Taiwanese embedded computing company Advantech has launched a series of compact edge artificial intelligence (AI) systems powered by the Nvidia Jetson family.

They suit edge AI applications such as traffic monitoring, defect inspection, automated guided vehicles, autonomous mobile robots, people counting and medical imaging.

The Air-020 devices measure 139 by 110 by 44.5mm and deliver low-power computing with AI inferencing capabilities using Nvidia Jetson Nano, TX2 NX and Xavier NX systems-on-module (SoMs).

The Air-020X is powered by the Nvidia Xavier NX SoM, the Air-020T by the Jetson TX2 NX and the Air-020N by the Jetson Nano to meet diverse AI application and performance needs. The Air-020X supports up to 21Tops (tera operations per second) and 1058 frames per second, targeting high resolution imaging processes. The Air-020T and Air-020N support 1.33/0.5Tflops and up to 109/48 frames per second.

The series handles 12 to 24V DC input, -10 to +55˚C operating temperature, and vibration and humidity resistance.

As AI projects are used in a variety of application, the requirement of peripheral connections varies. The series is equipped with IO ports including two USB 3.2 type A, USB 3.2 type C, one or two GbE, one or two RS-232/422/485, 8bit DIO, and CanBus for data acquisition and communications.

The compact AI boxes are pre-installed with 4 or 8Gbyte LPDDR4 and 16Gbyte eMMC 5.1. Moreover, they provide 128Gbyte of M.2 storage as the data storage default setting for AI usage.

The series bundles with the Ubuntu 18.04 LTS OS environment, Advantech Edge AI suite and JetPack SDK 4.5.1. Engineers can use them to develop AI models and deploy their applications. For data security, they adopt TPM 2.0 trusted platform module and secure boot, which opens the door for compute-intensive industrial applications and better system security at the edge.