Surprisingly Useful AI Article Enhancements
Asus IoT has unveiled the PE3000N, a compact edge Ai platform designed for robotics and intelligent automation. The new system is powered by Nvidia’s Jetson Thor and incorporates the Blackwell GPU, a 14-core Arm CPU, and up to 128GB of LPDDR5X memory.
The company said the PE3000N delivers 2,070 FP4 TFLOPS of Ai performance in a space-efficient chassis, making it suitable for robotics where power and size constraints are significant.
Built For Harsh Environments
The PE3000N has been developed with industrial durability in mind, meeting MIL-STD-810H standards. It supports a wide voltage input range from 12 to 60V and is capable of operating in temperatures between -20°C and 60°C.
The system also supports up to four optional 25GbE links and 16 GMSL cameras, which Asus said allows for high-bandwidth sensor fusion and machine vision. These features target use cases in areas such as autonomous vehicles, factory automation, and smart city infrastructure.
“As robotics and industrial systems evolve, the need for edge computing platforms that can perform under challenging conditions has grown,” said a spokesperson from Asus IoT. “PE3000N is designed to balance energy efficiency, ruggedness, and Ai compute power for mission-critical applications.”
Configurable Expansion
Flexibility is central to the design. The modular I/O system enables customisation with support for PoE, GMSL, CAN, and QSFP28. The optional second stack allows vertical expansion while maintaining a compact 2U height.
The platform also incorporates PTP/PPS for precise sensor synchronisation, TPM 2.0 for security, and support for LTE, 5G, and GNSS modules, making it adaptable across different industries.
Ai Workloads At The Edge
Asus positioned the PE3000N as a platform capable of running advanced generative Ai models such as visual language models and large language models, alongside real-time analytics and autonomous control.
It integrates with Nvidia Isaac for robotics, Nvidia Holoscan for real-time sensor processing, and Nvidia Metropolis for video analytics workflows. This includes features like Blueprint for Video Search and Summarisation, which enable the deployment of video analytics agents directly at the edge.
“Processing data locally reduces latency and reliance on cloud infrastructure,” said an Asus spokesperson. “This ensures faster decision-making and more responsive automation in robotics and industrial environments.”
Availability
The Asus IoT PE3000N is scheduled for launch in Q1 2026. Pricing has not yet been disclosed, but Asus confirmed full specifications will be made available on its product page.
Last Updated on October 29, 2025 by Nick Ross
