RoboCup Small Size League: Design of Group IDs and Algorithm for Posture Parameters

In the RoboCup small size league soccer vision system, butterfly IDs are the most frequently used ID design and currently all the posture information of robots in the teams is obtained by calculating the region’s center of the IDs. This paper describes how we calculate the robot posture information taking into account the region’s area, position and length-width ratio. Besides, Gauss’function-based object filtration functions are also designed to filter disturbances. Our experiment shows that parameters of this solution, with their simple setting, helps increase the calculation precision of the robot position and posture and provides high resistance to disturbance.

[1]  Tucker Balch.  Realtime Machine Vision Perception and Prediction , .

[2]  Manuela M. Veloso,et al.  Fast and accurate vision-based pattern detection and identification , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[3]  Manuela M. Veloso,et al.  Fast and inexpensive color image segmentation for interactive robots , 2000, Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113).

[4]  Manuela Veloso,et al.  CMDragons 2009 Team Description , 2009 .