Goals

Vision:

• Get Intel code compiling on Ubuntu and into a Mercurial tree. (20 hours)
• Hook up .Net wrapper to Intel vision code. (20 hours)
• Create / find a 2-frame GUI tool which takes a picture and applies Intel code to it and displays an output image of its analysis. (40 hours)
• Hook the input of vision recognition to the output of the 3-D engine! (40 hours)

Driving:

• Create a C# wrapper for the Torcs driving APIs. (Maybe Bernhard or someone from Torcs) (100 hours)
• Port smart baseline driving code to C#. There is lots of driving code to write, so we need this code to be clean. (100 hours)
• Stress it by creating various terrain. (40 hours)
• Hook the output of the vision recognition into the input of the driving engine! (40 hours)
• (For debugging purposes, hook the output of the vision recognition into the input of the 3-D engine, by creating ghost images.)

Later Goals

• Add other features like waypoints.
• Work on urban driving rules like stopsigns. (Someone else looking to do this with Torcs as well)

Better 3-D Engine?

• Evaluate better & more professional-looking 3-D engines.
• What other features do they have? Eg, what about the ability to log all changes to the world so you can replay it later?