Car Racing Competition

1. Car Racing Competition

2. Goal • Learn or design a controller for TORCS that races as fast as possible alone or in the presence of others drivers • “Spiritual successor” of CEC 2007 Competition

3. Car Racing Competition meets TORCS • More representative of real game AI • Better interaction with human players • Many good programmed controllers available • Challenges • How to make it easy accessible? • Not designed for Machine Learning! • More similar to a real-world problem

4. The Open Racing Car Simulator

5. The Open Racing Car Simulator • TORCS is a state of the art open source simulator written in C++ • Main features • Sophisticated dynamics • Provided with several cars, tracks, and controllers • Active community of users and developers • Easy to develop your own controller • OS Support • Linux: binaries and building from sources suppo • Windows: binaries and “limited” bulding from sources support • OSX: legacy binaries and no building from sources support 

6. Competition API • To make TORCS more easy to use we developed an API based on socket (UDP) • Values of sensors and effectors are sent through UDP • 3 components • Torcs Patch • Server Bot (C++) • Client API (C++ and Java) TORCS Patch Server BOT UDP Client Controlller

7. Track Sensors Opponent Sensors Sensors • Rangefinders to sense • Opponents • Edges of the track • Speed • Position on track • Rotation speed of wheels • RPM • Angle with track • Distance raced • Fuel and damage • ...

8. Effectors • Basically 4 effectors • Steering wheel [-1,+1] • Gas pedal [0, +1] • Brake pedal [0,+1] • Gearbox {-1,0,1,2,3,4,5,6}

9. Rule • Hand coding controller were allowed • Unknown Track • Distance raced by each controller within 10000 tics(200 sec)

10. The Results

11. Submissions • 5 entries have been submitted to the competition: • Matt Simmerson • Leonard Kinnaird-Heether – Wayne State University • Chin Hiong Tan – National University of Singapore • Diego Perez - University Carlos III, Madrid • Simon Lucas – University of Essex • 3 more controllers have been considered • Daniele’s heuristic C++ controller • Julian’s heuristic Java controller • Luigi Cardamone - Politecnicodi Milano

12. Scoring setup • A server with 2 Quad-core Xeon 2.66 GHz, 8GB RAM, running Fedora Core 6

13. Scoring process • Scoring is a two stage process involving three tracks (unknown to the competitors): • RUUDSKOGEN • STREET1 • D-SPEEDWAY • In the first stage only a controller at once is tested and performance is defined as the distance covered within 10000 game tics • In the second stage all the controllers (except the three not in the competition) race at the same time and performance is defined simply as the arrival order after 3 laps

14. First Stage: RUUDSKOGEN

15. First Stage: STREET1

16. First Stage: D-SPEEDWAY

17. First Stage: overall results • F1 point system is used to compute the final scores of the controllers on the 3 tracks

18. Second Stage: Competition League • Also in this stage, F1 point system is used to compute the final score

19. Second Stage: Full League

20. Summary of results • 3 learned controllers are significantly better than programmed controllers • Some possible overfitting to training tracks? • Poor performance in avoiding and overtaking opponents • Some problems with recovery behavior • Still more work to reach the performance of controllers provided with TORCS but initial results are promising!

21. TORCS • Official Site • http://torcs.sourceforge.net/ • Source Code Download • http://torcs.sourceforge.net/index.php?name=Sections&op=viewarticle&artid=3 • Robot Tutorial • http://www.berniw.org/