For months, engineering teams from USPS and NVIDIA have been developing AI models that help USPS address labels read faster and more effectively. The system starts with high-performance servers equipped with NVIDIA V100 Tensor Core GPUs and deep learning software that train multiple algorithms. The trained models are then deployed in nearly 200 USPS facilities on NVIDIA EGX edge computing systems.
System delivery and testing begin this year, and AI is expected to be fully operational by early 2020. This is a big win for NVIDIA. It shows that AI processes are finding more practical application.
USPS is also experimenting with self-propelled postal carts. This spring, it signed a contract with the self-driving truck company TuSimple in San Diego over a two-week pilot. This involved the company's trucks carrying USPS trailers on five round trips between the postal service distribution centers in Phoenix, Arizona and Dallas, Texas.
USPS is developing a drone airline to deliver medical samples in the US. United Parcel Service (UPS) is working on this project.