XIMEA and the Swiss Federal Institute of Technology use high speed cameras to discover the winner when it comes to the ultimate challenge between humans and robots – table foosball!
Professors and students at the Swiss Federal Institute of Technology in Lausanne are developing a robotic player installed into a foosball table that can be more accurate, faster, and strategic than any other human player.
The idea is to replace a human player by a system able to sense the position of the ball on the table, evaluate a strategy to score, and command the player controls with precision motors to execute this strategy. The latest performance improvement to vision and strategy deals with the ability of the robot to keep the position of the ball under control, made possible by the implementation of a XIMEA xiQ high-speed camera.
The camera, positioned under the table and runs at 500 frames per second (fps), creates a solid basis for detection of the ball in real time. At its current state of development, the foosball table robot is be able to beat any regular player it encounters.
The Automatic Control Baby-foot project is one of several projects at EPFL (École polytechnique fédérale de Lausanne). People of all ages are fascinated by the concept and implementation every time it is on display, thanks to the ingenious way the lab worked to bring an old game to the 21st century. This is an opportunity to improve the student’s required skills in multiple subjects and to realise a complete and multidisciplinary project for engineers interested in robotics and automation at a high level.
EPFL student and professor playing against the foosball table
At first glance, the foosball table located in the middle of the Automatic Control Laboratory looks perfectly normal. However, looks can be deceiving. One of the levers has a mechanical arm capable of propelling the ball into the opposing goal at a speed of six meters per second. “This is already enough to beat the average player,” said researcher Christophe Salzmann, who heads the project. And this is only the beginning.
Among many disciplines, this project requires knowledge of mechanics, analogue and digital electronics, programming, and disciplines. The current idea is to replace a human player by a system able to sense the position of the ball on the foosball table, evaluate a strategy to score and command the levers to execute this strategy.
The complete automatisation of the rotation arm needs to be improved to implement complex computations during the game. That is, not only defensive strategies but also attacking and early evaluation of the counterparty’s moves as one of the project’s goals.
The overall goal is to provide the automatic laboratory with a concrete, effective, functioning demonstration system of both software and hardware assemblies.
Continue reading article…