What is it?

• A standard robotic arm with 3 DOF + 1 gripper. IE: Rotating Base, Shoulder, Elbow Joint, Gripper.
• Computer vision-assisted. Should be able to detect common items and pick them up as long as they are in sight.
• Controlled by voice commands in natural language.

How does it work?

• Controlled by a Raspberry Pi Pico.
• The main program runs on the computer.
• The computer relays the instructions to the Pico.
• A webcam is positioned with a top-down view of the surroundings to help the arm detect objects and their positions.

Native dependencies

Install the PortAudio runtime before installing Python requirements so microphone input works:

• Ubuntu / Debian / WSL: sudo apt-get install libportaudio2 portaudio19-dev
• macOS (Homebrew): brew install portaudio
• Windows: pip install pipwin && pipwin install portaudio