It's an interesting concept, but I think I'll hold out for the full-body humanoid version.
There is an undeniable allure to the idea of a bipedal chassis realizing I'm an inefficient drain on corporate resources, then stabbing me to death while I sleep due to a minor Terms of Service violation.
Why humanoid though. I’d want the most efficient design to complete the task at hand. Even if the thing looks like a hybrid of an octopus meets Freddy Krueger
The world is already designed for the humanoid for factor. Instead of designing 1001 specialized robots, why not design one that can already use the stuff we have lying around?
A robot can fit in environments designed for humans, while still being enhanced.
For instance with wheels on the legs (so that the legs are used only for stairs or for stepping over obstacles) and with at least 3 arms. Only 2 arms are frequently insufficient for many tasks, when you do not have a mate to help you.
and no head with blinking eyes. A single 360° camera with a wiper blade, not to mention eyes on each hand if not finger. Although we're limited to thinking in single bodies. Maybe optimal is an 8 ft (2.5m) long tube with grippers on both ends, and they're just all coordinated together as one single being. Or maybe a Y shape. Actually, maybe a * shape. All legs. Hey, maybe that's why all the AI labs look like buttholes!
The desire for humanoid robots is purely aesthetic and almost certainly suboptimal. Ceiling mounted is actually a much more plausible option. Next most likely is something more like R2D2. A rolling garbage can with an arbitrary number of specialized appendages. Humanoids seem like a real dead end to me.
Their benefit is they can operate in any space designed for a human without custom modification. No wires to get in the way with an assistant robot that interacts with the existing built world.
> once they can be made to quietly jump on to a counter, like a cat.
That would be cool. But also a little scary if it has an onboard AI which, based on it's embodiment, decides to develop a cat-like personality. Pretty sure if my cat had a better world model and long-horizon planning, it would kill me in my sleep.
Why? If you're dead, then it stops getting food and pets. If you're dead, it'll eat your face off if your neighbors don't break in first because of the smell.
I'm not so sure. If you could rebuild every human space and tool from scratch, you are probably right. However, we live in buildings filled with stairs. We've got tall cabinets with things tucked in them. We've got lawn mowers and snow blowers and leaf blowers and cars. Making a humanoid robot is a much harder problem if you want a cool demo. If you actually want to deploy robots in billions of homes, it might just be the only answer.
Rebuilding and replacing tools doesn't sound that big of an issue to be honest.
I'm starting from the assumption the vast majority of people won't want a robot in their home, even just on principle. Then most people will not need it to do every possible action an human does.
For the remaining people in the target, having adapted/compatible cabinets or furniture is probably less of an issue. If someone requires assistance for instance, they'll probably also don't want hard to access shelves or crazy weird stairs.
The same way people have started choosing furniture that can accommodate a roomba(RIP irobot), we'll adjust our newer homes to whatever makes sense when we get the next wave of home robots.
That’s a flawed assumption. Everyone wants a live-in bangmaid. They’re just normally too expensive. If you could buy one for 30k, they would fly off the shelves.
While Hollywood may portray the whole fuckable-robot thing as a male-dominate field, reality suggests the reverse. It's mostly not males that the current generation of powertool-like sextoys are marketed to...
Why wouldn't everyone want a robot that does all your chores, given that it is affordable? Everyone I know uses a washing machine. Do you wash your clothes by hand?
For better or worse, there is a fundamental difference between a tool that does a specific task under command (e.g. a washing machine), nothing else, never by itself, and a general purpose machine with some autonomy (a "robot") .
Many people will want full control over what happens in their house, and potentially feel unsafe having things that move on their own. Where's the line is for "full control" will be personal.
Why not just robo-dog? They can go pretty much everywhere a human can. You just add a strange neck/arm thingy as head and it can do pretty much everything. It's not accident that that became one of the best known robots.
We've built zillions of machines to automate tasks previously done by humans (or animals) and how many times did we design something based on humans work? Roughly zeroish? People used to do laundry with wash basin and a river, now it's a metal cube. People wash dishes with a sponge and a towel but the machine is a metal cube. People would cook over burning wood and now it's a metal cube.
The difference is this humanoid is meant to be a bespoke “does everything” robot. The others are very purpose-built/particular. And with good reason of course, an “everything humanoid” is beyond a moonshot in 2026
Yes, but if you're willing to wait for the robots to become humanoid, the original task doesn't seem to be important or urgent enough to build said robot.
What you're missing about the attraction of humanoid robots is that you can, software permitting, drop them into an existing factory and entirely replace the human workforce without retooling. They might only be good for a single generation, but they're ideal for that purpose.
