Visual Robot Detection in RoboCup Using Neural Networks

Robot recognition is a very important point for further improvements in game-play in RoboCup middle size league. In this paper we present a neural recognition method we developed to find robots using different visual information. Two algorithms are introduced to detect possible robot areas in an image and a subsequent recognition method with two combined multi-layer perceptrons is used to classify this areas regarding different features. The presented results indicate a very good overall performance of this approach.

[1]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[2]  Günther Palm,et al.  Object Classification Using Simple, Colour Based Visual Attention and a Hierarchical Neural Network for Neuro-symbolic Integration , 1999, KI.

[3]  Günther Palm,et al.  Object classification with simple visual attention and a hierarchical neural network for subsymbolic-symbolic coupling , 1999, Proceedings 1999 IEEE International Symposium on Computational Intelligence in Robotics and Automation. CIRA'99 (Cat. No.99EX375).

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

[5]  Jurjen Caarls,et al.  Fast and Accurate Robot Vision for Vision Based Motion , 2000, RoboCup.

[6]  Vahab S. Mirrokni,et al.  A Fast Vision System for Middle Size Robots in RoboCup , 2001, RoboCup.

[7]  Michael Beetz,et al.  Watch their moves: applying probabilistic multiple object tracking to autonomous robot soccer , 2002, AAAI/IAAI.

[8]  Michael Beetz,et al.  Toward RoboCup without Color Labeling , 2002, AI Mag..

[9]  Hans Utz,et al.  Improving Vision-Based Self-localization , 2002, RoboCup.

[10]  Javier Ruiz-del-Solar,et al.  Evolving Visual Object Recognition for Legged Robots , 2003, RoboCup.

[11]  Michael Beetz,et al.  Toward RoboCup without color labeling , 2003 .

[12]  Hans Utz,et al.  Playing Robot Soccer under Natural Light: A Case Study , 2003, RoboCup.

[13]  Andreas Zell,et al.  Real-time object tracking for soccer-robots without color information , 2004, Robotics Auton. Syst..