate and real-time UAV delivery by performing cooperative path planning. However, this application exposes imperative computing requirements on resource-limited UAVs. To address the problem, we propose a multi-sized AI model-assisted parcel delivery framework with RAN resource optimization. In this design, we propose a double-scale AI model cooperation algorithm to implement highly accurate UAV path planning for safe parcel delivery. We then propose a transformer-based resource optimization algorithm to perform high-efficiency resource allocation for real-time and reliable communication and computing cooperation among UAVs. Simulation results demonstrate that our algorithm improves network throughput by 15.4% compared to other benchmarks on average while achieving a high successful delivery ratio of 92% for robust UAV delivery.