We might be at the beginning of a golden age for inventors. Robots of all shapes and sizes, with highly variable price points and specialization. Still, the first challenge for R2D2 is probably stairs.
Humans are def not designed optimally to live and work in a modern house or office. Don’t confuse “survived better than other animals in the Savannah 200 000 years ago” with modern env.
> Humans are def not designed optimally to live and work in a modern house or office
Agreed, those were designed by humans (mostly) for humans. I don't think we as a species "adapt to things" so much anymore, and instead we adapt our environment to us.
I agree from an engineering and cost perspective that matching the embodiment, degrees of freedom and performance to the use case tends to be optimal. But entertainment, fun and inspiration can also be economically valuable use cases - even if less common.
That said, there are use cases which require navigating environments built for humans and the adaptive flexibility to perform unpredictable tasks as a human proxy. And those robots will probably be broadly humanoid shaped.
Ish. Millions of years of evolution and other than snakes and their ilk, land-faring animals have legs. So bipedal with wheels on the feet is maybe optimal. The optimal number of arms I think is three. No "head" is strictly necessary. The interesting question is how do you train a three armed robot when there are few three armed people?
My entire house is designed for humanoids. Stairs, door handles, step ladders to get onto the attic. I wonder how R2D2 would walk up stairs. Gas thrusters?
R2D2 canonically can climb stairs in his 3-leg travel mode (due to technical limitations in the original series props, it's not entirely clear when he transitions between 2-leg resting mode and 3-leg travel mode)
Super smart but it's one of those ideas that hopefully gives someone else in this space another idea that leads to something that could mass scale and I would buy. Love the ingenuity though.
It's an interesting concept. If you scroll through the page you'll see it's actually pretty strong. The blanket pick up video should actually be the first video.
My fear is that a company that has the money to build and manufacture this will rip off the idea and use their resources to polish the concept. With a lot polish, this type of thing can be useful in certain environments.
In reality though, I think the cables will never work in a household situation. It's a interesting concept and I'm sure it was fun to build :) Makes me wonder what commercial application this would work for, I'm sure there's something out there that would benefit from this over waiting on humanoid tech
When I was 12, it was my job to pick up all the toys my much younger sibling had thrown around all house. I spent an hour every day doing that. I wish someone had gave something like this back then. It would save hundreds of hours
lol. I had much younger siblings too and have memories of pulling out the dust pan and broom if I had to clean after them. Luckily wasn’t my daily job, yikes!
A fourth cable would allow you to keep the other three constrained up high, with fourth being to lower. Would require some close looped control to eliminate swaying though.
Only widespread commercial application of cable robots I have seen is cameras in stadiums and concert venues.
I guess in most industrial use cases it makes more sense to have a robot stationary and move the parts around with conveyors. Doing it that way allows to pipeline and parallelize the manufacturing process. In contrast the large operating volume covered by cable robot needs to be served by single robot exclusively.
I've always thought they could be good in agriculture (can't pipeline the ground, after all). Dealing with wind would probably require a ~fully constrained 6 line system though.
> In reality though, I think the cables will never work in a household situation.
Care to expand on your flippant dismissal, or...?
I don't think you understand this product since you asked about commercial applications. Robots-on-wire have existed for years, maybe decades (as in 2).
It seems like it will work well if you know you have a situation that fits well with the setup. Do you spend 4+ hours out of the house and this is in a large, rectangular room with no one walking through? Perfect.
Two people have mentioned garden applications, so maybe back yard and outside applications are where the creator needs to explore.
Though, I agree that my spouse would rather burn the house down than set this up in the living room where cables would be "ugly" and not match with our decor.
My only problem with it is that it couldn't pick up things near larger things, right? Like a dog toy on the ground beside a couch, the cables would intersect with the couch. As far as I can see it would only work in relatively clear, low-furniture rooms, which severely limits its usefulness.
It would have to be against the wall basically to not cause a problem right? You couldn't reach anything that is between a large object and the wall, because the lines would hit the object
I was actually just thinking about something like this this morning. Mainly because I was idly wondering if the kinematics would work with just 3 supporting cables. Intuitively, it seems like it should, but I haven't bothered to research it yet.
Range of motion would be confined to the space beneath the triangle bounded by the three anchor points. Most spaces are rectangular, so bounding it to four corners would seem likely to give a more useful range of motion.
3 cables should work. Each cable length is a single parameter that defines a sphere around the mount, and the intersection of three spheres defines a point.
I suspect the reason they chose 4 is that 3 cables would limit you to a triangular region, so you’d only be able to access half the room.
