How Point One Turned GPS Accuracy Into a Robotics Platform

0:09What's up, everybody? Welcome in episode 269 of the Robot Report podcast. I'm Steve Crow, executive editor of the Robot Report. Thank you, as always, for tuning into the show. Hope everybody's having a great week. Thanks to our new sponsor this month, Intel, for supporting the podcast really appreciate that joining me as always is mike oitzman senior editor of our robotics group what's going on brother well steve it seems like the weeks are just falling off the calendar it's been such a busy time i i think everybody else is sort of experiencing the the craziness of the moment now you know between the holidays or before the holidays is everybody seems like they're trying to get their news announced uh we're going to talk about some other interesting things, you know, in the news today, but wow, we are just so busy here.

0:56And that means everybody else is busy as well, I'm sure. Yeah. And we thought yesterday, the agility robotics IPO, right, which we've been covering, we've been preparing for coverage, they've obviously been preparing, we thought that that was going to be the biggest story yesterday, right? Is the SPAC finally closed with Churchill Capital, and they're going public and tracking the stock. It's the first, they're touting the IPO is the first pure play humanoid robot maker in the US to debut right on the stock market. Obviously, that was not the biggest story yesterday. Right. It turned out the ABB SoftBank deal being blocked turned out to be the biggest story, which we'll get into that a little bit later on in the program.

1:38But yeah, crazy, crazy week as always. But it was it was an interesting day to debut on the Nasdaq. Right. Yesterday, Mike, the Nasdaq crash is not the right word, obviously, but one of the worst days in recent memory for the Nasdaq down about five over five percent into correction territory. You know, a lot of tech stocks, whether it's Nvidia was down, Rockwell was down, Teradyne was down. Other pure play robotics companies serve robotics, intuitive, symbolic, we're way down as well. So not a, not a great day to debut on the start on the NASDAQ for agility. But despite that, they ended the day up about 2%, slightly over 2%.

2:21So, so miracles do happen, Mike. Yeah. Well, you know, and again, it was a crazy week for the, for us in the U S with the elections and we're not going to get political here, but you know, I think the stock stock market has been a whiplash all week you know it was down and then it was up and then it was down so you know it really has been a chaotic week on the stock market and you know through all of that you know just imagine the elation for you know our friends at agility um through all of that and you know now we'll have to see in the coming week and in months um you know how things settle out for them yeah So again, one day doesn't mean anything, right?

3:01So we've talked about this IPO at length. So we'll wrap it up here, but we'll obviously continue to track it. We'll watch the stock performance over the next several months. But again, the most important thing, like we've mentioned a number of times, is that now being a publicly traded company, they do have to release their financials every three months. So we'll start to get some insight into, are they growing their deployments? Are they growing their revenue? Agility claims they have, I think it's$300 million in back orders for the new Digit 5. So we'll start to see. We'll start to see if they can actually deliver on that.

3:40And it's a monumental challenge for not only them, but for any industrial humanoid company in the US to make the economics work for deploying these things at scale. But it was a good first day for Agility. I think there's no denying that, but we'll continue to to follow that. Did you buy in? I didn't buy in, not yet, but we'll have to see. I think the good news is I drive by Salem now every time I go up to visit my kids in Portland. So I keep asking them for a visit to the RoboFab. So I hope here in the next six months, I'll get a chance to stop by RoboFab and also peek under the hood a bit and see those systems being built in person.

4:22Awesome. So we'll, again, later on in a few minutes here, we'll recap some of the other news stories of the week. And we'll also play a conversation with Aaron Nathan, CEO of Point One Navigation, a little bit later on in the show. But Mike, why don't you preview what that conversation is about? Yeah, as we're going to learn, Point One Navigation delivers accurate location information for outdoor robotics and autonomous vehicles of all type. And Aaron is going to introduce us to their technology. And we're going to learn how Point One Nav helps those outdoor robotics remain localized with centimeter accuracy.

4:56So very important if you're doing something outdoors. Yeah, awesome. So we'll play that a little bit later on in the show. We do want to plug, of course, our next upcoming event, Robotics Summit Boston, which takes place June 2nd and 3rd, 2027 at the Heinz Convention Center in downtown Boston. We're going to have over 5 ,000 people there, over 250 exhibitors on the show floor. We're talking all things commercial robotics development. Again, a lot of the technical decisions that go into building and designing a robot is what this show is all about. This is, I think, the eighth time that we're going to do this show, which is crazy to think about.

