Recently awarded the 2021 Taiwan Excellence Award, the BOXER-8521AI focuses on deployment and connectivity. The BOXER-8521AI features a PoE-PD port, allowing the system to be deployed further away from its power source, as well as enable internet connection and remote monitoring of the system over the same single cable, reducing the complexity of installation. By using both the PoE-PD port and the DC input, the hardware can continue to operate even if one of the two power supplies is cut off.

The BOXER-8521AI brings computing power for artificial intelligence to the network edge. The integrated Google Edge TPU system-on-module (SoM) is housed in a shock- and vibration-resistant enclosure. The Google Edge TPU combines the NXP i.MX 8M SoC (Quad Cortex-A53, Cortex-M4F) with the Google Edge TPU coprocessor to deliver speeds of up to 4 TOPS at an energy-efficient 2 TOPS per watt.

Thanks to the Google Edge TPU, developers and users have access to Google’s training software suite, AutoML Vision Edge. This software helps developers design and train AI models using Google’s cloud services. The model is then exported to the BOXER-8521AI and the Google Edge TPU. The system supports the TensorFlow Lite framework, improving AI model efficiency, system performance, and processing speeds.

The BOXER-8521AI’s fanless design keeps out dust and contaminants, and can also operate at temperatures from -5°C to 50°C without performance loss. The BOXER-8521AI is equipped with one RS-232/485, one HDMI 2.0a, two USB 3.2 Gen 1 and two USB 2.0 interfaces. It also has a 40-pin multi-I/O port for connecting additional sensors and controllers, such as cameras, temperature sensors and more.