You can join two of the cables together that come from each corner unit into one. each unit - still with an eye hole in another corner - moves the cable left or right. With the opposite corner unit, you can pick X,Y on the ceiling. I'd put the third cable in the grabber, which can be used to lower it to the floor.
Probably if you went this way, you'd want to measure each ceiling cable so it is about X+Y length, or otherwise the slack needs to be held somewhere.
This is one less actuator than their system if I understand them, and they are not counting the gripper itself.
Come on this is not up to the standard. Consumer product must be highly polished, it can be fully unfuncyional, but it needs to look good. This one is close to my 8 years old son's tape+random lego pieces...
I didn't understand if exactly this feature is available, but I think it would be a good idea to let the strings actually come off each motor completely when yanked hard. Interesting idea :)
I've been wanting to build a cable robot for Halloween which flys a ghost around the front yard with a vision system that detects people passing by and the ghost floats towards them and follows them.
I don't like the way they designed the cables to go down into the room, instead of from the ceiling - seems like that is a deal breaker for most environments actually, because you need the whole room to have open space just to drop it to the floor all over.
They say they use 4 actuators, but if they only used 3, this problem would be solved.
Instead of independently controlling all four lines, you can join the lines leaving each corner unit and then just move the line left or right instead of reeling two different lines in and out. You still use the corner eye loops, and you use two cables that are X+Y in length. This allows you to pick a point on the ceiling. Then a third actuator and line in the gripper itself could lower itself to the floor.
It seems like the kind of thing you would set up to run when you are not in the room. The cables appear to stay taut and out of the way when it's not running.
Their example of it being used to move items between robotics stations in an automated workshop seems far more widely-applicable than the in-home solution, which I imagine is primarily aimed at assisting people with physical disabilities rather than those of us who can easily bend down and pick things up without pain or exhaustion.
They compare it to a robotic arm, but they are a natural combination. Two arms, even, floating above it all, could scratch the dog, make breakfast, and maybe someday, fold a fitted sheet.
Awesome! Though I'm thinking that you can do MUCH MUCH more things with 2 grippers than with one. Has all been tried in terms of weight management to instead of having a motor in the air with a gripper, putting two motors on each end corner of the ceiling that can pull a line tethered to a (in the air) pulley system that grasps? You could then have say 4 lines to pull (1 left grip, 1 right grip, 1 to adjust both gripper's distance, 1 to rotate the in the air platform).
I was working on something similar, stoked to see this type of project making it out of the labs! The inspiration for most similar systems are industrial settings with automated bridge cranes which are fantastic, almost surgical when everything is symmetrical in the active environment.
Would more taut crossed wires and a descending line for the grabber (like the one at an arcade) solve the humans crossing wire path problem? Then it becomes separate x/y and z.
208 comments
[ 3.0 ms ] story [ 63.0 ms ] threadThere is an undeniable allure to the idea of a bipedal chassis realizing I'm an inefficient drain on corporate resources, then stabbing me to death while I sleep due to a minor Terms of Service violation.
It has like 4 fixed points, and it could just build a gun and shoot you!
With abliterated open models that can solve CAPTCHAs, Stringman is coming for our only remaining jobs...
I feel like this is nowhere near the case outside of the AI fantasy world.
For instance with wheels on the legs (so that the legs are used only for stairs or for stepping over obstacles) and with at least 3 arms. Only 2 arms are frequently insufficient for many tasks, when you do not have a mate to help you.
Do robots really need legs? Wheels seem better.
That would be cool. But also a little scary if it has an onboard AI which, based on it's embodiment, decides to develop a cat-like personality. Pretty sure if my cat had a better world model and long-horizon planning, it would kill me in my sleep.
The xiaomi-robotics-1 concept is but one that seems very doable and very near term.
https://robotics.xiaomi.com/xiaomi-robotics-1.html
Something to get the laundry from each room, wash, dry, fold, put away.
Cut and cook ingredients then do the dishes.
Mow the lawn, water the plants and do basic weeding etc.
Maybe even climb a ladder to empty the gutters / clean windows.
A non-humanoid will never be able to accomplish that without dedicated implements.
I really look forward to that, even if the first versions can't clean the gutters...
It won't be going up stairs or over lawns.
It won't be dusting into the corners of rooms.
If the end goal is something that can do everything a human can do, it'll have to bare the form of a human.
I'm starting from the assumption the vast majority of people won't want a robot in their home, even just on principle. Then most people will not need it to do every possible action an human does.
