> The company says the robot completes Laundry Flow and Daily Reset tasks autonomously by default, but uses teleoperation assistance when needed to guarantee task completion.
Suspiciously absent: a rough idea of what percentage of tasks need the assistance.
Totally agree but the idea is this gives you a teleoperation environment that is truly on policy and not some artificial lab. The idea is that these robots, like those Amazon stores, are predominantly just controlled by actual humans.
Hey I totally agree I do not want a teleoperator looking into my house, it’s just so deliciously tempting to get in home on policy data. Not sure the reason why they are super interested in home environments vs business or public spaces.
There are at least two companies out there that can fold some laundry in a controlled environment already. At this point it's just a matter of categorizing fabrics and shapes and expanding that knowledge. Two years at the outside until it can fold 80% of your laundry.
This is basically a solved problem. Humans have latency, more than your Internet connection. We predict what's going to happen based on the shapes we see. Computer vision and LBMs do the same thing.
Yeah, again the WYSIWYG model of AI: if you see a robot folding a shirt, that robot can fold that shirt. Maybe it can fold another that's very similar, maybe only different in colour, but don't bet your money on it.
A robot folds a shirt and you think it can fold a tee? Not unless it's explicitly trained to fold that one tee, too.
I think blankets are harder simply because of their size. I often have to "whip" the blanket to get the other end to properly fold on itself. I also use a much large space because of the size (often the floor). Could a robot fold a big blanket? Probably? But what is the success rate going to be? If I just have to refold it 50% of the time, is that actually worth it?
Surrogate slavery is going to be a large business one day.
If you are telling me that one day I'll have a robot that cooks, cleans, is a personal assistant, a therapist. Eventually it'll be a chauffeur, babysitter, and obviously sex slave.
Why wouldn't i pay 50000 for that, besides the obvious "you are a creep" like why do I care when it's coming and market forces are going to make it an indistinguishable substitute human a la Joi from blade runner?
> The company says the robot completes Laundry Flow and Daily Reset tasks autonomously by default, but uses teleoperation assistance when needed to guarantee task completion.
Does that mean some random human looking at my dirty laundry in the middle of my home, the most intimate place in existence for me? No thank you.
When comes to lower part it’s always bipedal (hard to balance) or wheels (low capabilities).
Why no one makes 4-6 legs, insect like?
That seems like an easier problem to solve while gives much better mobility.
wheels are so much simpler that it seems much easier and more cost efficient to solve the "transporting a wheeled robot up the stairs problem" than it does to go fully bipedal.
Once again, the text is riddled with LLM'isms. Is this the new norm nowadays? Looking at OP's submission history, it's evident that they are utilizing HN for SEO farming.
A much more valuable discussion would be centered around the company's own website, which contains the same information, and doesn't require an LLM mediator: https://www.weaverobotics.com/isaac-1
I also saw Tesla is ramping up to make millions of Optimus robots. And Amazon bought Fauna robotics which I predict we will start seeing "last 100 ft" deliveries soon. Amazon's Rivian packmobile will pull up to a block and 5 Fauna robots (they are short) will jump out and start delivering packages to the neighborhood.
The first thing that jumped out at me is its form factor. It is easier to engineer (cheaper) and less threatening than a bipedal robot. The drawback, of course, is that it is less mobile.
So the play here is obvious, use the teleoperation as training data for a more general purpose AI controller. You need that data to make a model in the first place.
What doesn't make sense to me is the cost. Yes, $8000 is probably low for this robot but it's a reasonable price range for something like this. The AI credits though? I know vision LLMs are not cheap, they're not going to run something like Llama3.2vision on every frame. Very curious about the embodied AI architecture that this is going to use, and how it can get cheap enough that it's not going to use $500/month in electricity every month.
The way one of their employees told me it to me as like a dishwasher.
Of course the dishwasher should be more expensive. When you add up the hours in labor saved and multiply by the hourly median wage, you get something in the $50k to $100k range.
But it's essentially just a sprinkler.
Ain't no one going to to pay the cost of a new BMW for a dishwasher.
Same thing here for the laundro-bots. Their competition isn't against the time saved for a person to do it themselves. The competition is a maid that does your whole house for $70.
> Of course the dishwasher should be more expensive. When you add up the hours in labor saved and multiply by the hourly median wage, you get something in the $50k to $100k range.
