Español English Contacte con nosotros http://www.uc3m.es/portal/page/portal/biblioteca
DSpace e-Archivo

Archivo Abierto Institucional de la Universidad Carlos III de Madrid > Investigación > Departamentos > Departamento de Informática > Grupo de Control, Aprendizaje y Optimización de Sistemas (CAOS) > DI - CAOS - Comunicaciones en Congresos y otros eventos >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10016/10179

Google™ Scholar. Others By: Muñoz, Jorge - Gutiérrez, Germán - Sanchis, Araceli
Files in This Item:
human_munoz_2010_ps.pdf258,94 kBAdobe PDFformato pdf
Title: A human-like TORCS controller for the Simulated Car Racing Championship
Author(s): Muñoz, Jorge
Gutiérrez, Germán
Sanchis, Araceli
Publisher: IEEE
Issued date: 2010
Citation: 2010 IEEE Symposium on Computational Intelligence and Games (CIG). IEEE, 2010, pp. 473-480.
URI: http://hdl.handle.net/10016/10179
ISBN: 978-1-4244-6296-4 (Online)
978-1-4244-6295-7 (Print)
DOI: http://dx.doi.org/10.1109/ITW.2010.5593318
Description: Proceeding of: IEEE Congres on Computational Intelligence and Games (CIG'10), Copenhagen (Denmark), 18-21, August, 2010.
Abstract: This paper presents a controller for the 2010 Simulated Car Racing Championship. The idea is not to create the fastest controller but a human-like controller. In order to achieve this, first we have created a process to build a model of the tracks while the car is running and then we used several neural networks which predict the trajectory the car should follow and the target speed. A scripted policy is used for the gear change and to follow the predicted trajectory with the predicted speed. The neural networks are trained with data retrieved from a human player, and are evaluated in a new track. The results shows an acceptable performance of the controller in unknown tracks, more than 20% slower than the human in the same tracks because of the mistakes made when the controller tries to follow the trajectory.
Sponsor: This work was supported in part by the University Carlos III of Madrid under grant PIF UC3M01-0809 and by the Ministry of Science and Innovation under project TRA2007- 67374-C02-02.
Publisher version: http://dx.doi.org/10.1109/ITW.2010.5593318
Keywords: Data retrieval
Human like TORCS controller
Human player
Neural network
Scripted policy
Simulated car racing championship
Speed prediction
The open racing car simulator
Trajectory prediction
Rights: © IEEE
Appears in Collections:DI - CAOS - Capítulos de Monografías
DI - CAOS - Comunicaciones en Congresos y otros eventos

Refworks Export

SFX Query

Items in E-Archivo are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0! © Universidad Carlos III de Madrid - Software DSpace - Terms of use - Feedback