The document describes the 2010 Simulated Car Racing Championship competition held at three conferences. The competition involves 9 races across 3 tracks, with drivers developing controllers for the TORCS racing simulator. During qualifying, drivers are evaluated on their performance over 10000 game ticks on each track. The top drivers then advance to races on each track, where points are awarded based on finishing position. Descriptions are provided of the controllers developed by the competing teams, including techniques like neural networks, fuzzy logic, and imitation learning. Results are shown for qualifying performance on each track and points awarded for the races.
Car Setup Optimization Competition @ EvoStar 2010Daniele Loiacono
The contest involved three tracks. The optimization algorithm had to find the best car setup for each one of the tracks. The contest was divided into an optimization phase and an evaluation phase.
During the optimization phase, the optimization algorithm was applied to search for the best parameter setting. During the evaluation phase, the best solution was scored according to the distance covered in a fixed amount of game time.
A parameter setting is represented by a vector of real numbers. The competition software provides an API to evaluate a specific parameter setting on a track and returns the best lap time, the top speed, the distance raced, and the damage suffered. Through the API, it is possible to specify the amount of game ticks to use for evaluating a car setup. The game tics spent for an evaluation are subtracted from the total amount of game tics available. When the 1 millions of game ticks are exhausted or the evaluation process has taken up more than 2 hours of CPU time, no further evaluation will be possible.
Organizers
•Luigi Cardamone, Politecnico di Milano, Italy
•Daniele Loiacono, Politecnico di Milano, Italy
•Markus Kemmerling, TU Dortmund, Germany
•Mike Preuss, TU Dortmund, Germany
2012 Simulated Car Racing Championship @ GECCO-2012Daniele Loiacono
Second leg of the 2012 Simulated Car Racing Championship held during GECCO-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
Car Setup Optimization Competition @ EvoStar 2010Daniele Loiacono
The contest involved three tracks. The optimization algorithm had to find the best car setup for each one of the tracks. The contest was divided into an optimization phase and an evaluation phase.
During the optimization phase, the optimization algorithm was applied to search for the best parameter setting. During the evaluation phase, the best solution was scored according to the distance covered in a fixed amount of game time.
A parameter setting is represented by a vector of real numbers. The competition software provides an API to evaluate a specific parameter setting on a track and returns the best lap time, the top speed, the distance raced, and the damage suffered. Through the API, it is possible to specify the amount of game ticks to use for evaluating a car setup. The game tics spent for an evaluation are subtracted from the total amount of game tics available. When the 1 millions of game ticks are exhausted or the evaluation process has taken up more than 2 hours of CPU time, no further evaluation will be possible.
Organizers
•Luigi Cardamone, Politecnico di Milano, Italy
•Daniele Loiacono, Politecnico di Milano, Italy
•Markus Kemmerling, TU Dortmund, Germany
•Mike Preuss, TU Dortmund, Germany
2012 Simulated Car Racing Championship @ GECCO-2012Daniele Loiacono
Second leg of the 2012 Simulated Car Racing Championship held during GECCO-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
2011 Simulated Car Racing Championship @ GECCO-2011Daniele Loiacono
Summary f the second leg of the 2011 Simulated Car Racing Championship held during GECCO-2011
More information at
http://cig.dei.polimi.it
http://groups.google.com/group/racingcompetition
http://sourceforge.net/projects/cig/
Organizers
Daniele Loiacono, Politecnico di Milano
Luigi Cardamone, Politecnico di Milano
Martin Butz, University of Würzburg
Pier Luca Lanzi, Politecnico di Milano
2012 Simulated Car Racing Championship @ CIG-2012Daniele Loiacono
Third leg of the 2012 Simulated Car Racing Championship held during CIG-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
2012 Simulated Car Racing Championship @ Evo*-2012Daniele Loiacono
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
Simulated Car Racing Competition held during GECCO-2013
More information at
http://groups.google.com/group/racingcompetition
http://scr.geccocompetitions.com
Organizers
Daniele Loiacono, Politecnico di Milano
Pier Luca Lanzi, Politecnico di Milano
Abstract—In this paper, we overview the 2009 Simulated Car
Racing Championship—an event comprising three competitions
held in association with the 2009 IEEE Congress on Evolutionary
Computation (CEC), the 2009 ACM Genetic and Evolutionary
Computation Conference (GECCO), and the 2009 IEEE Sympo-
sium on Computational Intelligence and Games (CIG). First, we
describe the competition regulations and the software framework.
