The NVIDIA Jetson AGX Orin—the world’s smallest, most powerful, and energy-efficient AI supercomputer for robotics, autonomous machines, and edge computing applications—was announced today at NVIDIA GTC.
The new Jetson single-chip computer is so small you can fit it in the palm of your hand, and yet it can deliver processing power similar to a GPU-enabled server. It maintains the same form-factor and pin compatibility as the Jetson AGX Xavier series, while providing users with 6X the performance—up to 200 trillion operations per second.
“As robotics and embedded computing transform manufacturing, retail, 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 provide the ability to feed multiple concurrent AI application pipelines.
The new module accelerates the full NVIDIA AI software stack. Developers can deploy the largest, most complex models needed to solve demanding challenges in edge AI and robotics, such as natural language understanding, 3D perception, multisensor fusion, and more. It is ideal for next-generation autonomous machines like delivery and logistics robots, factory systems, and large industrial UAVs.
Comprehensive Software and Ecosystem Support
Supported by the NVIDIA CUDA-X accelerated computing stack and NVIDIA JetPack SDK, customers using the Jetson AGX Orin can leverage the latest NVIDIA tools for application development and optimization, including cloud-native development workflows. Pretrained models from the NGC catalog are optimized and ready for fine-tuning with the NVIDIA TAO toolkit and customers’ datasets. This reduces time and cost for production quality AI deployments while cloud-native technologies allow seamless updates throughout a product’s lifetime.
Software frameworks for customer-specific use cases powered by Jetson AGX Orin include NVIDIA Isaac Sim on Omniverse for robotics, Clara for healthcare, and Metropolis for smart cities. The latest Isaac release includes significant support for the Robot Operating System (ROS) developer community.
NVIDIA has also released new Isaac GEMs—hardware-accelerated software packages that make it easier for ROS developers to build high-performance AI-enabled robots on the Jetson platform.
The Jetson partner ecosystem encompasses a range of services and products including cameras and other multimodal sensors, carrier boards, hardware design services, AI and system software, developer tools, and custom software development.
The NVIDIA Jetson AGX Orin module and developer kit will be available in the first quarter of 2022.