Aug 12 2016
EPFL students have developed a robot that is capable of competing against human players with average skills in table football.
The next step is to organize a competition among the robots after programming them with some strategy.
All brawn, little brains: EPFL students’ table-football robot
Video Credit: EPFL/Youtube.com
The bigger question here is will humans be able to win a game of table football against the robots designed by student from EPFL? This questioned arises as some people have found it more difficult than expected.
The robot is able to beat the players with average skill set using an uncomplicated strategy. What is the secret behind this success? Shooting power and speed.
The robot was primarily developed to serve as a research platform for Bachelor’s and Master’s students. Now it has reached a significant stage in development.
For years the robot which has been under development in the Automatic Control Laboratory, and now it is more accurate, quicker and more powerful.
Much More Efficient Industrial Motors
The robot was fixed with new agile and powerful “arms”. They operate with high dynamic linear motors, similar to the type found in manufacturing.
They can quickly position the player on the field and then perform a rotational movement using another motor to shoot. The robot can move quicker than a human as the motors are precise to less than a millimetre and can produce 9 g in acceleration.
The robot also has exceptional vision. A high-speed camera placed beneath the game’s transparent floor captures the ball’s movement. The camera gathers 300 images per second, which is later processed by a computer.
Léo Sibut, a Master’s student, worked on data acquisition and actuator control for six months.
I learned a lot about image processing, which is a field I didn’t know very well.
Léo Sibut, Masters Student, EPFL
His efforts enhanced the robot’s reliability and precision.
Plenty of Brawn but Just a Little Brain!
At the moment, the system is capable of detecting the ball, stopping it and then shooting it towards the goal. “It’s a very basic strategy, but it works surprisingly well,” said Christophe Salzmann, the scientist in charge of the project.
However, he thinks it is too simple.
At this stage, the system is like a bodybuilder with a tiny brain. But in addition to being strong, we want the robot to be able to fake out the opponent, steer clear of the opponent, and predict the ball’s path and the opponent’s position.
Christophe Salzmann, Scientist, EPFL
The students have started working on these improvements by installing lasers that can detect the position of the opponents’ handles. This is what the robot needs to be able to apply a real strategy.
Competing Software
Meanwhile, Salzmann is planning to conduct a table football competition among the robots. Participants will have to program some strategy into the software and then have the robots square off.