K-Scale Labs: Open-source humanoid robots, built for developers
kscale.dev
See also Show HN: Train and deploy your own open-source humanoid in Python - https://news.ycombinator.com/item?id=44022106
kscale.dev
I do robotics research but not humanoid. Almost every component used in production came down drastically in price in recent years. Lidar sensors are a few hundred dollars now.
The moment your high gear reduction actuator is forming a contact with anything, it will have to either decelerate instantly, push the object away or move into the object by deforming it. If your robot arm is moving at speed and hitting a wall, the deceleration needs to shed all velocity in a few milliseconds. This is fine for the arm itself, but if you have a 100:1 gear reduction ratio, one gear is moving at 100 times the speed of the robot arm and since kinetic energy is 1/2mv^2, the energy stored in the gear is significant. Stop the arm and you'll break off the teeth on your gears!
Unless you have some energy dumping mechanism, like connect your servo to arm with flexible connector. Making whole arm or leg with bit flexible plastic will also reduce max load on gear. Precision will suffer, but should be still good enough for walk and house work. The problem with energy is that it should be undone when direction changes. This affects reaction time. And that time should be smaller for small, a... proportional to square root of size, right? That's how long it takes to fall. Not sure, didn't take into account the inertia of solid body.
BTW, heavily geared humanoid robots walk in some more stable way on bent legs. This is obvious on old videos. Like they are afraid to sh*t their pants. Also have problems with balance. Small hobby robots usually in addition to bent legs have huge feet. The point is, with servos it cannot be done much better.
We do have an entirely 3D printable robot with build guide here, if you're interested: https://docs.kscale.dev/docs/zeroth-bot-01#/
Looking forward to helping however we can
When I see a video of one of these things taking a shower, I'll think about buying it :-)
Would that still be too manual? I guess you could have another robot do it for you/it :)
Perhaps a more general way to put this is, think about having this bot in a house with a small child. It would need to clean itself after the kid gets it dirty, and it shouldn't stop working if the kid sticks a Lego brick in some gap.
These open framed robots are fine for development purposes, but for general use they don't seem practical.
https://www.goodthingsguy.com/fun/roomba-poohpocalypse-throw...
They also patched the known jailbreak methods early this year, so all newer models lack sensor access unless you pay Unitree massive $$$ for SDK access.
The base Go2 is a fun toy, though. There’s a high level web SDK you can use for free.
There are a lot of "really great, real soon now" humanoid robot startups.[2][3] As far as I can tell, nobody has yet deployed one in a production environment.
On the mechanical engineering side, it's likely that a drone company will have the first big low-cost product. Drone companies have people who understand sensors, balance, navigation, reliability, and weight/cost/strength tradeoffs.
[1] https://james.darpinian.com/blog/you-havent-seen-these-real-...
I mean if you're actually training humanoids in under an hour with sim-to-real transfer that "just works" then congrats, you've solved half of embodied AI
the vertical integration schtick (from "metal to model") echoes early apple, but in the robotics space that usually means either 1) your burn rate is brutal and you're ngmi, or 2) you're hiding how much is really off-the-shelf
Clearly the real play here, assuming it's legit, is the RL infra. K-Sim is def interesting if it's not just another wrapper over Brax/Isaac. Until we see actual benchmarks re say, dexterous manipulation tasks trained zero-shot on physical hardware, it's hard to separate "open-source humanoid stack" from the next pitch that ends in "-scale"
IMO humanoid companies do make a lot of big claims which is why it's important to make everything open-source. Don't have to take my word for it, can just read the code
IME the COTS angle cuts both ways. It brings costs down and makes iteration faster, but whats the moat then?
if the value is in integration, that’s fine, but integration is fairly fragile IP. Open source is good reputationally but accelerates the diffusion of your edge unless the play is towards community+ecosystem lock-in or being the canonical reference impl (cf. ROS, HuggingFace)?
I think humanoids are in their infancy. Eventually most of the margin will come from software capabilities, which we do plan to charge a lot of money for (like, download a software package and your robot can clean your house, that's probably worth something). But in order for that business model to work we need to have commodity, standardized hardware.
The tesla analogy makes sense to me but with a caveat: they still spend billions on CapEx and own verticals like battery chemistry and drivetrain design. In this case you’re betting that the value collapses upward into software, like the shift from phones to apps, but for that to work, your software has to deliver exponential delta per dollar
With that I think the real risk is that your "clean your house" package is deceptively hard in the long tail, and you will end up with the iRobot Roomba UX. Novelty fades fast when it constantly gets stuck under the couch or whatever the equivalent of that is for humanoids. To be fair iRobot/Roomba is a household name but still "only" a ~$1.5B company, which seems meager compared to ambitions in this space
As an aside I would love to see an RFC-style doc on how you think humanoid software standards should emerge. ROS is still a frankenstein, and someone needs to kill it gently lol
If I made ~15M USD/yr and was much younger, I’d strongly consider buying this, specifically because it seems wide open. Others will just buy it and won’t think about the cost, but they’ll probably consider the community. You can’t have community for something like this unless it’s open. If it’s open you’ll get early adopters which can help develop the community.
You must focus on making it better and cultivating a community first.
For reference, for the current Kbot to be 10% of your annual income, you would need to make $90,000 a year. And we plan to drive the cost down much much lower for the hardware.
Just like reprap worked a treat, I hope initiatives like this bring experimental bots into people's workshops.
Seems they only ship to Canada, United Kingdom, USA and surprisingly France, but no other EU countries.
The actuators also have encoders that allow you to read all of the joint positions very precisely.
PS: If the last time you saw the robots was last year, we encourage you to visit us again! Kscale robots improve fast :)
But here you are asking from us, the talkers, to design your RL reward function.
Although if they can truly ship a 9,000 dollar humanoid robot that will be impressive. If their software sucks there's other options out there.
Not that I think you do not have a point. I too worry that it seems to be a somewhat recent approach of too many aspiring platforms ( and therein may lie a problem ).
Still..