Then, the five best teams describe the methods of computational
intelligence they used to develop their drivers and the lessons they
learned from the participation in the championship. The orga-
nizers provide short summaries of the other competitors. Finally,
we summarize the championship results, followed by a discussion
about what the organizers learned about 1) the development of
high-performing car racing controllers and 2) the organization of
scientific competitions.
PartⅠ. Applicationdescription
The sharing-- electric scooter project is prevalent in NorthAmerica, Europe,
Southeast Asia and other countries and regions. The whole project mainly includes
three parts of operation system software, device and electric scooter, which will
solve the last one kilometer problemsindeed
Xpeng Motors' P7's self-driving roadmap and system design Junli Gu
Public presentation for nvidia gtc 2019. You can also refer to the public recorded video at: https://on-demand.gputechconf.com/gtc/2019/video/_/S91049/
A presentation given at the 2016 Traffic Safety Conference during Breakout Session 9: Motorcycle Safety. By Chiara Silvestri-Dobrovolny, Associate Research Scientist, Roadside Safety, Texas A&M Transportation Institute
Car electronization trend in automotive industryKenji Suzuki
As EV/HEV and other alternative powertrain gaining popularity, more and more electronics are adopted in a vehicle. Until recently, such electronics were supplied mainly by "conventional" tier1s and tier2s in the industry. However, the increase in electronics used in a vehicle is opening up the door for consumer electronics manufacturers to join.
What does it mean in terms of reliability and durability of a vehicle. What needs to be done for reliability and durability assessment.
The 2014 Mitsubishi Outlander Sport is now available at Gary Lang Mitsubishi in McHenry, IL. The Outlander Sport has been a very popular SUV at Gary Lang. Contact us for more information.
Results of the GPUs for GEC Competition held at GECCO 2013.
Organizers
Daniele Loiacono, Politecnico di Milano
Antonino Tumeo, Pacific Northwest National Laboratory
Webpage
http://gpu.geccocompetitions.com
2011 Simulated Car Racing Championship @ GECCO-2011Daniele Loiacono
Summary f the second leg of the 2011 Simulated Car Racing Championship held during GECCO-2011
More information at
http://cig.dei.polimi.it
http://groups.google.com/group/racingcompetition
http://sourceforge.net/projects/cig/
Organizers
Daniele Loiacono, Politecnico di Milano
Luigi Cardamone, Politecnico di Milano
Martin Butz, University of Würzburg
Pier Luca Lanzi, Politecnico di Milano
2012 Simulated Car Racing Championship @ CIG-2012Daniele Loiacono
Third leg of the 2012 Simulated Car Racing Championship held during CIG-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
2012 Simulated Car Racing Championship @ Evo*-2012Daniele Loiacono
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
Simulated Car Racing Competition held during GECCO-2013
More information at
http://groups.google.com/group/racingcompetition
http://scr.geccocompetitions.com
Organizers
Daniele Loiacono, Politecnico di Milano
Pier Luca Lanzi, Politecnico di Milano
Abstract—In this paper, we overview the 2009 Simulated Car
Racing Championship—an event comprising three competitions
held in association with the 2009 IEEE Congress on Evolutionary
Computation (CEC), the 2009 ACM Genetic and Evolutionary
Computation Conference (GECCO), and the 2009 IEEE Sympo-
sium on Computational Intelligence and Games (CIG). First, we
describe the competition regulations and the software framework.
Then, the five best teams describe the methods of computational
intelligence they used to develop their drivers and the lessons they
learned from the participation in the championship. The orga-
nizers provide short summaries of the other competitors. Finally,
we summarize the championship results, followed by a discussion
about what the organizers learned about 1) the development of
high-performing car racing controllers and 2) the organization of
scientific competitions.
PartⅠ. Applicationdescription
The sharing-- electric scooter project is prevalent in NorthAmerica, Europe,
Southeast Asia and other countries and regions. The whole project mainly includes
three parts of operation system software, device and electric scooter, which will
solve the last one kilometer problemsindeed
Xpeng Motors' P7's self-driving roadmap and system design Junli Gu
Public presentation for nvidia gtc 2019. You can also refer to the public recorded video at: https://on-demand.gputechconf.com/gtc/2019/video/_/S91049/
A presentation given at the 2016 Traffic Safety Conference during Breakout Session 9: Motorcycle Safety. By Chiara Silvestri-Dobrovolny, Associate Research Scientist, Roadside Safety, Texas A&M Transportation Institute
Car electronization trend in automotive industryKenji Suzuki
As EV/HEV and other alternative powertrain gaining popularity, more and more electronics are adopted in a vehicle. Until recently, such electronics were supplied mainly by "conventional" tier1s and tier2s in the industry. However, the increase in electronics used in a vehicle is opening up the door for consumer electronics manufacturers to join.
