1 / 15

RACE CAR STRATEGY OPTIMISATION UNDER SIMULATION

RACE CAR STRATEGY OPTIMISATION UNDER SIMULATION. Naveen Chaudhary Shashank Sharma. Objective. Computation of optimal racing line given a track Design a controller for traversing a car on this optimal racing line found. Motivation.

helen
Download Presentation

RACE CAR STRATEGY OPTIMISATION UNDER SIMULATION

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. RACE CAR STRATEGY OPTIMISATION UNDER SIMULATION Naveen Chaudhary Shashank Sharma

  2. Objective • Computation of optimal racing line given a track • Design a controller for traversing a car on this optimal racing line found

  3. Motivation • Traditional methods require large amount of computational resources and are impractical for fast pace and real time games. • Problem demands a more efficient and fast solution • Enthusiast in computer games.

  4. Determination of optimal path • Track represented as a set of connected polygons • Waypoints are defined on the connected edges • Sharp turns avoided • Three consecutive points should not bend too much towards different directions

  5. Track representation Track represented as connected polygons [5]

  6. Choice of direction along the width Probability density along width of track [6]

  7. Choice of points Sharp turns to be avoided [6]

  8. How to select the path? • Set the starting point 0 • For each point i chose the point i+1 • Run many times and compare • Best energy and best time path are selected • Energy Consumption • Where, K is the curvature of the path s

  9. Forward looking algorithm Linear approximation of probability density function [6]

  10. Design of controller to drive on optimal path found • ANN implementation • Inputs- • Current speed of the car • Angle of the car with the axis • Current gear • Lateral speed of the car • R.P.M of the wheels • Current position on the track • Outputs- • Accelerate / brake value • Gear change • Steering

  11. Cost function for ANN • Distance from optimal racing line • Difference between current speed and max possible speed at that point

  12. Platform • TORCS (The Open Racing Car Simulator) • http://www.torcs.sourceforge.net/

  13. References [1] Jung-Ying Wang and Yong-Bin Lin, “Game AI: Simulating Car Racing Game by Applying PathfindingAlgorithms”, International Journal of Machine Learning and Computing, Vol 2, No.1, Feb 12. [2] J. Togelius and Simon M. Lucas, “Evolving Controllers for Simulated Car Racing”, Proceedings of the congress on evolutionary computation, 2005, pp. 1906-1913. [3] C. H. Tan , J. H. Ang , K. C. Tan and A. Tay "Online adaptive controller for simulated car racing", Proc. IEEE Congr. Evol. Comput., pp.2239 -2245 2008. [4] L. Cardamone , D. Loiacono and P. L. Lanzi "On-line neuroevolution applied to the open racing car simulator", Proc. IEEE Congr. Evol. Comput., pp.2622 -2629 2009. [5] L. Cardamone, D. Loiacono, P.L. Lanzi, and A.P. Bardelli, “Searching for the optimal racing line using genetic algorithms”, In Computational Intelligence and Games (CIG), 2010 IEEE Symposium on, pages 388-394, aug. 2010. [6] Y. Xiong, “Race Line Optimization” thesis submitted to MIT, September 2010.

  14. Questions??

  15. Thank You

More Related