论文信息 - Research on action select strategy of robot soccer based on Petri net and position prediction

Research on action select strategy of robot soccer based on Petri net and position prediction

This paper proposes a robot soccer action select strategy based on Petri net and position prediction. It predicts the positions of robots and the ball according to information of newly-generated frames from the vision system. Then the paper proposes a model of action select strategy of goalkeeper based on the results of data preprocess. The method is modeled, analyzed and simulated by Petri net and the properties of boundness, safety and reversibility are proved to show the correctness of the model. The framework of realization of the system is also given and it has been tested by program. The results show the practicability and validity of the method.

Bo Huang | Nan Xu | Yuwang Yang | Lina Yan

[1] Rajesh Elara Mohan,et al. Validating extended neglect tolerance model for human robot interactions in humanoid soccer robots , 2011, Robotica.

[2] Hans Utz,et al. Implicit Coordination with Shared Belief: A Heterogeneous Robot Soccer Team Case Study , 2010, Adv. Robotics.

[3] Pedro U. Lima,et al. Petri Net Plans , 2011, Autonomous Agents and Multi-Agent Systems.

[4] Yang Yi-min,et al. A self-localization method with monocular vision for autonomous soccer robot , 2005, 2005 IEEE International Conference on Industrial Technology.

[5] L. Iocchi,et al. Petri Net Plans A Framework for Collaboration and Coordination in Multi-Robot Systems , 2013 .

[6] Daniele Nardi,et al. Policy gradient learning for quadruped soccer robots , 2010, Robotics Auton. Syst..

[7] Wu Boying,et al. Study and Application of Reinforcement Learning in Cooperative Strategy of the Robot Soccer Based on BDI Model , 2009 .

[8] Jong-Hwan Kim,et al. Evolutionary multi-objective optimization in robot soccer system for education , 2009, IEEE Computational Intelligence Magazine.