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

Humanoid Robot Actuators

firgelli.com

Post reply on HN
Print view View original

61–70 of 82 posts

Re: Humanoid Robot Actuators

#61

Post by fragmede »

rob74 wrote: post #38
po1nt wrote: post #26

Earlier quoted context omitted.

Why not make a robotic chair? Why not build our environment out of specialized robots instead of using a hammer for everything?

Sure, there are already robot vacuum cleaners, but I somehow fail to imagine how (a) specialized robot(s) that can e.g. sort your used laundry, wash it, dry it, iron it (if necessary), fold it and put it back into the cupboard would look like?

If we're designing magic future devices, why are they separate machines? It wouldn't take a robot, I'd just dump my dirty clothes in one end of the machine, and the other end of the machine is my dresser drawers. We can't even handle smushing the washing machine and dryer into one machine, and that technology exists today.

And the other thing is, why is the washing machine itself not seen as a specialized robot? Like if you're designing a machine to machine machines, doesn't it make sense to revisit the whole thing?

Re: Humanoid Robot Actuators

#62

Post by fragmede »

ReptileMan wrote: post #8

Except we don't need 100% bipedal robots. Wheels are perfectly ok for majority of city work and factory floor. Put the robot on rollerskates break the wheels for the occasional stair.

I don't know about your city, but my city, while covered in smooth surfaces, still has a lot of interactions between those surfaces. Most of the roads have a curb between the sidewalk and the road, though the ADA means there's curb cuts and ramps. I don't know that I'd agree that they're "perfectly okay". Traversing over a 20 cm/8 inch obstacle constantly seems to make wheels less than perfect.

Re: Humanoid Robot Actuators

#63

Post by fragmede »

mattclarkdotnet wrote: post #57
thrownthatway wrote: post #48

Earlier quoted context omitted.

I need to get on to one of the prediction markets. I’m willing to bet we’ll have a humanoid robot that can drive a car before we have level 5 autonomous vehicles. And by can drive a car I mean a general purpose humanoid robot that can do basic household chores like move the car and wash it with a foaming brush and a hose. I don’t mean the robot will be capable of sitting in any regular car and doing level 5 autonomou…

So you’re wanting to bet that we’ll get humanoid robots capable of driving a dumb car at L4 before we get cars capable of L5? When we have no humanoid robots driving cars, and many L4 cars driving around? I’ll take that!

Geohot's Comma.ai body is going in that direction, so the question is how much do you want to bet?

Re: Humanoid Robot Actuators

#64

Post by regularfry »

Animats wrote: post #12
Fraterkes wrote: post #11

Earlier quoted context omitted.

Silly question maybe, but didn’t Boston Dynamics have videos of bipedal robots doing acrobatics / running ~7/8 years ago? Kinda looked like they “solved” locomotion then

Their approach required pre-computation and simulation before execution. If you watch their videos carefully, you can see the advance planning work on some of the screens.

Some of it was pre-computed. The middle layer, if you like. The Boston Dynamics group had walking gait of a sort nailed in the 80's; the trotting-on-the-spot that BigDog did was essentially a continuation of those mechanics and that's all based on a conceptually simple balance problem which is intrinsically reactive and not pre-planned. So that's what was going on at the lowest level.

At the top level you have the actual environment, with those meme videos of the robot trotting through a car park, getting kicked off balance, and recovering. The whole point of those tests was to demonstrate how robust their tech was to non-precomputed disturbances.

And between the two you've got the direction and planning layer, telling the robot to go from A to B with some set of suitably convoluted parameters that nobody but the operators would have understood. That planning layer might do all sorts of pre-computation and simulation but it needs to do it in the context of a noisy and possibly adversarial environment. That's equally true for Atlas as much as it was for BigDog, even when there's nobody actually kicking it. What I suspect the precompute and simulation is doing at that layer is a) checking for physical viability of the requested route, and b) parameter tuning in response to sensor readings over a number of runs. Not telling the robot the exact sequence of motions. But I'm nowhere near those teams (oh, I wish) to comment on whether that's true - maybe someone else round here is.

