Robby Fischer is a chess-playing robotic arm system that uses computer vision and imitation learning AI to play chess autonomously against human opponents.
About Us • Overview • Features • Hardware • Wiring Diagram • Credits
Team Name: TPC
Team Number: 18
GitHub Usernames:
- @TaniWanKenobi
- @techn1-cal
- @ChanminK
(insert video here )
- Hugging Face LeRobot SO-ARM101
- AMD PC
- USB Cameras (x3)
- Chess Board (3D printed)
- Chess Pieces (3D printed)
ChessArm is an intelligent robotic chess system that:
- Captures the board state using multiple calibrated cameras
- Detects opponent moves via vision-based piece tracking
- Analyzes board positions using the Stockfish chess engine
- Executes moves using the Hugging Face LeRobot SO-ARM101 robotic arm
Game Flow:
Camera Input → Board Detection → Stockfish AI → Arm Execution → Repeat
- Multi-Camera System: Three cameras (wrist, top-down, side)
- Perspective Calibration: Automatic 4-point homography correction
- Piece Detection: Brightness-based occupancy detection (threshold = 140)
- AI Integration: Stockfish engine with 2-second move time limit
- Turn Logic: Alternates between human (White) and robot (Red)
This project uses the following open-source projects
- Onshape was used to CAD the chess pieces and board
- AMD and Hack Club provided the hardware and software resources we used!
- OpenCV was used for image processing and computer vision tasks
- Stockfish was used for chess engine analysis