Nvidia GTC conference

Developing ROS-based Mobile Robots using NVIDIA Isaac ROS GEMs [S41833]

Source: NVIDIA GTC 2022, March 23, 2022 [1]
Get a technical overview of how NVIDIA's hardware-accelerated robotics software packages, Isaac ROS GEMs, are used to help a robot's perception, localization, and mapping.

Best of Both Virtual Worlds: Bridging Ignition and Isaac Sim [S42593]

Source: NVIDIA GTC 2022, March 23, 2022 [2]
Open Robotics is responsible for Ignition (formerly Gazebo), the premier open-source robotics simulator. Ignition is a de facto standard tool for roboticists, who rely on it for development, testing, and QA of a wide array of autonomy applications. NVIDIA's Omniverse is a powerful and flexible platform for simulating a variety of physical environments. Omniverse has entered the robotics domain as Isaac Sim, allowing researchers and engineers to simulate their robot applications, from wheeled autonomous mobile robots to manipulators in work cells. We'll present the result of our collaboration with NVIDIA to bridge these two complementary products. We'll cover bidirectional conversion between SDFormat and USD to share world and vehicle models, and runtime scene transfer via Ignition plugins and Omniverse Nucleus to support parallel and hybrid simulation.

News

NVIDIA Introduces 60+ Updates to CUDA-X Libraries, Opening New Science and Industries to Accelerated Computing

Source: NVIDIA Newsroom, March 22, 2022 [3]
NVIDIA today unveiled more than 60 updates to its CUDA-X™ collection of libraries, tools and technologies across a broad range of disciplines, which dramatically improve performance of the CUDA® software computing platform.

NVIDIA Hopper Architecture In-Depth

Source: NVIDIA Technical Blog, March 24, 2022 [4]
NVIDIA CEO Jensen Huang introduced the new NVIDIA H100 Tensor Core GPU based on the new NVIDIA Hopper GPU architecture. This post gives you a look inside the new H100 GPU and describes important new features of NVIDIA Hopper architecture GPUs.

NVIDIA Omniverse Ecosystem Expands 10x, Amid New Features and Services for Developers, Enterprises and Creators

Source: NVIDIA Blog, March 22, 2022 [5]
NVIDIA announced new releases and updates for Omniverse — including the latest Omniverse Connectors and libraries — expanding the platform’s ecosystem by 10x, and making Omniverse even more accessible to creators, developers, designers, engineers and researchers worldwide.

NVIDIA Unveils Isaac Nova Orin to Accelerate Development of Autonomous Mobile Robots

Source: NVIDIA Blog, March 22, 2022 [6]
NVIDIA introduces Isaac Nova Orin, a state-of-the-art compute and sensor reference platform. It's built on the powerful new NVIDIA Jetson AGX Orin edge AI system, available today. The platform includes the latest sensor technologies and high-performance AI compute capability.

H100 Transformer Engine Supercharges AI Training, Delivering Up to 6x Higher Performance Without Losing Accuracy

Source: NVIDIA Blog, March 22, 2022 [7]
The NVIDIA Hopper architecture is built from the ground up to accelerate next-generation AI workloads. The largest AI models can require months to train on today's computing platforms. Transformer Engine will speed up AI performance and capabilities, and help train large models within days or hours.

NVIDIA Announces Digital Twin Platform for Scientific Computing

Source: NVIDIA Newsroom, March 22, 2022 [8]
NVIDIA announced a platform for scientific digital twins that accelerates physics machine-learning models to solve million-x scale science and engineering problems thousands of times faster than previously possible.

Portwell to Develop and Deliver NVIDIA® Clara Holoscan MGX-based Hardware Solution

Source: EIN News, March 22, 2022 [9]
This new solution will help developers shorten the development time of AI-inference for medical applications. It also reduces the need for regular costly cycles of software and hardware updates.

Asahi Linux Distro Improves Apple M1 Support With First Alpha Release

Source: It's FOSS News, March 21, 2022 [1:1]
You can now dual-boot Arch Linux with respectable hardware support on Apple M1 devices, thanks to Asahi Linux.

RISC-V Processor Core of Fraunhofer IPMS now ready for Edge AI

Source: Design And Reuse, March 17, 2022 [2:1]
Fraunhofer Institute for Photonic Microsystems IPMS offers ready-made, platform-independent IP core modules. Core is based on the open RISC-V instruction set architecture. Edge AI means that AI algorithms are executed either directly on the device or on a server close to the device.

Previous Hardware Acceleration in Robotics Newsletters

  1. Crume, J. (2022, March 21). Asahi Linux Distro improves Apple M1 support with first Alpha release. It's FOSS News. https://news.itsfoss.com/asahi-linux-alpha/ ↩︎ ↩︎

  2. RISC-V processor core of Fraunhofer IPMS now ready for edge AI. (2022, March 17). Design And Reuse. https://www.design-reuse.com/news/51610/risc-v-processor-core-fraunhofer-ipms-edge-ai.html ↩︎ ↩︎

  3. NVIDIA Newsroom. (2022, March 22). NVIDIA introduces 60+ updates to CUDA-X libraries, opening new science and industries to accelerated computing. NVIDIA Newsroom Newsroom. https://nvidianews.nvidia.com/news/nvidia-introduces-60+-updates-to-cuda-x-libraries-opening-new-science-and-industries-to-accelerated-computing ↩︎

  4. Michael Andersch, Greg Palmer, Ronny Krashinsky, Nick Stam, Vishal Mehta, Gonzalo Brito, & Sridhar Ramaswamy. (2022, March 24). NVIDIA Hopper architecture in-depth. NVIDIA Technical Blog. https://developer.nvidia.com/blog/nvidia-hopper-architecture-in-depth/ ↩︎

  5. RICHARD KERRIS. (2022, March 22). NVIDIA Omniverse ecosystem expands 10x, amid new features and services for developers, enterprises and creators. NVIDIA Blog. https://blogs.nvidia.com/blog/2022/03/22/omniverse-ecosystem-expands/ ↩︎

  6. GERARD ANDREWS. (2022, March 22). NVIDIA unveils Isaac Nova Orin to accelerate development of autonomous mobile robots. NVIDIA Blog. https://blogs.nvidia.com/blog/2022/03/22/nvidia-isaac-nova-orin-amrs/ ↩︎

  7. DAVE SALVATOR. (2022, March 22). H100 transformer engine supercharges AI training, delivering up to 6x higher performance without losing accuracy. NVIDIA Blog. https://blogs.nvidia.com/blog/2022/03/22/h100-transformer-engine/ ↩︎

  8. NVIDIA Newsroom. (2022, March 22). NVIDIA announces digital twin platform for scientific computing. NVIDIA Newsroom Newsroom. https://nvidianews.nvidia.com/news/nvidia-announces-digital-twin-platform-for-scientific-computing ↩︎

  9. Portwell to develop and deliver NVIDIA® Clara Holoscan MGX-based hardware solution. (2022, March 22). EIN News. https://www.einnews.com/pr_news/566134011/portwell-to-develop-and-deliver-nvidia-clara-holoscan-mgx-based-hardware-solution ↩︎