1. TORCS WORKS
Jang Su-Hyung

2. Social Network Base Code by Berniw Rule GA Controller by Diego Prerez
Stuck
Speed limit
Distance
Accelerator
Rule GA Controller by Diego Prerez
Input Data
Base Individual
Rule GA Individual
Evolving a Fast Controller for TORCS Using NEAT by Luigi Cardamone
NEAT
Sensors and Controllers
Controller Design
Social network define our relationship to others in society. such connections help us define social context,
which in turn affects the roles we embody
The roles that we play and the social networks that develop around them help us define
our individual identity.

3. Stuck

4. Stuck

5. Stuck

6. Stuck

7. Stuck

8. About Speed Limit

9. About Speed Limit

10. Distance

11. Accelerator

12. Input Data 1
Angle
- to
Discretization to range: [0,4]

13. Input Data 2
Track Position
-1 to 1
Discretization to range: [0,1]

14. Input Data 3
Speed
0 to …(km/h)
Discretization to range: [0,3]

15. Input Data 4 Track 19 sensors, from 0 to 100
Discretization to range: [0,3]
If any < 20 :1
If any < 100 : 0
Else : 2

16. Base Individual 1 First approach Angle : [0.4] Track Position : [0,1]
Speed : [0,3]
Track : [0,2]
Each Rule :
Steering : [-1.1]
Acceleration : [0,1]
Gear bound
3000 rpm
6000 rpm

17. Base Individual 2 First approach Second approach
Evolve a GA maximizing the distance raced
TORCS did not behave in a stable way
Second approach
Find the rule set that allows the vehicle to end a lap, centered on the track.
Minimize angle to track axis.

18. Rule GA Individual
Rules from base individual compose the GA individual.
N rules, depending on base individual.
Including left (conditions) and right (actions) sides.

19. Rule GA Step Create a new rule by genetic operators.
Substitute the new one for the most similar in the individual.
If fitness decreases, new rule stays. If not, recover the previous one.
combination of lap time (40%) and damage (60%).

20. Sensors and effectors

21. NeuroEvolution selection cross over mutation Input Hidden Output1
selection
mutation
cross over
population A B C D
Fitness
evaluation
Search
space
reproduction
Chromosome

22. NEAT(encoding)
NeuroEvoloution of Augmenting Topologies

23. NEAT(mutation)

24. NEAT(crossover)

25. rtNEAT

26. Sensors and effectors The following sensors were used:
Track sensors at -90°,-60°,-30°,+30°,+60°,+90°
Frontal sensor: max reading among the frontal track
sensors at -10°,0°,10°
Car speed
The network controls
Steering wheel
Gas/Brake pedals

27. Controller design
To avoid wasting time with fast but slower controller, we set gas pedal to 1 (the max value) when the car is on a straight
In addition, the neural controller does not deal with gear shifting and the scripted policy provided is used instead
We also used a very simple scripted policy to avoid at least the opponents that are “close and in front” of the bot

28. Evaluation of Controllers
The fitness is computed on an entire lap as
Where Tout is the number of game tics the bot was outside the track
Savg is the average speed
D is the distance raced
As soon as a Tout becomes greater than 500 game tics, the evaluation is immediately stopped

29. An example of behaviors evolved

30. Hacked controller Simon M. Lucas Based on SimpleSoloController
Java
Low recover ability
Over accelerate
Target Speed
Normal : 100 km/h
Safety mode : 50 km/h

31. Hacked controller Change Target Speed Track Position Limit TrackFac
Normal : 250 km/h
Safety : 167 km/h
Track Position Limit
0.3 -> 0.15
More effort to stay close to the centerline of the track
TrackFac
0.38
Steering angle : > 0.005
Reduce the risk of skidding
Manually chosen parameter

33. Homework 1 TORCS 지능형 드라이버 Bot 만들기 바이너리 파일(dll) Source Code 테스트 결과
Presentation 자료
4월 13일 자정까지

34. Question