jellekok.nl

UvA Trilearn 2005 - Soccer Simulation Team

Objectives

robocup

UvA Trilearn is the RoboCup Soccer Simulation team from the Intelligent Autonomous Systems Group (IAS) of the University of Amsterdam. This team participates since 2001 in the RoboCup competition with as main success the world champion title in RoboCup-2003.

In our current work, UvA Trilearn 2005, we are especially interested in specifying further the coordination between the different agents using approximate alternatives for variable elimination in coordination graphs and apply this model for teammate coordination.

Research Group Members

drs. J.R. Kok (jellekok@science.uva.nl) - Research and Implementation
dr. N. Vlassis - Research Coordinator
Prof. dr. ir. F.C.A. Groen (groen@science.uva.nl) - Team Coordinator

Funding

University of Amsterdam (UvA), Faculty of Science
Intelligent Autonomous Systems Group
Kruislaan 403, 1098 SJ Amsterdam, The Netherlands

Publications

  • Using the Max-Plus Algorithm for Multiagent Decision Making in Coordination Graphs (RoboCup Symposium 2005), Best Scientific Paper Award: Kok05robocup.pdf.
  • Team Description UvA Trilearn 2005 (Proceedings CD RoboCup 2005 Symposium). Kok05robocupTeam.pdf.

Competitions

RoboCup-2005: Osaka

We participated in the RoboCup-2005 World Championship in Osaka and became 10th (of 17 qualified teams) in this competition.

Results:
Round 1 Opponent Score
Round 1 Brainstormers (Germany) 1-4
  NUBOT (China) 4-4
  RoboSina (Iran) 1-1
Round 2 Brainstormers (Germany) 0-4
  Oxsy (Romenia) 2-4
  STEP04 (Russia) 3-1
  SEU_T (China) 6-0
  Apollo (China) 2-4
  Aria (Iran) 1-0
  ZJUBase (China) 1-1
9th/10th place NUBOT (China) 5-6
    26-29

All the results can be found here. The binary used in this competition can be downloaded here.