Nvidia releases new items for robotics programmers

A simple AI platform for beginning robotics: NVIDIA introduces the Jetson Orion Nano. Nvidia releases new items for robotics programmers.

During the celebrations at its autumn 2022 GTC conference, Nvidia introduced new robotics-related hardware and services aimed at enterprises designing and testing machines in industries such as manufacturing. Designers may model interactive robots using Isaac Sim, which entered into open beta last June, with the assistance of realistic mock-ups.

NVIDIA has extended the Jetson line-up and upped the bar for entry-level edge AI and robotics with the release of Jetson Orin Nano system-on-modules. These new items can outperform the previous generation by up to 80 times. The Nvidia Jetson Orin range of AI application supercomputers is designed to power autonomous machines, robotics, and other systems at the network edge. It is powerful, compact, and energy-efficient. They have Arm-based central processing units, as well as deep learning.

Jetson Orion Nano

For the first time, the NVIDIA Jetson family now includes six Orin-based production modules to service the full range of edge AI and robotics applications. The Orin Nano has the quickest Jetson small factor and up to 40 trillion operations per second (TOPS) of AI performance, while the AGX Orin has 275 TOPS for more advanced autonomous machines. The Jetson Orin includes an NVIDIA Ampere architecture GPU, Arm-based CPUs, cutting-edge deep learning and vision accelerators, high-speed interfaces, quick memory bandwidth, and support for multimodal sensors. Because of its performance and adaptability, more clients may commercialize goods, including engineers implementing cutting-edge AI applications and developers constructing the next generation of intelligent robots utilizing the Robotics Operating System (ROS).

The Orin Nano is compatible with the company’s previously announced Orin NX and enables AI application pipelines with Ampere architecture GPU, Nvidia’s 2020-launched GPU architecture. The Orin Nano 8GB, with up to 40 TOPS and power options ranging from 7W to 15W, and the Orin Nano 4GB, with up to 20 TOPS and power options ranging from 5W to 10W, will both be available in January for $199. Developers will be able to construct robotics apps for the Jetson Orin Nano using the Nvidia Isaac Sim platform, which is now available on the cloud. Jensen Huang, Nvidia’s founder and CEO, announced today at GTC that the Isaac Sim robotics simulation platform is now available on the cloud.