A paddle-wielding robot built by Sony AI has done something that researchers have been working toward for decades: it has beaten professional human athletes at their own game, in a real physical environment, under official rules. The achievement, detailed in a paper published in the journal Nature on April 22, 2026, marks what Sony calls 'the first time a robot has achieved human, expert-level play in a commonly played competitive sport in the physical world.'

The robot, named Ace, is a custom-built robotic arm with eight degrees of freedom. It is equipped with nine cameras positioned around the court, giving it a 360-degree view of the playing surface and the ability to track the ball's spin. The system operates at 200Hz — fast enough to respond to shots that arrive in fractions of a second.

Learning to Play from Experience

Ace learned to play table tennis using reinforcement learning. 'There's no way to program a robot by hand to play table tennis. You have to learn how to play from experience,' said Sony AI researcher Peter Dürr, co-author of the Nature paper. Sony built an Olympic-sized table tennis court at its Tokyo headquarters to give professional athletes a level playing field with the robot.

Japanese professional players Minami Ando and Kakeru Sone were among those who competed against Ace. Two umpires from the Japanese Table Tennis Association judged the games. After submitting the paper to peer review, Sony researchers kept experimenting — Ace accelerated its shot speeds and played more aggressively. Competing against four high-skill players, Ace defeated all but one of them in December 2025.

One expert player, Kinjiro Nakamura — who competed in the 1992 Barcelona Olympics — observed Ace play a shot and remarked: 'No one else would have been able to do that. I didn't think it was possible. But the robot now having done it means that there is a possibility that a human could do it too.' Michael Spranger, president of Sony AI, noted that the technology could play a significant role in manufacturing and other industries requiring high-speed adaptive physical manipulation.