2012 Simulated Car Racing Championship @ Evo*-2012
Upcoming SlideShare
Loading in...5
×
 

2012 Simulated Car Racing Championship @ Evo*-2012

on

  • 836 views

First leg of the 2012 Simulated Car Racing Championship held during Evo*-2012 ...

First leg of the 2012 Simulated Car Racing Championship held during Evo*-2012

More information at
http://games.ws.dei.polimi.it/competitions/scr/
http://groups.google.com/group/racingcompetition
http://www.geccocompetitions.com

Organizers
Daniele Loiacono, Politecnico di Milano
Luigi Cardamone, Politecnico di Milano
Pier Luca Lanzi, Politecnico di Milano

Statistics

Views

Total Views
836
Views on SlideShare
809
Embed Views
27

Actions

Likes
0
Downloads
6
Comments
0

1 Embed 27

http://games.ws.dei.polimi.it 27

Accessibility

Categories

Upload Details

Uploaded via as Adobe PDF

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment

2012 Simulated Car Racing Championship @ Evo*-2012 2012 Simulated Car Racing Championship @ Evo*-2012 Presentation Transcript

  • The 2012 Simulated Car Racing Championship @ Evo*-2012 Daniele Loiacono, Luigi Cardamone, and Pier Luca Lanzi2012 Simulated Car Racing Championship @ evo*-2012
  • 2012 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 championship2012 Simulated Car Racing Championship @ evo*-2012
  • Roadmap of the 2012 Championship 1. EVO*-2012, Malaga (Spain) April 11-13, 2012 2. ACM GECCO-2012, Philadelphia (US) July 7-11, 2012 3. IEEE CIG-2012, Granada (Spain) September 11-14, 20122012 Simulated Car Racing Championship @ evo*-2012
  • 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 sensors2012 Simulated Car Racing Championship @ evo*-2012
  • The Open RacingCar Simulator
  • 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 BOT2012 Simulated Car Racing Championship @ evo*-2012
  • 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 direction2012 Simulated Car Racing Championship @ evo*-2012
  • 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 together2012 Simulated Car Racing Championship @ evo*-2012
  • Competitors
  • The competitors  A single entry in this first leg: Mr. Racer, TU Dortmund  Three reference entries (selected from the top entries of the past championship) : Mariscal & Fernández, Málaga University Ready2Win, Slovak University of Technology – FIIT AUTOPIA, Madrid and Granada2012 Simulated Car Racing Championship @ evo*-2012
  • Mr RacerJan Quadflieg, Tim Delbruegger and Mike PreussTU Dortmund2012 Simulated Car Racing Championship @ evo*-2012
  • Mr. Racer 2012  Joined effort of Jan Quadflieg, Tim Delbruegger and Mike Preuss  Variables learned offline with the CMA-ES, now including optimized settings for recovery , the clutch and…  NEW: Parameters of the opponent handling module have been optimized  Optimization of the opponent handling will hopefuly result in a CIG competition paper2012 Simulated Car Racing Championship @ evo*-2012
  • Noise Handling1. Low pass filter on sensor values2. 2 Regression polynoms are fitted to each side3. Resample the polygons4. Calculate our measure (see CIG paper 2010)5. Low pass filter on the last measurements2012 Simulated Car Racing Championship @ evo*-2012
  • Online Learning during Warmup  We learn a model of the racetrack  One of two parameter sets is chosen  Target speeds for all corners are then fine tuned  All information is saved at the end of the warmup  And later used during qualifying and the race2012 Simulated Car Racing Championship @ evo*-2012
  • 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 plan2012 Simulated Car Racing Championship @ evo*-2012
  • 2012 Simulated Car Racing Championship @ evo*-2012
  • Mariscal & Fernández  General approach: expert systems improved by multi- objectives evolutionary computation techniques Maximize distance. Minimize damage  Steering based on a simple rule follow the track sensor with biggest distance.  Overtaking based on simple rules and expert systems2012 Simulated Car Racing Championship @ evo*-2012
  • 2012 Simulated Car Racing Championship @ evo*-2012
  • 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-road2012 Simulated Car Racing Championship @ evo*-2012
  • AUTOPIAIndustrial Computer Science Department.Centro de Automática y RobóticaConsejo Superior de Investigaciones CientíficasMadrid, SpainContact:E. Onieva (enrique.onieva@car.upm-csic.es)2012 Simulated Car Racing Championship @ evo*-2012
  • 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)2012 Simulated Car Racing Championship @ evo*-2012
  • Qualifying
  • Scoring process: Warm-up & Qualifying  Scoring process involves three tracks: Kerang (desert track) Mueda (city track) Zvolenovice (mountain track)  The tracks are not distributed with TORCS: Generated using the Interactive Track Generator for TORCS and Speed Dreams available at: • http://trackgen.pierlucalanzi.net 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 ticks2012 Simulated Car Racing Championship @ evo*-2012
  • Dirt-1Kerang
  • Qualifying: Kerang NO-NOISY Ready2Win NOISY Mr. Racer Mariscal & Fernandez AUTOPIA 0 5000 10000 150002012 Simulated Car Racing Championship @ evo*-2012
  • Dirt-1Mueda
  • Qualifying: Mueda Ready2Win NO-NOISY NOISY Mr. Racer Mariscal & Fernandez AUTOPIA 0 2000 4000 6000 8000 10000 120002012 Simulated Car Racing Championship @ evo*-2012
  • Dirt-1Zvolenovice
  • Qualifying: Zvolenovice NO-NOISY Ready2Win NOISY Mr. Racer Mariscal & Fernandez AUTOPIA 6000 6500 7000 7500 8000 8500 90002012 Simulated Car Racing Championship @ evo*-2012
  • Qualifying summary (scores with noise) Driver Kerang Mueda Zvolenovice Total AUTOPIA 10 10 6 26 Mr. Racer 6 8 10 24 Ready2Win 8 5 8 21 Mariscal & Fernandez 5 6 5 162012 Simulated Car Racing Championship @ evo*-2012
  • Qualifying summary (scores with noise) Driver Kerang Mueda Zvolenovice Total AUTOPIA 10 10 6 26 Mr. Racer 6 8 10 24 Ready2Win 8 5 8 21 Mariscal & Fernandez 5 6 5 16 Evolutionary Approaches2012 Simulated Car Racing Championship @ evo*-2012
  • What about the qualifying results? AUTOPIA still the fastest controller… …but Mr. Racer is now very close Almost all the controllers deal very well with noise2012 Simulated Car Racing Championship @ evo*-2012
  • Races
  • Three Tracks For each track we run 4 races with different 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 race2012 Simulated Car Racing Championship @ evo*-2012
  • Final Results Competitor Kerang Mueda Zvolenovice Total AUTOPIA 13 13 13 39 Mariscal & Fernandez 7 7 6 20 Ready2Win 6 5 8 19 Mr. Racer 5 6 5.5 16.5 Next leg @ GECCO-2012 in Philadelphia2012 Simulated Car Racing Championship @ evo*-2012
  • What about the race results?Qualifying and final results are very differentSome drivers were not able to complete the race (even if only 4 cars are on track) Further analysis will be performed to have more insight on these results!
  • Thank you!SCR ContactsOfficial Webpagehttp://games.ws.dei.polimi.it/competitions/scr/Emailscr2012@sigevolution.orgGoogle Grouphttp://groups.google.com/group/racingcompetition