An Improved Fuzzy Mechanism for 3D Soccer Simulation Agent's Shoot Skill

Abstract

RoboSoccer simulation is a complex multi-agent system in which agents play the role of soccer players and the main goal is to have a perfect domain for research and investigation on artificial intelligence. This paper intends to propose a new scoring module to select the best point on the goal line to shoot, considering player's position, catching and shooting time difference, and distance to target. Two different approaches have been implemented for this purpose. The first one is a simple decision making policy and the latter one takes advantage of statistical measurement and fuzzy decision making. Results show the superiority of the proposed method performance in over our previous work implemented on Nexus 3D RoboSuccer team of Ferdowsi University