The 2011 Simulated Car Racing Championship @ Evo*-2011

5,626 views
5,508 views

Published on

These slides report the results of The 2011 Simulated Car Racing Championship @ Evo*-2011

Published in: Technology
0 Comments
1 Like
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
5,626
On SlideShare
0
From Embeds
0
Number of Embeds
3,650
Actions
Shares
0
Downloads
17
Comments
0
Likes
1
Embeds 0
No embeds

No notes for slide

The 2011 Simulated Car Racing Championship @ Evo*-2011

  1. 1. The 2011 Simulated Car Racing Championship @ Evo*-2011 Daniele Loiacono, Luigi Cardamone, Martin V. Butz, and Pier Luca Lanzi2011 Simulated Car Racing Championship @ EVO*-2011
  2. 2. 2 2011 Simulated Car Racing Championship 9 races during 3 conferences Develop a driver for TORCS (hand-coded, learned, evolved, …) Drivers will be awarded based on their score in each conference competition At the end, the team with highest overall score wins the championship2011 Simulated Car Racing Championship @ EVO*-2011
  3. 3. Roadmap of the 2011 Championship 1. EVO*-2011, Torino (Italy) April 27-29, 2011 (Now!) 2. ACM GECCO-2011, Dublin (Ireland) July 12-16, 2011 3. IEEE CIG-2011, Seoul (South Korea) August 31 September 3, 20112011 Simulated Car Racing Championship @ EVO*-2011
  4. 4. Motivations  Proposing a relevant game-based competition more representative of commercial games AI more similar to a real-world problem  Proposing a funny and exciting competition you can see and play with the entries of this competition human players can interact with AI a lot of programmed AI available for comparison  Proposing a challenging competition computationally expensive real-time on-line learning noisy sensors2011 Simulated Car Racing Championship @ EVO*-2011
  5. 5. The Open RacingCar Simulator
  6. 6. 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 Windows: binaries and “limited” bulding from sources support OSX: legacy binaries and no building from sources support 2011 Simulated Car Racing Championship @ EVO*-2011
  7. 7. The Open Racing Car Simulator & the Competition Software TORCS TORCS PATCH BOT BOT BOT SBOT SBOT SBOT  The competition server UDP UDP UDP  Separates the bots from TORCS  Build a well-defined sensor model  Works in real-time BOT BOT BOT2011 Simulated Car Racing Championship @ EVO*-2011
  8. 8. Sensors and actuators  Rangefinders for edges on the track and opponents (with noise)  Speed, RPM, fuel, damage, angle with track, distance race, position on track, etc.  Six effectors: steering wheel [-1,+1], gas pedal [0, +1], brake pedal [0,+1], gearbox {-1,0,1,2,3,4,5,6}, clutch [0,+1], focus direction2011 Simulated Car Racing Championship @ EVO*-2011
  9. 9. Structure of the Race
  10. 10. 12 What is the structure of a race? Three stages: warm up, qualifiers, actual race During warm-up, each driver can explore the track and learn something useful During qualifiers, each driver races alone against the clock (the best 8 drivers move to the race) During the race all the drivers race together2011 Simulated Car Racing Championship @ EVO*-2011
  11. 11. Competitors
  12. 12. The competitors  Four entries in the first leg: Mr. Racer, TU Dortmund Mariscal & Fernández, Málaga University Ready2Win, Slovak University of Technology - FIIT Powaah, Blekinge Institute of Technology  Three more entries from the 2009 championship: AUTOPIA, Madrid and Granada COBOSTAR (Lönneker & Butz, University of Würzburg) POLIMI (Cardamone, Politecnico di Milano)2011 Simulated Car Racing Championship @ EVO*-2011
  13. 13. Mr RacerJan Quadflieg, Tim Delbruegger and Mike PreussTU Dortmund2011 Simulated Car Racing Championship @ EVO*-2011
