NVIDIA launches IGX Edge AI Computing Platform for secure autonomous systems

NVIDIA today has the NVIDIA IGX platform for high-precision edge AI that brings advanced security and proactive security to sensitive industries like manufacturing, logistics, and healthcare. Historically, such industries required costly solutions specifically designed for specific use cases, but the IGX platform is easily programmable and configurable to meet different needs.

As a platform for safe autonomous systems, IGX improves human-machine collaboration. To the manufacturing and logistics, IGX provides an extra layer of security in highly regulated factories and warehouses in the physical world. To the medical edge AI use casesIGX provides secure, low-latency AI inference to meet clinical demand for instant insights from a range of instruments and sensors for medical procedures such as robotic surgery and patient monitoring.

“As humans increasingly work with robots, industries are setting new functional safety standards for AI and computing,” said Jensen Huang, founder and CEO of NVIDIA. “NVIDIA IGX will help companies create the next generation of software-defined industrial and medical devices that can operate safely in the same environment as humans.”

NVIDIA IGX Platform – Ensuring Compliance in Edge AI

The NVIDIA IGX platform is a powerful combination of hardware and software that includes NVIDIA IGX Orin, the world’s most powerful, compact, and energy-efficient AI supercomputer for autonomous industrial machines and medical devices.

IGX Orin Developer Kits will be available early next year for companies to quickly prototype and test products. Each kit comes with an integrated GPU and CPU for powerful AI computations and an NVIDIA ConnectX®-7 SmartNIC to deliver high-performance networking with ultra-low latency and advanced security.

ADLINK, Advantech, Dedicated computingKontron, Leadtek, MBX, Onyx, PortwellProdrive Technologies and YUAN will be among the first embedded computing manufacturers to develop products based on the IGX design, which was developed for the needs of the industrial and medical device industries.

Also included is a powerful software stack with critical security features that can be programmed and configured for different use cases. These capabilities enable organizations to bring proactive security to environments where humans and robots work side-by-side, such as B. in warehouses and operating rooms.

The IGX platform can run NVIDIA AI Enterprise software, which streamlines the development and deployment of AI workflows and ensures organizations have access to the AI ​​frameworks and tools they need. NVIDIA also works with operating system partners such as Canonical, red hat and SUSE to provide long-term full-stack support for the platform.

For the management of IGX in industrial and medical environments, NVIDIA Fleet Command™ enables organizations to securely deliver over-the-air software and system updates from a central cloud console.

Building the industrial edge

NVIDIA is working with a broad ecosystem of companies to bring the IGX platform to market.

One of the first companies to deploy IGX at the edge is Siemens, a technology leader in industrial automation and digitalization working with NVIDIA on a vision for autonomous factories.

Siemens is collaborating with NVIDIA to extend its work into industrial computing, including digital twins and for the industrial metaverse.

The collaboration will allow companies to complement the work carried out with the NVIDIA Omniverse™ platform for 3D design and collaboration and the Siemens Xcelerator open digital business platform with the strengths of IGX. The platform enables data generated from digital twins in the virtual world to be used to train intelligent machines operating in real factories and warehouses with industrial-grade computing infrastructure from Siemens.

Siemens is already adding next-level perception to its edge-based applications NVIDIA Metropolis. With millions of sensors in factories, Metropolis connects entire fleets of robots and IoT devices to bring AI to industrial environments, making it one of the premier application frameworks for edge AI running on the IGX platform.

“As part of our ongoing collaboration with NVIDIA to accelerate digital transformation, Siemens will integrate IGX technologies into our industrial computing portfolio to reduce repetitive factory tasks and better support workers,” said Rainer Brehm, CEO of Factory Automation at Siemens. “By connecting intelligent devices on the factory floor more closely and using this data for intelligent machine operation in production, we can increase efficiency and flexibility for our customers.”

Made for medical environments

For healthcare, the IGX platform supports NVIDIA Clara™ holoscan – a real-time AI computing platform for medical devices – enabling the rapid development and production deployment of new devices that deliver AI applications directly into operating rooms, where over 300 million surgeries are performed worldwide each year.

More than 70 medical device companies, startups and medical centers have already used Holoscan to advance their efforts to deploy AI applications in clinical settings and evolve medical devices into a software-as-a-service business model. These include Activ Surgical, Moon Surgical and Proximie building next generation surgical systems. With Clara Holoscan and IGX, Moon Surgical said it saved significant development time in its imaging pipelines, management system and hardware in developing its next-generation Maestro robotic surgical assistant.

“Moon is creating an exceptional surgical experience by leveraging NVIDIA Clara Holoscan to support the capabilities of next-gen Maestro,” said Anne Osdoit, CEO of Moon Surgical. “This collaboration has reduced Moon’s time to market and allowed the team to focus on developing novel features and algorithms with confidence that a state-of-the-art computing architecture is at the heart of the Maestro system.”

Laisser un commentaire

Votre adresse e-mail ne sera pas publiée. Les champs obligatoires sont indiqués avec *