Multi-objective evolution for Car Setup Optimization

Author

Muñoz, Jorge ; Gutierrez, German ; Sanchis, Araceli

Author_Institution

Comput. Sci. Dept., Univ. Carlos III de Madrid, Leganés, Spain

fYear

2010

fDate

8-10 Sept. 2010

Firstpage

1

Lastpage

5

Abstract

This paper describes the winner algorithm of the Car Setup Optimization Competition that took place in EvoStar (2010). The aim of this competition is to create an optimization algorithm to fine tune the parameters of a car in the The Open Racing Car Simulator (TORCS) video game. There were five participants of the competition plus the two algorithms presented by the organizers (that do not take part in the competition). Our algorithm is a Multi-Objective Evolutionary Algorithm (MOEA) based on the Non-Dominated Sorting Genetic Algorithm (NSGAII) adapted to the constraints of the competition, that focus its fitness function in the lap time. Our results are also compared with other evolutionary algorithms and with the results of the other competition participants.

Keywords

computer games; genetic algorithms; EvoStar; TORCS; The Open Racing Car Simulator; car setup optimization; multi-objective evolutionary algorithm; non-dominated sorting genetic algorithm; video game; winner algorithm; Equations; Evolutionary computation; Games; Immune system; Mathematical model; Optimization; Software algorithms;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence (UKCI), 2010 UK Workshop on

Conference_Location

Colchester

Print_ISBN

978-1-4244-8774-5

Electronic_ISBN

978-1-4244-8773-8

Type

conf

DOI

10.1109/UKCI.2010.5625607

Filename

5625607