The D-Robotics RDK X5 is an upgraded AI development board built around the Sunrise X5 octa-core SoC and designed for more demanding ROS-based applications. Compared to the Sunrise X3-based RDK X3 and Horizon X3 AI development boards, which feature a 4-core CPU and 5 TOPS BPU, the RDK X5 comes with an 8-core Cortex-A55 SoC, a 10 TOPS NPU, and 8GB of RAM, doubling both the AI power and memory for demanding workloads.
The board also features various I/O options with Wi-Fi 6, Bluetooth 5.4, CAN FD, and PoE support, whereas the X3 is limited to Wi-Fi 5, Bluetooth 4.2, and optional PoE. The X5 also adds four USB 3.0 ports and 4K 60 FPS video output, making it suitable for complex computer vision, robotics control, and machine learning applications.
D-Robotics RDK X5 development board Specifications
- SoC – Sunrise X5 SoC with
- 8x Arm Cortex-A55 cores @ 1.5GHz
- 10 TOPS BPU (Neural Processing Unit)
- 32 GFLOPS GPU
- H.265/H.264 video decoding and encoding up to 3840×2160 @ 60fps
- JPEG encode/decode up to 16MP
- Memory – 4GB or 8GB LPDDR4 options
- Storage – microSD card slot (no onboard eMMC)
- Display
- HDMI Type-A up to 1080p60
- 4-lane MIPI DSI connector
- Camera – 2x 4-lane MIPI CSI for stereo vision
- Audio – 3.5mm audio jack (input/output)
- Networking
- Gigabit Ethernet RJ45 port with optional PoE support
- Wi-Fi 6 and Bluetooth 5.4 with onboard antenna
- USB
- 4x USB 3.0 Type-A (host) ports
- USB 2.0 Type-C (device, Flash Connect support) port
- Micro USB port for debug UART
- Expansion
- 40-pin GPIO header with 28 usable GPIOs (UART, PWM, I2C, SPI, I2S)
- JST connector for CAN bus
- Misc – Power and User LEDs
- Power Supply – 5V/5A input via USB Type-C
- Dimensions – 85 x 56 x 20 mm
- Temperature Range – -20°C to 60°C
It’s a bit odd that there’s no specific pinout information available for the RDK X5. If the company is using the same pinout structure as the RDK X3, then that can be used as a reference for pinout details.
This Sunrise X5-based RDK X5 development board runs Ubuntu 22.04 and supports popular open-source frameworks like ROS, TensorFlow, and PyTorch. The 10 TOPS NPU can be used for a range of machine vision tasks, including keypoint detection, deep learning-based optical flow estimation, stereo depth mapping, and occupancy analysis. These enable robots to analyze their surroundings with precision in conditions like low light, glare, or weak textures. There are also over 200 open-source algorithm examples via NodeHub. The full documentation with a Getting Started Guide can be found on the company’s Wiki in English.
The RDK X5 comes in 4GB and 8GB variants and is available in multiple stores, notably on AliExpress starting at $89.79, on Amazon for $98.99/$129.99, Waveshare, and, DFRobot with prices varying by store. As a side note, an RDK S100 SBC is also in the works with a 100 TOPS NPU, and some documentation is available, but only in Chinese for now. We’ll make sure to cover that one once more details are available
Debashis Das is a technical content writer and embedded engineer with over five years of experience in the industry. With expertise in Embedded C, PCB Design, and SEO optimization, he effectively blends difficult technical topics with clear communication
Support CNX Software! Donate via cryptocurrencies, become a Patron on Patreon, or purchase goods on Amazon or Aliexpress. We also use affiliate links in articles to earn commissions if you make a purchase after clicking on those links.
