RoboCup
Introduction
The Robot World Cup Initiative (RoboCup) is an attempt to foster AI and intelligent robotics research by providing a standard problem in which a wide range of technologies can be integrated and examined. RoboCup's ultimate goal is to develop a team of fully autonomous humanoid robots that can beat the human world champion soccer team. In order to realize this goal several competitions have been set up which all focus on different aspects of the overall problem. One of these competitions is the Simulation League which concentrates mainly on RoboCup aspects at a high level of abstraction such as team strategy and learning capabilities.
UvA Trilearn
UvA Trilearn was initially built for a graduation project of two students, Jelle Kok and Remco de Boer, in the fields of Computer Science and Artificial Intelligence (resulting master's thesis can be found here. This team (UvA Trilearn 2001) has participated in the German Open 2001 in Paderborn and in the World Championship 2001 in Seattle (USA). After graduation, Remco de Boer decided to leave the University. Jelle Kok stayed as a PhD-student at the Intelligent Autonomous Systems Group (IAS) of the University of Amsterdam and continued the work on UvA Trilearn together with his supervisor Nikos Vlassis. This resulted in UvA Trilearn 2002 that participated at the German Open 2002 and was able to win this Championship. During the RoboCup-2002 competition UvA Trilearn again just failed to reach the podium and again became fourth. UvA Trilearn 2003, however, participated in three tournaments (German Open, American Open and RoboCup-2003) and won all three of them!
The information about UvA Trilearn has been sorted by year:
- UvA Trilearn 2001 (5th German Open, 4th RoboCup-2001)
- UvA Trilearn 2002 (Champion German Open, 4th RoboCup-2002)
- UvA Trilearn 2003 (Champion German Open, American Open and RoboCup-2003)
- UvA Trilearn 2004 (Champion German Open, 7th RoboCup-2004)
- UvA Trilearn 2005 (10th RoboCup-2005)