NVIDIA Expands Edge AI and Robotics Platform Lineup for Embedded Developers with Jetson AGX Orin 32 GB Production Module

By Chad Cox

Production Editor

Embedded Computing Design

August 08, 2022


Over 30 members in the NVIDIA Partner Network are also releasing more commercially accessible products driven by the new Jetson AGX Orin 32 GB production module.

Having the capability of up to 200 trillion operations per second (TOPS) and assistance for numerous concurrent AI application pipelines, the Jetson AGX Orin 32 GB production module with NVIDIA Ampere architecture GPU accelerates deep learning workloads. Connectivity possibilities include WiFi 6/6E, LTE and 5G.

NVIDIA announced four Jetson Orin-based production modules, including the new Jetson AGX Orin 32GB, a 64GB version (expected November), and two Orin NX production modules anticipated within the year. All four of these modules can be emulated on the Jetson AGX Orin Developer Kit, which delivers up to 275 TOPS for advanced embedded and autonomous machines.

Additionally, NVIDIA Jetson ecosystem partners are creating assets for designers to develop and implement the Orin-powered systems. The Jetson AGX Orin 32 GB production module easily works with cameras, sensors, software, and connectivity of AI, robotics, AIoT and more embedded applications.

The ready to go systems are available with differing options including peripherals that help customers with hurdles faced when developing edge AI and embedded applications in industries ranging from:

  • manufacturing
  • retail
  • construction
  • agriculture
  • logistics
  • healthcare
  • smart cities
  • last-mile delivery

Developing Efficient AI-Driven Products

Conventionally, system designers have been constrained in handling several parallel data streams for complicated edge environments.

They also face stringent latency needs, energy-efficiency constraints, issues with high-bandwidth wireless connectivity, or handling over-the-air software updates.

Engineers have been forced to include various and multiple chips in their designs to generate the compute power necessary to manage the multitude of data being utilized in today's applications.

Leveraging the power of the Jetson AGX Orin 32 GB production module, system designers can create better in-house results utilizing complex AI models. The AI models can solve problems such as natural language understanding, 3D perception, and multi-sensor fusion.

The NVIDIA Jetson ecosystem has numerous organizations and developers creating and employing enhanced AI solutions on Jetson. According to NVIDIA, “On top of JetPack SDK, which includes the NVIDIA CUDA-X accelerated stack, Jetson Orin supports multiple NVIDIA platforms and frameworks such as Isaac for robotics, DeepStream for computer vision, Riva for natural language understanding, TAO Toolkit to accelerate model development with pretrained models, and Metropolis, an application framework, set of developer tools and partner ecosystem that brings visual data and AI together to improve operational efficiency and safety across industries.”

For more information, visit retail and distribution partners worldwide 

Chad Cox. Production Editor, Embedded Computing Design, has responsibilities that include handling the news cycle, newsletters, social media, and advertising. Chad graduated from the University of Cincinnati with a B.A. in Cultural and Analytical Literature.

More from Chad