Predicting away the Delay

This paper describes a method to reduce the eects of the system immanent delay for the RoboCup small size league. It explains how we solved the task by predicting the movement of our robots using a neural network. We have successfully eld-tested the system at several RoboCup compe- titions with our FU-Fighters team. The predictions improve speed and accuracy of play.

[1]  Sven Behnke,et al.  FU-Fighters 2001 (Global Vision) , 2001, RoboCup.

[2]  Sven Behnke,et al.  Using Hierarchical Dynamical Systems to Control Reactive Behavior , 1999, RoboCup.

[3]  Raúl Rojas,et al.  Neural Networks - A Systematic Introduction , 1996 .

[4]  O. J. M. Smith,et al.  A controller to overcome dead time , 1959 .

[5]  Hiroaki Kitano,et al.  RoboCup-98: Robot Soccer World Cup II , 2001, Lecture Notes in Computer Science.

[6]  Manuela M. Veloso,et al.  CMUNITED-98: RoboCup-98 Small-Robot World Champion Team , 2000, AI Mag..

[7]  Brett Browning,et al.  Improbability filtering for rejecting false positives , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[8]  Sven Behnke,et al.  Robust Real Time Color Tracking , 2000, RoboCup.

[9]  D. Wolpert,et al.  Is the cerebellum a smith predictor? , 1993, Journal of motor behavior.