▲ 191 points
back
264 comments
A year ago this [0] table tennis robot backed by Google DeepMind was discussed on HN.
It plays much worse and the HN discussion is anchored around whether it's OK to call it "human-level" or if the authors should have clarified that they meant a human who doesn't actually play table tennis. But it was accepted as being SOTA at that time.
What happened since then? This looks like the kind of level of advance we see in, say, coding AIs, but I thought physical robotics was advancing much more slowly.
A partial answer is that the new robot cheats in ways that DeepMind didn't seem to. It has high speed cameras all over the room and can detect spin by observing the logo on the ball. But I'm not sure this explains such a big advance.
As a human player (of a not-high standard) I cannot see the spin of the ball directly. I can only infer it from the movement of my opponents bat. So I would wonder that a camera could pick it up in real time.
Also IT'S TABLE TENNIS, NOT PING PONG!
Reminds me of the Mitch Hedberg joke: "The depressing thing about tennis is that no matter how good I get, I'll never be as good as a wall."
I used to love Mitch Hedberg. I still do, but I used to, too.
The official Sony AI video, which is really interesting and has some glorious footage: https://youtu.be/FrGq8ltb-_E?si=PWm1Dv0T9UHUFw0t
More details and videos at https://ace.ai.sony/
Don't table tennis players learn to predict how the ball will act based on their opponents movements? Seems like if they aren't able to do that with a robot opponent (who doesn't look or behave like a human) then they wouldn't be able to play at their best.
Yes, you're dead on:
Rui Takenaka, an elite-level player who has won and lost matches against Ace, said in comments provided by Sony AI: "When it came to my serve, if I used a serve with complex spin, Ace also returned the ball with complex spin, which made it difficult for me. But when I used a simple serve - what we call a knuckle serve - Ace returned a simpler ball. That made it easier for me to attack on the third shot, and I think that was the key reason why I was able to win."
I do expect this to have a "novelty edge" over human opponents - which can be closed with practice, on the human end.
And, like many AIs, it can have "jagged capability" gaps, with inhuman failure modes living in them - which humans can learn to exploit, but the robot wouldn't adapt to their exploitation because it doesn't learn continuously. Happened with various types of ML AIs designed to fight humans.
Interesting point. There are a lot of sports (football, basketball) where the cumulative rules end up requiring any player to have a humanoid form (references to elbows and knees and hands and feet, etc.), but even in ping pong it kind of seems like cheating to have a non-humanoid form factor.
Exactly. There are cues that an opponent provides when approaching a ball that help the player prepare for and limit the range of possible responses (this happens with most racket games). With these robots, the players only find out after the ball is already coming in their direction.
I wonder how much practice these players had against the machine in the weeks leading up to the actual game. That would be significant to ensure they are playing at their pro level.
I'll be impressed when it's a humanoid robot that has to contend with similar kinematic limitations as a human player.
Here is the paper:
https://www.nature.com/articles/s41586-026-10338-5
I would love to see a video of this thing that shows the whole table. From the paper I guess they have to light the area very brightly. But it seems like a pretty serious set up.
My biggest fear at the moment is robot armies and police forces.
Case in point : we're all expecting China needs to invade Taiwan soon, or they will run out of soldiers because of the one child policies of the 70s/80s.
Meanwhile, Ukraine is holding up against a "modern" army with quickly assembled drones.
So it all seems a bit like "they'll never put tanks through the Ardennes", sort of ?
Where and when will the first invasion of a country by a purely remote controlled, AI assisted army take place ?
Will robot battalions embed civilians to act as human shields ? Will the AI learn to mistreat the locals to maintain fear, or will they see it as a needless distraction and rush to the center of powers ?
If war is mostly played out from a disrance, will years of playing RTS give South Korea an edge ?
Nature video
https://www.youtube.com/watch?v=EH8kZDc7OLk
Makes sense that it would.
Reminds me of this old The Onion story: https://theonion.com/ping-pong-somehow-elicits-macho-posturi...
I'm very surprised to see the rapid advancement in robotics these days. After all the fancy demos of Boston Dynamics and others from 10 years ago, and no real advancement beyond them, we kinda learned to treat robotics as "fancy toys".