5:31So the call for speakers is now open. We'll link to that in the show notes. You can also go to roboticssummit.com. We're already getting flooded with submissions. So if you want to be considered for this, make sure you get your session proposal in as soon as possible. The deadline is going to be late December. We're still finishing finalizing the exact deadline, but it's going to be late December. But if you want to be considered for one of the breakout talks or maybe a keynote, something like that, make sure you fill out a session proposal ASAP. We're still looking for sponsors, speakers, partners, all the rest of it.

6:03So go to roboticsummit.com to learn more, or you can reach out to any one of us here at the Robot Report. Again, Robotics Summit Boston. Coming to the Heinz Convention Center June 2nd and 3rd, 2027. We'll obviously continue to talk about that event as it gets closer. So tell me about the Heinz Center. I've never been there. Obviously, every event we've done has been at the big convention center downtown. The Heinz is located where? Yeah, so it's in downtown. It's not too far from Fenway Park, actually. But we were at the venue yesterday visiting it. So, yes, it's a huge space. So we have a lot of cool opportunities to do different things, bring in different types of robotic systems and demos and networking opportunities.

6:40So a new venue for us, but it's going to be bigger and better than ever. So looking forward to that. Cool. Yeah. On to the news of the week. And we have you covered with all the latest news and information with our network of websites, including the Robot Report and Automated Warehouse. Make sure you follow us on social media. Make sure you sign up for our weekly newsletters for both those brands so you never miss a beat. All right. We mentioned this in the show open and obviously maybe the biggest story of the year, Mike. I think it's not overblowing it or overstating the importance of Chinese regulators blocking SoftBank's$5.4 billion acquisition of ABB robotics.

7:21This was first reported by the Financial Times. We have confirmed it with ABB that they are indeed that the sale is on on pause. So you can check out the story by Brianna Wessling on the robot report. But pretty massive story here. Yeah, it's been more than a year since ABB announced it signed the agreement to sell the division to the SoftBank Group for, as you stated,$5.375 billion. And it seems that China's Office of the Working Mechanism for Foreign Investment Security Review, that's a lot of words, has prohibited the acquisition in the country. Yeah, and I don't really understand. I mean, I think I do, right?

8:05I think I understand why this is happening. I'm not sure I buy the reason that everybody is sharing around the news here. I guess the concern, China is concerned about robotics data being transferred overseas and used by, I guess, SoftBank in this case to train its AI models. So obviously, SoftBank is a Japanese company. ABB does a ton of work in China. It's significantly grown its business in China. But I think what I don't understand is, you know, ABB is already an overseas company, right? ABB is a Swiss company. Is that right? So what's stopping them from taking the data that they're already capturing from these deployments in China and using that to train their AI models already?

8:56Again, I understand SoftBank is a different company and a Japanese company, and there's political things between China and Japan forever. But the same problem already exists, right? ABB can already transfer a lot of the data that it's capturing. I mean, yeah, I think it's a question for any country or any organization in this world of physical AI. Is your information being used? And in many cases, we know that, that, you know, a deployed fleet of robots, especially in a robots as a service situation, you know, every placement, every acquisition, every move, that information can come back and help make the entire fleet better.

9:41Right. There's that. And we know we've talked about security with so many cameras on so many devices. So I think you got something there. And it comes down to how much of ABB's business, robot businesses in China. And in 2025, according to the numbers, ABB Robotics booked$925 million in orders from China, up from almost$700 million in 2024. And I guess in Q3, their business in China alone rose 32%, according to the article. So, you know, the business there is growing. It seems that, you know, ABB products are rock solid in industrial use cases. So that's great for ABB. And they still build a lot of robots in its Shanghai factory.

10:31That was the other requirement, right, is that domestic manufacturing. So they do have factories there. And so, again, we can't uncover all of the political implications here. but there's something else you know under the surface going on here yeah and it doesn't mean that this deal is dead right there's there's other things like and i'm sure they're scrambling and going back to the negotiating table to try to figure this out i think everybody probably you know from the abb and softbank side obviously want this to happen abb at one point did have a plan to just spin off the robotics division if you remember that yeah they were just going to spin it off into a standalone business unit.

