The DSGW-380 is an edge computing gateway designed for AI applications based on the RK3588 chip. This chip features an integrated CPU consisting of a quad-core Cortex-A76 alongside a quad-core Cortex-A55 and is further enhanced by a NEON coprocessor. The gateway is also equipped with an NPU (Neural Processing Unit) capable of hybrid operations with INT4, INT8, INT16, and FP16 and offers a computing capacity of up to 6 TOPS. In addition, the DSGW-380 is highly compatible with various neural network models, supporting a range of frameworks such as TensorFlow, MXNet, PyTorch, and Caffe.
The rugged design with aluminum alloy structure, active fan cooling, rich I/O interfaces, and stable performance make the DSGW-380 highly suitable for various applications. These include robotics, autonomous delivery vehicles, low-altitude security, intelligent detection systems, and smart infrastructure. It is the optimal choice for implementing AI computing capabilities at the edge in deep learning scenarios.
RK3588 Quad-core ARM Cortex-A76 and Quad-core ARM Cortex-A55
System
Debian 11
RAM
8 GB LPDDR4
Storage
Up to 128 GB eMMC
Power Supply
Input: DC 12V/4A
Indicator LEDs
The Power LED remains GREEN when the device is on. The 5G LED flashes BLUE when functioning correctly. The Wi-Fi LED flashes BLUE when operating properly. The LoRa LED remains BLUE when functioning correctly.
Reset Button
Factory reset button. To reset the Gateway to its original factory settings, press and hold it for more than 10 seconds