Abstract
With the development of network autonomy, Unmanned Aerial Vehicles (UAV) applications are attractive to serve intelligent logistics with the advantages of miniaturization and flexibility. It, however, is difficult to implement accurate UAV control in complex distribution scenarios. In this context, Digital Twins (DT) is a potential tool to assist UAVs in acquiring feasible cooperative distribution decisions with the ability of imitation and derivation. Nonetheless, it is challenging to perform real-time DT implementations due to the limited computing resources of UAVs. To address the mentioned problems, we achieve a Hardened DT (HaDT) framework, operating at the edge side, to enable a double DT cooperation manner for efficient resource scheduling and path planning. The resource scheduling model can implement the integration of computing and communication resources among UAVs to acquire feasible cooperative logistics distribution decisions. The decisions can drive the path planning model to derive positions and velocities of UAVs for low-latency logistics distribution performance with energy saving. Experiment results demonstrate the efficiency of our HaDT framework. Compared to state-of-the-art logistics distribution solutions, our solution reduces the distribution latency by 63.9% while improving the successful distribution ratio by 10.9%.