JXX LIU: JXX LIU: Hello, everyone. My name is JXX. And I'm a founding engineer at K-Skill Labs. We build open source human robots from hardware to software to machine learning models. And we build it especially for developers. JXX LIU: Yeah, so humanoids have been getting a lot of hype recently.

You saw the Tesla Optimus. You have Unitree robots. You have 1x and et cetera. They're quite proprietary, and they're quite expensive. And the humanoids are getting so much hype is because of very big problems, like physical labor shortage, consumer household, and also like off-world exploration and et cetera. Yeah, so for us at K-Skill Labs, our goal is to really solve general purpose robotics for everyone, and open sourcing the entire stack to the entire world.

So everyone will be benefiting from this really, really useful technology instead of a few different companies. Yeah, and our team is about 15 people in Palo Alto. You could visit us anytime. We're launching some robots in the next coming month. And yeah, I'll be demoing some robots in the slides.

Cool. So we're currently working on two robots, the K-Bot and Z-Bot. The K-Bot is a 4.11 humanoid robot that we made in the last five months. It has a full aluminum body, runs an RL controller for locomotion. And it's pretty sensor complete. So you can do all the really cool tasks that the previous presenter was showing.

And this will also be one of the cheapest humanoid robots on the market. And it's ready for pre-order right now, delivered by October. Yeah. So if you come visit, there's a demo we do. You can kick the robot. The controller is quite robust. And the robot can take a lot of damage.

On the robot itself, you also have-- basically, you can do VR teleoperation with building hands. I'll describe the modularity a bit more. But yeah. So the robot is able to run a bunch of different local manipulation policies, running our own RL training framework. So when we started building the K-Bot, we thought about how do we make humanoids scale in the future?

And what makes it possible for people to adopt humanoid robots? So we basically designed this humanoid robot to be the simplest factor as possible. And it's going to be the most affordable developer and research-grade humanoid robot at $9,000. The next cheapest option is probably at $40,000, which is the unit tree robot.

This is roughly the cost of most robot arms today. Like if you buy UR5, that's, I think, $15,000, et cetera. So the entire robot is going to be open source. What that means is we're going to have open bomb. Every single piece of the hardware, CAD design, electronics, PCB, software, machine learning models will be fully open sourced.

So you can replicate those if you want to. And it's also going to be very, very modular, which means that you can basically change out end effectors. We have different mechanical designs that you can easily make interface with our end effectors. And you can just take out the hand to-- for a parallel gripper instead of a five fingers hand.

or you can use whatever end effector you want to use, like the wumi grippers or et cetera. And that means we can also easily upgrade and also fix the robot. So our goal with selling this to developers is that when we have new hardware updates, you can easily just re-screw the robot in with brand new legs or brand new arms and also brand new head.

So, you know, compute improves, like you get new NVIDIA chips, you can easily just add a new head onto the robot. Yeah, we're also building--we have built an entire Python/Rust SDK for people to use. If you come visit us, you can start programming this robot basically immediately. It's like pip install package and you can start working on it.

And it's capable of running the latest state-of-the-art ML algorithms. So in terms of local motion, you can use like NVIDIA, Isaacson to train a PPO policy. We use MJX, which I'll explain a bit later, but you can use all kinds of different frameworks. You can also run like different VLMs, like language models on the robot.

Maybe not locally directly, but you can run it through cloud. Or you can run VLAs and et cetera as well. So this robot, by default, it's going to be five DOF arms, but you can easily interchange to a seven DOF arm. So that'll suit most of the research need, research labs need.

And we'll make continuous like model and software improvements with OTA rollouts. So every week, basically, we'll make new changes to the software as we go. Yeah, here are some more specs. I can't release the full spec yet because we're launching soon. But yeah, you see, it uses MIT cheetah actuators, pretty standard components with like MUs, just different audio modules, displays, cameras, and up to 250 TOPS compute currently.

Yeah, and we really started this project in about October last year. So we'll be moving pretty fast. We have brought this to mass manufacturing. And we have a new, basically, design that we completed that I can't show you now, but you'll be able to see in two weeks. Yeah, so we started off this -- the KBOT is like the KScale Stompy project, like a full-sized humanoid robot that's 3D printable.

Then we move to like a prototype, and we work with different manufacturing partners to actually make the new one that you see. Yeah, it's launching soon if you're interested in the KBOT. And you can go to kscale.dev. Yeah, I'll give you a second. No, I'm done. Whoa, that's only one robot.

Not even one-third finished. I'm joking, joking. Yeah, and so what if you can't spend $9,000 on a cool humanoid robot? What if your, like, wife or husband doesn't allow you to do it? Well, introducing the ZBOT, which is a 1.5 feet humanoid robot that we also made at KScale Labs.

