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

**Tony Zhao** (0:05)
Nobody wants to do their dishes. Nobody wants to do their laundry. People will love to spend more time with their family, with their loved ones. So what we believe in is that if the robot is cheap, safe, and capable, everyone will want our robot. And we see a future where we have more than one billion of these robots in people's homes within the decade.

**Sarah Guo** (0:29)
Thanks, Memo. Hi, listeners. Welcome back to No Priors. Today, we're here with Tony Zhao and Cheng Chi, co-founders of Sunday and makers of Memo, the first general home robot. We'll talk about AI and robotics, data collection, building a full-stack robotics company, and a world beyond toil. Welcome.

**SPEAKER_3** (0:52)
Cheng, Tony, thanks for being here.

**Tony Zhao** (0:53)
Thanks for having me.

**Sarah Guo** (0:55)
Okay.

**SPEAKER_3** (0:56)
First, I want to ask, where are we here? Because classical robotics has not been an area of great optimism over time, or massive velocity of work. And now people are talking about a foundation model for robotics or a child GPT moment. Can you just contextualize the state of AI robotics and why we should be excited?

**Tony Zhao** (1:15)
I will say, I think we're kind of in between the GPT moment and the child GPT moment. Like in the context of LLMs, what it means is that it seems like we have a recipe that can be scaled, but we haven't scaled up yet. And we haven't scaled up so much so that we can have a great consumer product out of it. So this is what I mean by GPT, which is like a technology, and child GPT, which is a product.

**Cheng Chi** (1:41)
Yeah. And so we're seeing across academia, there's consensus around what's the method for manipulation, but everybody's talking about scaling up. It's like, we know there's sign of life for the algorithms people are picking, but people don't know if we have more data, like what happened to GPT-2, GPT-3, what will happen. But we see a clear trend that there's no reason to believe that robotics doesn't follow the trajectory of other AI fields, that scaling up is going to improve performance.

**SPEAKER_3** (2:11)
Maybe even if you took a step back, what was the process for deploying a robot into the world like 10 years ago, like pre set of generalizable AI algorithms? Like why was it so slow as a field?

**Cheng Chi** (2:24)
Yeah, 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. And therefore, it feels like we're just running in loops. We build one system, and then we build the next one. But there's no synergy between them. And as a result, the progress has been somewhat slow.

**SPEAKER_3** (3:13)
I feel like that's a good segue into some of the amazing research work that you guys have contributed over the last five years to the field. Should we start with diffusion policy? What was the impact of that?

**Cheng Chi** (3:23)
Yeah. So diffusion policy is like a specific algorithm for a paradigm called imitation learning. That's really like the most intuitive way of how to use machine learning for robotics. You collect paired data, action and observation of what the robot should do. You use that to train a model that supervises learning, and then the robot do the same thing.
The problem is that in the field it's known to be very finicky. So when it comes to researchers, when I start into the field, people are like, the researchers themselves, the specific researcher need to collect the data so that there's exactly one way to do everything. Otherwise, the robot, either the model of training will diverge or the robot will behave some weird way. And the 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.

**SPEAKER_3** (4:17)
So it doesn't have to be you personally wearing a tele-op set in order to make a robot learn.