Goals: Difference between revisions
From SpaceElevatorWiki.com
Jump to navigationJump to search
(New page: '''Vision:''' * Get Intel code compiling on Ubuntu and into a Mercurial tree. * Hook up .Net wrapper to Intel vision code. * Create some tests which do simple feature recognition. * Hook t...) |
No edit summary |
||
| Line 6: | Line 6: | ||
'''Driving:''' | '''Driving:''' | ||
* Create a C# wrapper for the Torcs driving APIs. (Maybe Bernhard or someone from Torcs) | |||
* Create a C# wrapper for the | * Port smart baseline driving code to C#. There is lots of driving code to write, so we need this code to be clean. | ||
* Stress it by creating various terrain. | |||
* Hook the '''output''' of the vision recognition into the '''input''' of the driving engine! | * Hook the '''output''' of the vision recognition into the '''input''' of the driving engine! | ||
* (For debugging purposes, hook the output of the vision recognition into the input of the 3-D engine, by creating ghost images.) | * (For debugging purposes, hook the output of the vision recognition into the input of the 3-D engine, by creating ghost images.) | ||
* Add other features like waypoints. | * Add other features like waypoints. | ||
* Work on urban driving rules like stopsigns. (Someone else looking to do this with Torcs as well) | * Work on urban driving rules like stopsigns. (Someone else looking to do this with Torcs as well) | ||
Revision as of 15:34, 9 June 2008
Vision:
- Get Intel code compiling on Ubuntu and into a Mercurial tree.
- Hook up .Net wrapper to Intel vision code.
- Create some tests which do simple feature recognition.
- Hook the input of vision recognition to the output of the 3-D engine!
Driving:
- Create a C# wrapper for the Torcs driving APIs. (Maybe Bernhard or someone from Torcs)
- Port smart baseline driving code to C#. There is lots of driving code to write, so we need this code to be clean.
- Stress it by creating various terrain.
- Hook the output of the vision recognition into the input of the driving engine!
- (For debugging purposes, hook the output of the vision recognition into the input of the 3-D engine, by creating ghost images.)
- 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?
