Advantech unveils AIR-020 AI inference systems
Advantech has announced the launch of the AIR-020 series, an ultra-compact series of edge AI systems powered by the NVIDIA Jetson family.
The compact AIR-020 series has been designed to deliver low power computing with powerful AI inferencing capabilities utilising NVIDIA’s Jetson Nano, TX2 NX, and Xavier NX SoM and is intended for edge AI applications such as traffic monitoring, defect inspection, AGV/AMR, people counting, medical imaging and more.
Within the series the AIR-020X is powered by the NVIDIA Xavier NX SoM, AIR-020T by the Jetson TX2 NX, and the AIR-020N by the Jetson Nano to meet diverse AI application and performance needs.
The three offerings deliver an ultra-compact design making them easy to integrate into the applications. The AIR-020X supports up to 21 TOPS (Tera Operations per Second) and 1058 frames per second (FPS) targeting high resolution imaging processes. The AIR-020T and AIR-020N support 1.33/0.5 TFLOPS and up to 109/48 frames per second (FPS). The AIR-020 series supports wide-range 12-24V DC input, -10 to 55°C operating range, and vibration and humidity resistance.
AI projects are used in a great variety of applications, so the requirement of peripheral connections varies. The AIR-020 series is equipped with extensive I/O ports including 2 x USB 3.2 Type A, USB 3.2 Type C, 1 or 2 x GbE, 1 or 2 x RS-232/422/485, 8-bit DIO, and CANBus for data acquisition and communication. The ultra-compact AI boxes are pre-installed with 4GB/8GB LPDDR4 and 16GB eMMC 5.1. Moreover, the AIR-020 series provides 128GB of M.2 storage as the data storage default setting for AI usage.
The AIR-020 series bundles with the Ubuntu 18.04 LTS OS environment, Advantech Edge AI Suite and JetPack SDK 4.5.1. Developers can easily develop AI models and deploy their applications.
For data security, the AIR-020 series adopts the TPM 2.0 trusted platform module and secure boot, which opens the door for compute-intensive industrial applications and better system security on the edge.