Car Setup Optimization Using Multi-Objective Swarm Algorithms
March 26, 2011

Marcos Oliveira, Marcelo Lacerda, Érick Barbosa, Paulo Cordeiro, and Carmelo Bastos-Filho

Abstract

In this paper, we propose to use two multi-objective swarm optimization algorithms, called MOPSO-CDR and MOABC, to tackle the car setup optimization problem. We aim to find the best set of parameters for the car in order to improve its performance during the races. We used The Open Racing Car Simulator (TORCS) in our simulations and we compared our results to the ones presented in the 2010 Car Setup Optimization Competition. We demonstrated that the MOABC can achieve similar results when compared to the state-of-art algorithms. The MOPSO-CDR outperformed all the previous approaches, including the MOABC algorithm for this problem

Anais do X Congresso Brasileiro de Inteligência Computacional, Fortaleza, Brazil. 2011.

[Download preprint here]
[Link to publication]