Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Learning athletic humanoid tennis skills from imperfect human motion data

zzk273.github.io

Post reply on HN
Print view View original

21–30 of 44 posts

Re: Learning athletic humanoid tennis skills from imperfect human motion data

#21

Post by kadoban »

V__ wrote: post #14

This is so interesting. Especially since it's kinda weird to train a robot to mimicking human play. I wonder what a perfect robot what actually behave like. It wouldn't need to split-step to activate muscles, the footwork would probably be minimal. I imagine a lot of different unusual looking swings to confuse human players, while still making perfect contact. It could make really late drop shots or even rotate the r…

> I wonder what a perfect robot what actually behave like.

Really depends what its hardware is. One with hardware a lot like a human would behave like a human.

Since you didn't specify, I'm going to go with a robot that looks like a giant pong paddle.

Re: Learning athletic humanoid tennis skills from imperfect human motion data

#22

Post by nradov »

Aboutplants wrote: post #5

Really impressive. In a few years there will be robotic AI instructors for the wealthy and their kids

Ironically something like this could eventually make elite level tennis training cheaper and more accessible. Families of some top US juniors already spend $100k per year, much of that on 1:1 coaching. Some fraction could eventually be automated, at least for repetitive basic skills practice. Like the next level of a tennis ball machine.

Re: Learning athletic humanoid tennis skills from imperfect human motion data

#23

Post by impossiblefork »

ilaksh wrote: post #15

We have just started ramping up practical use of imitation learning from human demonstrations in humanoids. A bigger development is that one or two projects are working on training foundational vision action language models based on large video datasets. I think before the end of summer general purpose physical knowledge and capabilities will start to be demonstrated by one or more humanoid AI or robotics groups. May…

I think that's a bit too optimistic, but I still think the direction is right-ish. It feels hard to give a timeline though. Robotics is hard.

Re: Learning athletic humanoid tennis skills from imperfect human motion data

#24

Post by andai »

ilaksh wrote: post #15

We have just started ramping up practical use of imitation learning from human demonstrations in humanoids. A bigger development is that one or two projects are working on training foundational vision action language models based on large video datasets. I think before the end of summer general purpose physical knowledge and capabilities will start to be demonstrated by one or more humanoid AI or robotics groups. May…

The "AGI" (-ish) moment for AI was shoving Common Crawl into a transformer.

What's the animal intelligence (physical int.) equivalent of that? I don't think such a dataset exists? (e.g. NVidia is trying to compensate for that with simulated worlds, i.e. synthetic data)

Re: Learning athletic humanoid tennis skills from imperfect human motion data

#27

Post by p1esk »

ilaksh wrote: post #15

We have just started ramping up practical use of imitation learning from human demonstrations in humanoids. A bigger development is that one or two projects are working on training foundational vision action language models based on large video datasets. I think before the end of summer general purpose physical knowledge and capabilities will start to be demonstrated by one or more humanoid AI or robotics groups. May…

I’ve been thinking about this too, and I share your optimism: https://news.ycombinator.com/item?id=47213310

Re: Learning athletic humanoid tennis skills from imperfect human motion data

#28

Post by p1esk »

nmaley wrote: post #20
ilaksh wrote: post #15

We have just started ramping up practical use of imitation learning from human demonstrations in humanoids. A bigger development is that one or two projects are working on training foundational vision action language models based on large video datasets. I think before the end of summer general purpose physical knowledge and capabilities will start to be demonstrated by one or more humanoid AI or robotics groups. May…

" Do we have any standard benchmarks for humanoids to do domestic tasks?" The answer is yes. Steve Wozniak proposed the Coffee Test. See https://www.youtube.com/watch?v=MowergwQR5Y It's actually very clever. Despite the apparent simplicity, no current model could pass it. Re your forecasts, I think they are optimistic in terms of timing but not ridiculously so.

I think coffee test for robots will be similar to Turing Test for LLMs, which was quietly achieved and forgotten somewhere between gpt-3.5 and gpt-4. Real tests are tasks like cooking or plumbing - I expect that to come in 2-3 years.

Re: Learning athletic humanoid tennis skills from imperfect human motion data

#29

Post by sam1r »

So this is all pretty much theoretical, but very tightly woven strictly bounded protocols to be brought to production-- perhaps an accelerated alternative to perceive a much sooner ETA of 18months...

Maybe its moreso about reaching out to the right people about this "white paper" worthy research.

AFAIK, billions of dollars are poured into tennis mechanics at the highest level.

Introduce this to the right group of people, I truly can see this funded to play Janik Sinner where he would pay as a service to play against his worst nightmare.

Post reply on HN