Robots playing to win: evolutionary soccer strategies
Arvin Agah, Kazuo Tanie · 2002
Automatic development and learning of robot soccer strategies are presented in this paper. It is shown that using a novel control system, it is possible to allow teams of robots to acquire strategies for playing a better game of soccer through successive generations, utilizing simulated evolution. A number of soccer techniques, as developed through robot games, are discussed. The mechanism presented in the paper is suitable for other tasks requiring multiple robots to interact and cooperate in teams.