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

Artificial muscles robotic arm with full range of motion [video]

youtube.com

Post reply on HN
Print view View original

61–70 of 75 posts

Re: Artificial muscles robotic arm with full range of motion [video]

#61

Post by harperlee »

animal531 wrote: post #16
m0zg wrote: post #11

For comparison, a decently trained human male can hold approximately 80kg (175lb) per hand (350lb total) fairly easily without any assists such as straps, and without using hook grip. With hook grip or straps, the strength of your back is the limiting factor. That said, as a first step this is very impressive and very lifelike, too. The main issue with this is going to be proprioception more than anything - it doesn'…

I have a really bad back and as a result I can't really exercise. So let's say I can carry 8kg max per hand (1/10th). And yet I'm a fully functional adult human being and can get by perfectly fine in life. So for me from a robotics point of view a much smaller starting range is perfect, once you've built it into a platform you can start optimizing and increasing potential.

I always joke that if I build a robot I will first target a very old person that can ask for help in a lot of situations. Weak muscles, slow moving, and yet the world will adapt to it, seeing that it is fragile and it needs our help for some things.

Re: Artificial muscles robotic arm with full range of motion [video]

#62

Post by robomartin »

goldenkey wrote: post #46
robomartin wrote: post #45

Well, this technology dates back to the 1950's. https://en.wikipedia.org/wiki/Pneumatic_artificial_muscles Hydraulic, rather than pneumatic, operation has also been attempted. Fun stuff, but nowhere close to being practical in any way for real world robotics. And, no, it isn't a matter of iterating and optimization. These kinds of actuators will never be anywhere close to the energy efficiency and technical simplicit…

Reusable rockets weren't practical either. But someone was maverick enough to attempt it anyways. [1] You provide valuable information but I just hate how you succumb to easy thinking, an appeal to tradition [2]: "well it hadn't been done then so it can't possibly be done now." It's a form of anachronistic gatekeeping. It doesn't belong in the age we currently reside in. We have totally different computational abilit…

> I just hate how you succumb to easy thinking, an appeal to tradition

No. I appeal to PHYSICS.

This isn't an emotional argument. Or one out of "tradition".

The reusable rocket was a question of implementation, not physics. The math actually supported the idea of being able to do that. It wasn't some magical juju bean Musk pulled out of his behind. They did the math. The math proved you could do it. They built it. It took a lot of trial and error and, yes, failure, but they KNEW the math supported the concept.

This inflatable muscle thing (air or fluid) isn't supported by the PHYSICS.

What do I know anyhow? I've only been in robotics since the early 80's. I have literally seen in robotics and artificial intelligence since that time. And here we are, we still don't have a robot of any kind that is as capable as a house fly, even with a supercomputer running it remotely.

And that, BTW, is the test for fantastical actuators. The technology has to support an amazing range in terms of scale. At one extreme you have something like an ant and, opposite that, an elephant. Even within a human being the range of size and strength in muscles is likely 1000 to 1 (haven't done the math).

> Boston Dynamics would have never created Atlas or Spot

I don't think you have a good sense of what these machines are and are not. Hint: They are not what you think they are.

Re: Artificial muscles robotic arm with full range of motion [video]

#63

Post by micromacrofoot »

fho wrote: post #48
micromacrofoot wrote: post #43

Earlier quoted context omitted.

These things always start off large and gradually get smaller (and often miniaturization is where the really interesting optimizations come), apparently this apparatus can already fit roughly within a human-sized body... which isn't a bad start.

While this definitely is an impressive an impressive one, those artificial pneumatic muscles have been around for ages [1] but have not become much smaller. My guess would be that there is some physical limit on how useful they can be. [1] https://en.wikipedia.org/wiki/Pneumatic_artificial_muscles

Physics certainly makes fools of us all.

Re: Artificial muscles robotic arm with full range of motion [video]

#64

Post by fstrthnscnd »

zakary wrote: post #57
conjectures wrote: post #17

Earlier quoted context omitted.

This and op is all wholesome content. On the criticism, do you think more limited / lab-bound systems will help develop control technology in advance of better muscles?

Short answer: yes. Long answer: I think that the more minds there are working on this (or any other interesting) problem, the more progress will be made. And we shouldn’t let the perfect be the enemy of the good enough. The field of robotics, and especially soft robotics like this, is so new and uncharted that individuals tinkering in their garage can and have made real advances for the field. That said, really good…

> There is no robot hand in the world that can do that simple task.

Is the technology dealing with interfacing with the brain good enough, even if on the arm side it's not?

