November 9, 2021

NVIDIA JetsonAGX Orin 400x275NVIDIA has announced the new Jetson AGX Orin, a small, powerful and energy-efficient AI supercomputer aimed for robotics, autonomous machines, medical devices and other embedded computers at the edge.

Built on NVIDIA’s Ampere architecture, Jetson AGX Orin provides 6x the processing power and maintains the form factor and pin compatibility with its predecessor, the Jetson AGX Xavier, the company said. Orin can deliver 200 trillion operations per second, similar to that of a GPU-enabled server, but in a size that fits in the palm of your hand.

The new system accelerates the full NVIDIA AI software stack, allowing developers to deploy large and complex models needed to solve edge AI and robotics challenges, including  natural language understanding, 3D perception, and multisensor fusion.

“As robotics and embedded computing transform manufacturing, healthcare, retail, transportation, smart cities and other essential sectors of the economy, the demand for processing continues to surge,” said Deepu Talla, vice president and general manager of embedded and edge computing at NVIDIA. “Jetson AGX Orin addresses this need, enabling the 850,000 Jetson developers and over 6,000 companies building commercial products on it to create and deploy autonomous machines and edge AI applications that once seemed impossible.”

The Jetson AGX Orin features an NVIDIA Ampere architecture GPU and Arm Cortex-A78AE CPUs, along with next-generation deep learning and vision accelerators. High-speed interfaces, faster memory bandwidth and multimodal sensor support give the ability to feed multiple concurrent AI application pipelines, the company said.

In addition, customers using Jetson AGX Orin can leverage NVIDIA’s CUDA-X accelerated computing stack, JetPack SDK and other tools for application development and optimization, including cloud-native deployment workflows. Pre-trained models from the NVIDIA NGC catalog are optimized and ready for fine-tuning with the TAO tool kit and customer datasets, NVIDIA said. 

An embedded computing partner ecosystem includes several services and products, including cameras and other multimodal sensors, carrier boards, hardware design services, AI and system software, developer tools and custom software development.

“Driven by the advancements in AI, the robotics market is growing exponentially,” said Jim McGregor, principal analyst at TIRIAS Research. “NVIDIA is the recognized leader in AI and continues to leverage this expertise to advance robotics through a robust ecosystem and complete end-to-end solutions, including a range of hardware platforms that leverage common tools and neural network models. The new Jetson platform brings the performance and versatility of the NVIDIA Ampere architecture to enable even further advancements in autonomous mobile robots for a wide range of applications, ranging from agriculture and manufacturing to healthcare and smart cities.”

Software frameworks for specific use cases include NVIDIA’s Isaac Sim on Omniverse for robotics, Clara Holoscan SDK for healthcare, and DRIVE for autonomous driving. The latest Isaac release includes significant support for the Robot Operating System (ROS) development community. NVIDIA also released the new Omniverse Replicator for synthetic data generation and Isaac GEMs, hardware-accelerated software packages that make it easier for ROS developers to build high-performance AI-enabled robots on the Jetson platform.

NVIDIA said the Jetson AGX Orin module and developer kit will be available in Q1 2022. Interested developers can register to be notified for availability, access detailed specifications and download a white paper.