Robot learned to play table tennis in 90 minutes Researchers ran a
simulation so the artificial intelligence could learn how the speed and orientation of the racket affected the trajectory of the ball.
After the algorithm was able to hit balls in
more situations, the scientists set it up to
control the arm movement of a real robot near the table.
The system used
two cameras to track the location of the ball every
7 milliseconds. The algorithm processed the signals and decided where to move the robotic arm to hit the ball.