Sunday Robotics: Scaling the Home Robot Revolution with Co-Founders Tony Zhao and Cheng Chi

Cheng Chi: So previously, classical robotics have this sense, plan, act modular approach where there's a human designing interface between each of the modules. And those are need to be designed for each specific task and each specific environment. In academia, that means for every task, That means a paper. So a paper is you design a task, design an environment, and you design interfaces, and then you produce engineering work for that specific task. But once you move on to the next task, you throw away all your code, all your work, and you start over again. And that's also kind of what happened to industry. So for each application, people build a very specific software and hardware system around it, but it's not really generalizable.

Cheng Chi: The problem is that in the field, it's known to be very finicky. So when I talk to researchers, when I start into the field, people are like, the researcher themselves, the specific researcher, need to collect the data so that there's exactly one way to do everything. Otherwise, the robot either, like, use the model training will diverge or the robot will behave some weird way. And diffusion model really allows us to capture multiple modes of behavior for the same observation in a way that's still preserved training stability. And that really kind of unlocked more scalable training and more scalable data collection. So it doesn't have to be you personally wearing a tele-ops set in order to make a robot learn. Yep, So like we can have multiple people, sometimes even untrained people collecting data, and the result will still be great.

Cheng Chi: Traditionally, most robots are designed for industrial use cases. And the robots are very fast, they are very stiff, and they're very precise. The reason is because all the industrial robots are blind. So they're blindly following a trajectory that's programmed by someone. It's not reaction to perception. Correct. But because of the breakthrough we had in AI, like now robot have eyes, so it can actually correct its own mechanical and hardware inaccuracies. So that kind of opened up a new different space of design. And intuitively, it should be like, I can't tell you exactly what the distance is here on a millimeter scale, but I'm going to get to the cup because I could stop. So that allows us to use these low cost actuators that's cheap, that's compliant, but they're imprecise. But because of the AI's algorithms and systems we build, it allows us to build robots that's mechanically inherently safe and compliant, while simultaneously be able to achieve the sufficient accuracy we need for the home tasks.

Tony Zhao: We see a lot of great promise for RL in locomotion, and we think that will continue to be true for locomotion. So what we see, really, like RL is a method, it's very powerful, but it is much less sample efficient compared to imitation learning. And we see that to work great in environments where it's easy to simulate. For the case of locomotion, you don't need to worry about rigid body dynamics and rigid body contact between the robot and the ground. And, you know, because you engineer a robot, you know everything. But for manipulation, it's kind of hard for us to imagine, like, have this actually the same amount of diversity and the distribution of real object. in terms of matching both appearance and physical properties. And we think that it's going to be challenging compared to globe data collection and tidy up. I think it's really about which method can get us there faster. There might be different methods that will eventually get there. For example, like, you know, simulation world model, right? And like it's almost a tautology to say that if I have a perfect world simulator, Anything can be done there. Like as long as you can do it in the real world, you can do it in a simulation and you can like, cure cancer in a simulator, right? But what it turns out for robotics is that some things are harder than others and it really depends on the problem itself. So in the case of locomotion, as I mentioned, all we need to model in a simulator are point contacts with a somewhat flat ground. More like feet. Yes. But sort of the behavior we want out of it is actually very difficult to model. Like it's all these reactive behaviors that when you feel like your leg is hitting something, you should retract and step again. These are very, very hard to describe or try to learn from demonstrations directly. But in the case of manipulation, I think the difficulty is flipped. That it's a lot easier to capture the behavior itself, and it's a lot harder to simulate the world. For example, if you were to grasp a transparent cup with some orange juice in it, it's ridiculously hard to simulate how your hand deforms around the cup and how all those ripplings, how those like the color of the juice results in like the rendering and what the policy end up seeing. Simulating that is very expensive and difficult. But all we need to learn is just to like get your hand to be in front of the cup and then close with the appropriate amount of force. And that's actually very easy to learn. That's why like we see so many success of imitation learning in the case of robotics manipulation is because the behavior itself is actually not as hard as simulating the world.