  14. 14. Mr. Racer 2011  Mostly described in the Evo* Paper “Driving Faster Than a Human Player“  13 Variables learned offline with the CMA-ES  Warmup used to learn a model of the track  Noise Handling: Low pass filter on sensor values 2 Regression polynoms are fitted to each side Resample the polygons2011 Simulated Car Racing Championship @ EVO*-2011
  15. 15. Mr. Racer 2011 - Opponent Handling  Noise filtering with a lowpass filter  Observer module interprets filtered sensor readings  This leads to a recommended speed and an overtaking line (created on the fly!)  Planning module incorporates recommended target speed and overtaking line into the plan  Lots of nummerical parameters not yet tuned: left for Gecco Competition2011 Simulated Car Racing Championship @ EVO*-2011
  16. 16. 2011 Simulated Car Racing Championship @ EVO*-2011
  17. 17. Mariscal & Fernández  General approach: expert systems improved by multi- objectives evolutionary computation techniques  Steering: based on a simple rule follow the track sensor with biggest distance.2011 Simulated Car Racing Championship @ EVO*-2011
  18. 18. Mariscal & Fernández - Throttle/Brake  Implemented via a parameterized expert system whose parameters were optimized via a Multi-Objective Evolutionary Algorithm (NSGA-II)  Two objectives: Maximize distance. Minimize damage.  Linear function (Ci are parameters to optimize): C1 (Speed) + C2 (Distance to the next turn) + C3 (Turn degrees)  We obtain three sets of parameters (1) To run fast (i.e., controllers) to be used under (2) To run safe specific conditions of the race (3) To run on dirty tracks.2011 Simulated Car Racing Championship @ EVO*-2011
  19. 19. Mariscal & Fernández - Overtaking  Expert system with four groups of rules:  Other strategies are implemented (via expert systems) such as collision avoidance and slipstream overtakings.2011 Simulated Car Racing Championship @ EVO*-2011
  20. 20. 2011 Simulated Car Racing Championship @ EVO*-2011
  21. 21. Ready2Win  Modular architecture: Driving module: • The speed is computed using the maximum braking distance Overtaking module Recovery module ABS module  Track learning during the warm-up: First lap, driven slow, to identify turns (start, end, entry position, curvature) and learn the track model Other laps, speed adaptation: • Increasing according to lateral speed • Reducing when the car goes off-road2011 Simulated Car Racing Championship @ EVO*-2011
  22. 22. Powaah Tim Uusitalo Blekinge Institute of Technology Supervisor: Stefan Johanson2011 Simulated Car Racing Championship @ EVO*-2011
  23. 23. Powaah  Based on Artificial Potential Field  Every sensor in the span (-40, +40) has a charge  The charge is determined by how far the sensor measures the track  Coulomb’s law is used to calculate potentials in the field  Pot = (C1 * C2 ) / d2  The sensor with the highest potential is used for computing how much steering is needed2011 Simulated Car Racing Championship @ EVO*-2011
  24. 24. AUTOPIAIndustrial Computer Science Department.Centro de Automática y RobóticaConsejo Superior de Investigaciones CientíficasMadrid, SpainContact:E. Onieva (enrique.onieva@car.upm-csic.es)2011 Simulated Car Racing Championship @ EVO*-2011
  25. 25. AUTOPIA  Fuzzy Architecture based on three basic modules for gear, steering and speed control optimized with a genetic algorithm  Learning in the warm-up stage: Maintain a vector with as many real values as tracklength in meters. Vector initialized to 1.0 If the vehicle goes out of the track or suffers damage then multiply vector positions from 250 meters before the current position by 0.95.  During the race the vector is multiplied by F to make the driver more cautious in function of the damage: F=1-0.02*round(damage/1000)2011 Simulated Car Racing Championship @ EVO*-2011
  26. 26. COBOSTAR Thies Lönneker and Martin V. Butz University of Würzburg http://www.coboslab.psychologie.uni-wuerzburg.de2011 Simulated Car Racing Championship @ EVO*-2011