11:12And then the soft bank opportunity presented itself. But you think robotics is becoming a new political battleground? It certainly seems that way. Well, yeah. I mean, just what even within the US government, right? In the last year, trying to block the import of Chinese robots. And so, unfortunately, yeah, maybe we're caught up in the middle of all of this. Sort of the, I don't know, what's a bad analogy of kids in a divorce, right? Where parents are fighting and where as an industry, you know, caught up between all of this. So I think that's unfortunate, you know, and remember in April, China prevented Meta from acquiring the AI startup Manus for$2 billion.

11:59dollars. Manus was founded in China, but it had relocated to Singapore. And as we learned last week, Meta is now working with Chinese human aid, humanoid maker Fourier on a new meta specific humanoid robot in their robotics in, I don't know, physical AI division. So, you know, so many things happen on so many levels, Steve. We live in an international world and it's really hard and And it sort of sucks when these other sort of overlying things impact business. Yeah. I mean, I think about, I always, in these situations, look on the individual level. And people who have been at ABB and the robotics group for years and have built that and they're super successful and probably were positioned to make a lot of money from this deal.

12:47Right. And change their lives and change their future and maybe even future generations of their families. It's a big moment for those folks. Right. And to see something like this potentially stop that from happening. I don't know how they, again, on an individual level deal with this kind of stuff. I know how I would have a hard time, you know, mentally dealing with that kind of stuff. So that's where my mind immediately goes as to the Marx of the world, right? Like someone who's been there for so long leading this stuff and to see just political BS potentially get in the way of making something like this happen kind of stinks.

13:25But again, yeah, you mentioned some of the U.S. stuff, right, with the Section 232 report last week where the U.S. government says robotic imports are potentially a national security problem. But then again, how are we actually rebuilding the U.S. robotics ecosystem and encouraging and supporting and promoting the building of more domestic robotics companies that are scaling products at a significant level rather than just, hey, ABB, yes, you have U .S. manufacturing as well. Can you scale that up? I mean, they're not a U.S. company. So it's you have the FCC already banning new foreign made advanced robotics devices as well, including mobile robots and humanoids and quadrupeds.

14:11Again, they're also citing supply chain vulnerabilities. So it's it's all it's all just craziness. And, you know, it's unfortunate that we can't all just get along. Yeah. Well, you know, and again, this whole discussion about strategic assets, you know, robotics is a strategic asset. I mean, let's not forget the other news that's happened in the world in the last week, which is, you know, these industrial refrigerators getting hacked, right? Being turned off and spoiling food, that kind of thing, just as sort of malfeasance, if you want to call it, hackers doing that. But at the same time, you know, when robotics and automation is a core part of building, you know, your infrastructure within the country, I think, again, we as an industry have to take security as a paramount concern in terms of these connected devices.

15:04I think the last thing any of these countries want is someone being able to remotely hack the system and turn off the switch and turn off production on critical infrastructure. Again, it's worth talking about as an industry, and we've got to keep on this story because I think this is just one symptom. of, you know, the new world in the next decade. Yeah. And I think do, do these robotics companies have to think about regulatory risk as right. When they're approaching certain types of deals or strategic moves, right. And how are those relationships with other countries, how will that impact these moves and their business decisions and all the rest of it?

15:48Right. So we've reached out to ABB. We've reached out to SoftBank to try to learn more about this. Obviously, nobody wants to really talk about this at the moment. We'll continue to follow it and dig in and see what we can learn. You know, where my mind also went on this is that we reported a few weeks ago that SoftBank has agreed to acquire the Robotics and AI Institute, right, from Hyundai. Yeah. Right. So that's the Boston Dynamics spinoff led by Mark Rayburn and Al Rizzi and a bunch of other amazing folks. again, SoftBank, Japanese company, Robotics and AI Institute, a US company based in Massachusetts.

