Live data from Hacker News

Xiaomi-Robotics-1

robotics.xiaomi.com

51–60 of 347 posts

Re: Xiaomi-Robotics-1

#51

Does this require a given hardware platform, or for example, could I run this model with a cheap mini robot with a single camera (i.e. good enough without depth), tracked treads, and an arm?

When the page says "embodiment-free (UMI)" it means they've used a standardised gripper and camera arrangement [1], while aiming to be agnostic to the type of robot arm that gripper is attached to.

[1] https://umi-gripper.github.io/

Re: Xiaomi-Robotics-1

#52
post #16

Coining the term: Slopfold When you Robot folds your clothes but it's kinda wrinkly and sloppy but you accept it anyway because it's easier than precisely folded and pressed clothes.

When AI is a the forefront of scientific breakthroughs and all human endeavor is painfully minuscule compared to AI, we'll still be calling it slop as we all hypocritically generate more and more slop.

Re: Xiaomi-Robotics-1

#53

Of all the tasks I do, folding clothes takes a ridiculously small slice of my time. Is this and all the other robotics videos aimed at H&M staff?

As a parent with 3 kids and both my wife and I working, folding clothes is the most tedious household chore. It's physically and mentally exhausting (unlike doing the dishes, which is only physically exhausting as I can wash piles of dishes while zoning out). And not to mention take so much time, a week's worth of unfolded pile of clothes for our entire household can take me 1-2 hours to fold uninterrupted (2-3 hours if I do it while watching Netflix or something).

Re: Xiaomi-Robotics-1

#54
post #28

Designing a non humanoid robot is the way to go. The design of new tools and appliances for hybrid human/robot use will eventually follow: the zip line for the shoe bag required way too much precision work.

I can't believe someone shares my point of view. We have already many non humanoid robots to do boring stuff (underwater maintenance, stuff like that). For some reasons people tend to think that for robots to do stuff close to humans, we need human like robots.

We do not. I want a swarm of insects-like robots to fight mosquitos. A snake one that fixes my pipe. A spider-like robot that cleans surfaces. Etc.

Re: Xiaomi-Robotics-1

#55
post #34
post #16

Coining the term: Slopfold When you Robot folds your clothes but it's kinda wrinkly and sloppy but you accept it anyway because it's easier than precisely folded and pressed clothes.

Isn't that the story of technology? When the coffee machines first came to be, Barista was definitely a better option. However, through the evolution, in many cases today machine does better job than barista.

Better analogy would be that even though the coffee machine is still worse, we choose it because it's more convenient (at least I think that's the case).

Re: Xiaomi-Robotics-1

#57
post #28

Designing a non humanoid robot is the way to go. The design of new tools and appliances for hybrid human/robot use will eventually follow: the zip line for the shoe bag required way too much precision work.

I will suggest mix of both: some everyday tools are already built for being used with hands and legs (e.g opening a door). But indeed adding some different grip types, additional arms, etc, could be helpful.

Re: Xiaomi-Robotics-1

#58

It makes me think of why couldnt they just automate ironing and folding. I can stick stuff in the suitcase myself.

Automated ironing sounds like massive fire hazard even for showing off video.

Re: Xiaomi-Robotics-1

#59

Watching the two-handed robot has me thinking that a third hand, perhaps with a different set of capabilities (like a tentacle grip) might make many tasks easier. I realise that more limbs = more problems, but even so, having additional ways to hold and turn things would be a big help.

My thoughts exactly, but to train it you'd need a lot of data with someone manually operating it. With just two hands it's enough to have a lot of footage of humans doing it. Maybe down the line the robots will be able to self-improve or someone will come up with ways to optimize this..

Re: Xiaomi-Robotics-1

#60
post #54
post #28

Designing a non humanoid robot is the way to go. The design of new tools and appliances for hybrid human/robot use will eventually follow: the zip line for the shoe bag required way too much precision work.

I can't believe someone shares my point of view. We have already many non humanoid robots to do boring stuff (underwater maintenance, stuff like that). For some reasons people tend to think that for robots to do stuff close to humans, we need human like robots. We do not. I want a swarm of insects-like robots to fight mosquitos. A snake one that fixes my pipe. A spider-like robot that cleans surfaces. Etc.

the cube shaped one that I put my dishes in.
Post reply on HN