Cramming a Cyclone II FPGA … into Mario’s Brain
Jason Wright, Sima Mitra, and I built an FPGA-based (Field Programmable-Gate Array) AI that uses video input from an NES console to automatically play the game Super Mario Bros. All of the video analysis and AI techniques are performed using Verilog-compiled hardware running on an Altera DE2 Cyclone board. The project combines NTSC decoding, VGA output, kernel-based pattern matching, real-time image manipulation, and NES controller emulation. We launched a website that explains the working of the system in extreme detail. Visit the website to get all the nitty-gritty technical details:
Video of our FPGA AI in Action
This video shows the AI beating World 1-1 of Super Mario Bros. without breaking a sweat:
Supporting Documentation, Schematics, and Code
The Nintendo Ninja Super Mario FPGA AI is released as entirely open source hardware and software. All materials are distributed under the GNU General Public (Open-Source) License. Please Attribute and Share-Alike. All files are hosted on GitHub.
Nintendo Ninja in the News
- 05/19/2013 – Nintendo Ninja on Hack-a-Day