Development kit gives AI designers the edge

It was created in collaboration with Renesas, Syntiant, TDK, and Edge Impulse, and will be demonstrated in the Avnet Embedded booth (1-510) at embedded world 2023 in Nuremberg (March 14-16).

RASynBoard targets industrial and consumer applications needing battery powered, always-on, smart sensing capabilities, such as sound recognition, command recognition, vibration sensing and environmental sensing. Its small (30mm x 25mm) size makes it ideal as an add-on sensor module for existing products, or its design can be customised and integrated in a larger system for enhanced sensing needs.

The RASynBoard module, or Core Board, comprises two domains: an always-on AI processor with on-board sensors and an MCU-based controller with a low-power WiFi/BT wireless module. The AI processing system has the ability to wake up the MCU controller when it detects an AI triggered “event,” allowing the MCU system to take action or send notification through the wireless module and then return to the low-power AI sensing mode.

Developers can customize both the sensors connected to the AI processor as well as the AI algorithm running on the AI processor.

The Syntiant NDP120 Neural Decision Processor is the AI processor used on RASynBoard and the Renesas RA6M4 MCU is the MCU controller.

Also included on the Core Board is the Renesas DA16600 low-power WiFi/BT combo module, and two TDK sensors: the ICM-42670-P 6-axis IMU and the MMICT5838 PDM digital microphone.

RASynBoard can work standalone with nothing more than a battery. For development and prototyping it can be plugged into the IO Board, which is included in the RASynBoard Development Kit. The IO Board provides on-board debug and programming capabilities for the RA6M4 MCU, along with expansion capabilities for both the MCU and NDP120.

Both Pmod and Click interfaces are available for adding different sensors or control functions, offering maximum flexibility for prototyping. The IO Board also includes a micro-SD card interface to the RA6M4 MCU, for additional data storage if needed.

“Avnet’s strong relationship with industry leading suppliers such as Renesas, TDK and our new supplier Syntiant allows us to combine the unique offerings and capabilities of each partner into a complete system-level, production-ready solution,” said Jim Beneke, vice president Advanced Applications Group, Avnet. “Our design customisation and manufacturing capabilities also allow us to offer production-ready solutions for customers needing a full-turnkey option.”

The RASynBoard kit features:

• Always-on, edge AI sensing capability to detect events based on real-time sensor data
• Dedicated AI processor offering the flexibility to run single neural network or multiple neural networks in parallel, providing true sensor fusion AI processing capability
• A small sensor board that can work stand-alone or plugged into the included IO Board for easier sensor prototyping and software development
• Included WiFi/BT module providing wireless connectivity for enhanced cloud capabilities with Avnet’s IoT Connect and AWS and Azure support
• Edge Impulse Studio support for AI model development, training, optimisation, and deployment
• e2 studio IDE from Renesas enabling application development for the RA6M4 MCU