RoboCup Logo

The international RoboCup robot soccer competition entails the construction of fully autonomous robot soccer teams that compete with one another in a robotic soccer match. The robots are permitted to communicate via wireless transceivers to each other or to a global-decision-making computer. A global vision system (typically a video camera) may be used for global robot and ball position determination. Functionally, the robotscan be broken down into essentially three subsystems: electromechanical (the chassis, the drive unit, the passing unit, and the local sensors), communication (the wireless transceiver), and intelligence (a PC or microcontroller). The coordination of the robots is typically handled by a central computer, which has access to the global visual feed and which can communicate with each robot, but Cornell has distributed this to the robots as part of its commitment to research.

Cornell vs. Germany at RoboCup 2000 in Melbourne, Australia

The RoboCup is an excellent test bed for developing new tools and techniques for controlling autonomous systems in uncertain and dynamic environments. From an educational perspective, it is also a great means for exposing students to the systems engineering approach for designing, building, managing, and maintaining complex systems.

RoboCup-related research has typically been addressed in academia by computer scientists; in particular, by scholars in the field of artificial intelligence. We have shown, by winning the RoboCup championship in our first attempt in 1999, and by then defending our championship in 2000, 2002, and 2003, that dynamics and control are an integral component in the successful deployment of these types of systems. There is potentially a great synergy between computer scientists and control theoreticians when tackling the new problems in distributed and hierarchical control of autonomous systems. Our long-term research objectives include understanding how problems typically studied by computer scientists, such as artificial intelligence, distributed computation, and program verification, can complement control-related research and allow us to more effectively control complex, autonomous systems.

More information about the F-180 league (a.k.a. Small Size) can be found at the official F-180 league web site.