Ace the Ping-Pong Robot Can Whup Your Ass
This feat represents a milestone for the world of robotics, a field that has long regarded this sport, among the most technical in the world, as one of the most difficult tests of technological advances.
Robot Player
We have already seen artificial intelligence systems win virtual competitions in games such as chess, Go, and even StarCraft II, but physical games are much more difficult to master. A robot needs to sense unpredictable changes in the external environment, interpret their meaning, decide how to react, and then perform the necessary action, all in a very short time.
That is precisely what Ace, a very complex robot composed of three main parts, has managed to do. It is equipped with a perception system that allows it to detect the rotation of the ball, which can change its bounce and trajectory in the air, and an artificial intelligence system that can make decisions in real time. Finally, it has high-speed robotic hardware: an eight-jointed, extremely agile robotic arm that can make precise and quick decisions about where and how to place the racket.
To put Ace to the test, the researchers had the robot compete with five high-level amateur players, resulting in three wins out of five matches. Against two professional players from the Japanese league, Minami Ando and Kakeru Sone, however, Ace's skills weren't as effective, winning only one out of seven matches. Subsequent analysis of Ace's matches showed that the robot gained points not so much by hitting harder, but by its control ability, successfully repelling 75 percent of the balls.
“This research has shown that an autonomous robot can actually win in a sports competition, equaling or exceeding the reaction time and decisionmaking ability of humans in a physical space,” says Peter Dürr, director of Sony AI and project leader on Ace, in a press release.
Beyond Table Tennis
Ace's performance represents a breakthrough in the field of robotics. It is a system that combines high-speed sensing, artificial intelligence for decisionmaking, and robotic control to compete with human players in real-world conditions, making extremely fast reactions in real time.
“Table tennis is a game of enormous complexity that requires split-second decisions as well as speed and power,” Dürr adds. Robots like Ace could offer a way to learn new techniques and skills to improve player performance in many other fields.
“This breakthrough is much more important than table tennis,” says Peter Stone, chief scientific officer for artificial intelligence at Sony, in the same release. "It represents a pivotal moment in AI research, demonstrating for the first time that an AI system can perceive, reason, and act effectively in complex and rapidly changing real-world environments that require accuracy and speed. Once AI is able to operate at a level equal to that of a human expert, it will pave the way for a whole new class of real-world applications that were previously unattainable."
