Two cameras are mounted on each side of the robot to help it identify the ping-pong balls, which is identical to the way a human would see an object in a 3D space. Omron claims the machine can detect the ball’s speed and rotation up to 80 times per second, which allows it to predict the ball’s trajectory. There’s another camera in the middle, which tracks the player’s movements to evaluate their skill level. Analyzing the trajectory of the ball in relation to the player using machine learning, the AI can judge its opponent’s abilities and adjust its own playing level to match it.
Forpheus flashes encouraging messages on an LED screen on the table net, which earned it the Guinness World Record title of being the “first robot table tennis tutor.”
Finished the Expert Level? Build the robot which plays the table tennis!! Learn about the servo motors and code them!!