The Robot Report Podcast
00:34:03 · Aaron Nathan
[00:34:03] S2: Right? Stations. Yeah. And so it it was just like the equivalent of, you know, before cell phones, like, you would need, like, a radio tower or something to communicate, you know, with your local crew. And so this is not a really scalable solution if it required that. So we said, well, why don't we build that infrastructure first? And we always had this plan, when we started the company, which was that the problem of location is never going to be solved by any single technology. We have a lot of experience with GPS technology. We have a lot of experience with other technologies too. And we chose to start with RTK because it does really solve a huge chunk of the problem, especially for outdoor primary robots. So, Mike, you and I have, you know, talked about agricultural robots in the past. If you're operating, you know, in an open sky on a farm, I mean, RTK is really magic. Like, it just... You have centimeters, and it just works all the time. It's it's it's really actually incredible. And so that unlocks, you know, huge productivity gains in agriculture. You know, you can use less fertilizer. You could use less water. You can have higher yields. I mean, it's just more. So I think in general, what we're doing though is there's a whole bunch of those corner cases. You know? Going back to this whole notion of how you make location always work, you can't just use RTK. And so a lot of what we've done as Point One is build, like, the whole layer, the base station networks, the positioning engine, which is, like, the software that actually does the integration of the correction data from these base stations with, like, other sensors you may have on your tractor or on your car or drone or whatever the platform might be. And then we've even gone so far to build ready to use hardware that some of our customers use. And at the top of all of that, we have the... Some of this kind of, like, fleet coordination, that allows you to kinda manage this at scale. And I think the key for us has always been we don't wanna think of it as, hey. Here's this shiny technology customer. Go figure out how to use it. We've really tried to take the lens of the customer has this problem that we want to help them solve, and then we have all of these different capabilities that we can use to address that problem. And I think it's...
00:36:42 · Aaron Nathan, Mike Oitzman
You know, that's probably because we are like our customers. Like, we come from a background in robotics, and that's what makes us very unique. [00:36:51] S1: Yeah. I mean, correct me if I'm wrong. I mean, RTK has its roots in surveying. I mean, total station is the concept that a surveyor needs to pull the stick around, needs to know within, you know, a couple centimeters or where some point is so they can accurately understand a given site. And and again, you mentioned it, you know, meters for a cell phone today, combining that into the... Location point in in feedback for a device to know where it is in space as it moves around a property. Talk a little bit more in plain plain English about what that means for a developer.
00:37:31 · Aaron Nathan
[00:37:31] S2: Yeah. So, I mean, you know, we've all experienced just having GPS in our phone and using it to navigate to the coffee shop or something like this. And so for humans, you could make the argument that, hey. Like, you know, GPS is pretty good, and, like, it does what I need, and that's most of the time true. What's actually very interesting and what we're seeing now is when you have, like, a higher level of accuracy for robotics applications, it's pretty obvious that now, oh, okay. I can actually get the robot not just to the general location of the coffee shop, but, like, to the door or to the pickup window. And so, you know, you can imagine for delivery robots and things like this, this is very important. And so you now have a much more predictable path to be able to accomplish whatever the robot's task is. Now on top of that, it turns out that this is actually useful useful for humans too. And we started to see that in these applications, like in logistics, where you have a delivery driver who's trying to find the entrance to some condo complex, and it's like a huge stay. He could spend minutes walking around trying to figure out where the mail room is or be guided directly to the door at that complex. And so there is, actually a huge amount of efficiency that happens not just in navigating robots, but actually also navigating humans that are trying to do something very specific. And so we see both of those becoming just more prevalent applications. The one that really blew my mind was we actually have some customers that are doing this as well on animals. And so knowing what part of the area they're grazing in, being able to know that, hey. Your dog is actually right up to the perimeter. You know, that's, like, a big thing for making sure your dog's, like, invisible fence is working properly. It... It's really wild to see once you have that capability, the imaginations of people who build the applications on top, where they find things.
00:39:38 · Mike Oitzman
[00:39:38] S1: I I mean, the other problem that that I've heard from some developers is... In egg, it's in the orchard. You get under the canopy. Maybe you're losing GPS or in your delivery robot example, you're in some concrete canyon between buildings in some urban setting and, again, signals bouncing around. Now suddenly things are a little bit confused as to exactly where you are. Does this solve that? Or how... Or how does that RTK and the other technologies evolve?
00:40:07 · Aaron Nathan, Eugene Demetri
[00:40:07] S2: Yeah. It's it's a great question. And this is why, like, Point One is this broader thing of a location company because RTK by itself does not magically make urban canyons work. It doesn't magically make, you know, the tree cover work. What it does do is it allows us to do what we call sensor fusion, which ultimately allows you to take other sources of information. So it could be, like, an inertial measurement unit that tells you kind of your relative motion. It could even be, like, a camera or a LiDAR scanner, a normal use perception we actually can use to help integrate that solution forward in time. And the idea is, like, well, how do you blend, you know, that with RTK? And that problem is actually much harder to do well. There's, you know, obviously, like, very simple ways that you could do it where you have something that just, like, switches, which is what a lot of people try, and then you end up with this, like, handoff problem. So you end up, kind of as you start to peel the layers of the onion realizing that this problem is way better if you could just have a magic RTK that worked all the time. And that's kind of our north star for point one is, like, how do you just deliver centimeter level accuracy regardless of the environment? And, that's really the path that, we're on and what we're delivering to our customers. [00:41:35] S3: You mentioned other technologies. How do you see RTK in relation to approaches like SLAM and Vision or newer ones like LEO?
00:41:44 · Aaron Nathan
[00:41:44] S2: Yeah. I mean, RTK is very unique in that it does provide you the absolute frame reference that basically no other sensor is able to do. And I would say that this is true of any satellite nav system where you are sort of, like, building one grid across the safe... Surface of the earth and able to put everybody in that same kind of grid. I like to think about it as like... It's like a language, and everyone's speaking the same language because you can reference each other and know what you're talking about when you're saying, hey. I'm at this position. Like, that means something to the people around them. That is... Sounds almost obvious, but it's, like, not by default how these other approaches you mentioned like SLAM work, where SLAM traditionally is a very egocentric way of navigation, meaning that, like, I know where I am relative to what I've seen, and I don't care about anything else. And so that's great. That's, like, how your, you know, robot actions work. But the reality is that we are not, again, of this mindset where you must always use RTK. The real answer is that you have to combine the capabilities that SLAM delivers with these absolute capabilities of technologies like RTK. And that's a lot of what we are exploring and working with our customers on. Very often, you know, our customer may have, like, a SLAM solution that they've implemented, and then they'll be using the RTK system that we have to be able to integrate those two. Same thing with, like, vision based navigation systems, like lane followers. To give maybe a concrete example, we're in production cars today. And so if you think of a production car, you'll basically have these, like, two stacks running in parallel. One of them is a camera looking at lanes on the highway and saying, like, keep the car in between the two lines of paint. That's basically, you know, the algorithm. And then the other one is saying, have this high definition map that came from, you know, a different company, like Ushr. Right? And that's effectively, like, GPS waypoints that define, like, the central line of every lane on the highway. And then they'll use point one to say, well, I know I'm exactly in Lane two on 280 in, you know, Mountain View, and now you have these completely two independent sources that tell you this is exactly where I am.