What does it mean in terms of reliability and durability of a vehicle. What needs to be done for reliability and durability assessment.
The 2014 Mitsubishi Outlander Sport is now available at Gary Lang Mitsubishi in McHenry, IL. The Outlander Sport has been a very popular SUV at Gary Lang. Contact us for more information.
Results of the GPUs for GEC Competition held at GECCO 2013.
Organizers
Daniele Loiacono, Politecnico di Milano
Antonino Tumeo, Pacific Northwest National Laboratory
Webpage
http://gpu.geccocompetitions.com
Random Artificial Incorporation of Noise in a Learning Classifier System Envi...Daniele Loiacono
Ryan J. Urbanowicz, Nicholas A. Sinnott-Armstrong, Jason H. Moore. "Random Artificial Incorporation of Noise in a Learning Classifier System Environment", IWLCS, 2011
Summary of the Car Racing Competition held at the 2008 IEEE World Congress on Computational Intelligence, organized by Daniele Loiacono, Julian Togelius, Pier Luca Lanzi
More information available at http://cig.dei.polimi.it
Results of the Car Racing Competition held at the 2008 IEEE World Congress on Computational Intelligence, organized by Daniele Loiacono, Julian Togelius, Pier Luca Lanzi
More information available at http://cig.dei.polimi.it
Evolving Neural Networks Through Augmenting Topologies
2010 Simulated Car Racing Championship @ CIG-2010
1. The 2010 Simulated Car Racing
Championship @ CIG-2010
Daniele Loiacono, Luigi Cardamone,
Martin V. Butz, and Pier Luca Lanzi
2010 Simulated Car Racing Championship @ CIG-2010
2. 2
2010 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
2010 Simulated Car Racing Championship @ CIG-2010
3. The 2010 Simulated Car Racing Championship
CIG-2010
Copenhagen, August 18–21
Dusty Leg
GECCO-2010 Winner: ???
Portland , July 7-11
American Leg
Winner: Autopia
WCCI-2010
Barcelona, July 18-23
Formula Leg
Winner: Jorge Muñoz
2010 Simulated Car Racing Championship @ CIG-2010
4. 4
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
2010 Simulated Car Racing Championship @ CIG-2010
5. What’s new?
If everything seems under control, you're not going fast enough
— Mario Andretti
Warm-up stage
Before qualifying stage, competitors have 100000 game
ticks to race on the track
Allows track learning and optimization of parameters
Noisy sensors
Track sensors and opponent sensors are affected by a
Gaussian noise (standard deviation equal to 10% of the
readings)
Extended sensor model
Focus sensors
Z position and speed
Direction of track sensors fully customizable
Added clutch control and focus command
2010 Simulated Car Racing Championship @ CIG-2010
7. 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
2010 Simulated Car Racing Championship @ CIG-2010
8. 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
2010 Simulated Car Racing Championship @ CIG-2010
9. Sensors and actuators
Rangefinders for edges on the track and opponents
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
2010 Simulated Car Racing Championship @ CIG-2010
11. The competitors
Five entries in the second leg
AUTOPIA, Madrid and Granada
J. Muñoz, Carlos III University of Madrid
S.Pohl, J. Quadflieg and T. Delbrügger, TU Dortmund
Joseph Alton, University of Birmingham
Timothy Alford (Xiaodong Li), RMIT University, Melbourne
Neil Clarke, University of Birmingham
Two more entries from the 2009 championship
COBOSTAR (T. Lönneker & M.V. Butz, University of
Würzburg)
POLIMI (Cardamone, Politecnico di Milano)
2010 Simulated Car Racing Championship @ CIG-2010
12. 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)
2010 Simulated Car Racing Championship @ CIG-2010
13. 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)
2010 Simulated Car Racing Championship @ CIG-2010
14. Mr Racer
Susanna Pohl, Jan Quadflieg and Tim Delbrügger
TU Dortmund
2010 Simulated Car Racing Championship @ CIG-2010
15. Mr. Racer
Save the model after warm-up, use it during
qualifying and the race
The track model is built using a classifier
Use the model to derive a plan consisting of
target speeds and a racing line
Unfortunately the noisy completely
breaks the classifier
2010 Simulated Car Racing Championship @ CIG-2010
16. Jorge Muñoz
Department of Computer Science
Carlos III University of Madrid
2010 Simulated Car Racing Championship @ CIG-2010
17. Jorge Muñoz
Build a model of the track during the warm-up stage.