Except most dishwashers aren't competing against people washing dishes by hand and making the hourly median wage, they're competing against other dishwashers
>> Very curious about the embodied AI architecture that this is going to use, and how it can get cheap enough that it's not going to use $500/month in electricity every month.
In practice most of the costs would be the teleoperation costs rather than AI inference.
I find it very suspicious that the laundry folding segment of the video has awkward cuts of the interesting parts. Makes me question if it is actually capable of doing that
I'll buy a robot that can put fitted sheets and fold every piece of laundry no matter how contorted/inside-out it is. Till then, they're just gimmicks. Also, it should have legs.
140 comments
[ 0.21 ms ] story [ 87.6 ms ] threadSuspiciously absent: a rough idea of what percentage of tasks need the assistance.
If they ever get the tech down (I doubt it), they will then try move to broader labour replacement.
This is why all the robots need to be humanoid.
moving a soft object from a to b is doable, folding/separating/sorting at any kind of speed is very much an area of active research.
Teleoperated robots are a better fit for businesses and public spaces
folding a flat, well presented tshirt, that is a known quantity, and never inside out, is fairly "easy"
in an unknown environment, with unknown clothes, that's still active area of research. Its still not that practical to navigate in a house yet.
Annoying when you play games, likely expensive when the robot keeps breaking things.
Is your doubt caused by blankets being bigger than shirts?
(I didn't see it folding a button-up shirt, only tee-shirts. That's an extra degree of difficult and I do doubt that it can do that.)
A robot folds a shirt and you think it can fold a tee? Not unless it's explicitly trained to fold that one tee, too.
If you are telling me that one day I'll have a robot that cooks, cleans, is a personal assistant, a therapist. Eventually it'll be a chauffeur, babysitter, and obviously sex slave.
Why wouldn't i pay 50000 for that, besides the obvious "you are a creep" like why do I care when it's coming and market forces are going to make it an indistinguishable substitute human a la Joi from blade runner?
Does that mean some random human looking at my dirty laundry in the middle of my home, the most intimate place in existence for me? No thank you.
https://www.youtube.com/shorts/x9TdqrvDHWY
Especially the arm clamp is the same shape, the actions are practically the same (take object and put in basket, teleoperation with live camera).
The type of thing you have lot of fun for 5 minutes.
Cheaper Unitree robots that starts at 4,900 USD are impressive in comparison.
Quite ridiculous. For 449 USD / month couldn't you just hire someone to clean your whole place and even sort your clothes, empty the trash, etc ?Must operate on a perfectly flat surface. My roomba could probably handle a larger carpet curb than that top-heavy thing.
Head and eyes appear to be at human crotch level for some reason... gross.
What a waste of engineering talent.
It could fold my laundry while I'm busy working from home as a teleoperator for Weave Robots.
A much more valuable discussion would be centered around the company's own website, which contains the same information, and doesn't require an LLM mediator: https://www.weaverobotics.com/isaac-1
I also saw Tesla is ramping up to make millions of Optimus robots. And Amazon bought Fauna robotics which I predict we will start seeing "last 100 ft" deliveries soon. Amazon's Rivian packmobile will pull up to a block and 5 Fauna robots (they are short) will jump out and start delivering packages to the neighborhood.
The robots are coming...
What doesn't make sense to me is the cost. Yes, $8000 is probably low for this robot but it's a reasonable price range for something like this. The AI credits though? I know vision LLMs are not cheap, they're not going to run something like Llama3.2vision on every frame. Very curious about the embodied AI architecture that this is going to use, and how it can get cheap enough that it's not going to use $500/month in electricity every month.
The way one of their employees told me it to me as like a dishwasher.
Of course the dishwasher should be more expensive. When you add up the hours in labor saved and multiply by the hourly median wage, you get something in the $50k to $100k range.
But it's essentially just a sprinkler.
Ain't no one going to to pay the cost of a new BMW for a dishwasher.
Same thing here for the laundro-bots. Their competition isn't against the time saved for a person to do it themselves. The competition is a maid that does your whole house for $70.
Except most dishwashers aren't competing against people washing dishes by hand and making the hourly median wage, they're competing against other dishwashers
In practice most of the costs would be the teleoperation costs rather than AI inference.
My laundry is upstairs and my washer is downstairs.
Also doesn’t seem to be able to start washer/dryer and transfer loads.