  27. 27. COBOSTAR  One of the best controller of the 2009 Championship  Parameterized controller optimized with CMA-ES  Dynamically saves crash points2011 Simulated Car Racing Championship @ EVO*-2011
  28. 28. CIG-2008 Champ Luigi Cardamone Politecnico di Milano2011 Simulated Car Racing Championship @ EVO*-2011
  29. 29. Luigi Cardamone  Winner of the CIG-2008 Car Simulated Competition  The controller is based on a neural network evolved with NEAT  Very simple policy for overtaking2011 Simulated Car Racing Championship @ EVO*-2011
  30. 30. Qualifying
  31. 31. Scoring process: Warm-up & Qualifying  Scoring process involves three tracks: OldPeak Polimi HillRoad  The tracks are not distributed with TORCS: Generated applying evolutionary computation The competitors cannot know the tracks  Each controller raced for 100000 game ticks in the warm-up stage and then its performance is computed in the qualifying stage as the distance covered within 10000 game ticks2011 Simulated Car Racing Championship @ EVO*-2011
  32. 32. Dirt-1OldPeak
  33. 33. Qualifying: OldPeak Autopia 8202,92 Cardamone 7372,23 Cobostar 6799,89 Mariscal&Fernan 5062,1 dez Mr. Racer 8159,67 Powaah 4606,09 Ready2Win 7441,21 0 1000 2000 3000 4000 5000 6000 7000 8000 90002011 Simulated Car Racing Championship @ EVO*-2011
  34. 34. Dirt-1Polimi
  35. 35. Qualifying: Polimi Autopia 8307,57 Cardamone 96,1469 Cobostar 6694,85 Mariscal&Fern 7775,64 andez Mr. Racer 8570,81 Powaah 3891,01 Ready2Win 6343,6 0 1000 2000 3000 4000 5000 6000 7000 8000 90002011 Simulated Car Racing Championship @ EVO*-2011
  36. 36. Dirt-1HillRoad
  37. 37. Qualifying: HillRoad Autopia 11088,4 Cardamone 8937,33 Cobostar 10006,7 Mariscal&Fern 10547,8 andez Mr. Racer 10250,3 Powaah 10075,3 Ready2Win 7528,29 0 2000 4000 6000 8000 10000 120002011 Simulated Car Racing Championship @ EVO*-2011
  38. 38. Qualifying summary Driver OldPeak Polimi HillRoad Total Autopia 10 8 10 28 Mr. Racer 8 10 6 24 Mariscal&Fernandez 3 6 8 17 Cobostar 4 5 4 13 Ready2Win 6 4 2 12 Cardamone 5 2 3 10 Powaah 2 3 5 102011 Simulated Car Racing Championship @ EVO*-2011
  39. 39. How much does noise affect the performance?2011 Simulated Car Racing Championship @ EVO*-2011
  40. 40. HillRoad with and without noise Autopia Cardamone Cobostar Mariscal&Fernandez Mr. Racer Powaah Ready2Win 0 2000 4000 6000 8000 10000 12000 NO-NOISY NOISY2011 Simulated Car Racing Championship @ EVO*-2011
  41. 41. The Race
  42. 42. 46 Three Tracks For each track we run 7 races with random starting grids Each race is scored using the F1 point system (10 to first, 8 to second, 6 to third, …) Two points to the controller with lesser damage Two points for the fastest lap of the race2011 Simulated Car Racing Championship @ EVO*-2011
  43. 43. Race: OldPeak Competitor Score Autopia 12 Mr. Racer 8 COBOSTAR 6 Cardamone 5 Ready2Win 5 Mariscal&Fer nandez 4 Powahh 22011 Simulated Car Racing Championship @ EVO*-2011
  44. 44. Race: Polimi Competitor Score Autopia 10 Mariscal&Fer nandez 8 Mr. Racer 8 COBOSTAR 7 Cardamone 4 Powahh 3 Ready2Win 32011 Simulated Car Racing Championship @ EVO*-2011
  45. 45. Race: HillRoad Competitor Score Autopia 12 Mariscal&Fer nandez 8 Mr. Racer 6 Powahh 5 COBOSTAR 4 Cardamone 3 Ready2Win 22011 Simulated Car Racing Championship @ EVO*-2011
  46. 46. Final Results Competitor OldPeak Polimi HillRoad Total Autopia 12 10 12 34 Mr. Racer 8 8 6 22 Mariscal&Fernandez 4 8 8 20 COBOSTAR 6 7 4 17 Cardamone 5 4 3 12 Powaah 2 3 5 10 Ready2Win 5 3 2 102011 Simulated Car Racing Championship @ EVO*-2011
  47. 47. What about the race results?Race and Qualifying have similar outcomes (with the exception of Ready2Win) AUTOPIA still very competitiveOpponent manegement is crucial on race start. Very difficult with noise!
  48. 48. Thank you!Looking forward to see yourcontrollers @ Gecco-2011

×