To make Raspberry Pi Pico more robust for TFLite Micro, the Arducam team took the Raspberry Silicon (also known as the RP2040 chip) and created Pico4ML, a microcontroller dev board made exclusively for running and training machine learning examples.
Arducam Pico4ML Specifications
Microcontroller: Raspberry Pi RP2040
IMU: ICM-20948 (low power)
Mono channel microphone w/ direct PCM output
Camera Module: HiMax HM01B0, Up to QVGA (320 x 240 @60fps)
Screen: 0.96 inch LCD SPI Display (160 x 80, ST7735)
Operating Voltage: 3.3V
Input Voltage: VBUS: 5V +/- 10%. VSYS Max :5.5V
Length: 51 mm
Width: 21 mm
Bluetooth module
IMU Specifications
3-axis gyroscope, 3-axis accelerometer, 3-axis compass, and a Digital Motion Processor™ (DMPTM) in a 3 mm x 3 mm x 1 mm (24-pin QFN) package
DMP offloads computation of motion processing algorithms from the host processor, improving system power performance
EIS FSYNC support
Lowest Power 9-Axis Device at 2.5 mW
3-Axis Gyroscope with Programmable FSR of ±250 dps, ±500 dps, ±1000 dps, and ±2000 dps
3-Axis Accelerometer with Programmable FSR of ±2g, ±4g, ±8g, and ±16g
3-Axis Compass with a wide range to ±4900 μT
Onboard Digital Motion Processor (DMP)
Android support
Auxiliary I2C interface for external sensors
On-Chip 16-bit ADCs and Programmable Filters
7 MHz SPI or 400 kHz Fast Mode I²C
Digital-output temperature sensor
VDD operating range of 1.71V to 3.6V
MEMS structure hermetically sealed and bonded at wafer level