Re: Humanoid Robot Actuators

#65

Post by regularfry »

num42 wrote: post #2

Check out opensource actuator for robots. Opentorque actuator https://www.gabrael.io/new-page https://github.com/G-Levine/OpenTorque-Actuator

In the context of the torques in the article, a nylon sun gear in the gearbox feels optimistic.

Re: Humanoid Robot Actuators

#66

Post by ModernMech »

blueblisters wrote: post #51
RaSoJo wrote: post #35

How can we trust this article or the company if the writer/so-called chief engineer decides to hide himself behind an AI avatar? From what I can understand this is the Robbie Dickson in question: https://www.huffpost.com/entry/lessons-from-a-serial-ent_b_9... Nobody has a problem with companies using AI to edit articles, create images. But when even the writer is an AI persona, the trust factor gets destroyed.

You evaluate the merits of the content? From a high-level systems pov, the article is largely correct, even if some details might be missed / simplified

Nobody is interested in correct information anymore. In 2026, trustworthy information is what people want.

Re: Humanoid Robot Actuators

#67

Post by regularfry »

amelius wrote: post #60

Those running blades used e.g. in the paralympics can make locomotion more efficient.

Similar principle taken to more of an extreme: https://is.mpg.de/publications/bb01

I really want to build one of those, they look great fun. (specifically in context of the article I want to see what happens if you lower the CG. Harder balance problem, but might reduce some of the instantaneous torques)

Re: Humanoid Robot Actuators

#68

Post by RaSoJo »

ModernMech wrote: post #66
blueblisters wrote: post #51

Earlier quoted context omitted.

You evaluate the merits of the content? From a high-level systems pov, the article is largely correct, even if some details might be missed / simplified

Nobody is interested in correct information anymore. In 2026, trustworthy information is what people want.

Yes. This distinction is important.

As a lay person, I have limited knowledge of this field, yet am extremely interested. Unfortunately AI gen content is being used widely to spread spurious information/fake news etc. So my knee jerk reaction to AI gen content is - "this is going to be fake".

If the information you are trying to convey is true, and is technical/objective in nature, then why shy away from associating your identify to it?

Re: Humanoid Robot Actuators

#69

Post by ModernMech »

ofrzeta wrote: post #28
gpugreg wrote: post #27

This is AI slop and the article contains some of the worst illustrations I have ever seen. Most do not make any sense mechanically. Here are the worst ones: - The "orbiting threaded rollers" in figure 6 are not meshing with anything (not that they could, since they are orientated in the wrong direction). - The ball of the ball screw in figure 7 deforms the screw and the roller screw "meshes" with a flat surface. - Th…

Is it? Now I feel bad for having posted it. I mean, I know some stuff but not enough to judge over all the content in this article. It's unfortunate but from glancing over I thought it was a comprehensive and useful resource. I guess I will just give up on the Internet or something like that.

You just need some AI literacy, this document is very plainly AI generated. You don’t need to be an expert in the content to see that. First time you see an em dash your AI sense should be tingling. Then you see random bolded words alarm bells should be going off. Next you notice 70% of the headlines follow the pattern “The X: Y” and that seals it.

Re: Humanoid Robot Actuators

#70

Post by regularfry »

blueblisters wrote: post #53
vova_hn2 wrote: post #39

Probably a dumb question, because I know nothing about robotics, but: > The "Zero RPM" Problem > When a robot bends its knees to stand, the motor must constantly fight gravity. There is no skeletal structure to lock against. To an electric motor, holding a static load—known as stall torque—is the most punishing state possible. Why not just add some kind of brake that can fully or partially lock the joint?

Brakes are being added to actuators but they're more useful for static holds / locking than dynamic balancing. Standing even in humans is a dynamic balancing activity.

It is, but you don't have to do it at every joint all the time. If you lock your knees your front and back thigh muscles don't have to work on balancing in that axis at all.
Post reply on HN