Design and Validation of Action Chain Search during Free Kick in RoboCup2D Simulation

The usefulness of artificial intelligence has been recognized in fields such as Go and Shogi. However, it is impossible to apply the knowledge gained there to real-world problems. If we can apply artificial intelligence to real-world problems, the potential of artificial intelligence will be further expanded. Therefore, in order to set up a real-world problem, we used the “RoboCup Soccer Simulation 2D League” as the subject of our experiment, aiming to improve team performance through artificial intelligence. The experiment was conducted using fuzzy inference methods and genetic algorithms. The same methods have been used in past experiments, but in this paper, we further added improvements to the fuzzy inference method and verified its usefulness and other features compared to those designed in past experiments.