Meet Ace, the table-tennis robot that can beat elite players
Nature Podcast
podcast@nature.com
4.5 • 893 Ratings
🗓️ 22 April 2026
⏱️ 26 minutes
🧾️ Download transcript
Summary
In this episode:
00:45 The table-tennis robot that can mix it with the pros
Research Article: Dürr et al.
News and Views: Robot can beat elite players at table tennis
Video: This robot can beat you at table tennis
14:13 Research Highlights
Nature: Venus’s impenetrable haze could be made of cosmic dust
Nature: Graves reveal plague’s inequitable toll
16:21 Why physicists can’t agree on the strength of Big G
Nature: How big is Big G? Mystery deepens after ten-year effort to measure gravity’s strength
Research Article: Schlamminger et al.
Hosted on Acast. See acast.com/privacy for more information.
Transcript
Click on a timestamp to play from that location
| 0:00.0 | nature in an experiment i don't know yet why is it like so far like it sounds so simple they had no idea |
| 0:10.7 | but now the data's i find this not only refreshing but but at some level astounding nature welcome nature. |
| 0:26.2 | Welcome back to the nature podcast. |
| 0:30.2 | This week, the robot that could beat you at table tennis, |
| 0:34.7 | and the latest attempt to test the strength of Big G. |
| 0:36.5 | I'm Benjamin Thompson. When it comes to humans versus artificial intelligence, there's a long history of researchers designing |
| 0:52.6 | machines to beat humans at games. Things like chess, |
| 0:57.1 | backgammon, go, we've covered several of these kinds of stories on the pod before. But things |
| 1:03.0 | are getting a little more physical with the latest paper we're covering, the story of an AI-powered |
| 1:09.3 | robot that can beat elite players at table tennis. |
| 1:13.7 | Reporter Jeff Marsh spoke to Sony AI's Petardur to find out how and why. |
| 1:19.4 | If you look at the history of AI, scientists have often used games as benchmarks. |
| 1:28.5 | And in a way, games are very interesting because they allow us to directly compare the performance of an AI agent to a human's performance. |
| 1:40.3 | Okay, great. |
| 1:41.6 | Do you want to introduce yourself then? |
| 1:43.4 | Yes, very nice to meet you. |
| 1:45.8 | My name is Peter Dür, director of Sony AI in Zurich, and also the lead engineer of what we internally call Project Ace, which is a robot that can challenge human athletes. |
| 2:04.4 | And I'm a roboticist by trade, and so this is really a dream project for me. What is it that makes table tennis per se such a challenging |
| 2:11.0 | sport to compete in? So when a professional player hits a fast ball, it can reach velocities of 25, up to 30 meters per second. |
| 2:21.4 | They also impart a massive amount of spin on the ball. |
| 2:26.3 | So this lets players influence how the ball flies. |
| 2:30.2 | This also causes the ball to bounce differently on the table and then causes the ball to bounce differently from the opponent's racket. |
... |
Please login to see the full transcript.
Disclaimer: The podcast and artwork embedded on this page are from podcast@nature.com, and are the property of its owner and not affiliated with or endorsed by Tapesearch.
Generated transcripts are the property of podcast@nature.com and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.
Copyright © Tapesearch 2026.