Two neural networks to predict the trajectory using the track
model. Two neural networks to predict the target speed
given the model of the track and the current car position
The four neural networks are trained with backpropagation
using data retrieved from a human player
Learning during the warm-up:
The car remember where it goes out of the car or drives
far form the trajectory and in the next laps goes slower in
those points
The car remember where it follows the trajectory perfectly
and tries to go faster in the next laps.
2010 Simulated Car Racing Championship @ CIG-2010
18. Joseph Alton
Joseph Alton
2010 Simulated Car Racing Championship @ CIG-2010
19. Joseph Alton
Scripted controller
During warm-up the controller drives with a fixed speed of
60 km/h
During this time for each segment (meter) of the track, the
turns are recorded and mapped to a speed.
The speeds are as follows:
Type Value Speed ( km/h)
Sharp turn > Absolute 0.1 60
Turn > Absolute 0.05 100
Straight 200
Noise filtering is done through having multiple sensors at the
same position
2010 Simulated Car Racing Championship @ CIG-2010
20. Timothy Alford (supervised by Xiaodong Li)
RMIT University, Melbourne, Victoria
2010 Simulated Car Racing Championship @ CIG-2010
21. Tim Alford
All components of the car are controlled by Fuzzy Logic
(excluding gears and recovery )
Recovery, Gears are controlled with simple rules
GA is exploited in the Warm-up
Fuzzy system
Action object
Y
Gears
Sensors on track
?
N Action object
Recovery
2010 Simulated Car Racing Championship @ CIG-2010
22. Timothy Alford (supervised by Xiaodong Li)
Neil Clarke
RMIT University, Melbourne, Victoria
University of Birmingham
2010 Simulated Car Racing Championship @ CIG-2010
23. Neil Clarke
Controller based on a Feed Forward Multi Layer Neural
Network
Imitation Leaning
Trained using the human data provided by the author
Very simple policy for the opponents
2010 Simulated Car Racing Championship @ CIG-2010
24. COBOSTAR
Thies Lönneker and Martin V. Butz
University of Würzburg
http://www.coboslab.psychologie.uni-wuerzburg.de
2010 Simulated Car Racing Championship @ CIG-2010
25. COBOSTAR
One of the best controller of the 2009 Championship
Parameterized controller optimized with CMA-ES
Dynamically saves crash points
2010 Simulated Car Racing Championship @ CIG-2010
26. CIG-2008 Champ
Luigi Cardamone
Politecnico di Milano
2010 Simulated Car Racing Championship @ CIG-2010
27. 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 overtaking
2010 Simulated Car Racing Championship @ CIG-2010
29. Scoring process: Warm-up Qualifying
Scoring process involves three dirt tracks:
Dirt-1
Olethros-Dirt
Rocky
Only the track Dirt-1 is provided with TORCS distribution:
Olethros-Dirt was created adding the sand to the original
track Olethros
Rocky is an evolved track
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
2010 Simulated Car Racing Championship @ CIG-2010
35. Qualifying: Rocky
Timothy Alford 1971,52
Neil Clarke 2261,45
MR. Racer 2736,39
COBOSTAR 6409,76
Cardamone 5881,37
Joseph Alton 0
Jorge Muñoz 4437,02
Autopia 6177,81
0 1000 2000 3000 4000 5000 6000 7000
2010 Simulated Car Racing Championship @ CIG-2010
36. Qualifying summary
Dirt-1 Olethros-dirt Rocky Total
Autopia
10 10 8 28
Cardamone
5 8 10 23
COBOSTAR
6 6 6 18
Neil
8 2 3 13
Mr. Racer
4 3 5 12
Tim
3 4 4 11
Jorge Muñoz
1 5 2 8
Joseph Alton*
2 1 1 4
Joseph Alton was disqualified from the race as crashes in 2 over 3 tracks
2010 Simulated Car Racing Championship @ CIG-2010
37. What about qualifying?
AUTOPIA is the fastest driver
Also, Cardamone (a very old driver ) did very well
For some drivers noise seems to affect significantly the
performance
However, some controllers are able to reach almost the same
performance even with noise
38. How much does noise affect the
performance?
