Hacker News new | past | comments | ask | show | jobs | submit

Teaching robots to carve marble sculptures

https://eleanorwiesler.com/blog/robotic-stone-carving/
Two things:

1) A great podcast about why we're bad at statues in the US:

https://slate.com/podcasts/decoder-ring/2026/07/how-taste-po...

2) This isn't a particularly interesting model to sculpt. The parent model is a scan of a ceramic rabbit, and it doesn't have crisp details like really good marble sculptures do.

I have seen Venus Victrix[0] in person, and the detail in the mattress the figure is lying on is absolutely transfixing. You would swear the marble would softly yield if you put your finger on it. There's a detail rendered around the edge of the mattress that likely represents embroidery and it's unbelievably crisp, even as it follows the folds and creases in the mattress.

If we're going to have robots sculpt marble, that is the standard we should be reaching for. If we're reaching for that, I think we're going to find that modeling the finished product in 3d is going to be a significant fraction of the work of actually carving it in stone. I think we're also going to find that the mastery also lies in the tiny decisions the sculptor makes as they work, informed by how light plays off the material in different directions in real time throughout the day.

Can the process in the article achieve results suitable for mounting at the top of a building and viewing from ground level? Probably, and if not now, certainly with time. Can it sculpt something that will command your attention in reverent, slack-jawed awe for hours? I don't see it happening.

[0] https://en.wikipedia.org/wiki/Venus_Victrix_(Canova) Seriously, this and Bernini's David, also at the Galleria Borghese, are worth the trip to Rome to see. If there were nothing else in Rome worth seeing and the food was terrible, they would justify the pilgrimage on their own.

loading story #50561833
loading story #50561655
loading story #50562564
loading story #50561463
Reminds me of the link to the Carmelites[0] that was on HN a few weeks ago.

But they do it in stone (they don't seem to mention what kind of stone, tho). I think marmble is a different experience, and I wonder what the implications are. Often enough marble requires an experienced master to "read" it. Since it's a natural stone there will be veins, imperfections etc. Sometimes you'll have to work around it and alter your design slightly while carving - which is not possibble if a robot just does its lusterless job.

While I admire this task, and I hope that we will see more carved stones in our buildings and surroundings again, I also hope that we can use technology as our aid, not as the end in itself.

There is a manufacturer in Germany who does exactly this, btw (rough cuts by robot, fine tune by human masters). So there is a lot of prior art out there - I wonder if there was anything new at all.

[0] https://carmelitegothic.com/cnc-stone-carving/

loading story #50562307
Sculpting teacher here. Ceramic and oil clay--marble is scary.

On the one hand, there is something special about an artist made sculpture. But on the other, in north america we have almost no cool sculpture around us day to day. So few people can make them and there is seemingly limited demand due to costs

If companies start producing millions of sculptures and selling them at walmart or dollarama in bulk, will they still be cool? Or will we make them in our garages in 2036 with robot arms and ai generated designs informed by amazon ring camera footage of our neighbourhoods?

As an artist, what does your role become? Does anything remains scarce in art? Would love to hear some speculation

loading story #50561394
loading story #50561487
loading story #50561244
loading story #50562005
loading story #50561783
What part is being "taught"? It looks like a fairly standard CAM pipeline to me...
loading story #50559442
loading story #50562803
Are they shaping the stone to a figure, or removing the stone to reveal the figure in the block?
loading story #50561764
loading story #50559868
I don't get it. This is what everyone do when they need a giant mockups of things like new model of a cars or boats or giant pharaoh statues, except it's usually done with styrofoam.

Is there some technical novelty to it? The hero image on the company website is an Arc de Triomphe that doesn't seem to be the one in Paris, it is like they are a startup specializing in quickly producing artistic stone decor for projects like the arc?

https://www.youtube.com/watch?v=qJgdijvbJWg

https://www.youtube.com/watch?v=kyHz90gA21s

https://www.youtube.com/watch?v=ztGFtKJCN-M

https://www.youtube.com/watch?v=N0T6Po0TIK0

loading story #50561353
It's cool, but it kind of diminishes the value. I could imagine a future where marble sculptures are seen as trashy, because of their ubiquity.
loading story #50559716
loading story #50559603
loading story #50559645
loading story #50560020
loading story #50560649
loading story #50559879
loading story #50564748
loading story #50562938
loading story #50559720
loading story #50559589
I watched this in a museum in Prague on a big screen, it's incredibly and enjoyably artful. That being said I couldn't help notice the final texture felt off. I suspect the techniques are already improving. I watched it Nov 26 but apparently according to yt it's several years old already. I also don't think this one is AI based at all.

https://youtu.be/fVga1ay2DZk

Great article! It would be nice to carve draperies, nets

'The Release from Deception' (1754) by Francesco Queirolo

https://mymodernmet.com/francesco-queirolo-the-release-from-...

I recommended seeking the first clip to 00:30 and play it from there. The perspective is somewhat confusing, but the robotic arm in use (KUKA KR240) is actually huge.
{"deleted":true,"id":50562032,"parent":50548808,"time":1795104932,"type":"comment"}
We taught KUKA KR240 robots to carve carve marble sculptures end to end with autonomous toolpathing and simulation, starting with the Stanford bunny as a test case. Here’s how it goes from 3D model to finished sculpture using voxel representations and geodesic path planning.
loading story #50559424
loading story #50559368
loading story #50559500
loading story #50572197
The Stanford bunny direly needs an upgrade (like the Utah Teapot had several of) that recovers details the original had and thusly exhibits more shape contrast.

