期刊名称：Brain. Broad Research in Artificial Intelligence and Neuroscience
印刷版ISSN：2067-3957
出版年度：2010
卷号：1
期号：3
页码：5-18
语种：English
出版社：EduSoft publishing
摘要：Robocup is an international competition for multi agent research and related subject like: Artificial intelligence, Image processing, machine learning, robot path planning, control, and obstacle avoidance. In a soccer robot game, the environment is highly competitive and dynamic. In order to work in the dynamically changing environment, the decision-making system of a soccer robot system should have the features of flexibility and real-time adaptation. In this paper we will focus on the Middle Size Soccer Robot league (MSL) and new hierarchical hybrid fuzzy methods for decision making and action selection of a robot in Middle Size Soccer Robot league (MSL) are presented. First, the behaviors of an agent are introduced, implemented and classified in two layers, the Low_Level_Behaviors and the High_Level_Behaviors. In the second layer, a two phase mechanism for decision making is introduced. In phase one, some useful methods are implemented which check the robot’s situation for performing required behaviors. In the next phase, the team strategy, team formation, robot’s role and the robot’s positioning system are introduced. A fuzzy logical approach is employed to recognize the team strategy and further more to tell the player the best position to move. We believe that a Dynamic role engine is necessary for a successful team. Dynamic role engine and formation control during offensive or defensive play, help us to prevent collision avoidance among own players when attacking the ball and obstacle avoidance of the opponents. At last, we comprised our implemented algorithm in the Robocup 2007 and 2008 and results showed the efficiency of the introduced methodology. The results are satisfactory which has already been successfully implemented in ADRO RoboCup team. This project is still in progress and some new interesting methods are described in the current report.