Re: Artificial muscles robotic arm with full range of motion [video]

#65

Post by jjk166 »

m0zg wrote: post #11

For comparison, a decently trained human male can hold approximately 80kg (175lb) per hand (350lb total) fairly easily without any assists such as straps, and without using hook grip. With hook grip or straps, the strength of your back is the limiting factor. That said, as a first step this is very impressive and very lifelike, too. The main issue with this is going to be proprioception more than anything - it doesn'…

A trained human might be able to deadlift 350lbs under ideal circumstances like being in a gym. No one is capable of lifting and holding that sort of weight for an extended period of time. For an average human under realistic circumstances, lifting 100lbs over your head is a difficult task. Lifting much more than 50 lbs unassisted frequently in a work environment is likely to lead to injury.

Re: Artificial muscles robotic arm with full range of motion [video]

#66

Post by goldenkey »

zakary wrote: post #60
goldenkey wrote: post #46

Earlier quoted context omitted.

Reusable rockets weren't practical either. But someone was maverick enough to attempt it anyways. [1] You provide valuable information but I just hate how you succumb to easy thinking, an appeal to tradition [2]: "well it hadn't been done then so it can't possibly be done now." It's a form of anachronistic gatekeeping. It doesn't belong in the age we currently reside in. We have totally different computational abilit…

It is always good to question assumptions. One you could consider is the assumption that all problems are created equal. This isn’t the case. There are fundamental and practical limits to things. For this kind of artificial muscle actuator, there are fundamental limits to the way the physics works for this design which prevent it from ever simultaneously having good efficiency in energy and power density, high strain…

Material science is part of hydraulics. The hydraulic fluid could end up being next-gen.

Re: Artificial muscles robotic arm with full range of motion [video]

#67

Post by goldenkey »

robomartin wrote: post #62
goldenkey wrote: post #46

Earlier quoted context omitted.

Reusable rockets weren't practical either. But someone was maverick enough to attempt it anyways. [1] You provide valuable information but I just hate how you succumb to easy thinking, an appeal to tradition [2]: "well it hadn't been done then so it can't possibly be done now." It's a form of anachronistic gatekeeping. It doesn't belong in the age we currently reside in. We have totally different computational abilit…

> I just hate how you succumb to easy thinking, an appeal to tradition No. I appeal to PHYSICS. This isn't an emotional argument. Or one out of "tradition". The reusable rocket was a question of implementation, not physics. The math actually supported the idea of being able to do that. It wasn't some magical juju bean Musk pulled out of his behind. They did the math. The math proved you could do it. They built it. It…

No, your appeal is to the "cult of science." Science is a moving target. Hydraulics involves materials known as hydraulic fluid. Material science is in its infancy. Your appeal is nothing more than to pessimism and the edifice of cocksure.

Re: Artificial muscles robotic arm with full range of motion [video]

#68

Post by fasterbynight »

zakary wrote: post #10

This guy is a great engineer, I’ve been following his stuff for a while now. But there are unfortunately several fundamental limits which mean this type of system will likely never reach human level performance in a real world system. I work in robotics, specifically compliant and modular actuators, similar to the ones in the video. As I see it, (and many others in the field) One of the biggest issues in robotics is…

I don't see why electric motors are not backdriveable enough. Boston Dynamics' Spot uses electric motors with harmonic drive gearboxes (or some other backdriveable transmission) as an example of this. Similarly, series elastic actuators are very capable of giving the characteristics you deem necessary to work alongside humans albeit with lower bandwidth than the harmonic drive gearboxes.

Re: Artificial muscles robotic arm with full range of motion [video]

#69

Post by Baeocystin »

zakary wrote: post #10

This guy is a great engineer, I’ve been following his stuff for a while now. But there are unfortunately several fundamental limits which mean this type of system will likely never reach human level performance in a real world system. I work in robotics, specifically compliant and modular actuators, similar to the ones in the video. As I see it, (and many others in the field) One of the biggest issues in robotics is…

What do you think of Festo's air muscle system, or air muscles in general? I don't work in the field, so my opinions are that of a layman, but I've been impressed with what I've seen in their videos.

Re: Artificial muscles robotic arm with full range of motion [video]

#70

Post by robomartin »

goldenkey wrote: post #67
robomartin wrote: post #62

Earlier quoted context omitted.

> I just hate how you succumb to easy thinking, an appeal to tradition No. I appeal to PHYSICS. This isn't an emotional argument. Or one out of "tradition". The reusable rocket was a question of implementation, not physics. The math actually supported the idea of being able to do that. It wasn't some magical juju bean Musk pulled out of his behind. They did the math. The math proved you could do it. They built it. It…

No, your appeal is to the "cult of science." Science is a moving target. Hydraulics involves materials known as hydraulic fluid. Material science is in its infancy. Your appeal is nothing more than to pessimism and the edifice of cocksure.

Nice one.
Post reply on HN