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

Protoclone: Bipedal, musculoskeletal Android

clonerobotics.com

Post reply on HN
Print view View original

21–30 of 54 posts

Re: Protoclone: Bipedal, musculoskeletal Android

#21

Post by dyauspitr »

viraptor wrote: post #8

It looks fun, but I'm still amazed by companies trying to create humanoid robots. I mean, any automation, factory improvement, transportation, etc. will be achieved with fewer issues and easier maintenance by purpose built robots. Alternatively by something simple but adaptable (like mounted or mobile arms with different attachments). Unless they're building a sexbot or art... who exactly is the target here? (I get t…

We already have purpose built and it’s not enough. The world is built around the human form so if a human can do it an android can.

Re: Protoclone: Bipedal, musculoskeletal Android

#22

Post by viraptor »

jayd16 wrote: post #19
viraptor wrote: post #11

Earlier quoted context omitted.

Why would you want to use human tools? Human tools exist because of how we work. If you're building a robot, it's extremely easier to give it a functionally equivalent attachment instead. (rather than a functionality equivalent arm with enough fine-grained pressure feedback to be able to reliably grab things) Teleoperation works great on purpose built robots too - for example https://www.bbc.com/future/article/201405…

Well I don't know that I quite buy it myself but if you want the thing to work along side humans you can't just put special handles in everything. If you want a robot to pour you coffee from a coffee maker humans also use, how do you imagine that working?

> If you want a robot to pour you coffee from a coffee maker humans also use, how do you imagine that working?

Two standardised grabbers for round and flat things. Simple three-finger device should cover almost all of the dishes. Same for water/beans refills. Zigbee/wifi/ir/whatever local comms to trigger the coffee machine.

Re: Protoclone: Bipedal, musculoskeletal Android

#23

Post by djokkataja »

viraptor wrote: post #8

It looks fun, but I'm still amazed by companies trying to create humanoid robots. I mean, any automation, factory improvement, transportation, etc. will be achieved with fewer issues and easier maintenance by purpose built robots. Alternatively by something simple but adaptable (like mounted or mobile arms with different attachments). Unless they're building a sexbot or art... who exactly is the target here? (I get t…

It looks like it's supposed to be a general purpose robot servant, although "Follows you around" from the list of skills on the pre-order page is hilariously disturbing. There would be a market for people willing to pay for a very humanlike robot, for the novelty if nothing else.

Plus if you want to make a robot which can do everything a human can do, without exception, you'll start running into weird edge cases if you make it with a fixed wheeled base. Like suppose you want it to climb a ladder or turn sideways to slip into a narrow space and retrieve something. Or maybe you want it to be able to climb in and out of vehicles designed for human occupants. Would you want to have to buy a special vehicle to bring your robot somewhere with you?

And judging by the name of the company and that they likely aspire towards more than what they've made so far, I'd guess that a long-term goal could be to also make something for people who realize the weakness of their flesh and crave the strength and certainty of steel.

Re: Protoclone: Bipedal, musculoskeletal Android

#24

Post by ekianjo »

viraptor wrote: post #8

It looks fun, but I'm still amazed by companies trying to create humanoid robots. I mean, any automation, factory improvement, transportation, etc. will be achieved with fewer issues and easier maintenance by purpose built robots. Alternatively by something simple but adaptable (like mounted or mobile arms with different attachments). Unless they're building a sexbot or art... who exactly is the target here? (I get t…

The world is a human interface. Instead of building robots for every specific task out there, this approach mimics the interface so that robots can replicate what humans are expected to do.

Re: Protoclone: Bipedal, musculoskeletal Android

#25

Post by ekianjo »

viraptor wrote: post #11
loanedempathy wrote: post #10

Earlier quoted context omitted.

Using humanoid robots means you get to reuse human tools and workflows, and use teleoperation (and training) until your AI catches up.

Why would you want to use human tools? Human tools exist because of how we work. If you're building a robot, it's extremely easier to give it a functionally equivalent attachment instead. (rather than a functionality equivalent arm with enough fine-grained pressure feedback to be able to reliably grab things) Teleoperation works great on purpose built robots too - for example https://www.bbc.com/future/article/201405…

Because all these tools already exist and require zero research.

Re: Protoclone: Bipedal, musculoskeletal Android

#26

Post by conductr »

viraptor wrote: post #16
HnUser12 wrote: post #15

Earlier quoted context omitted.

