A group of computer engineering students at BYU spent this past semester creating a robotic, computer-controlled foosball table with the goal of beating a human foosball player.
Turns out their project was a success. The software they created tracks the ball from a camera placed above the table, and the computer then controls the rods where the plastic players are attached. It anticipates, kicks and even scores.
Only problem? The artificial intelligence is a little too good.
“It’s becoming a challenge for us to beat the artificial intelligence,” said Nathan Warner, one of six students who created the robot foosball. “You think, ‘Oh yeah, humans ultimately should always be better than the computer,’ but we’re actually struggling to keep up.”
Mentored by electrical and computer engineering professor D.J. Lee, the undergraduate students tried to mimic how humans play the game and then programmed those ideas into their code. They coded the computer to predict movement and adapt in real time the same way human brains do almost instantly.
“Students learned how you can control machines to achieve the tasks that humans can do,” Lee said. “But, in this case, it actually reacts a lot faster than humans…