No Priors: Artificial Intelligence | Technology | Startups
00:30:07 · Sarah Guo, Tony Zhao
[00:30:07] S1: Okay. So you fast forward two, three years out. If you look like five years and beyond, the home robots are ubiquitous. Like, what does life look like? How does it change for your average person? [00:30:18] S0: This is a different answer for everyone. For me, like, I just really hate dishes. Like, in my sink, there's always, like, four or five dishes that are, like, somewhat dirty out there that kinda stinks a little bit. And after a long day of work, it really doesn't feel good to come out... Like, see a home like that. So I think the world we'll live in is It's gonna be cleaner. It's gonna be cleaner. And I was just thinking about it as, like, the marginal cost of labor in homes goes to zero. [00:30:47] S1: The last thing I wanna make sure we do is, like, talk about demos. Right? There's a lot of robotics launch videos today. It's been years since you saw an optimist serving drinks at a bar. Why are those not available, and what is actually hard? Yeah. [00:31:03] S0: I I think the way I will put it is make zero assumptions. No priors. [00:31:08] S1: Okay.
00:31:08 · Sarah Guo, Tony Zhao, Cheng Chi
[00:31:08] S1: Okay. [00:31:08] S0: As in Nice. If you see a robot handing one drink to one person, first, ask the question of, is that autonomous or is that tally operated? So this is the first thing. So we should look at the tweet and see what they say about it. And and then is that... Does it show giving another slightly different color cup to the same person or not? If they didn't show it, it means that a robot can literally only pick up that single cup and give it to that same person. When we look at demos, we tend to put our human instinct into it. They're like, oh, if you can hand a cup to that person, it must be able to hand a different cup to another person. Maybe you can also do more dishes. Maybe you can do a laundry. There are lot of, like, visual thinking that we can have about it, which is what's great about robotics that there are lot of imaginations. But I think when we look at demos, only index on things that is strong, and that's likely the full scope of that task. I think another aspect is... That is [00:32:07] S2: me as a review researcher. I I appreciate the number of interactions that happens in in in a demo. So, usually, the more interactions you have... Like, every interaction, there's a chance of failure. So the longer the sequence is, the harder it actually is. So that's something we really emphasize here. And that's actually somewhat uniquely easy for us because the GloVe way of data collection is so intuitive to people. [00:32:31] S0: Yeah. It's really about, like, generalization and reliability.
00:32:31 · Tony Zhao, Sarah Guo
[00:32:31] S0: Yeah. It's really about, like, generalization and reliability. [00:32:34] S1: So can you explain the demos that you guys are showing? [00:32:36] S0: Yeah. Of course. So we are showing, like, basically three categories of demos. The first one, as you saw, is we have this whole, like, messy table, and what the robot does is to clean up the whole table and, you know, dump the food into the food waste bin and load the dishes into a dishwasher and then operate the dishwasher. What makes this demo really hard is that it is a mix of really fine grained manipulation with these super long horizon full range task, as in, like, you need to go up and you need ask them to go down very much. It's a mobile manipulation task. Exactly. The reason that we can show this is just how nimble and easy for us to collect these datasets to make Verizon Dexter's demo possible. And it's also about the forces as well. So you might have seen, like, we're trying to pick up two wine glasses with one hand. [00:33:28] S1: Mhmm. I struggle with this, but... Yes.
00:33:30 · Tony Zhao
[00:33:30] S0: Yeah. It's actually really hard. And because it's, like, transparent objects, we need to also load it very precisely into the into the dishwasher. A lot of it is about how much force you apply. Mhmm. Because if you are trying to grasp two, in one hand, if you squeeze a little bit harder, you're going to break one of the glass. And when you load it into a dishwasher, if you're pushing it in the wrong direction and it hits something, it's going to shatter. We we did shatter a ton of glasses when we were, like, experimenting with it. So these are tasks that are, like, really high stake that is not just about recovering from mistakes, but about not making those mistakes in the first place. And this is what's generally the case in a lot of the home tasks, that you're just not allowed to make any mistakes. And then we get into the generalization demos, which we basically show our robot. We book, like, six Airbnbs, and we get it there, zero shots Mhmm. And see if it can do, like, part of the task. So two sides we use. One is I go around the table and collect all the utensils into the caddy. The other is to grasp a plate and then load it into the dishwasher. What makes these these demos very interesting is that we don't need any data when we enter that home. It's pure generalization. And this is as close to getting, like, a real product as you can get. Because when someone buy buy our home robot, we really don't want them to, like, collect a huge dataset themselves just to, like, unbox it. Also, in addition to visualization, those two tasks are also really precise. We're using the exact silver reverse in the home, and you need, like, basically, like, a few millimeter of precision where to grasp it properly. Those force are also hard to perceive because they're reflective. Like, the lights looks weird on it. We help have a transparent table home. Think I that the table looks like nothing, and the robot still, like, reacts very well to it. And, again, the reason that we can do it is because we have all these, like, more than 500 people, and we've seen so many glass tables Mhmm. In that dataset, so the robot is able to do it. I think the last bit of the task that we did is kinda pushing what's possible in terms of dexterity. The two tasks we chose, one is espresso... Operating espresso machine. The other is, like, folding socks.
00:35:44 · Cheng Chi, Tony Zhao, Sarah Guo
[00:35:44] S2: Mhmm. [00:35:45] S0: What makes these hard is that they require very fine grained force that is hard to get if you're doing with tally operation. Because these days, there's not a good tally operation system that can let you feel how much force the robot is feeling. Mhmm. So, basically, when you're tally operating, your hand is numb. Mhmm. And sometimes you are applying, like, a huge amount of force on the robot, but you don't know it. And that can result in, like, very low data quality that robot is also doing in that aggressive way that we really want to avoid for our system. The sock is a very good example that when you're trying to fold it, your two fingers can touch. Mhmm. And that forms a... What we call, like, a force closure. You have a closed loop for the force. And if your robot is stiff, you can apply infinite amount of force at it, and it doesn't look like anything. But for us, because we're using the glove to collect the data, the human who is collecting it can just naturally feel it. It's very intuitive. I think we're the first to do the sock folding and using end to end to do, like, espresso machine out of the whole industry. [00:36:53] S1: One of the things that you will also need to scale as you guys, you know, scale up the company is the team. What are you hiring for? What are you what are you looking for?
00:36:53 · Sarah Guo, Cheng Chi
[00:36:53] S1: One of the things that you will also need to scale as you guys, you know, scale up the company is the team. What are you hiring for? What are you what are you looking for? [00:37:03] S2: One thing I'm really looking forward is Thanks to me, Yeah. Yeah. So it's full stack roboticists and people who aspire to become full stack roboticists. Really, what we learn in this company is just that robotics is such a multidisciplinary field. You need to know a little bit of mechanical, a little bit of electrical, a little bit of code, a little bit data to actually fully optimize the system. And we have a couple examples of training just full stack software engineers to become roboticists, training engineers to become roboticists. And so if you want to learn about robotics, as you move on, you wanna learn the whole thing and not just to be boxing into your small, you know, little cubicle, let us know. [00:37:45] S1: Yeah. And you told me that you didn't write code until you got to college or something.