Evolving a fuzzy controller for a Car Racing Competition

Abstract

Computational intelligence competitions have recently gained a lot of interest. These contests motivate and encourage researchers to participate on them, and to apply their work areas to specific games. During the last two years, one of the most popular competitions held on computational intelligence in games conferences is the car racing competition. This competition combines the fun of driving to win and the challenge of obtaining autonomous driving, which is known as a very difficult problem and faced by a lot of researches from different perspectives. For this competition, we have developed a controller with fuzzy rules and fuzzy sets for input and output, which were evolved using a genetic algorithm in order to optimise lap times, damage taken and out of track time. The design of this controller is explained in detail in this article, as well as the results obtained at the end of the contest.