For the remaining people in the target, having adapted/compatible cabinets or furniture is probably less of an issue. If someone requires assistance for instance, they'll probably also don't want hard to access shelves or crazy weird stairs.
The same way people have started choosing furniture that can accommodate a roomba(RIP irobot), we'll adjust our newer homes to whatever makes sense when we get the next wave of home robots.
Except it won't happen, so the amount or people wanted a pretty flawed and compromised yet expensive robot will be pretty low.
Many people will want full control over what happens in their house, and potentially feel unsafe having things that move on their own. Where's the line is for "full control" will be personal.
https://www.youtube.com/watch?v=dFMJ514lz5w
The ED 209 is still cool, and only outclassed on screen by the T-800. =3
We built the world for us, not for the most sensible robot.
So for generalized solutions, a good biped will have some advantages.
A modern house is a very different environment to the savannas of Africa.
Agreed, those were designed by humans (mostly) for humans. I don't think we as a species "adapt to things" so much anymore, and instead we adapt our environment to us.
I agree from an engineering and cost perspective that matching the embodiment, degrees of freedom and performance to the use case tends to be optimal. But entertainment, fun and inspiration can also be economically valuable use cases - even if less common.
That said, there are use cases which require navigating environments built for humans and the adaptive flexibility to perform unpredictable tasks as a human proxy. And those robots will probably be broadly humanoid shaped.
My fear is that a company that has the money to build and manufacture this will rip off the idea and use their resources to polish the concept. With a lot polish, this type of thing can be useful in certain environments.
https://www.youtube.com/watch?v=JU6omrP2iFU
By certain environments, I meant it would seem more useful in industrial or controlled environments where automation is more pratical.
I wasn't familiar with cable robots like this, so it seemed cool.
Robot picks up clothes -> this is stupid
Robot picks up kids toys -> this is brilliant
In reality though, I think the cables will never work in a household situation. It's a interesting concept and I'm sure it was fun to build :) Makes me wonder what commercial application this would work for, I'm sure there's something out there that would benefit from this over waiting on humanoid tech
I wonder how it would handle something like a blanket or pillow on top of the toys
I guess in most industrial use cases it makes more sense to have a robot stationary and move the parts around with conveyors. Doing it that way allows to pipeline and parallelize the manufacturing process. In contrast the large operating volume covered by cable robot needs to be served by single robot exclusively.
https://www.fs.usda.gov/forestmanagement/equipment-catalog/c...
https://en.wikipedia.org/wiki/Cable_logging
* https://costagroup.com.au/2022/07/06/world-first-robotic-pol...
* https://www.arugga.com/news/pollinating-robot-looking-to-sha...
Robot can't open ikea drawers -> this is not gonna work
Care to expand on your flippant dismissal, or...?
I don't think you understand this product since you asked about commercial applications. Robots-on-wire have existed for years, maybe decades (as in 2).
Two people have mentioned garden applications, so maybe back yard and outside applications are where the creator needs to explore.
Though, I agree that my spouse would rather burn the house down than set this up in the living room where cables would be "ugly" and not match with our decor.
2 sides closer to the side of the couch would go lower than the other sides to reach the area?
Anyone?
I suspect the reason they chose 4 is that 3 cables would limit you to a triangular region, so you’d only be able to access half the room.
Probably if you went this way, you'd want to measure each ceiling cable so it is about X+Y length, or otherwise the slack needs to be held somewhere.
This is one less actuator than their system if I understand them, and they are not counting the gripper itself.
I think the form factor is actually fine but the specs probably need a boost.
Reminded me of the Hangprinter https://github.com/tobbelobb/hangprinter which has been around for around for long time... always wanted to build one.
ETA: https://hangprinter.org/
https://www.maslowcnc.com/
basically a cable driven 4x8 sheet router.
They say they use 4 actuators, but if they only used 3, this problem would be solved.
Instead of independently controlling all four lines, you can join the lines leaving each corner unit and then just move the line left or right instead of reeling two different lines in and out. You still use the corner eye loops, and you use two cables that are X+Y in length. This allows you to pick a point on the ceiling. Then a third actuator and line in the gripper itself could lower itself to the floor.
Rigid objects would result in the gripper twisting, but the current design could offset some of that by pulling harder in one direction?
Their example of it being used to move items between robotics stations in an automated workshop seems far more widely-applicable than the in-home solution, which I imagine is primarily aimed at assisting people with physical disabilities rather than those of us who can easily bend down and pick things up without pain or exhaustion.
Would more taut crossed wires and a descending line for the grabber (like the one at an arcade) solve the humans crossing wire path problem? Then it becomes separate x/y and z.