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

Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots

news.ycombinator.com

Post reply on HN
Print view View original

71–80 of 98 posts

Re: Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots

#71

Post by lucubratory »

codekansas wrote: post #65
lucubratory wrote: post #59

Hey, just chiming in to say that I think this project is really cool even though it's outside the price range of what I can spend on a cool hobby. I'm disabled, and one thing I'm really interested in long-term for humanoid robots is disability support work. Disability support work involves a huge variety of individual tasks, as many as a typical person will do in their life, so it's a good fit for an extremely genera…

This is really interesting to read about. To be honest, I know very little about this space, but it's something a few people have approached me about tackling. I do think that this is a great application of a general purpose robot. I'm not sure what the technical timeline will be, but it would certainly be cool for my parents to have such a robot when they are elderly.

I spend a lot of time thinking about it day-to-day because of my disability and reliance on multiple disability support workers, as well as living with my husband who is also disabled, so if you ever wanted to talk to someone with disability support workers feel free to ask.

Re: Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots

#72

Post by dan344 »

codekansas wrote: post #68
dan344 wrote: post #63

So the non full autonomy would mean little software upgrades? More do it yourself? Also, what’s the different bt the computes: like what’s the onboard computer running (the 2 options)? Thanks.

Yeah, the basic robot is just a robot, albeit with open-source software and hardware For compute - we're exploring a few boards right now, but the base model will be something from Amlogic and the higher end model will be something from Nvidia

nice! For manipulation taskes, is kscale planning to train in sim mostly and transferring to real, or is some imitation learning used, like with gloves and such? maybe both?

Appreciate it

Re: Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots

#76

Post by nativeit »

idiotsecant wrote: post #58
codekansas wrote: post #47

Earlier quoted context omitted.

Yes, we are aware of this customer segment. I don't think they have thoroughly considered the implications of what high torque actuators can do to the human body

You might have a significant portion of those customers that are into that

Castration via motorized actuator? Pretty niche kink, I'd say.

Re: Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots

#77

Post by nativeit »

I give you a lot of credit for your communication and openness. I am afraid full-autonomy is a fairy tale to rationalize the ungodly expense of LLMs, I personally would find taking money on spec for something like fully autonomous robotics to be a little shaky, ethically speaking. But then, I don't believe this is an unsolved problem, I believe this is an unsolvable problem, so more of a philosophical difference than an empirical position at this point.

Re: Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots

#78

Post by codekansas »

nativeit wrote: post #77

I give you a lot of credit for your communication and openness. I am afraid full-autonomy is a fairy tale to rationalize the ungodly expense of LLMs, I personally would find taking money on spec for something like fully autonomous robotics to be a little shaky, ethically speaking. But then, I don't believe this is an unsolved problem, I believe this is an unsolvable problem, so more of a philosophical difference than…

I think it's a very hard problem, but I would like to align our company's incentives towards solving it

Re: Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots

#79

Post by codekansas »

randomNumber7 wrote: post #70
codekansas wrote: post #67

Earlier quoted context omitted.

My overall plan is basic joystick control -> VLA with RL -> self-supervised embodied representation -> end-to-end RL -> end-to-end control. I suspect there will be some very good multi modal models coming out in the next few years which we might use as base models, although more likely, we will adapt their techniques to work on data from our own robot. I agree that the hardware is easier than the software - I am a so…

I like the K-Sim Gym. Im looking forward to fiddle with it a bit when I have more time. I could see that you get something usefull out of people competing on your leaderboard xD It's my hot take that the next big ML breakthrough needs s.th. that learns from its own actions in an environment, so this goes in the right direction imo. On the other hand a lot of big companies struggle with self driving cars even though t…

I really do think that building through the open source community is the best way to compete with the big players, even without having a lot of capital. Of course, it doesn't mean we can't execute well, but I do think it's a good way to make a lot of progress without spending a lot of money.
Post reply on HN