Robotics is a truly fascinating technical field - I was originally drawn to it because of its potential and its complexity. There is something alluring about having to understand mechanical, electrical, and software engineering expertly to create something unique.
What I quickly discovered though is it dominated entirely by technologists who believe that developing better technology will solve hard problems, without actually understanding the real intricacies of the problems they say they are solving.
There are so many brilliant engineers in robotics, and very few talented designers, product managers, and other necessary people to make robotics technology useful and ubiquitous for everybody. And that's probably why we have articles like this - because engineers only know about engineering (broadly speaking).
Previous generations of animatronics lacked the fidelity of motion that this one has. Disney's experience with CG animation shows through here, which is animating with CG puppets.
This is actually extremely well known to most people building robots. Anybody who's ever met Peter Dilworth will have seen his slides talking about how all you need to make something artificial relatable is a set of articulated eyebrows and he's right. Expressiveness is a game changer. It's just that it's far from the most pressing issue right now.
The article mentions that we (robotics researchers) don't think about movement first but the fact of the matter is that those of us working on humanoids can't STOP thinking about movement and how hard of a problem it is to solve. The issue is that we don't have anywhere near the technology in either electric motors or hydraulic actuation that is required to solve the problem of smooth, high-fidelity, accurately-controlled motion that is also safe for human co-operation (which typically means torque control or some other scheme for feedback control over the impedance between the robot and the environment). Hydraulics are far too "stiff" and dangerous to be used in robots that work directly alongside humans, and electric motors can't hit the torque vs. velocity requirements for dynamic motions that allow the robots to be both safe and expressive and dynamic like a living organism.
But nobody is funding research in to actuation because it doesn't have short term payoff and it isn't sexy. So here we are.
I've heard about it but near as I can tell it's still very much in the lab phase, and I'm not clear on just how strong the actuators are. Human leg joints need to be able to put out an astonishing amount of torque at pretty high rotational speeds sometimes.
The future will probably be some sort of artificial muscle derived actuator, absolutely. But for now the only way to do anything useful with a humanoid robot is with hydraulics (Atlas), huge electric motors that are either too slow or water-cooled, or sacrificing capabilities to focus on just a few things (Cassie)
> all you need to make something artificial relatable is a set of articulated eyebrows
I think of Legion from the Mass Effect games. It's a robot with a blank circle for a face... but with plates around that circle that are animated in a distinctly eyebrows-like way.
Festo is.[1] Over the last decade, they've built a robotic bird, a robotic fish, a robotic kangaroo, and a robotic hand. Many are pneumatic, and their technology for precision pneumatic control is available for industrial applications.
I have a bit of trouble performing some tasks that a smaller person could easily do, because when I was weight lifting, I had a few incidents where I pushed or pulled on something as hard as I remembered and ended up breaking it. I trained myself never to push as hard as I absolutely can, because if it takes that much pressure I'm probably doing it wrong.
I don't follow cycling as much as I used to, but in an attempt to keep rich teams from building bicycles out of unobtanium, they put some minimum weight restrictions on the bikes. One of the early results was that some telemetry gear started getting built into these bikes. The biggest one I know of was building a torque meter into the rear wheel. For the cost of a fraction of a percent of power output, it could tell the coach if you're really going all out or dogging it. The difference in those numbers would hint at you being sick, a subtle equipment failure, or an aerodynamics problem.
It should take a certain range of force to open a door, drill a hole, tighten a bolt, or raise a platform. If you are using more than that, something is jammed, your bit is wearing faster than expected, the bolt is cross threaded, or something is stuck on the platform and you're trying to ram it through the roof.
Some tools are very difficult to scale up to high torque situations, but it seems like this data should be available to a robot, via sensors on the power supplies if nothing else.
> The Robotics Industry Could Learn a Lot From Puppeteers
Absolutely, positively not. Absolutely garbage.
The actual title is a bit more dreamy and more Blade Runner, but still technically wrong, but perhaps artistically interesting "The Robots of the Future Should Look Like Puppets"
Puppets don't have Force Feedback/ Haptic feedback.
This is what's hard with robots. That's what we need to solve/improve.
This allows a robot to pick something up. Puppets can't pick a thing up! (Puppets with a human can). Then the next obvious step, we will make them look pretty just like Apple does.
It's an interesting discussion, but I am not sure we need to add expressiveness to a Roomba... I suppose it depends on how much time the robot will have an audience? For bots that are intended to interact with people, I can certainly see the value; but lots of them intentionally work when no human is there to see them.
The old Roomba I had made these really expressive chirps to communicate when it’s was starting, finished etc. If it got stuck on something it would make an apologetic “uh-oh” type of tone, and if it succeeded at something it would play a happy tone.
