Robotic Soccer Simulation

RoboCup is an international research initiative intending to expedite AI and intelligent robotics research by defining a set of standard problems where various technologies can and ought to be combined solving them. Annually, there are championship tournaments in several leagues - ranging from rescue tasks over real soccer-playing robots to simulated ones.

The term "Soccer Simulation" refers to those of RoboCup's sub-leagues where soccer is played without real robots, but with simulated soccer-playing software agents instead. In the 2D Simulation League two teams of soccer-playing agents, each consisting of eleven players plus a coach agent, compete against one another using the Soccer Server, a real-time soccer simulation system.The 2D league is the league with the longest history within the RoboCup federation, and it is the one where the rules of real-life soccer are imitated to the largest degree possible. Furthermore, the fact that the development of a soccer simulation team involves no hardware development and maintenance, resulted in the fact that learning and AI-based ideas are comparatively easy to implement. Hence, the 2D league is also the league, in the scope of which most machine learning approaches were implemented by the participating teams.

Soccer Server

The Soccer Server allows autonomous software agents written in an arbitrary programming language to play soccer in a client/server-based style: The server simulates the playing field, communication, the environment and its dynamics, while the clients - eleven agents per team - are permitted to send their intended actions (e.g. a parameterised kick or dash command) once per simulation cycle to the server via UDP. Then, the server takes all agents' actions into account, computes the subsequent world state and provides all agents with (partial) information about their environment via appropriate messages over UDP. The course of action during a match can be visualised using an additional program, the Soccer Monitor.

You may visit the RoboCup Homepage for further details on robotic soccer and RoboCup. If you are interested in finding out, what progress has been made in RoboCup throughout the previous years, you might follow this link or watch the YouTube video below.

Soccer Simulation Team FRA-UNIted

The robotic soccer team FRA-UNIted is a team participating in the 2D Simulation League of the RoboCup competition. FRA-UNIted is a continuation of the Brainstormers project whose research and development had recently been done by the Machine Learning Lab at the University of Freiburg, Germany, maintained by team leader Thomas Gabel and team founder Martin Riedmiller, and which has moved to Frankfurt University of Applied Sciences in 2015.

Key facts:

  • founded in 1998
  • three times world champion: 2005, 2007, and 2008
  • six consecutive European-level titles: 2005 through 2010
  • research focus: use of artificial intelligence-based and reinforcement learning approaches to the largest degree possible
  • more than 20 publications on the use of machine learning techniques in the context of robotic soccer
Video Highlights

Selected Publications