The goal of the international RoboCup initiative is to develop a team of humanoid robots that is able to win against the official human World Soccer Champion team until 2050. In some sense the RoboCup challenge is the successor of the chess challenge for artificial intelligence (a computer beating the human World Chess Champion) that was solved in 1997 when Deep Blue won against Garry Kasparow. Currently, there exist a number of different RoboCup soccer leagues that focus on different aspects of this challenge. The Humanoid League is one of the most dynamically progressing leagues and the one closest to the 2050 goal.
About the Humanoid League
In the Humanoid League, autonomous robots with a human-like body plan and human-like senses play soccer against each other. Unlike humanoid robots outside the Humanoid League the task of perception and world modeling is not simplified by using non-human like range sensors. In addition to soccer competitions technical challenges take place. Dynamic walking, running, and kicking the ball while maintaining balance, visual perception of the ball, other players, and the field, self-localization, and team play are among the many research issues investigated in the Humanoid League. Several of the best autonomous humanoid robots in the world compete in the RoboCup Humanoid League.
Robot Soccer Competitions
The robots are divided into three size classes: KidSize (40-90cm height), TeenSize (80-140cm) and AdultSize (130-180cm). In the KidSize soccer competition teams of four, highly dynamic autonomous robots compete with each other. Since 2010 the TeenSize soccer competition features teams of two autonomous robots competing with each other. In AdultSize soccer, a striker robot plays against a goal keeper robot first and then the same robots play with exchanged roles against each other. For details on the games, refer to the rules.