A new compact edge AI system from Asus, the PE3000N, runs on the NVIDIA Jetson Thor platform with a Blackwell GPU, a 14-core Arm CPU, and 128 GB of LPDDR5X memory. It’s designed for robotics and automation, and delivers up to 2,070 FP4 TFLOPS of performance in a relatively small form factor.
PE3000N is built for tough operating environments, taking 12-60v DC input and operates between -20°C and 60°C. It uses MIL-STD-810H connectors and a low-profile chassis to handle vibration and physical stress, and supports as many as four optional 25GbE links and up to 16 GMSL cameras. It’s suitable for operation with factory equipment, autonomous machines, and smart-city systems.
The platform uses a scalable chassis and modular I/O layers that support PoE, GMSL, CAN, and QSFP28 interfaces. An optional second stack adds vertical expansion in a 2U height.
It also includes PTP/PPS support for sensor timing, onboard TPM 2.0 for hardware-based security, and the option to add LTE, 5G, and GNSS modules for wireless deployments.
PE3000N can run generative AI models that offer real-time video analysis through NVIDIA workflows like Blueprint for Video Search and Summarisation from NVIDIA Metropolisand autonomous control. It supports NVIDIA’s tools for physical AI workloads, like NVIDIA Isaac for robotics and NVIDIA Holoscan for sensor processing.
By processing large amounts of data on-device, the system can make decisions with less latency than similar cloud technologies and reduce traffic through internet connections.
(Photo by Rubaitul Azad)
See also: How Amazon is using AI and IoT to help its workforce
Want to learn more about IoT from industry leaders? Check out IoT Tech Expo taking place in Amsterdam, California, and London. The comprehensive event is part of TechEx and is co-located with other leading technology events, click here for more information.
IoT News is powered by TechForge Media. Explore other upcoming enterprise technology events and webinars here.
