Wednesday, November 6th 2019
![NVIDIA](https://tpucdn.com/images/news/nvidia-v1723816949774.png)
NVIDIA Provides U.S. Postal Service AI Technology to Improve Delivery Service
NVIDIA today announced that the United States Postal Service - the world's largest postal service, with 485 million mail pieces processed and delivered daily - is adopting end-to-end AI technology from NVIDIA to improve its package data processing efficiency. The new system starts with high-performance servers powered by NVIDIA V100 Tensor Core GPUs and deep learning software to train multiple AI algorithms. The trained models are then deployed to NVIDIA EGX edge computing systems at close to 200 Postal Service facilities throughout the U.S. to enable more efficient package data processing. The NVIDIA-powered systems are being purchased by the Postal Service under contract with Hewlett Packard Enterprise.
"AI is transforming multiple industries, enabling processes, accuracy and efficiency not possible before," said Anthony Robbins, vice president of the Federal Sector Business at NVIDIA. "The U.S. Postal Service's adoption of AI demonstrates how this powerful technology can improve an excellent service that we rely on every day. Benjamin Franklin would be proud." The Postal Service operates the world's highest volume logistics operation, processing and delivering some 146 billion pieces of mail annually, including more than 6 billion packages. The new AI system will process package data 10x faster and with higher accuracy.Engineering teams from the Postal Service and NVIDIA have been collaborating for several months to develop AI models, using NVIDIA software including TensorRT for high-throughput, low-latency inference optimization; automatic mixed precision in PyTorch to accelerate training while maintaining model accuracy; NGC containers, which are GPU-optimized for streamlining software deployment; and DeepOps tools for optimizing GPU clusters.
Delivery and testing of the system will start this year and it is expected to be fully operational by spring of 2020.
"AI is transforming multiple industries, enabling processes, accuracy and efficiency not possible before," said Anthony Robbins, vice president of the Federal Sector Business at NVIDIA. "The U.S. Postal Service's adoption of AI demonstrates how this powerful technology can improve an excellent service that we rely on every day. Benjamin Franklin would be proud." The Postal Service operates the world's highest volume logistics operation, processing and delivering some 146 billion pieces of mail annually, including more than 6 billion packages. The new AI system will process package data 10x faster and with higher accuracy.Engineering teams from the Postal Service and NVIDIA have been collaborating for several months to develop AI models, using NVIDIA software including TensorRT for high-throughput, low-latency inference optimization; automatic mixed precision in PyTorch to accelerate training while maintaining model accuracy; NGC containers, which are GPU-optimized for streamlining software deployment; and DeepOps tools for optimizing GPU clusters.
Delivery and testing of the system will start this year and it is expected to be fully operational by spring of 2020.
16 Comments on NVIDIA Provides U.S. Postal Service AI Technology to Improve Delivery Service
reads like an advert
More opportunities for the USPS gorillas to do their thing.
As for the cat, she is the resident postal inspector/supervisor, who is merely waiting around to collect her pension, just like most of the other nursing home escapees that work there, making all the AI assistance in the world a totally moot point......
USPS in my experience, they do pretty good holding their own against UPS/FedEx for ground packages. I generally find it cheaper and just as effective to ship USPS over UPS/FedEx.
Technology is not needed, but expedient and reliable workers are, balanced work loads too.
I don't need spam mailed faster to me.
This is good news for Nvidia and HPE. I'm guessing it's going to be millions of dollars for all the equipment and support. I wish there was more info on the size of the deal. As for whether it's good for the USPS, well, if they don't cut costs greater than the amount they spent on this fancy AI stuff, then it doesn't make much sense. I wonder how much slack there is in the operational budget where fancy neural networks will find the efficiencies.
It's a corporate press release. Me too. It's by far the best service available (and cheapest) here on the west coast.