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.
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.
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.
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.
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 ?
To some extent it already has, Ukraine had a press release a few days ago stating they had attacked and taken a position using only robots and drones for the first time
> If war is mostly played out from a disrance, will years of playing RTS give South Korea an edge ?
Not sure if this is serious, but RTS skills are different from real-world battlefield skills. Macro is completely different, and while micro skills might be slightly transferrable, computers are so much better that no human will ever be microing real units on a real battlefield.
That being said, "the Russian army will be driven to a virtual stalemate by a former comedian leading a decentralized group of startups remote-controlling handmade Wall-E clones equiped with machine guns, while the former real tv anchor leading the US army helps the Russian side to distract people from the pedophile ring he did _not_ take part in" would have sound very tongue on cheek, too.
We are less than 5 years from robot armies. I mean if you put a person behind a Unitree robot, we have robot armies now. Those things run pretty fast and are quite good at obstacle clearance. They also cost $20,000 per unit which is throwaway money by any metric. Full autonomy is real close though.
I left a company because they pivoted to exactly this. There are so many companies in this space today, testing what they call "physical AI autonomy" today, and we have to recognize that this is our today.
There are entire marketplace options for buying the pretrained, supported, private models, or the datasets if you have your own goals. If you're interested purely in ditzing around with GPS denied, or communications lost, you can do that today.
I watched a demo video, in March where a company was sharing their remote instructed (note, not controlled) multiple format (spider, dog) robot swarm. The company claimed to be 35km away from where the drones dropped off the payloads, and the mission was engaged. Lightweight explosives were used to toss off a car.
Remote controlled autonomous robots/drones can also be used for, say, elder care.
A nurse can log in to a HelperBot remotely, check up on the client, tidy up the house and maybe even give medication. Instead of having to drive around between clients, losing maybe hours a day just on transit, one person can manage more people per day.
...but the same system can be modified for KillerBot easily like we know from EVERY SCI-FI BOOK EVER.
Ah geez, again this China invading Taiwan nonsense, China ain't USA, Israel or Russia attacking sovereign countries, they just use money to take over, they will do exactly same with Taiwan. Eventually Taiwanese people will figure out that siding with agressive country run by crazy old men is worse option than siding with China.
China has all time in the world not being run by crazies with 5 year election terms rushing to keep their mark in the history, not necessarily positive...
I suppose the Tibetan people would have a different opinion. But it's true that China has not fought as many war as the US, UK or France in the past decades.
Which is actually part of the enigma : if China decided to use a window of opportunity to invade a neighbor (and they have claims on Taiwan, they keep telling the world they have claims on Taiwan, and they keep preparing their navy to invade Taiwan, so it's not entirely unreasonable to expect that country would be Taiwan), would they have an inexperienced army making rookie mistakes and miscalculations, or would they catch everyone of guard with a a crazily autonomous army of robots that don't care about the weather or war crimes ?
I would not ask the same question about any other country in the world, but, if Russia and the US surprised us by failing at what they were supposed to be great at, and Ukraine surprised us by being good at one no one expected, I expect a surprise from china, but I don't know which one !!!
What if there are no human soldiers or fighters at all? No-one needs to die in a war again, but wars are won by the side with the stronger tech.
What are the possible outcomes of this? Technologically superior countries start a race to acquire more territory, so large blocks expand and absorb other countries? More wars? Fewer wars? More suffering? Less suffering?
Disclaimer: I'm not imagining this is really possible. As long as some humans from group A don't want to be under the rule of group B, humans will resist and fight. But it is just a thought experiement.
Not sure China actually needs to invade Taiwan - it just needs to be patient. cf Hong Kong.
Totally agree with you about the dangers of autonomous killing machines - I think the two key problems here are.
1. Reduces the political cost of going to war. Though as Iran has shown, there are other ways to exert political pressure even if the other military can hit you with almost impunity.
2. This is really a follow on from the first - low cost ( in all meanings of the word ) weapons makes asymmetric warfare available to all - and this won't be limited to governments.
On the positive side one of the potential outcomes of 2. is that countries and the world will need to operate on the principle of consent, as force will be nigh on impossible.
Is it possible South Koreans edge in RTS games is from their compulsory military service?
Also, China is not likely to invade Taiwan any time soon. It'd be geopolitical suicide and they're currently in a very good spot geopolitically. Invading the country with the rest of the worlds chip fabs is the quickest way to lose that
> 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.
I expect China to invade Taiwan, because they now know they likely can. I do not expect them to "run out of soldiers".
> we're all expecting China needs to invade Taiwan soon
Ah yes, China has a track record of invading countries.
> or they will run out of soldiers because of the one child policies of the 70s/80s
As opposed to NATO countries who have a steady increase in the number of young conscripts.
> Meanwhile, Ukraine is holding up against a "modern" army with quickly assembled drones.
I don't know why you put modern in parentheses. Russia did make a mistake of not adopting cheap drones earlier in the war. But Russians were the first to use optic fiber drones resistant to electronic warfare which gave them an edge during Summer offensive last year. Ukrainians have since caught up and their allies were able to supply them with large number of drones. But both Ukraine and Russia rely primarily on drone warfare and artillery becomes less important for both sides. Which all explains the static state of this war.
People were making jokes about the recent chinese robot marathon saying this is how it will be when they get drafted to defend taiwan from chinese invasion. Just running from these robots that can full sprint as fast as a tiger with no lactic acid build up. They were hot swapping batteries during the race so these things really have no down time.
