Crazyflie AI-deck – with GAP8 RISC-V MCU & ESP32 Wi-Fi

Crazyflie AI-deck is built around the GAP8 RISC-V multi-core MCU build for AI on the edge purposes. Adding to this is a QVGA monochrome camera and an ESP32 WiFi MCU. This all together creates a pretty good platform to develop low power AI on the edge for a drone.

Features

• Ultra-low-power GAP8 8+1 core RISC-V IoT application processor built for AI at the edge
• Ultra-low-power Himax HM01B0 320×320 greyscale camera to enable autonomous navigation
• ESP32-based NINA-W102 Wi-Fi module to stream images to PC
• 512 Mbit HyperFlash and 64 Mbit HyperRAM for faster speeds
• Ability to work standalone by powering the board through VCOM
• 2 x Cortex-M 10-pin JTAG Interface to program on the GAP8 and ESP32
• Can be easily mounted on the Crazyflie V2.1 with the 2 x 10-pin male headers
• Button connected to ESP32 for UART bootloader or other actions
• Green LED status indicators for GAP8 and ESP32

Description

What is Crazyflie?

Crazyflie is a versatile open-source flying development platform that only weighs 27g and fits in the palm of your hand. Crazyflie is equipped with low-latency/long-range radio as well as Bluetooth LE. This gives you the option of downloading an app and using your mobile device as a controller or, in combination with the Crazyradio PA, using your computer to display data and fly with a game controller.

Crazyflie AI-deck for super edge computing

Crazyflie AI-deck is built around the GAP8 RISC-V multi-core MCU build for AI on the edge purposes. With the GAP8 IoT application processor and the ULP camera, the Crazyflie is able to capture, analyze, and classify its environment. This lightweight and low-power combination opens up many research and development areas for the micro-sized Crazyflie 2.X UAV.

GAP8 delivers over 10 GOPS of computing power at exceptionally low power consumption enabling complex tasks such as path-finding and target following on the Crazyflie, consuming less than 0,1% of the total energy

The AI-deck extends the computational capabilities and will enable complex artificial intelligence-based workloads like Convolutional Neural Networks to run onboard, with the possibility to achieve fully autonomous navigation capabilities. The ESP32 adds WiFi connectivity with the possibility to stream images as well as handling control.

Block Diagram

Specifications

• Power supply 3V-5V @ VCOM up to 300mA
• 1-wire memory for automatic expansion board detection
• UART connected between GAP8 and Crazyflie (RX1, TX1)
• UART connected between ESP32 (RX2, TX2)
• ESP32 sysboot pin connected to Crazyflie (IO_1)
• Reset to GAP8 and ESP32 connected to Crazyflie (IO_4)
• SPI between GAP8 and ESP32
• GAP8 (B1) -> ESP32 (GPIO_5) io
• ESP32 (GPIO_25) -> GAP8 (A13) io
• Weight: 4.4g
• Size (WxHxD): 30x52x8mm

Dimensions

Parts List

• 1 x AI-deck
• 2 x Long pin headers