Factories, farms, refineries, and construction sites are full of dirty and dangerous environments. Numerous industries are increasingly using robotics and automation, but many companies have struggled to incorporate the benefits of artificial intelligence and deep learning in the most demanding applications, said NVIDIA Corp.
The company said its new NVIDIA Jetson AGX Xavier Industrial module makes it possible to deploy AI at the edge in harsh environments where safety and reliability are critical priorities.
Designed for reliability, safety, and security
NVIDIA said Jetson AGX Xavier Industrial combines the supercomputing capabilities of the Jetson AGX Xavier system-on-module with new reliability, availability, and serviceability features. These include error correction codes, single error correction, double error detection and parity protection to deliver internal RAM resilience, address and data bus error detection and correction, and IP resiliency in industrial applications.
The module comes with functional safety capabilities supervised by the Safety Cluster Engine (SCE), making it suitable for safety-certified industrial-grade products, said NVIDIA.
In addition, it has the same key accelerators and high-speed I/Os included with Jetson AGX Xavier. It is pin-compatible with the Jetson AGX Xavier and has up to 20 times the performance and four times the memory of Jetson TX2i.
Jetson AGX Xavier Industrial features a 512-core NVIDIA Volta graphics processing unit (GPU) with 64 Tensor Cores, two NVIDIA deep learning accelerators, two vision accelerators, an eight-core NVIDIA Carmel Arm CPU, an encoder and decoder, and more.
The new SCE contains dual Arm Cortex-R5 processors that can be used for integrated fault-detection mechanisms, lock-step subsystems, and enabling built-in-system tests. The Cortex-R5, which is in an always-on domain, can be used for safety and error correction functions, said NVIDIA.
It also includes hardware-verified secure boot, hardware-accelerated cryptography, support for encrypted storage, memory, and other security features to protect customer software.
Built for the most demanding industrial use cases
Jetson AGX Xavier Industrial is targeted at industries including aerospace, defense, construction, agriculture, logistics, inventory management, delivery, and healthcare. NVIDIA said it enables applications such as worker and site safety, site access and monitoring, and inspection in hazardous and harsh environments.
In the oil and gas industry, the Jetson AGX Xavier Industrial can streamline anomaly and failure predictions at the edge by providing real-time insights based on monitoring or inspection of pipelines, valves, equipment, and maintenance work, according to NVIDIA. The extended reliability of the module allows it to be used in safety, predictive maintenance, and compliance and where equipment is always on in changing environmental conditions.
Automotive plants producing more than 1,000 vehicles a day needs to inspect over 6 million welding points on the fly. With the AI and computer vision on the Jetson AGX Xavier Industrial, a factory can analyze process and quality data directly from weld guns. This would reduce inspection time, improve quality prediction, and ultimately help deliver safer cars to consumers, claimed NVIDIA.
Jetson AGX Xavier. Source: NVIDIA
Another example was presented at GTC 2021, where AI-driven anomaly detection in die-casting processes can enables early prediction of product quality, avoiding further process costs by up to 30% and decreasing defect rates by up to 40%. The result is more efficient and safer processes, improving productivity and return on investment.
Similarly, construction sites employ heavy equipment that must operate reliably in various climates. Farms require tractors that can carry fertilizers and herbicide sprayers, and harvest thousands of acres of crops on various terrains. Unmanned aerial vehicles and drones can experience extreme shock and vibration while flying in harsh environments. Point-of-care ultrasounds and patient monitors require consistent operation over long lifetimes.
NVIDIA said Jetson AGX Xavier Industrial provides the features necessary to bring autonomy to all of these machines.
Software support and availability
Powered by the NVIDIA CUDA-X accelerated computing stack and JetPack SDK support, Jetson AGX Xavier Industrial is a fully software-defined platform enabling cloud-native capabilities.
NVIDIA said its CUDA-X acceleration, free production-ready pretrained models on NGC and NVIDIA Transfer Learning Toolkit give developers the fastest path to build and deploy deep learning and AI training and inference systems.
With the use of Jetson AGX Xavier Industrial and JetPack, customers can easily maintain and update ruggedized and safety critical systems in the field using cloud-native technologies for orchestration and management.
The new Jetson AGX Xavier Industrial module is available to order now and will be available in late July. Developers can start building the smartest edge and embedded systems for their industrial applications today using the Jetson AGX Xavier Developer Kit, downloading JetPack, and designing with all the documentation available on the NVIDIA Jetson site.
Email Sign Up
Get news, papers, media and research delivered
Stay up-to-date with news and resources you need to do your job.
Research industry trends, compare companies and get market intelligence every week with Robotics 24/7.
Subscribe to our robotics user email newsletter and we'll keep you informed and up-to-date.