Nvidia module enables AI-powered autonomous machines

December 17, 2018 //By Rich Pell
Nvidia module enables AI-powered autonomous machines
Nvidia (Santa Clara, CA) has announced that the production module of its Jetson AGX Xavier - what it calls "the AI Platform for Autonomous Machines" - is now available.

The Jetson AGX Xavier module delivers up to 32 TOPS of peak compute and 750 Gbps of I/O in a 100 x 87-mm form factor. This, says the company, gives developers more than 20X the performance and 10X the energy efficiency of its predecessor - the NVIDIA Jetson TX2.

The system-on-module is powered by the company's Xavier SoC and is designed specifically for autonomous machines. In addition, says the company, it comes with integrated memory, storage, power management, and an innovative thermal design to enable faster time to market.

The module also supports applications developed with the JetPack and DeepStream software development kits. JetPack includes a board support package, an Ubuntu Linux OS, NVIDIA CUDA, cuDNN, and TensorRT software libraries for deep learning, computer vision, GPU computing, multimedia processing, and more.

DeepStream enables streaming analytics, bringing AI to IoT and smart city applications. Developers can build multi-camera and multi-sensor applications to detect and identify objects of interest, such as vehicles, pedestrians, and cyclists.

Volume pricing of the module in quantities of 1,000+ units is $1,099.

Nvidia

Related articles:
Nvidia robotics platform heralds 'new era' of autonomous machines
Nvidia to provide AI platform for Chinese EV startups
Nvidia platform brings AI to next-gen medical instruments


Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.