My newer model roomba now uses a really low quality prerecorded voice that says things like “error”. It sucks.
I dont care how sympathetic my mechanical slave is. I just want it to spot weld my car bodies perfectly, repeatedly and cheaply.
People adapt to technology -- you dont need to anthropomorphize the outputs, you need to make them simple to understand. LEDs, tones, motion etc can all do this without getting in the way of a robots core functions the way a sophisticated expressive system would. R2D2 'nuff said
19 comments
[ 3.2 ms ] story [ 59.5 ms ] threadWhat I quickly discovered though is it dominated entirely by technologists who believe that developing better technology will solve hard problems, without actually understanding the real intricacies of the problems they say they are solving.
There are so many brilliant engineers in robotics, and very few talented designers, product managers, and other necessary people to make robotics technology useful and ubiquitous for everybody. And that's probably why we have articles like this - because engineers only know about engineering (broadly speaking).
https://robots.ieee.org/robots/navishaman/
Previous generations of animatronics lacked the fidelity of motion that this one has. Disney's experience with CG animation shows through here, which is animating with CG puppets.
This reminded me of Keepon:
https://m.youtube.com/watch?v=3g-yrjh58ms
Basically an unarticulated clown nose with dots for a face and 3 degrees of freedom.
And yet it is clearly dancing. In other videos it manages to look contemplative when it is processing data.
The article mentions that we (robotics researchers) don't think about movement first but the fact of the matter is that those of us working on humanoids can't STOP thinking about movement and how hard of a problem it is to solve. The issue is that we don't have anywhere near the technology in either electric motors or hydraulic actuation that is required to solve the problem of smooth, high-fidelity, accurately-controlled motion that is also safe for human co-operation (which typically means torque control or some other scheme for feedback control over the impedance between the robot and the environment). Hydraulics are far too "stiff" and dangerous to be used in robots that work directly alongside humans, and electric motors can't hit the torque vs. velocity requirements for dynamic motions that allow the robots to be both safe and expressive and dynamic like a living organism.
But nobody is funding research in to actuation because it doesn't have short term payoff and it isn't sexy. So here we are.
The future will probably be some sort of artificial muscle derived actuator, absolutely. But for now the only way to do anything useful with a humanoid robot is with hydraulics (Atlas), huge electric motors that are either too slow or water-cooled, or sacrificing capabilities to focus on just a few things (Cassie)
Have you seen Digit? (https://www.youtube.com/watch?v=LSk8uCHN5CY)
I think of Legion from the Mass Effect games. It's a robot with a blank circle for a face... but with plates around that circle that are animated in a distinctly eyebrows-like way.
Festo is.[1] Over the last decade, they've built a robotic bird, a robotic fish, a robotic kangaroo, and a robotic hand. Many are pneumatic, and their technology for precision pneumatic control is available for industrial applications.
[1] https://www.festo.com/group/en/cms/10156.htm
I don't follow cycling as much as I used to, but in an attempt to keep rich teams from building bicycles out of unobtanium, they put some minimum weight restrictions on the bikes. One of the early results was that some telemetry gear started getting built into these bikes. The biggest one I know of was building a torque meter into the rear wheel. For the cost of a fraction of a percent of power output, it could tell the coach if you're really going all out or dogging it. The difference in those numbers would hint at you being sick, a subtle equipment failure, or an aerodynamics problem.
It should take a certain range of force to open a door, drill a hole, tighten a bolt, or raise a platform. If you are using more than that, something is jammed, your bit is wearing faster than expected, the bolt is cross threaded, or something is stuck on the platform and you're trying to ram it through the roof.
Some tools are very difficult to scale up to high torque situations, but it seems like this data should be available to a robot, via sensors on the power supplies if nothing else.
Absolutely, positively not. Absolutely garbage.
The actual title is a bit more dreamy and more Blade Runner, but still technically wrong, but perhaps artistically interesting "The Robots of the Future Should Look Like Puppets"
Puppets don't have Force Feedback/ Haptic feedback.
This is what's hard with robots. That's what we need to solve/improve.
This allows a robot to pick something up. Puppets can't pick a thing up! (Puppets with a human can). Then the next obvious step, we will make them look pretty just like Apple does.
People already antromorphize the machinery once it looks human. If it also looks whacky- and relateable, the whole "this is family" effect sets in.
A robot puppeteer is easier than an autonomous robot because it can have the weight of its actuators in a fixed base.
I dont care how sympathetic my mechanical slave is. I just want it to spot weld my car bodies perfectly, repeatedly and cheaply.
People adapt to technology -- you dont need to anthropomorphize the outputs, you need to make them simple to understand. LEDs, tones, motion etc can all do this without getting in the way of a robots core functions the way a sophisticated expressive system would. R2D2 'nuff said