Sat. Mar 25th, 2023

Listen to this article

-NVIDIA today announced a number of brand new tools for robotics developers during its GTC event, including Jetson Orin Nano system-on-modules, updates to the Nova Orin reference platform for autonomous mobile robots (AMRs) and cloud-based availability for its Isaac Sim technology.

NVIDIA expanded its Jetson lineup with the launch of Jetson Orin Nano system-on-modules with regard to entry-level edge AI plus robotics applications. The new Orin Nano delivers up to 40 trillion operations per second (TOPS) of AI performance, which NVIDIA said is 80x the performance over the prior generation, in the particular smallest Jetson form factor yet.

Jetson Orin features an NVIDIA Ampere architecture GPU, Arm-based CPUs, next-generation deep learning and vision accelerators, high-speed interfaces, fast memory bandwidth plus multimodal sensor support. The Orin Nano modules will be available in two versions. The Orin Nano 8GB delivers up to 40 TOPS with power configurable from 7W in order to 15W, while the 4GB version delivers as much as 20 COVERS with energy options as low as 5W to 10W.

Orin Nano will be supported by the NVIDIA JetPack software advancement kit and is powered from the same -NVIDIA CUDA-X accelerated computing stack used in order to create AI products in such fields as industrial IoT, manufacturing, smart cities and more.

The Jetson Orin Nano modules will certainly be obtainable in January 2023 starting in $199.

“Over 1, 000 customers and 150 partners have embraced Jetson AGX Orin since NVIDIA introduced its accessibility just six months ago, plus Orin Nano will significantly expand this adoption, ” said Deepu Talla, vice president associated with embedded and edge computing at NVIDIA. “With a good orders-of-magnitude increase in performance regarding millions of edge AI and ROS developers today, Jetson Orin is the ideal system for virtually every kind of robotics deployment imaginable. ”

The Orin Nano modules are form-factor and pin-compatible with the previously announced Orin NX modules. Full emulation support allows customers to get started developing for the Orin Nano series today using the AGX Orin developer kit. This gives customers the flexibility to design one system to support multiple Jetson modules and easily scale their applications.

The particular Jetson Orin platform is usually designed to solve tough robotics challenges and brings accelerated processing to over 700, 000 ROS developers. Combined with the particular powerful hardware capabilities associated with Orin Nano, enhancements within the latest NVIDIA Isaac software intended for ROS put increased overall performance and productivity in the hands of roboticists.

Jetson Orin has seen broad support across the robotics and embedded computing ecosystem, including through Canon, John Deere, Microsoft Azure, Teradyne, TK Elevator and many more.


Isaac Sim in the particular clouds
-NVIDIA also introduced there will be three ways to access its Isaac Sim robotics simulation platform on the cloud:

  • It will soon be available around the brand new NVIDIA Omniverse Cloud system
  • It’s obtainable now on AWS RoboMaker
  • Developers can now download it from NVIDIA NGC plus deploy this to any public impair

Roboticists will be able to generate large datasets from physically accurate messfühler simulations in order to train the AI-based perception models on their robots. The synthetic data generated in these simulations improve the model efficiency and provide training information that often can’t be collected in the real world.

-NVIDIA said the particular upcoming release of Isaac Sim will include NVIDIA cuOpt, a real-time fleet task-assignment and route-planning engine to get optimizing robot path planning. Tapping into the more rapid performance associated with the cloud, teams can make dynamic, data-driven decisions, whether designing the ideal warehouse layout or optimizing active procedures.

Nova Orin up-dates
NVIDIA also shared new details about three Volkswagen Orin reference platform configurations for AMRs. Two use a single Jetson AGX Orin — which runs the NVIDIA Isaac robotics stack and the Robot Operating System (ROS) with the GPU-accelerated framework — and one relies upon two Orin modules.

-NVIDIA said the Nova Orin platform is definitely designed to improve reliability and reduce growth costs pertaining to building and deploying AMRs. Nova Orin provides industrial-grade configurations of sensors, software and GPU-computing capabilities.

The particular Nova Orin reference architecture designs are provided meant for specific make use of cases. There is one Orin-based design without safety-certified sensors, and one that includes them, along with a safety programmable logic controller. The third structures has a dual Orin-based design that depends on vision AI designed for enabling functional safety.

Sensor support can be included just for stereo cameras, LiDAR, ultrasonic sensors plus inertial measurement units. The particular chosen detectors have been selected in order to balance functionality, price and reliability for industrial programs. The stereo cameras plus fisheye cameras are custom designed by NVIDIA in coordination with camera partners. All sensors are usually calibrated and time-synchronized, plus come with drivers for reliable data capture. These sensors allow AMRs to detect objects and obstacles across the wide range of situations while furthermore enabling simultaneous localization and mapping (SLAM).

NVIDIA provides two LiDAR options, 1 for apps that don’t need sensors certified with regard to functional safety, and the particular other regarding those that will do. In addition in order to these 2D LiDARs, Nova Orin supports 3D LiDAR for mapping and ground-truth data collection.

The base OS includes motorists and firmware for all the equipment and adaptation tools, as well because design guides for integrating it along with robots. Volkswagen can be integrated with a ROS-based robot application. The detectors will have validated models in Isaac Sim for software development plus testing without having the need for an actual robot.

The cloud-native data acquisition tools eliminate the arduous task associated with setting up information pipelines intended for the vast amount of sensor data needed for training models, debugging and analytics. State-of-the-art GEMs developed to get Nova sensors are GPU accelerated with the Jetson Orin platform, providing key building blocks such as visual SLAM, stereo system depth estimation, obstacle detection, 3D reconstruction, semantic segmentation and pose estimation.

Nova Orin facilitates secure over-the-air updates, since well as device management and monitoring, to enable easy deployment and reduce the cost of maintenance. Its open, modular design enables developers to use some or all capabilities of the platform plus extend it to quickly develop robotics applications.

NVIDIA is working closely along with regulatory bodies to develop vision-enabled safety technologies to further reduce cost and enhance the dependability of AMRs.

You may also like:


By Wired

Leave a Reply

Your email address will not be published. Required fields are marked *