16:27But is there a potential impact on that deal happening? Right. You know, if this deal for ABB doesn't go through, do they rethink a lot of the moves that SoftBank has been trying to make? I don't know. Or does it impact the price that it would cost to acquire the RAI Institute? From my understanding, I reached out about this yesterday to some folks and they say that REI deal is still being reviewed. So it sounds like it's still happening, but you know, if there's collateral damage as well on something like this, it's very possible. So a lot of potential things and dominoes could be falling from this.

17:01So again, we'll continue to follow all of it as best we can. Moving on, we published, Mike, the Startup Radar 2026 this week. Features 60 robotic startups working on a range of applications, a variety of robots, whether it's for ag, defense, healthcare, manufacturing, based all over the world. They've raised millions of dollars. Again, this is the second time that we've published this. So what's your take? What do you think people should know about the startup radar? Yeah, we did this for the first time last year, and it was a super popular our download. Again, it's not no judgment in this, right?

17:43We basically were just looking to shine a light on the new startups each year. And there's a range of companies in here. Some of them have raised quite a bit of money. Some of them are still pretty young, but I think it's really just a snapshot. And that's our intent each year, just to highlight where some of these startups are. And I guess once we've done this for a couple of years, we can begin to put some analysis behind the types of companies and types of investment that's going in. And I think this year it's across the spectrum. I did some review with Gene. Gene compiled this. The cutest robot is probably from a company called Dynamic Creatures, a little Muppet-ish looking little Little robot.

18:35We also have, you know, physical intelligence skilled in there. Those are some of the companies that have raised, you know, almost a billion dollars. So they've got lots of money, but they're on the frontier of physical AI. But they're really still a startup because it's not, you know, not still clear how they're going to mature. And there's an interesting company called SafeWorld. And they're trying to test how robots behave around people in rare, dangerous and unexpected situations. So, again, it's always fun to look through this radar and, you know, try to just understand where the investment's going, where the innovation is happening, the amazing ideas that people are trying to bring to reality.

19:16Yeah. So to kind of hammer home your point, this is not a ranking of the best startups in robotics. Right. And this happened last year. I got I got some text messages from some close industry friends. Right. Like, how did you not have us on this ranking? It's like, well, if you've been around for seven years, you're not really a startup anymore. So you don't qualify. Right. Number one. And I saw it happen again this year. Somebody said that we ranked the 60 most innovative startups. We're not ranking. Like this is not a ranking, right? So whether we - It's an alphabetical list, actually. Literally a listing of, hey, here's 60 robotic startups that we've come across that we know of.

19:54There's a million more startups out there. It's impossible to include every single startup in this list. So if you are excluded, it's nothing personal. It's not that we think that you're doing crappy work. Right. So, again, this is just literally, hey, here's 60 interesting startups to watch. So go check that out. You can download that for free. And thanks to the sponsors that participated in this as well. And I just note that the call for submissions for the Robot Report 50 Robotics Innovation Awards, that's also open. We'll include a link to that in the show notes. This is our annual awards program where we honor a robot of the year, a startup of the year, an application of the year, the robots for good.

20:37We have a new category this year called best use of AI. Right. So make sure you submit to that. And we'll honor the winners at the Robotics Summit Boston on the night of June 2nd for our annual awards gala. So make sure you submit to that. Make sure we're aware of all the interesting work that you're doing. But again, we'll link to that in the show notes or you can apply on the robot report dot com. And that's going to do it for the news section. Again, we have you covered with all the latest news and information with our network of websites, the robot report and automated warehouse. Again, make sure you follow us on social media, all the different channels and make sure you sign up for our weekly newsletters so you never miss a beat.

21:14All right. On to the featured interview this week, a conversation with Aaron Nathan. He's the CEO at Point One Navigation. Mike, why don't you set this up for us? Yeah, because I follow so many mobile robots, especially outdoor robots now in ag, for example. We're talking about one of the most important and often overlooked challenges with outdoor robotics, and that's knowing where you are. Aaron has spent the last two decades, as we're going to hear, working on robotics and autonomous vehicle systems. He started his career at Cornell's DARPA Grand Challenge Team, and later he founded PointOne to build reliable, high-precision location technology.

21:50and in this conversation Aaron's going to explain to us why location is foundational to robotics and how RTK can improve positioning from meters to centimeters and why RTK alone isn't enough in environments like orchards, urban canyons and construction sites to keep you located. He's also going to share with us how you can scale from a robotics pilot to a production fleet. So again, if you're building mobile robots, it's definitely going to be an interesting conversation. So let's listen to that now.

