Arducam has announced its first product built around the Raspberry Pi RP2040 microcontroller, taking the Raspberry Pi Pico design and adding a camera module, microphone, inertial measurement unit (IMU), and LCD display — to target tinyML users working with TensorFlow Lite Micro.
That Arducam was interested in bringing its tinyML skills to bear on the RP2040, launched earlier this year as the first in-house silicon from Raspberry Pi, is no secret: A month ago the company got its Arducam Mini SPI Camera working with the RP2040-powered Raspberry Pi Pico.
The Arducam Pico4ML, though, is different. It takes the core design of the Raspberry Pi Pico and shifts it with a focus on use with TensorFlow Lite Micro for on-device machine learning. Alongside the RP2040 microcontroller, the board boasts a color display, a microphone with wake word detection, an inertial measurement unit (IMU), and a camera module — all in a neat and robust housing.
"As the RP2040 SoC is based on a high-clocked dual Cortex-M0+, it’s also a remarkably good platform for endpoint AI, or more specifically tinyML," James Adams, chief operating officer at Raspberry Pi, explains. "The TensorFlow Lite Micro library has already been ported to the RP2040, enabling users to run machine learning (ML) models to do sensor-based analysis such as voice and image recognition and accelerometer-based gesture recognition."
Pricing for the Arducam Pico4ML has yet to be confirmed, but interested parties can sign up to be notified when the product launches on the Arducam website.