2010 Simulated Car Racing Championship @ CIG-2010
39. Dirt-1 with and without noise
1707,26
Timothy Alford
2291,56
6204,14
Neil Clarke
5696,28
5097,69
MR. Racer
4168,25
5380,04
COBOSTAR
5218,73
5404,24
Cardamone
5340,37
2666,12
Joseph Alton
2665,89
4966,6
Jorge Muñoz
4851,54
6201,71
Autopia
6125,74
0 1000 2000 3000 4000 5000 6000 7000
NO-NOISY NOISY
2010 Simulated Car Racing Championship @ CIG-2010
41. 43
Three Tracks
For each track we run 7 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
2010 Simulated Car Racing Championship @ CIG-2010
42. Race: Dirt-1
Competitor Score
Cardamone 10
Autopia 8
COBOSTAR 8
Neil 7
Jorge Muñoz 4
Tim 4
Mr. Racer 3
2010 Simulated Car Racing Championship @ CIG-2010
43. Race: Olethros-dirt
Competitor Score
Autopia
12
COBOSTAR
8
Cardamone
6
Tim
6
Neil
5
Mr. Racer
4
Jorge Muñoz
2
2010 Simulated Car Racing Championship @ CIG-2010
44. Race: Rocky
Competitor Score
COBOSTAR
8
Cardamone
8
Mr. Racer
8
Jorge Muñoz
6
Autopia
5
Neil
4
Tim
3
2010 Simulated Car Racing Championship @ CIG-2010
45. Final Results
Competitor Dirt-1 Ole-Dirt Rocky Total
Autopia 8 12 5 25
Cardamone 10 6 8 24
COBOSTAR 8 8 8 24
Neil 7 5 4 16
Mr. Racer 3 4 8 15
Tim 4 6 3 13
Jorge Muñoz 4 2 6 12
2010 Simulated Car Racing Championship @ CIG-2010
46. Final Standings
Competitor GECCO WCCI CIG Total
AUTOPIA 34 24 25 83
COBOSTAR 14 28 24 66
Jorge Muñoz 22.5 28 12 62.5
Cardamone 16 16 24 56
Mr. Racer 16 9 15 40
Joseph Alton 15.5 11 - 26.5
Tim Alford - 10 13 23
Neil Clarke - - 16 16
2010 Simulated Car Racing Championship @ CIG-2010
47. Final Standings
Competitor GECCO WCCI CIG Total
AUTOPIA 34 24 25 83
COBOSTAR 14 28 24 66
Jorge Muñoz 22.5 28 12 62.5
Cardamone 16 16 24 56
Mr. Racer 16 9 15 40
Joseph Alton 15.5 11 - 26.5
Tim Alford - 10 13 23
Neil Clarke - - 16 16
2010 Simulated Car Racing Championship @ CIG-2010
48. The 2010 Simulated Car Racing Championship
CIG-2010
Copenhagen, August 18–21
Dusty Leg
GECCO-2010 Winner: Autopia
Portland , July 7-11
American Leg
Winner: Autopia
WCCI-2010
Barcelona, July 18-23
Formula Leg
Winner: Jorge Muñoz
2010 Simulated Car Racing Championship @ CIG-2010
50. Analysis of results
Competitor GECCO WCCI CIG
AUTOPIA 34 24 25
COBOSTAR 14 28 24
Jorge Muñoz 22.5 28 12
Cardamone 16 16 24
Mr. Racer 16 9 15
Joseph Alton 15.5 11 -
Tim Alford - 10 13
Neil Clarke - - 16
2010 Simulated Car Racing Championship @ CIG-2010
51. Analysis of results
GECCO WCCI CIG
1
2
3 AUTOPIA
COBOSTAR
4 Jorge Muñoz
Cardamone
5
Mr. Racer
6
7
8
2010 Simulated Car Racing Championship @ CIG-2010
52. What about new challenges?
Noisy sensors
Addressed by almost all the competitors
For most of the approaches is critical only for opponent
management
Still an open problem
Warm-up stage
Addressed by almost all the competitors
Simple on-line adaptation (e.g., list of crash points
implemented in COBOSTAR) still very competitive
We expect big improvements in this task in the future
Custom Rangefinders Setup and Clutch Control
2010 Simulated Car Racing Championship @ CIG-2010
53. Conclusions
Car Racing Community
Overall 6 competitors entered the competition (last year
we got 11 entries)
Almost the same authors in the first positions
New competitors enter for a while and leave
Do not be scared
The source of entries will be available on-line
A lot of opportunities to improve the current controllers
2010 Simulated Car Racing Championship @ CIG-2010