https://lite.berkeley-humanoid.org/ is only $5000. What's the extra $3000 get me?
Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots
11–20 of 98 posts
Re: Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots
#12I love the idea of humaniod robot and commercially available. I like to think of such expensive things as an investment rather than a toy if I have to buy. Question is what are some good use cases that can be solved with such a humanoid robot ?
Re: Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots
#13I have some technical questions about feet.
Human feet have metatarsophalangeal joints connecting the toes to the rest of the foot. But humanoid robots don't have these (at least, the vast majority don't). Why? These joints are very useful.
Also, the bottom of the human foot is soft and has thousands of nerve endings. Can we really expect robots to get anywhere near human mobility performance without this level of compliance and sensory sophistication?
Re: Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots
#14https://lite.berkeley-humanoid.org/ is only $5000. What's the extra $3000 get me?
Yeah, really like that project. The main difference is that it's much shorter than ours, and shorter robots are cheaper. The downside is that it can't really reach normal human spaces. Actually, we made another robot called Zeroth Bot which you can build for $350 if you want: https://docs.kscale.dev/docs/zeroth-01
We are planning to release a similar-size robot later this year (calling it M-Bot) that will be closer in height and price, but our current focus has been on launching the full-size humanoid.
Mechanically, I think Berkeley Humanoid Lite is pretty similar to the 3D printed one we made last year. Our main focus with the K-Bot redesign was to make it not break so much. 3D printed components break a lot and repair time can be quite long. Also, having the wiring routed internally makes a huge, huge difference. So there are some benefits to doing QA on a manufacturing line in terms of quality and consistency.
Re: Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots
#15https://lite.berkeley-humanoid.org/ is only $5000. What's the extra $3000 get me?
Yeah, really like that project. The main difference is that it's much shorter than ours, and shorter robots are cheaper. The downside is that it can't really reach normal human spaces. Actually, we made another robot called Zeroth Bot which you can build for $350 if you want: https://docs.kscale.dev/docs/zeroth-01 We are planning to release a similar-size robot later this year (calling it M-Bot) that will be closer i…
How far away from robot hands/manipulators that are dexterous enough to repair other robots?
Re: Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots
#16Earlier quoted context omitted.
I spent two years on Tesla's FSD team, and I think from a cash flow perspective for funding R&D this model did make a lot of sense - basically, it takes cash upfront for training models, but there's zero marginal cost for distributing the models once you've developed them. I think this kind of "promise the future, pay now" model does alienates some people, especially when the tech is not ready today. That's why we're…
From a cash flow perspective of course it makes sense to sell the future before you have it as working product. It just needs a great salesman or narrative to keep it going, im not arguing that. > that feedback loop is very important for improving machine learning models at scale Oh will you have your own feedback loop with let's say user's data? Or you meant as an example? > * That's why we're open sourcing everythi…
> Oh will you have your own feedback loop with let's say user's data? Or you meant as an example?
That's more or less the idea - obviously since it's open source we wouldn't scrape peoples' data without their consent, but I would hope that people would contribute to the project in some form. Like, the core idea of the open source ethos is that building something like this collaboratively is a better / cheaper way to scale data collection / experience than us trying to collect all the data ourselves.
> it does not increase the chances of it being ready/autonomous in the future.
Yea that's true. At the end of the day it's just technical execution, so it's pretty risky. I just prefer that if people sign up for something risky, it's pretty transparent what exactly it is they're signing up for :)
Re: Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots
#17Pretty sweet! Don’t have the time (or budget) to directly invest in the hardware but do you have a list of open source “open” software problems you are looking to solve?
We do! https://bounties.kscale.dev/ We haven't updated it much but it's a good starter point
Amazing, pretty nice list! Two quick suggestions:
a) some of these definitely look they could be done without hardware or with light hardware support from a staff member?
b) if you do a) and are open source completely I bet you don’t even need to do bounties. The increased participation could mean some great community generated solutions quick.
Re: Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots
#18https://lite.berkeley-humanoid.org/ is only $5000. What's the extra $3000 get me?
Yeah, really like that project. The main difference is that it's much shorter than ours, and shorter robots are cheaper. The downside is that it can't really reach normal human spaces. Actually, we made another robot called Zeroth Bot which you can build for $350 if you want: https://docs.kscale.dev/docs/zeroth-01 We are planning to release a similar-size robot later this year (calling it M-Bot) that will be closer i…
obviously there's more to the kinematics than making the legs longer, but can't they just make the legs longer for it to be taller?
Re: Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots
#19Earlier quoted context omitted.
Yeah, really like that project. The main difference is that it's much shorter than ours, and shorter robots are cheaper. The downside is that it can't really reach normal human spaces. Actually, we made another robot called Zeroth Bot which you can build for $350 if you want: https://docs.kscale.dev/docs/zeroth-01 We are planning to release a similar-size robot later this year (calling it M-Bot) that will be closer i…
How far away from robot hands/manipulators that are dexterous enough to repair other robots?
That is a good question. I think mechanically we're probably there today, but on the intelligence level, who knows... If I had to guess, probably 1-3 years
Re: Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots
#20Earlier quoted context omitted.
Yeah, really like that project. The main difference is that it's much shorter than ours, and shorter robots are cheaper. The downside is that it can't really reach normal human spaces. Actually, we made another robot called Zeroth Bot which you can build for $350 if you want: https://docs.kscale.dev/docs/zeroth-01 We are planning to release a similar-size robot later this year (calling it M-Bot) that will be closer i…
obviously there's more to the kinematics than making the legs longer, but can't they just make the legs longer for it to be taller?
Longer legs means more inertia on the actuators, which means bigger actuators + bigger battery, which means heavier robot, which means...