Now, this feels to me very much like a Deep Blue moment in chess, when to everyone's surprise it won over Garry Kasparov 3.5 to 2.5. 20 years in, and no one even considers competing with chess engines.
This Ace robot won over table tennis professionals in 3 matches and lost in 2. Even the score is similar. I wonder what it'll all look like in 20 years from now.
I find Sony's work valuable. In my opinion, the primary purpose of AI is still, first and foremost, to relieve us of the physical labor we don't want to do. The next step to be taken is to create a universal basic income. Evolution will then unfold, as creative people will be able to dedicate their whole life undisturbed to the problems they deem important.
Here a video where one can actually see the robot in action:
Well, I guess we’re going to fire all the Ping-pong players at the office and replace them with these robots.
I'm not that excited about 'x beats human at y' anymore. I am more interested in 'x beats human at made up on the spot tasks p d and q'. That is starting to happen more generically and is a bigger sign of emerging capability. We can always create something confined that will beat humans, it isn't until recently that we are starting to be able to generally beat humans at tasks.
> In matches detailed in the study, Ace in April 2025 won three out of five versus elite players and lost two matches against professional players, the top skill level in the sport. Sony AI said that since then Ace beat professional players in December 2025 and last month.
What exactly is an "elite" player, if it's not a professional?
The motion system constrains the problem quite a bit. This video of high speed vision/actuators is 16 years old - https://www.youtube.com/watch?v=bfdHY26E2jc
I was expecting/hoping for a humanoid robot.
Anyone else entirely unimpressed? I'm just thinking about all the sensor and responsive things that must exist for cars, planes, manufacturing etc, and this just seems like an inevitable trick that someone could do?
Like, my kid watches the Mark Rober videos and this is just that?
I suppose this recent love-letter video to a random table top game from Rockstar games from NakeyJakey is now relevent to this thread...
Not to take anything away from the robot, but I would have liked to see the match be against a male player, as they can impart higher speed an spin on the ball, which would give the robot less reaction time.
In case anyone is interested, here is a paper on how they implement this.
Is there a video of this in action? Pictures are not satisfying at all!
Glad to see new kind of robots other than those cliche dog like ones....that does nothing but walk. In india its pretty much seen in every public event as a marketing gimmick.
Any links to actual full matches played? I only see a point here, a point there, no full matches.
What happens when two of them play each other?
How easy is it to introduce artifacts that reduce accuracy and performance?
I wonder if a top player with access to a robot like this can get an extra edge in training?
Robo-augmented padel, the future
I wonder if human TT players can learn to use multiple cameras or points of view.
Much like the robots beating half marathon records in China recently… who cares? Cake making robots can make cakes way faster than human bakers. Cars and motorcycles go faster than bicyclists. It is a boring given that purpose made machines perform the tasks they are built to perform better than humans.
The greatest blernsball player was a machine for playing blernsball.
I don’t care about robots being better than humans at human achievement.
Would anyone ever watch Clankers play hockey against eachother at a Clanker Olympics? The idea is absurd, I want to see humans competing because they are humans not just because they are good.
> Now, Wireless Joe Jackson! There was a blern hitting machine.
> Exactly! He was a machine designed to hit blerns. I mean come on, Wireless Joe was nothing but programmable bat on wheels.
> Oh? And I suppose Pitch-o-mat 5000 was just a modifier howitzer?
> Yep!
This is great, I remember being sorely disappointed by the hyped up Timo Boll vs Kuka robot 12 years ago. I thought it was going to be a real match and seemed like the robot would destroy him, but ended up just being a marketing stunt and felt like a fixed fight, with no real digging into the tech or why the robot "lost". Still some cool footage: https://youtu.be/tIIJME8-au8
Cool. Now let's see two robots play and if it's fun let it become it's own thing. Other than that, this could be used for training actual players.
Is that a legal serve?
Finally an AI that takes someone's job and nobody's upset about it.
Now we need to find out if the robot can win against the wall
AI gets all the fun jobs. Yet again.
Now build a robot that can catch a bullet.