AI bats away ping-pong challenge as rise of the machines continues
- Reference: 1776942911
- News link: https://www.theregister.co.uk/2026/04/23/ai_bat_away_pingpong_challenge/
- Source link:
Humans strike back at Go-playing AI systems [1]READ MORE
Capering about with a small bat smacking a tiny air-filled plastic ball to-and-fro across a six-inch net requires a bit of athletic skill, but table tennis fans can't bank on being able to beat the machine anymore.
[2]A paper in Nature this week shows an AI-based robotic system can outperform elite table tennis players. Developed by Sony AI, the system it calls Ace shows the capacity for robots and AI to achieve complex, real-time interactive tasks which might have broader applications.
"The system can not only challenge professional players, but also provide valuable insights on human strategy and movement," according to an accompanying article describing the work.
[3]
Ace fires a shot back to its human opponent, Minami Ando, during a match in April 2025 – Pic credit: Sony AI
During amateur play, a table tennis ball might travel at about 96kph (60 miles per hour) across the table. With professional players, that can rise to as high as 150 kph (93 mph) during a smash. When players apply spin, it changes the ball's trajectory as the Magnus effect distributes airflow asymmetrically over the ball, and also as it bounces off the table.
The AI and engineering professors based in Brazil point out that designing and building a system able to play such a fast-moving sport requires engineers to design-in features which can detect an environmental change, decide how to react and then implement that reaction at speeds that enable them to compete with humans. The challenge cuts across many fields of engineering, they said.
[4]Bots, bias, and bunk: How can you tell what's real on the net?
[5]AI scores a huge own goal if you play up and play the game
[6]Go No! Google cyber-brain bests top-ranked human in ancient game
[7]AI shoves all in: DeepStack, Libratus poker bots battle Texas Hold 'em pros heads up
Ace is built from three modules, including a high-speed perception system, a control system and a robotic arm. "The perception system used conventional cameras to locate the ball and three 'gaze control systems' that estimated the rate at which it was spinning, known as its angular velocity. The direction and rate of a table-tennis ball's spin determines its trajectory — a skilled player can give the ball a desired spin to deliver shots that are difficult for their opponent to return," the accompanying news article explained.
The work was led by Peter Dürr, director of Sony AI in Zürich. Also involved was his colleague Peter Stone, chief scientist at Sony AI, who said the research represented "a landmark moment in AI research." It demonstrated that an AI system can perceive, reason, and act effectively in complex, rapidly changing real-world environments that demand precision and speed.
"Once AI can operate at an expert human level under these conditions, it opens the door to an entirely new class of real-world applications that were previously out of reach," Stone said. ®
[8]
Get our [9]Tech Resources
[1] https://www.theregister.com/2023/02/20/human_go_ai_defeat/
[2] https://www.nature.com/articles/s41586-026-10338-5
[3] https://regmedia.co.uk/2026/04/23/ace_vs_ando.jpg
[4] https://www.theregister.com/2025/12/05/bots_bias_bunk/
[5] https://www.theregister.com/2025/07/07/ai_scores_a_huge_own/
[6] https://www.theregister.com/2016/03/09/google_bests_sedol_in_go/
[7] https://www.theregister.com/2017/01/14/deepstack/
[8] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_software/aiml&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=2&c=2aepCI18dIjNa4meQc3iDHQAAAM8&t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0
[9] https://whitepapers.theregister.com/
” bend right over, and launch ping pong balls across the room?”
I sense someone cannot forget his trip to Thailand
ROTM
Wire it up to one of those Chinese half-marathon running robots with a samurai sword and away we go
"AI bats away ping-pong challenge"
AI prompt> Should I challenge AI at ping-pong at home or away?
AI?
I've read the Reg piece and the Nature paper. Kudos to the team for what looks like a genuine achievement. I do have a couple of comments though.
It is not clear to me at all how the ping-pong playing robot qualifies as "AI". There may have been elements that are familiar from ML/AI (the pre-LLM era), but the whole problem doesn't feel to me as something that fits the claims around "AGI" very well, frankly. I suppose that deciding where best to send the ball based on the position and posture of the human opponent would be closer in spirit, but the paper focuses on the ball and makes no attempt to model the actions of the opponent besides following the ball after the opponent's racket hits it. In fact, the paper says that human opponent modelling may be an "avenue of further improvement" (there are references to past studies, but no relation to this project, it seems).
Reinforcement learning (an "AI element") is mentioned, but the best I can discern is that qualified players estimated the "skill" of the robot's serve and give feedback based solely on where and how the ball landed on the opponent's side of the table. Again, there is no mention of the opponent's position, posture, movement, etc., at the moment of contact with the table or before that.
The difficult part of the ball's movement is its spin. Again, the robot estimates the spin by monitoring the motion of a logo on the professional-quality ball. Would it do as well with plain white balls without a logo? Now, when I was (a lot) younger I used to play some table tennis. Never professionally, although I've had a number of chances to play "friendlies" with very high level professional players (I nearly always lost, obviously, and they were very gracious about it). I don't recall any logos, the balls were plain white, and to the best of my recollection noticing the opponents' motion and a combination of moving and twisting the racket was a major, if not the only, way to estimate and maybe predict the ball's spin.
Watching the opponent and acting accordingly was a major and crucial part of the skill for the pitiful amateur (me) and the top professionals I was lucky to play with. Yes, there was reinforcement learning and feedback involved, on occasion.
It is not clear to me that the robot's advantage over humans was in some kind of "intelligence" rather than in being fast and precise enough while never getting tired or distracted or losing concentration, etc. Still, good job.
Re: AI?
I suppose it depends on how broadly or narrowly you wish to construe the word "intelligence". To take a couple of examples, bees (and some other insects) can perform prodigious acts of navigation, exploiting a diverse range of techniques, while primates, some cetaceans, corvids and octopuses are capable of sophisticated levels of social interaction and manipulation. Personally, I'm inclined towards a very broad view of what constitutes intelligence; for others it seems to be purely anthropocentric – if it ain't like us it's not intelligent – which I personally find both restrictive and hubristic.
I do agree with your final summary, though.
Re: AI?
It is not clear to me that the robot's advantage over humans was in some kind of "intelligence" rather than in being fast and precise enough while never getting tired or distracted or losing concentration, etc
That, plus the fact that you can't look the robot in the eyes or read its body language.
Ah yes, plenty of snake oil and bulls$hit going on here, check out the original video. The arm didnt beat the player, it was a draw -
- https://youtu.be/4pMo5k2FPF8
Also this is NOT Ai or ML, its a program/script similar to what we have seen on the YT channel, Stuff I made here -
- https://www.youtube.com/@StuffMadeHere
According to another article (I didn't check the video), it beat elite (non-professional players) but lost against the pros.
https://youtu.be/pH8tVBqCRLY?si=sQmshvJ91I8ihQVz
Its all over.
Flying to Salt Lake City
Seats 3a and b
I was down and needed a window
But in 3a sat Mitzi Dupree
She said Hi I am Mitzi
The queen of the ping pong
Where you going boy
I said nowhere....
Can the machine stand on the bar, bend right over, and launch ping pong balls across the room?