Edge AI Computer AIE900-XNX

• NVIDIA® Jetson Xavier™ NX (21 TOPS)
• 1 M.2 Key B slot for 5G
• Wide power input range of 9 to 36 VDC (with ignition)
• Supports four PoE for GigE cameras and LiDAR connectivity
• Wide operating temperature from -30°C to +50°C
• Supports device management and optional out-of-band service, powered by Allxon
• Optional SerDes FPD-LINK III

Its SerDes cameras are made through proprietary 5/6-axis active alignment advanced technology with a minimum 1-pixel optical axis offset and manufactured in IATF 16949 certified cleanroom factory. Sample and mass-produced cameras are IP69K rated and have quality for harsh environments from -40 to +85°C. Along with oToBrite’s innovation and expertise in camera and image processing, Axiomtek’s edge AI system, AIE900-XNX, is suitable for vision AI applications including computer vision, 3D scanning, vehicle surround view, autonomous mobile robot (AMR), obstacle detection, and more.

Axiomtek NVIDIA® Jetson Xavier™ NX based on Axiomtek AIE900-XNX offers the ability to connect to oToBrite’s SerDes cameras, thereby providing navigation capabilities for compute-intensive applications such as obstacle detection, pedestrian detection, collision avoidance, blind-spot detection, rear collision warning, as well as simultaneous localization and mapping (SLAM), said Annie Fu, a product manager of the AIoT Team at Axiomtek.

oToBrite develops, designs, and manufactures products ranging from vision-AI algorithms, ECU to automotive-grade cameras. Therefore, products can be sold in a flexible way according to customer needs even just a vision-AI IP license. oToBrite’s vision-AI algorithms have been low-bit optimized across different platforms. We are excited to expand the collaboration with Axiomtek, said Ian Tzeng, Product Strategy & Marketing Office Director at oToBrite Electronics.

Axiomtek’s AIE900-XNX has a powerful 6-core NVIDIA Carmel ARM v8.2 (64-bit) processor and 384-core NVIDIA Volta architecture GPU, delivering up to 21 TOPS accelerated computing performance for running modern AI workloads. To respond to the emerging needs of faster throughput, lower latency, and a higher density of connections, the advanced edge AI computing platform is equipped with one M.2 Key B slot for the 5G module. It also has one full-size PCIe Mini Card slot, plus one SIM slot for Wi-Fi/LTE/Bluetooth/GPS. Given that the use in sedans, buses, and trucks with the high-temperature operation and varying voltage input requirements, it has an extended operating temperature range of -30°C to +60°C and 9 to 36 VDC power input with optional ignition power control. The advanced edge AI computing platform supports high-speed networking capability functions such as the 5G module to drive AIoT innovation.