So this started from a hackathon project we did. It became really popular on Twitter and also WeChat. And so we're bringing this robot to mass manufacturing as well. It runs the same locomotion and software stack. Like, that means you can basically program stuff for the small robot, but you can also put it on the big robot.

So, you know, if you make, like, a voice chatting app, you can just put it on the idle robots. And it runs also locomotion policy as well. It works out with all the simulators. Yeah, we really got inspired by the Google DeepMinds robot soccer paper, where, you know, it runs around play soccer.

That's really how we were envisioning it. So, yeah, we have a pretty good-- the launch went really well for the 3D printing one. So our Discord has about 5,000 people. I think a few hundred people have actually made a 3D printed one on the orange one on the bottom.

Yeah, so we also started this project in November, and we are already bringing it into mass manufacturing, which we'll also be launching very soon. Some people-- yeah, we also run, like, monthly hackathons, so you can just come try out the robot. Yeah, same, same website. Okay. Okay, that's the hardware stuff.

We talked about the hardware components we just open sourced. Oh, yeah, also Zbot will be fully open sourced as well. And so we also open sourced our entire ML and software stack. So really, like, our core angle is basically to make this-- make the kbot autonomous. Well, so, you know, it's a pretty standard dual policy.

You have the high-level controller, which is a VLA. Then you have the RL whole body locomotion policy. Yeah. So what we really want right now is to basically finish-- we're currently working on both, basically. The RL part and also the VLA part. And we also made our own firmware/software architecture to power these robots in Rust.

Yeah. Our end goal is basically to make the robot so easy to use. Any developer could write apps for robots. So, you know, Python application that you can re-share with people. You make the robot do some very specific use cases that can be reused by other people. It's almost like an app store.

And to do that, basically, we offer a lot of really cool developer tools we've been working on in the last six months. So we open sourced the library for, basically, GPU-accelerated robot learning. Well, it's mostly like locomotion manipulation training. We used MJX for this. And, yeah, the video of you saw us kicking the robot, it runs the controller-- RL controller-- RL model that we trained in this training framework.

Yeah. We also are working on to basically being able to integrate and fine-tune all the different VLA and generalist policies that you see from Pi Zero and also NVIDIA group that we're also presenting today. So this robot will be able to run-- you know, we're trying to make infrastructure very easy to run any cool models that you see that will be useful.

Yeah. We also made this operating system, which is like a software framework plus like a Python interface that you can use to program the robot using Python or Rust. So, you know, you can just instead of-- I don't know, if you guys use Rust 1, Rust 2, they're pretty hard to set up.

But using our system, you can just install Python package, like pip install KOS, and you can start programming a robot. You just connect to IP. It's very, very easy to use. And we also have a digital twin in simulation. We call it a KOS-SIM. It has the same gRPC interface you can use for controlling robot in simulation.

And all you have to do between programming something in simulation and real is by changing the IP address. So you can prototype really, really rapidly without having to worry about breaking the robot, which is very cool. So, yeah, this is also fully open sourced. You can try today. You can actually program the robot just by using KOS-SIM.

Oh, I don't know what happened to the images. But yeah. And then, basically, what the machine learning and the operating system layers enables for us to run different policies, VLA models, and on our robot hardware. And for people to develop really cool applications with. So, yeah. I'm just going to go through like a very, very quick RL training and deployment examples of how researchers and developers could use our robot to train a local manipulation policy for the robot to, you know, grab different things or walk around or even dance.

So, yeah. So, yeah. Our training setup is very easy. You just get cloned the repository. And then, all you have to do is run python-m train. And in this train.py, you effectively have all the training code you need abstracted. It's about 500 lines for walking. Yeah. And then, basically, you can run this on like, you know, using run-power your local GPU.

It's MJX. So, it's like, you know, it's accelerated, accelerated compute. And training and walking policy roughly takes one hour to two hours. And, yeah. So, we're just going to run through like millions of different, not examples. Yeah. Iterations of the robot performing tasks you want. And you can tune the reward functions and et cetera.

And you can see the loss and reward functions in our observability. Basically, tensor board. Yeah. And afterwards, when the robots finish training, you can easily evaluate it in KOSM. So, all you have to do is like, k-inverse-sim, like, you run the policy. Yeah. And in simulation, and you see the robot.

If it's walking, if you can see if it's doing the thing you want it to be doing. For example, like walking, standing, picking up objects. And if that's really good in simulation, then you can just easily change the IP address. And then, you have sim to row deployment. Yeah.

And it's very cool. Like, you can basically get a robot to work in like, one-tenth of the time of like, what you would take to set up most training libraries right now. And also, like, we're a team of 15 people. We do everything from hardware to software to ML.

So, how we're able to do this is actually by working with our open source community. Currently, we have about like 5,000 active Discord members in a few servers. We have a lot of public open bounties that people are tackling. And because of our software's MIT lessons, yeah, a lot of people are coming to help us.