If the goal is to commoditize, does it not make sense to have a humanoid that you can sell to individual households? Not everyone would want to have a purpose-built robot arm in their kitchen. But this may be an easier sell if it works well.

What's the point of a humanoid in that case? Light frame on rollers would be much safer. There are rolling designs that can deal with stairs too. Humanoids waste lots of energy just balancing themselves and use precise adjustments (toes do quite a bit of work here). And if they fail at balancing, you've got tens to hundreds kilograms of equipment falling through a wall / on your possessions / on somebody. Equipment t…

I think the point is your humanoid is effectively as capable as you. If that was the only job worth solving, purpose built makes sense, but a general human form can (in theory) serve any purpose which is kind of the holy grail.

I don’t need to buy a roomba or the lawnmower version or hire a pool service or cleaning service, etc. if this one device can do it all. That makes this problem space extremely valuable. And the human form is a known form that can do all these things.

Even the things like food delivery robots, and food delivery fees of all types, grocery store pickers, some gig workers, etc. they kind of go away if I can tell this humanoid to run to McDonald’s and get me a #2

Re: Protoclone: Bipedal, musculoskeletal Android

#27

Post by Joel_Mckay »

quanto wrote: post #12

Their video: https://www.youtube.com/watch?v=H7dhwFcuUn0 Taken at face value, it is a very cool project. With pneumatic muscles, the biggest challenge is actually not strength but control. Fine strength/distance control is difficult. Pneumatic muscles are more for bang-bang control (on/off). The company seems to address this issue by having many "myofibers" and recruiting the fibers one by one. However, in the video,…

Indeed, the valve/line/pump mass will greatly dominate design cost.

The reason no one uses pneumatic actuators for repeatable positioning systems is gas is compressible, adiabatic thermal problems, and dangers when something fails.

Never saw automatons as particularly practical either, as the motion control planner balloons in complexity. Makes creepy looking sculptures though... =3

Re: Protoclone: Bipedal, musculoskeletal Android

#28

Post by rck »

They're claiming some revolutionary "synthetic muscle," but is there video of one of these things walking? If it's just pneumatics then this is a repeat of the early androids out of Japan, which looked cool but never got up and moved - they were basically just impressive animatronic dolls. My guess is that this ends up being something similar.

Re: Protoclone: Bipedal, musculoskeletal Android

#29

Post by conductr »

ulrikrasmussen wrote: post #18
viraptor wrote: post #11

Earlier quoted context omitted.

Why would you want to use human tools? Human tools exist because of how we work. If you're building a robot, it's extremely easier to give it a functionally equivalent attachment instead. (rather than a functionality equivalent arm with enough fine-grained pressure feedback to be able to reliably grab things) Teleoperation works great on purpose built robots too - for example https://www.bbc.com/future/article/201405…

Assuming the cost of the droid is low enough, I think the use-case is to have it do ad-hoc tasks using the tools you have at hand right now, without the need to invest in an expensive specialized tool which only the robot can use. The idea is not efficiency but versatility.

Yeah I think of it this way. I have an expensive vacuum and an expensive lawnmower. I paid a lot because they have a pretty dumb level of auto (eg roomba). If I could have bought a commodity push vac and push mower this humanoid could operate it. But they could also serve dozens of other valuable services with cheap existing tools for which no roomba equivalent even exists. At some point being surrounded by purpose built robots is not the best strategy even though when you are only focusing on a single purpose a specialized robot seems best.

Someone made a comment about energy efficiency and Bitcoin and AI should tell you everything about how much “we” actually care about energy efficiency, if this robot had infinite learning potential and the physical ability of a human it’s totally going to win out in the race to mechanize the world.

Re: Protoclone: Bipedal, musculoskeletal Android

#30

Post by culopatin »

quanto wrote: post #12

Their video: https://www.youtube.com/watch?v=H7dhwFcuUn0 Taken at face value, it is a very cool project. With pneumatic muscles, the biggest challenge is actually not strength but control. Fine strength/distance control is difficult. Pneumatic muscles are more for bang-bang control (on/off). The company seems to address this issue by having many "myofibers" and recruiting the fibers one by one. However, in the video,…

And beyond that, what does maintenance look like? A few fibers get, is it done? Is it modular?
Post reply on HN