Rugged embedded computers provider Neousys Technology has released RGS-8805GC, a new rugged high-performance computing server with optimized Size, Weight and Power (SWaP) for UGV applications. Powered by the AMD EPYC 7003 series'MILAN' processor with up to 64-core/ 128-thread computing power and high-end NVIDIA RTX A6000 or A4500 GPU, RGS-8805GC incorporates from the ground up Neousys cooling design, with compartmentalization allowing the system to operate in a temperature range from -25 C to 60 C. Neousys believes this effective cooling design guarantees high-performance, reliable computing for military and defense edge AI applications in the field. The RGS-8805GC accepts 8 to 48V wide range DC input and comes with expansion slots to add on automotive camera capture cards, LiDARs, mmWave for high-speed data transmission, and graphics cards for AI inference capabilities in unmanned systems. It enables autonomous robotics systems for a wide variety of both civilian and military applications operating in hazardous environments. The front-accessible I/Os are available with screw-lock connections to ensure rugged connectivity for USB and 10G/ 1G cables. The system is also MIL-STD-810G certified and comes with a patented damping bracket to withstand in-vehicle conditions.

Machine vision computer Nuvis-7306RT is capable of microsecond real-time I/O control for in-time or in-position image capture. With an integrated constant-current lighting controller, isolated 12V camera trigger output, encoder input for position information, digital I/O for sensors/ actuators, and Neousys' patented MCU-based architecture and DTIO/ NuMCU firmware, Nuvis-7306RT can overcome latencies between the sensor input and trigger output. Rugged Edge HPC Server RGS-8805GC brings HPC CPU and GPU processing power to the edge for advanced real-time machine vision inspection. With additional PCIe expansion slots to install function cards, the server can support frame grabber cards for industrial hi-res GigE or USB cameras to acquire detailed images. Supporting NVIDIA Tesla/ RTX GPU and AMD EPYC CPU, it enables perception and discrepancy recognition for mass data analysis, machine reasoning, and near human-level accuracies for machine vision applications.

The Nuvo-6108GC GPU computer from Neousys was presented to the customer as a suitable solution for their needs, reported to be the world's first'Industrial-grade edge AI GPU computer supporting high-end NVIDIA RTX 2080 graphics card'. The Nuvo-6108GC GPU computer is able to support the heavy power consumption requirements in order to offer reliable GPU computing performance in industrial environments, and has a patented airflow design and multiple storage drives in a compact form factor. To meet the customer's requirements, Neousys provided a bespoke card cage assembly for the specialised graphics card to secure it in place and protect against the shock and vibration that is commonplace with in-vehicle applications. The fact that all this was incorporated in to an in-vehicle box PC made the Nuvo-6108GC from Neousys the perfect all-in-one GPU computing solution for this innovative autonomous vehicle project. To find out more about WMG, University of Warwick's autonomous vehicle project click here.