And we also run hackathons almost on a bi-monthly basis that a lot of people come to participate. Yeah. So, we're also hiring electrical firmware and ML engineers. So, if you're interested, feel free to ask me. And then, also, go on the kscout.dev/joint website. Yeah, we're trying to hire a lot more cracked people to join us.

So, we're launching the robots and software stack in about two, three weeks. If you're interested, follow on the website. I'll be happy to answer any questions. Yeah, sounds good. Go ahead. Yes. Where's the power? The battery? Is it battery packed? Yeah, it's battery packed. Yeah, it just has a battery.

I don't know if I can show you in the picture. Yeah, it's behind this, basically. You can just slot in and it clicks in. Yeah. Yeah, the weight of the battery versus longevity. What do you mean? Yeah, longevity on the chart. Oh, like how long is? Yeah. Yeah, walking so far, our test is about two hours.

But you can pass through. So, you can power through the wall plug. So, it's, yeah, you can just keep letting it charge and also run at the same time. Yeah. Yes. Well, black jacket, yeah. What are the use cases that you guys are imagining to start off with? Is this going to be more for like commercial, like, you know, factory kind of use cases?

Or do you envision this more in the home, like helping out? Yeah, so basically, our bet, so a lot of companies, like especially in the US, are betting on like B2B. So, like Figure, for example, are selling to factories. Sims, Tesla itself is the customer. For us, our really bet is becoming the first US consumer robotics company.

Like, a robot, a humanoid robotics company. Yeah, so we're really selling it to anyone that's interested in developing robotics. So, a lot of our current customers, we accidentally launched our robots. Like, people accidentally started buying our robots through our Shopify page. That was a complete mistake. But a lot of people that bought were just people genuinely interested in using for household tasks, like programming for different research.

And also, there are a lot of companies also interested in working with us to make B2B businesses. Like, for example, the food demo that we just saw. Yeah. Sorry, if I can ask a follow-up question. Like, what household chores do you think it would be well suited for? Like, unloading the dishwasher, for example?

Yeah, yeah. I mean, right now, we don't have any, I don't think anyone really has a fully working VLA model yet. So, right now, it's pretty limited to teleoperating system, sorry, teleoperation. So, yeah. But soon, we hope to be able to have, like, this navigation VLA stack for you to do, like, you know, folding clothes or, like, doing dishwashing as the model capabilities improve.

Yes. White shirt? Oh, I mean, green shirt. Yeah, you can go first. Can I ask you? Yeah, of course. Okay, yeah. So, you kind of alluded to complexity of ROS2 in terms of the setup. Uh-huh. I'm wondering if there are other, like, benefits and trade-offs that you considered for foregoing something like ROS and ROS2 in that ecosystem?

Oh, yeah. Like, why not use ROS, basically? Yeah. Yeah. Well, there are a lot of reasons. Our robot is mostly programmed. So, ROS is really good because, like, the nodes and stuff, right? So, like, the async, like, the communication. But for our robot, we really don't have that many sensors.

And we really want to do this, like, model-based, like, policy-based robot. So, we don't have many complicated sensors that we need to, like, async-communicate at all times. The other part is, like, where I'm pretty opinionated. I used to ROS1 and ROS2, Foxy and Noetic. I've just had a pretty bad experience using it, having to set up Ubuntu, you know.

Like, I just want a robot that I can just buy, open the box, it stands or walks, and then I can just start programming it using my computer. Yeah. What kind of AI accelerator is on each of the robots? Yeah. So, basically, for the KBOT, it's going to be JSON, Nano, and AGX.

Yeah. So, yeah, there are different compute options you'll be able to choose when we launch. Yes, yeah, go ahead. How do you develop for this? So, you can just put either VR headset. So, there are a few different methods. So, the preferred option for a lot of people is VR headset.

We have this, like, we also turn, like, a pseudo-IK. So, basically, it's, like, going to position using, like, an RL model, instead of just, like, calculating an IK. But, it works pretty well with our VR setup. So, you can move the hand gestures, you can click button to open and close gripper, and just, yeah, move your arm and stuff.

Yeah. Can you still operate the small ones here? Yes. Yeah. You'll be able to. It runs the exact same software stack. Yeah. Last question. How does it compare to the Tesla? The Tesla humanoids? In terms of, like, mechanical powerness, like, you know, the Tesla's way more powerful. It has, like, linear actuators and et cetera.

But, in terms of, like, actual use cases, I don't think it's really that different. Yeah. I mean, Tesla is actually built for, like, a factory type of use cases. But, in terms of, like, you want to, for people to actually buy and use this robot, it's not very different.

I think the last time I heard Tesla Optimus is about 60k, at least. We can ask some Tesla engineers. But, our robot's $9,000 before mass production.