The idea is that AWS IoT Greengrass extends AWS to edge devices, allowing inferencing to be done locally, while using the cloud for management, analytics and durable storage.
Jetson-powered devices can thus take real-time action, and send data back to machine learning services such as Amazon SageMaker to improve model accuracy.
Performing the inferencing on local devices reduces cost and bandwidth requirements, according to Nvidia.
One example provided by Nvidia is that Jetson-powered cameras running AWS IoT Greengrass in an agricultural context could target weeds in near real time, capture previously unidentified weeds, upload anomalies to the cloud, and retrain and deploy the model quickly, thus making agriculture smarter and more efficient.
Another is that the technology could be used in automated optical inspection in factories so that product defects can be quickly identified, avoiding assembly line delays, and thus improving overall operational efficiency.
And in retail, Jetson-powered devices could monitor inventory, customer behaviour, and checkout and process data on the edge, using AWS IoT Greengrass to deploy trained neural networks to bring operational efficiencies and scale to the industry.
"Jetson is a high-performance computer that's built on the same architecture and unified software that powers the world's fastest supercomputers," said Nvidia vice-president and general manager of autonomous machines Deepu Talla,
"We offer the new Jetson Nano all the way to Jetson AGX Xavier, so IoT devices can now scale from small IoT devices to powerful IoT gateways."
In related news, Nvidia announced that its Jetson platform now works with AWS RoboMaker, simplifying robotic simulation and development of Jetson-based robots and other autonomous machines.
"AWS RoboMaker provides pre-built functionality to support customers during their entire project, making it significantly easier to build robots, simulate performance in various environments, iterate faster and drive greater innovation," said AWS robotics and automation services general manager Roger Barga.
"With Nvidia JetBot and Jetson Nano supported on AWS RoboMaker, robotics developers can use the power of the cloud and deploy on Jetson to speed innovation."