I'm already impressed by their progress, but I wouldn't say it puts robots on par with humans when it comes to table tennis.
Another limitation is that most humans[0] cannot actually see the spin that's on a ball, but need to predict it based on relative racquet movement to the ball. In the video, they say that their system measures spin.
[0]: Table tennis legend Timo Boll has stated that he has excellent eyesight, and can actually see the rotation of the ball, which helped him during service receive.
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.
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.
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
69 comments
[ 4.9 ms ] story [ 65.7 ms ] threadIt 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.
[0] https://news.ycombinator.com/item?id=43861207
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.
> 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!
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.
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 ?
https://www.businessinsider.com/ukraine-russia-position-take...
Not sure if this is serious, but RTS skills are different from real-world battlefield skills. Macro is completely different, and while micro skills might be slightly transferrable, computers are so much better that no human will ever be microing real units on a real battlefield.
That being said, "the Russian army will be driven to a virtual stalemate by a former comedian leading a decentralized group of startups remote-controlling handmade Wall-E clones equiped with machine guns, while the former real tv anchor leading the US army helps the Russian side to distract people from the pedophile ring he did _not_ take part in" would have sound very tongue on cheek, too.
I left a company because they pivoted to exactly this. There are so many companies in this space today, testing what they call "physical AI autonomy" today, and we have to recognize that this is our today.
There are entire marketplace options for buying the pretrained, supported, private models, or the datasets if you have your own goals. If you're interested purely in ditzing around with GPS denied, or communications lost, you can do that today.
I watched a demo video, in March where a company was sharing their remote instructed (note, not controlled) multiple format (spider, dog) robot swarm. The company claimed to be 35km away from where the drones dropped off the payloads, and the mission was engaged. Lightweight explosives were used to toss off a car.
This is our present.
A nurse can log in to a HelperBot remotely, check up on the client, tidy up the house and maybe even give medication. Instead of having to drive around between clients, losing maybe hours a day just on transit, one person can manage more people per day.
...but the same system can be modified for KillerBot easily like we know from EVERY SCI-FI BOOK EVER.
We live in interesting times.
China has all time in the world not being run by crazies with 5 year election terms rushing to keep their mark in the history, not necessarily positive...
Which is actually part of the enigma : if China decided to use a window of opportunity to invade a neighbor (and they have claims on Taiwan, they keep telling the world they have claims on Taiwan, and they keep preparing their navy to invade Taiwan, so it's not entirely unreasonable to expect that country would be Taiwan), would they have an inexperienced army making rookie mistakes and miscalculations, or would they catch everyone of guard with a a crazily autonomous army of robots that don't care about the weather or war crimes ?
I would not ask the same question about any other country in the world, but, if Russia and the US surprised us by failing at what they were supposed to be great at, and Ukraine surprised us by being good at one no one expected, I expect a surprise from china, but I don't know which one !!!
What if there are no human soldiers or fighters at all? No-one needs to die in a war again, but wars are won by the side with the stronger tech.
What are the possible outcomes of this? Technologically superior countries start a race to acquire more territory, so large blocks expand and absorb other countries? More wars? Fewer wars? More suffering? Less suffering?
Disclaimer: I'm not imagining this is really possible. As long as some humans from group A don't want to be under the rule of group B, humans will resist and fight. But it is just a thought experiement.
Totally agree with you about the dangers of autonomous killing machines - I think the two key problems here are.
1. Reduces the political cost of going to war. Though as Iran has shown, there are other ways to exert political pressure even if the other military can hit you with almost impunity.
2. This is really a follow on from the first - low cost ( in all meanings of the word ) weapons makes asymmetric warfare available to all - and this won't be limited to governments.
On the positive side one of the potential outcomes of 2. is that countries and the world will need to operate on the principle of consent, as force will be nigh on impossible.
Also, China is not likely to invade Taiwan any time soon. It'd be geopolitical suicide and they're currently in a very good spot geopolitically. Invading the country with the rest of the worlds chip fabs is the quickest way to lose that
I expect China to invade Taiwan, because they now know they likely can. I do not expect them to "run out of soldiers".
Ah yes, China has a track record of invading countries.
> or they will run out of soldiers because of the one child policies of the 70s/80s
As opposed to NATO countries who have a steady increase in the number of young conscripts.
> Meanwhile, Ukraine is holding up against a "modern" army with quickly assembled drones.
I don't know why you put modern in parentheses. Russia did make a mistake of not adopting cheap drones earlier in the war. But Russians were the first to use optic fiber drones resistant to electronic warfare which gave them an edge during Summer offensive last year. Ukrainians have since caught up and their allies were able to supply them with large number of drones. But both Ukraine and Russia rely primarily on drone warfare and artillery becomes less important for both sides. Which all explains the static state of this war.
Another limitation is that most humans[0] cannot actually see the spin that's on a ball, but need to predict it based on relative racquet movement to the ball. In the video, they say that their system measures spin.
[0]: Table tennis legend Timo Boll has stated that he has excellent eyesight, and can actually see the rotation of the ball, which helped him during service receive.
Now build a robot that can catch a bullet.
Reminds me of this old The Onion story: https://theonion.com/ping-pong-somehow-elicits-macho-posturi...
I was expecting/hoping for a humanoid robot.
How easy is it to introduce artifacts that reduce accuracy and performance?
> How easy is it to introduce artifacts that reduce accuracy and performance?
Probably pretty easy. Have less-than-perfect lighting or introduce some wind, and the AI has to do a huge amount of relearning.