Driving-Bots with a Neuroevolved BrainScreaming Racers

  1. Pujol López, Mar
  2. Rizo Aldeguer, Ramón
  3. Gallego, Francisco
  4. Llorens Largo, Faraón
Revue:
Inteligencia artificial: Revista Iberoamericana de Inteligencia Artificial

ISSN: 1137-3601 1988-3064

Année de publication: 2005

Titre de la publication: Nuevas tendencias en Sistemas Multiagente y Soft Computing

Volumen: 9

Número: 28

Pages: 9-16

Type: Article

D'autres publications dans: Inteligencia artificial: Revista Iberoamericana de Inteligencia Artificial

Résumé

The Videogame Industry of today is now just as strong as, and generates similar revenues to the Film Industry. Computer Games are distributed throughout the world and are sold to millions of people. Of the many different types of games, one of the most popular genres is car racing. Developers of this type of game are increasingly improving their Artificial Intelligence Systems so that their virtual drivers can exhibit Human-Level behaviours, and even higher. In this paper we show how these virtual drivers can be generically evolved using Neuroevolution, so obtaining several, distinct driving-bots with an increasing level of performance. These driving-bots can then be used as virtual opponents for different racing games, saving time and money in the development of a realistic AI System. To train our driving-bots and to test their performance we have developed Screaming Racers, a simple car-racing online videogame.