Skip to main content
See every side of every news story
Published loading...Updated

Sony AI Robot Ace Beats Elite Ping-Pong Players

Ace used reinforcement learning and high-speed sensors to beat elite players and challenge professionals, showing how adaptive robots can handle fast real-world competition.

  • On Wednesday, April 22, 2026, researchers published a study in Nature detailing how Sony AI's robot, Ace, achieved "expert-level play in a commonly played competitive sport in the physical world."
  • Between April 2025 and December 2025, Sony scientists refined Ace's performance, enabling the robot to beat both elite players and professional Japanese league players Minami Ando and Kakeru Sone.
  • Using high-speed cameras and proprietary reinforcement learning, Ace identifies the ball's 3D position, scoring 16 unchallenged "aces" and maintaining a 75% serve return rate.
  • Peter Dürr, director of Sony AI in Zurich, noted that table tennis requires "split-second decisions," highlighting potential for physical AI agents in complex, real-time interactive tasks.
  • "This breakthrough is much bigger than table tennis," said Stone, chief scientist at Sony AI, as the field has advanced rapidly since Google DeepMind's robot was defeated two years ago.
Insights by Ground AI

60 Articles

Lean Left

Robots can beat the "human" half-marathon world record, boxing and now defying table tennis professionals: this is what Sony announced in a research published on Thursday.

·Montreal, Canada
Read Full Article
Lean Right

72 revolutions per second, speed up to 70 km/h – the robot "Ace" plays table tennis at the top level in lightning speed and precision. Impressive videos prove the progress. One point, however, makes experts skeptical.

·Dortmund, Germany
Read Full Article
Right

A new artificial intelligence robot takes on and beats professional ping pong players, paving the way for adaptive robotics in the physical world

Read Full Article
Think freely.Subscribe and get full access to Ground NewsSubscriptions start at $9.99/yearSubscribe

Bias Distribution

  • 41% of the sources are Center
41% Center

Factuality Info Icon

To view factuality data please Upgrade to Premium

Ownership

Info Icon

To view ownership data please Upgrade to Vantage

letsdatascience.com broke the news on Tuesday, April 21, 2026.
Too Big Arrow Icon
Sources are mostly out of (0)

Similar News Topics

News
Feed Dots Icon
For You
Search Icon
Search
Blindspot LogoBlindspotLocal