22:29I want to welcome Aaron Nathan to the show today. He's the CEO and co-founder of PointOneNav. Aaron, welcome to the show. Thank you for having me. It's great to be here. Yeah, we're excited to dig under the hood of navigation technology. And it's one of those things that we recognize is so important for mobile robots. especially outdoor mobile robots. I think that's the first place that you and I sort of stumbled onto each other was talking about agriculture robots. You've been enabling ag robots to be more precise. We'll come back and talk about that in a minute. So you've been building, you know, location for robots and autonomous vehicles for 20 years now.

23:08You started Cornell's DARPA Grand Challenge Team in 2005. I'm sure that was an amazing process. and then you started Point One Nav in 2016. So tell us, what have you learned about what's hard for a machine to know where it is in the world today? Let's start there. Yeah, for sure. And again, thanks for having me here. And it's been great to kind of be on the journey together, so to speak. And yeah, I mean, 2005 was a long time ago. And the thing is that the robotics problems back then, they're still very much the same robotics problems we have today because we are still in the same physical world the robots have to work in so it turns out that location is one of those things that you really really have to get right early in the design process of like your robotic system otherwise everything else downstream kind of falls apart and so back in 2005 when we were doing the DARPA Grand Challenge.

24:12This was a highly ambitious thing. At the time, I was a sophomore, I think, in university. And, you know, we had this brilliant idea of like, oh, yeah, no problem. We can make a full-size car drive itself across the desert for over 150 miles, which was more or less the

24:30Aaron Nathan: challenge. And, you know, you tell a bunch of college kids like, yeah, you get a million bucks if you can pull it off. Like, we're off to the racers. And what we learned very quickly was that location was really the key to that problem because driving this one was off-road, so there wasn't other traffic or other vehicles to avoid. It was really a problem of, like, how do you stand the road? And the challenge was not necessarily, like, how do I get to some level of accuracy? Like, it's actually more how do you do it all the time? Because if you think about like driving for an endurance, it's about making the right decision like all the time, not 99 % of the time, but like all the time.

25:18Aaron Nathan: And that really highlighted to me like the importance of location technology and how it has to work like all the time. And, you know, fast forward now 20 years, which is wild. What we've seen is that this has only become more true. Basically, like, you know, the vehicles or other robotic systems, outdoor robots, ag robots, they're developing more and more capabilities. Like, you know, whether they're able to now, you know, very precisely. we have some customers who are literally like burning weeds with lasers or other, you know, ultraviolet light, all kinds of crazy things in agriculture, similar things in construction and mining, um, you know, guys delivering packages with drones to, you know, your doorstep.

26:09Um, all of those things are enabled because now we have a lot more capability in the like general robotics world, but it actually pushes further on this problem that like location has to work all the time because you have robots trying to do more things. And so the stakes are higher. The bounds of like, hey, can you make a mistake are actually smaller. So if anything, like the problem has become even more important. And I think, you know, that's that's something that the industry is starting to really pick up on is, hey, this is something that's not like a simple thing on the side. when I actually get to scale, it becomes like a foundational block that like really has to work all the time.

26:53We're going to dive deeper into your technology a little bit later on in the conversation here. But across that, the scope of the last 20 years, I mean, I think of the evolution what we have as consumers, you know, our cell phones can now tell us where we are. Google Maps tells us gets us from point A to point B today. But along the way, it seems like GPS has been ubiquitous along that whole path. But, you know, what's really changed in the last 20 years with GPS and or maybe some of the other technologies that are helping support this? Yeah, I mean, satellite navigation is like a broad topic, which is GPS is like the US government's flavor of that.

27:37It has been available, you know, kind of since the 90s. There is this whole thing where the government, there used to be like a scrambling that was on top of GPS that they removed and signed into law that they will not use that scrambling. And then, you know, the whole industry of, I'm sure everyone remembers, you know, putting that sticky Garmin thing on your windshield to navigate around you. That was like a whole thing, I think, when I was in high school or something. But yeah, so satellite navigation has been evolving, but slowly. And I mean, part of this is that GPS satellites are very complex, very expensive, and they technically are a DoD asset first, you know, so there's constraints that they have on things that they need to be able to do all the time.

