Live data from Hacker News

Xiaomi-Robotics-1

robotics.xiaomi.com

151–160 of 347 posts

Re: Xiaomi-Robotics-1

#151
post #139

Earlier quoted context omitted.

Absolutely! Also if this scale anywhere close to LLMs in 2 years they will fold at super human speed and much better than me.

The real question is whether a hardware platform today would be good enough. The model is software on a server or in the cloud, so the real question is are there any show stoppers from the hardware for going faster?

Physics. Right now the clothes folding is computationally limited, but assuming we get faster computers to get them folding faster, gravity and air resistance are still going to take their time.

Re: Xiaomi-Robotics-1

#152

I think this is the most satisfying video I’ve seen of a robot doing laundry. Not sure if it’s the camera angle, the 3× speed, or the music.

The uncut movie is at 2X speed.

You can easily save it on your computer, and then play it at 0.5X speed, to see it like in real life.

It was still satisfying.

Re: Xiaomi-Robotics-1

#153

Earlier quoted context omitted.

I am of course impressed by the model and the robot. Great stuff, But the downside is that won't we all just turn into the obese, stupid humans at the start of the WALL-E film? Mindfulness teaches us that we can enjoy the washing up, the laundry, planting seeds, tending the garden. It connects us to something. Without this will we end up with a rise in mental health issues, because for one thing people will just end…

Or we can use the free time to go to the gym. Anything that frees us from labour is good.

Unemployment frees us from labor too but it's not exactly good either, I'd rather avoid it.

Re: Xiaomi-Robotics-1

#154

I'm not sure why some comments here are so pessimistic. I was grinning ear to ear while seeing the video. You're telling me we've finally got robots that can do our laundry? And the model is at least as free as beer? To quote the lyrics/meme, we used to pray for times like this . This is what robotics should be used for.

> You're telling me we've finally got robots that can do our laundry? Did you watch it actually fold that shirt? Super slow and bad at it.

So what? it can take hours to do it and I can focus on something else. If these robots actually become available on affordable price I would buy one without blinking. It would totally free up my weekends, no more hours wasted doing laundry, cleaning the apartment etc.

Re: Xiaomi-Robotics-1

#155
post #96
post #56

The fact it didn't do the 2 second tshirt fold trick shows it's just copying trained movements. This is Automation not AI.

Well, couldn't it have been trained on the 2-second fold trick? Besides, it might require more precise or quick movements than a regular fold.

The movements are simple, but you must start with a much more precise grip, which seems difficult to achieve for a robot.

Re: Xiaomi-Robotics-1

#156
This is amazing! I can see in a few years having Home Assistant use an LLM to coordinate my home while I'm away. Tell the LLM to make an inventory of my home and then send the vacuum and the robot around to clean everything up. A multimodal LLM can inspect pictures for items that need to go in the dishwasher, the laundry or needs polishing and reorganise my closets to best allocate space, make the beds, take care of the plants. It has all day to do it while the solar panels provide ample energy anyway.

Re: Xiaomi-Robotics-1

#157

Earlier quoted context omitted.

> You're telling me we've finally got robots that can do our laundry? Did you watch it actually fold that shirt? Super slow and bad at it.

The very first car was absolutely awful. Super slow and bad at it.

Xiaomi's first car, on the other hand https://youtu.be/KGW8bQtcpJg

Re: Xiaomi-Robotics-1

#158

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?

Funny you mentioned H&M. They are boycotted on China due to their public stance against slave labour: https://www.bbc.com/news/business-57691415 It is important to remember that China is not only about open weight LLMs, fastest cars and flying taxis. There is still a lot of very serious human right abuse going on in this country.

When the last day's news were about other people shot dead by ICE without a plausible reason, it is hard to take seriously discussions about human rights abuse coming from USA. It is hard to imagine a more serious abuse than being randomly killed on the street, while walking or driving during your normal daily routine.

Unfortunately, there are very few, if any, countries remaining where human rights abuses are not frequent, so mentioning them in unrelated technology discussions has become non-relevant.

Re: Xiaomi-Robotics-1

#159
post #88
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 think this perspective is now demonstrably false. It was basically the defacto position of most roboticists until a few months back. But we've already seen the cost of humanoid robots fall precipitously (even without the kind of mass production that genuinely useful home and real world intelligence would bring). Which seems more likely, that cheap humanoids will continue to improve in dexterity, battery life, stren…

It’s not demonstrated yet as we still have to see a robot (humanoid or not) doing mundane tasks in full autonomy, efficiently and convincingly.

It still looks inefficient to have a humanoid robot vacuum a house by using an ergonomic tool designed around the human body.

Re: Xiaomi-Robotics-1

#160

I'm not sure why some comments here are so pessimistic. I was grinning ear to ear while seeing the video. You're telling me we've finally got robots that can do our laundry? And the model is at least as free as beer? To quote the lyrics/meme, we used to pray for times like this . This is what robotics should be used for.

> This is what robotics should be used for.

I disagree. We should use robotics to extend our reach into hazardous environments, enhance our physical capabilities, or to provide a steady handling of things where it's absolutely needed - doing laundry in my household is none of these.

Folding laundry takes me 10 mins every 10 days. I organize my closet once in a while according to my sense of fashion, and now I'll just need to keep that structure. I don't always like to do these chores, but I have no issue in acknowledging them as part of my responsibilities. Why would I even automate[0] that?

Robotics is costly, and I see no way how that would change anytime soon. That isn't a flaw of some kind either, it's rather just one of the limitations that needs to be accounted for, neglecting that would be detrimental to the future I envision.

Don't get me wrong, I love robotics with a passion, as engineer I like to tinker, and I'm a big admirer of FESTOs bionic research[1]. It's just that the field suffers from an "overpromised and underdelivered" aura as far as I can remember, and I remember the presentation of ASIMO[2] 26 years ago.

Some people would like to see the field hyped up, focused on the consumer like every other field in tech, probably for financial gain, but I personally see the value in its downplay. To be honest, I love these reality checks, as I see them as a valuable part of the learning process all together - a journey for what it means to automate, and what it means to define as human natural chore.

[0]: https://xkcd.com/1205/

[1]: https://www.festo.com/us/en/e/about-festo/research-and-devel...

[2]: https://en.wikipedia.org/wiki/ASIMO

Post reply on HN