Abstract—This paper presents an overview of our 3D soccer simulation robot . This paper describes the software design of the 3D soccer simulation robot systems of the ADRO Team in 2010. We have tried to focus on areas such as software architected, robot perception unit, robot controller, robot AI and behavior learning. This year, our developments for the 3D soccer simulation include: (1) the design and construction of our new Robot Artificial Intelligent (AI) Architected (2) the design and construction of a new software controller to be used in our robots. The project is described in two main parts: Software and Robot AI. The software is developed a robot application which consists walking controller, autonomous motion robot, self localization base on vision and AI part consist of Local AI and Global AI, Trajectory Planning, Motion Controller. The. Each agent is able to walk, fast walk, pass, kick and dribble when it catches the ball. The project is still in progress and some new interesting methods are described in the current report.

Index Terms—3D Soccer Simulation, Recurrent Neural Networks, Control systems, Robocup.

The authors are with Young Researchers Club, Isfahan Branch, Islamic Azad University, Isfahan, Iran.

Cite: S.Hamidreza Mohades Kasaei, S.Mohammadreza Mohades Kasaei and S.Alireza Mohades Kasaei, "Development an Omni Directional Walking Based on Neural Network for Biped Robot," International Journal of Computer and Electrical Engineering vol. 3, no. 5, pp. 624-628, 2011.