Sony's 'Ace' Robot Makes History by Defeating Elite Human Table Tennis Players

Kathmandu. A major breakthrough has been achieved in the field of Artificial Intelligence (AI) and robotics. A robot named 'Ace', developed by the AI research division of the Japanese company Sony, has set a new record by defeating high-level human players in table tennis.

It has become the world's first robot to perform at an expert level in a physical sport that requires rapid decision-making and precise strikes. According to a study published in the journal 'Nature', 'Ace' utilizes high-speed perception, AI-based control, and state-of-the-art robotic systems.

While AI has long surpassed humans in computer games, the high-speed physical nature of table tennis presented a significant challenge. According to Peter Durr, director of Sony AI Zurich and project lead, the robot has succeeded in operating within the limits of human reaction time required for table tennis.

The robot's performance is highly impressive. It is equipped with nine synchronized cameras and three vision systems, which can track a spinning ball more clearly and quickly than the human eye.

The robot's arm features eight joints, providing full control over the racket's position, direction, and swing speed. In matches held in April 2025, 'Ace' won three out of five games against elite-level players. By December 2025 and last month, it even succeeded in defeating professional players.

Professional player Mayuka Taira, who was defeated by 'Ace', stated that the robot's greatest strengths are its 'unpredictable style' and 'lack of emotion'. 'Because its reactions are unreadable, it is impossible to know what kind of shot it dislikes or struggles with,' she said.

Another player, Rui Takenaka, noted that while the robot could easily return complex spin shots, it showed some weaknesses against straight or simple serves.

According to project lead Durr, 'Ace' possesses an extraordinary ability to read ball spin and has a rapid reaction time. Because it learned to play by training itself in simulations rather than by observing humans, its shots are remarkably surprising.