Designing an excellent hull to reduce the sailing path energy consumption of UUVs is crucial for improving the energy endurance of UUVs. However, path energy consumption-based UUV hull design requires a tremendous amount of calculation due to the frequent changes in relative velocity and attack angle between a UUV and ocean current. In order to address this issue, this work developed a data-driven design methodology for energy consumption-based UUV hull design using artificial intelligence-aided design (AIAD). The design methodology in this work combined a deep learning (DL) algorithm that predicts UUVs’ resistance with different hull shapes under different velocities and attack angles with the particle swarm optimization (PSO) algorithm for UUV hull design. We tested the proposed methodology in a path energy consumption-based experiment, where the optimized UUV hull showed an 8.8% reduction in path energy consumption compared with the initial UUV hull, and design costs were greatly reduced compared with the traditional computational fluid dynamics (CFD)-based methodology. Our work demonstrates that AIAD has the potential to solve UUV design problems previously thought to be too complex by offering a data-driven engineering shape (body surface) design method.