Dusun IoT has announced the release of the latest product, the DSGW-380 Industrial AI Edge Computing Gateway. This gateway is designed for AI applications and is equipped with the RK3588 chip, which features a quad-core Cortex-A76 and quad-core Cortex-A55 CPU with a NEON co-processor, 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. It is an ideal device for deploying AI computing power at the Edge of deep learning. These include robotics, autonomous delivery vehicles, low-altitude security, intelligent detection systems, and smart infrastructure.
Key features of DSGW-380 industrial AI Edge Computing gateway
- Supports 5G, 4G LTE CAT4 and CAT1
- Supports Wi-Fi 6 (IEEE 802.11ax)
- Offers powerful computing performance, providing high-performance processing resources for AI Edge computing
- Supports a variety of industrial real-time Ethernet and fieldbus protocols, making it compatible with a wide range of industrial equipment
- Coming with rich I/O interfaces
- Supports ROS robot system
- Supports a variety of deep learning framework software, including TensorFlow, MXNet, PyTorch, and Caffe
- Includes an acceleration SDK based on the open-source YOLOV3 algorithm, which provides a variety of API interfaces
- Supports IoT wireless protocols, including BLE 5.2 and LoRaWAN
- Featuring a fully industrial design, making it rugged and ready for harsh conditions
High performance and Edge computing capability
Powered by Rockchip RK3588, one of the most popular IoT SoCs in the AIoT field, DSGW-380 offers excellent Edge computing capability. Rockchip RK3588 SoC is a high-range SoC made in 8nm process technology, integrated 8-core 64-bit ARM architecture, with 4 Cortex-A76 plus 4 Cortex-A55 and Mali G610 MC4 graphics processor, supporting 8K decoding. Most importantly, it has a built-in independent NPU (Neural Processing Unit) capable of hybrid operations with INT4, INT8, INT16, and FP16 and offers a computing capacity of up to 6 TOPS. Therefore, it can be used for industrial AI applications in building automation, industrial control, and predictive maintenance of IoT elevators, etc.
Consistently stable and exceptionally robust connectivity
The DSGW-380 offers several backhaul options including 5G LTE, Ethernet, and Wi-Fi6(IEEE 802.11ax). lt facilitates automatic switching between various backhauls and ensures a consistent online connection through auto link detection.
Rich interfaces and high programmability
DSGW-380 RK3588 AI gateway has abundant ports and interfaces ready for a variety of AIoT applications in the Industrial field, including RS485/232 serial port, CAN, USB 2.0, HDMI, Type-C, RJ45 port, etc. Meanwhile, it can run ROS and Debian operating systems, and support full-stack embedded software development. The DSGW-380 supports full-stack embedded software development. By utilising the integrated SDK and Wireless Module driver, it enables developers to build low-level and custom applications.
Easily connect with the largest IloT Clouds
In addition to offering comprehensive APIs that streamline the lT application development process the DSGW-380 supports MQTT,TCP,and HTTP protocols. It enables users to build applications on major IloT Clouds like Azure loT Edge efficiently and caters to private cloud platforms.
Fully industrial-grade design in harsh environment
Complying with stringent industrial standards, the product encompasses all essential components including the processor, RAM,Wireless module and power supply terminal. Adhering to benchmarks like IP30 and wide temperature ranges, it is well-suited for the challenging environments.
“We are excited to introduce the DSGW-380 Industrial AI Edge Computing Gateway tailored specifically for smart manufacturing,” said Mr.Jiang, CEO of DusunIoT. “This product underscores our commitment to providing cutting-edge solutions that empower manufacturers with intelligent AI capabilities, enabling them to optimise production processes and drive efficiency.”
There’s plenty of other editorial on our sister site, Electronic Specifier! Or you can always join in the conversation by commenting below or visiting our LinkedIn page.