Portwell, a global leader in embedded computing solutions and edge AI innovation, proudly announces the release of its PEDK-5230-AGX AI Developer Kit. Built on the NVIDIA® Jetson AGX Orin™ module, this powerful and feature-rich platform is tailored for industrial-grade AI development at the edge. It meets the growing demands for intelligent computing in robotics, machine vision, autonomous systems, and smart city infrastructure. With its compact open-frame form factor, advanced thermal solution, and versatile I/O interfaces, the PEDK-5230-AGX offers an efficient and scalable environment for edge AI prototyping and deployment. This launch underscores Portwell’s commitment to accelerating AIoT innovation with robust, ready-to-integrate platforms.
At its core, the PEDK-5230-AGX is powered by the NVIDIA® Jetson AGX Orin™ 32GB SOM, delivering up to 200 TOPS of AI performance, making it ideal for real-time deep learning workloads. The platform is equipped with 32GB LPDDR5 RAM and 64GB eMMC storage, providing ample memory and storage to support seamless software compatibility across the NVIDIA Jetson ecosystem.
Designed for demanding environments, the developer kit offers a comprehensive set of front and rear I/Os, including 12x PoE GbE (10W per port, maximum 120W), 1x 10GbE, 1x 1GbE, 1x HDMI 2.1, and 8x USB 3.2 Type-A, including Type-C for OS flashing and debugging. Audio I/O (Mic-in and Line-out), 2x RS-232/422/485 COM ports, 2x CAN FD interfaces, 1x DIO 8-bit, and 2x Nano SIM slots complete the connectivity package, ensuring high interoperability with both legacy and cutting-edge devices.
Expansion capabilities include M.2 B Key (3042/3052) for LTE/5G, M.2 E Key (2230) for Wi-Fi/Bluetooth, and M.2 M Key (2280) for PCIe Gen4 NVMe SSDs. Additionally, the platform supports Out-of-Band (OOB) network features, which can be implemented based on specific application requirements, providing enhanced remote management and monitoring capabilities. All of this is housed on a 270×190 mm baseboard, powered by a 19V–24V DC input, optimized for embedded deployment with remote power control support.
The Portwell PEDK-5230-AGX AI Developer Kit is purpose-built for real-world edge AI deployment, providing the computational power needed for applications such as AI-based visual inspection, robotics pathfinding, and intelligent traffic monitoring. The integrated PoE LAN ports enable direct device connectivity and power for IP cameras or smart sensors, while 10GbE bandwidth ensures high-throughput data transfer. Its M.2 modular expansion supports cellular, Wi-Fi, and high-speed storage needs, which are critical for mobile robotics and AI vision tasks.
Leveraging NVIDIA’s CUDA, TensorRT, and DeepStream SDKs, developers can quickly iterate and deploy scalable AI pipelines. The developer kit’s rugged and compact design makes it ideal for use in AGVs (automated guided vehicles), smart agriculture drones, industrial inspection systems, and border surveillance. With enhanced thermal management and robust connectivity, the PEDK-5230-AGX delivers real-time edge inference reliably, even in harsh environments.
With deep expertise in customized development for sectors such as manufacturing, gaming, transportation, and medical, Portwell is well-equipped to meet the unique requirements of a wide range of vertical markets. The company’s dedication to advancing edge AI innovation is evident in its comprehensive portfolio of products and services, designed to serve diverse industries including automation, machine vision, robotics, healthcare, retail, agriculture, and infrastructure.
Leveraging its strengths in embedded systems and edge AI computing, Portwell delivers intelligent solutions that optimize operational efficiency, enhance real-time decision-making, and support scalable business growth across various critical applications.
To provide the best experiences, we and our partners use technologies like cookies to store and/or access device information. Consenting to these technologies will allow us and our partners to process personal data such as browsing behavior or unique IDs on this site and show (non-) personalized ads. Not consenting or withdrawing consent, may adversely affect certain features and functions.
Click below to consent to the above or make granular choices. Your choices will be applied to this site only. You can change your settings at any time, including withdrawing your consent, by using the toggles on the Cookie Policy, or by clicking on the manage consent button at the bottom of the screen.