2012 Simulated Car Racing Championship @ Evo*-2012

The 2012 Simulated Car Racing
Championship @ Evo*-2012
Daniele Loiacono, Luigi Cardamone, and Pier Luca Lanzi

2012 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 championship


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, 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 sensors


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 BOT


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
direction

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 together


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 Granada


Mr Racer

Jan Quadflieg, Tim Delbruegger and Mike Preuss
TU Dortmund


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 paper


Noise Handling

1. Low pass filter on sensor
values
2. 2 Regression polynoms are
fitted to each side
3. Resample the polygons
4. Calculate our measure (see
CIG paper 2010)
5. Low pass filter on the last
measurements


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 race


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


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
systems


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-road


AUTOPIA

Industrial Computer Science Department.
Centro de Automática y Robótica
Consejo Superior de Investigaciones Científicas
Madrid, Spain
Contact:E. Onieva (enrique.onieva@car.upm-csic.es)

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)


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 ticks


Qualifying: Kerang

NO-NOISY
Ready2Win NOISY

Mr. Racer

Mariscal &
Fernandez

AUTOPIA

0 5000 10000 15000


Qualifying: Mueda

Ready2Win NO-NOISY
NOISY

Mr. Racer

Mariscal &
Fernandez

AUTOPIA

0 2000 4000 6000 8000 10000 12000


Qualifying: Zvolenovice

NO-NOISY
Ready2Win NOISY

Mr. Racer

Mariscal &
Fernandez

AUTOPIA

6000 6500 7000 7500 8000 8500 9000


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


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

Evolutionary Approaches


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 noise


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 race


Final Results

Competitor Kerang Mueda Zvolenovice Total
AUTOPIA 13 13 13 39
Ready2Win 6 5 8 19
Mr. Racer 5 6 5.5 16.5

Next leg @ GECCO-2012 in Philadelphia


What about the race results?

Qualifying and final results are very different

Some 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 Contacts

Official Webpage
http://games.ws.dei.polimi.it/competitions/scr/

Email
scr2012@sigevolution.org

Google Group
http://groups.google.com/group/racingcompetition

2012 Simulated Car Racing Championship @ Evo*-2012

Empfohlen

Empfohlen

Weitere ähnliche Inhalte

Ähnlich wie 2012 Simulated Car Racing Championship @ Evo*-2012

Ähnlich wie 2012 Simulated Car Racing Championship @ Evo*-2012 (20)

Mehr von Daniele Loiacono

Mehr von Daniele Loiacono (20)

Kürzlich hochgeladen

Kürzlich hochgeladen (20)

2012 Simulated Car Racing Championship @ Evo*-2012