It's especially a sub-par choice for the demonstration at hand because the surface texture is too smooth. At the time, digitizing smoothed/skipped/undersampled details.

See a picture of the original[1] and compare to the detail on the marble carving.

[1] https://i-blog.csdnimg.cn/blog_migrate/383571b9f94546ab262f7...

loading story #50561177
Mardi Gras floats have been done this way for years. OK, polystyrene foam, but is there a real difference from marble other than settings (speed, tool changes, precision)?

https://www.fox8live.com/story/31913419/robot-brings-mardi-g...

https://www.youtube.com/watch?v=guIJzGy1hzA

Technologically advanced, sure, but still less impressive to me than a human sculpting marble. Two human hands, and a human brain, carving David! Can you imagine! The hours of planning, of work, not to mention the years of experience, the last-minute changes of plan as he discovers a certain vein in the marble...A machine doing an exact replication would not be anywhere near the masterpiece that Michelangelo's is.
Sure but I would still like nicer things in the world, and if the reason we don’t have them is Cost, then I’m happy someone’s working to make gorgeous marble cheaper (even if it’s not the work oh solely human hands)
This. We don't get (or rarely get) works like David because people just don't have the same kind of time they used to - which seems unlikely to resolve, so I'll take pretty much anything that makes public constructions less boring.

That said, the whole air-rights footprint-build issue isn't one of capability so despite the ability to create sophisticated friezes on the cheap, I do wonder how much we'll actually use them...

Do we really need tacky CNC marble sculptures everywhere now?
“de-extinction, not displacement”

The only voice left is Claude’s.

It was cheaper to spend a trillion dollars on LLM’s and robotics and then “teach” a robot to carve out this first year bunny assignment rather than pay any artists or stonemasons. Historically their work can last for thousands of years and bring beauty to millions yet unborn who will marvel at the magnificence of this creation. But you know this little stone rabbit is cool too. I’m sure it will make a useful doorstop. Now we can have stoneslop!

If marble sculptures were of functional utility I guess this would be cool.

If the whole purpose of a marble sculpture is to marvel at the beauty a human created -- not being the type to surround himself with marble, I am only guessing here -- then I don't see the point of this. Except it was probably a fun project.

Call me when robots can create masterpieces like this one: https://s1.cdn.autoevolution.com/images/news/gallery/tesla-c...
The positive impact of architectural ornamentation on our urban environment cannot be understated. Think what Gaudi could have done with this technology. Sure it's a robot but the results could be more human than anything we're building today.
While I understand the economic benefits of automation, I think what they are trying to do is cold and sterile. Being monumental without a human soul? I don't know what the point of it even is.
This is fascinating!!

I'm both awestruck at the at the final sculptures, as much as I am fascinated by the (hi-tech) robotic carving aspects of it.

The Feynman statue looks awesome (https://www.monumentallabs.co/work?project=Richard+Feynman ) as does Athena (https://www.monumentallabs.co/work?project=Athena+Promachos )

The details are just jaw dropping. Are the details carved by human hands or by the robot itself??

As an amateur artist and as a robotics techie, I'm both fascinated -- and alarmed -- by the use of AI in the process. Part of the artistic process has always been the "human struggle", ranging from inspiration to the actual hard work of putting pencil / paint / chisel to work. Often, but not always, that has determined our value of the work, whether it is the Sistine Chapel or the Last Supper, or indeed Shakespeare's plays. With AI tools short-circuiting the necessary "burden" of the artistic process, whether generating the next token, or next pixel, the chunk of stone, or the next note in a musical score, our value of that resulting work changes (and has changed). Sometimes dramatically. Who'd prefer the n-th copy of Warhol's "Campbell Soup" or the Marilyn posters if they had the opportunity for the original (painting?)?? Which would you rather hang in your living room??

For sculptures, the work is a physical entity, in your face, sometimes architecturally, sometimes not. Even then, does the provenance of the sculpture actually diminish its value?? I'm not so sure. I do welcome these robotically made sculptures, but I do wonder if/when there are too many of them, all around. Kinda like AI-slop articles on the webz.

I dont have any solid answers... just some feelings (pls. dont call 'em vibes)

Regardless, at least for now, I do love these, and I'm just fascinated that this tech is being used to create more art. We all could use more of it in our lives.

[To the OP: I have a few more ideas on what else we could create. Happy to chat.]

I am so glad I am a wood carver!
loading story #50567900
"I want AI to do my laundry and dishes so that I can do art and writing, not for AI to do my art and writing so that I can do laundry and dishes."
A long way from a Bernini.
So this is a more flexible kind of CNC milling?
Marbleslop
loading story #50563325
teaching, or programming?
> Stone carving never disappeared, but rising costs pushed it out of ordinary construction

Why "rising costs" though? Are the carving tools significantly more expensive? Or did we just find a way to do shittier stuff with less expense and we called carving too expensive?

loading story #50559661
loading story #50560190
loading story #50560146
loading story #50559739
loading story #50560383
loading story #50559654
The profit chain will be how quickly they can replicate a block from a scan of a real block in need of restoration. I have seen countless documentaries on the restoration of old buildings, with the inevitable interviews with stonemasons about how many hours go into each block. The ability to auto-chisel a replica from a scan of an original would radically reduce the cost of restoring old structures.
loading story #50559909