28:26But that said, you know, we moved from a world where GPS and then the Russian system called GLONASS were really the two major systems that were out there. Then the European Union, they launched Galileo, which is, you know, basically a full navigation system similar to GPS. And then you also have the Chinese that launched Beidou, which is a very advanced navigation system that also works similarly to GPS. And so your phone, when you're walking around, uses all of those. It's not just using GPS. It's actually using all of these different what we call GNSS systems. And the accuracy you get from them is higher just because you have more satellites, more points.

29:14the other big thing that's happened is GPS and all of its cousins there's traditionally was one frequency that they would use and without getting too much into the weeds like having two frequencies or three frequencies now allows them to be actually much more precise because of how the physics works out and so this is a big thing now that like literally consumer level devices like what's in your phone are able to use not just one, but two frequencies. And, you know, consumers have seen this, like Apple actually made a big deal about it when they launched the latest Apple Watch, which was like, yeah, what do you see is like, well, I'm running, you know, in the city or something, my actual Strava track or whatever it is I'm recording on, like, looks really good, because you're actually now able to use those two frequencies.

30:10I mean, big technical things that had to happen, like ultimately do result in these consumer facing improvements.

30:18Aaron Nathan: So Aaron, let's talk about Point One Nav's upcoming Fuse conference. I understand it's not a product conference, but Ryan or one about location technology. Why have a conference about location technology? Yeah, so I think, you know, we have a very unique perspective that we are a location technology company, but we are made up of a bunch of people that have come from the robotics industry and other kinds of like what I like to call more the application side. And so we've had a number of customers go through this very difficult journey of bringing these complex products to market at scale. And location tech has been a big part of making that actually happen.

31:03And so we really wanted to be able to bring people together and then have a lot of people be able to hear this is how we did it in the real world as you know companies that are going through that journey and you know that this is not about necessarily using point one or our technology or something it is really about how do you like design these systems so that you do get the reliability of actually delivering a useful functional product in the real world so this is a I think just like a huge gap in the market. And so we're super excited to bring together, you know, those who build and see that as a place for us to kind of share ideas and experiences and learn together.

31:54Aaron Nathan: And can you give us a sense of who's coming to the event and when exactly is it? Yeah. So we have an amazing list of speakers for the conference. And, you know, this is people that I've worked with, you know, worked with our company. Brian Schimpf, who's the CEO of Anduril. Ali Agra from Field AI. Adrian McNeil from Foxglove. And we're really trying to bring people that come from different parts of the industry, whether they are building robots, building tools for robots, or building full scale systems around robotics so that you have that variety of experiences. The actual event, it's going to be at the Foundry in San Francisco on November 19th.

32:44Great. Look, I'm a geek. I want to come back to the technology. Always interested to learn more. We were talking about the accuracy of what we're able to see today. And again, it's key for any systems developer who's building the technology to locate themselves. So I think you're known as a RTK corrections provider in some sense. But again, you love calling yourself a location technology provider. What's the difference there? Yeah. So maybe to help those who aren't familiar with RTK as a tech, RTK is a specific flavor of GPS. technology that allows you to go from the five meters of accuracy you'll get from a normal receiver down to a handful, like two centimeters of accuracy.

33:40This technology has been used by surveyors. I mean, we used it, you know, 20 years ago in the urban challenge. The biggest challenge with RTK is that it's not a ubiquitous technology, or at least it wasn't. And so you had to like do a bunch of infrastructure and everything that you had to build yourself to make it really work. And ground stations, yeah. And so 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, well, why don't we build that infrastructure first?

34:25And 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 talked about agricultural robots in the past. If you're operating 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 really actually incredible.

35:12And so that unlocks, you know, huge productivity gains in agriculture. you know you can use less fertilizer you can 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 quarter cases you know going back to this whole notion of how you make location always work um 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.

36:03And 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 some of this kind of like fleet coordination that allows you to kind of manage this at scale. And I think the key for us has always been, we don't want to 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, you know, that's probably because we are like our customers.

36:48We come from a background in robotics and that's what makes us very unique. I mean, correct me if I'm wrong. I mean, RTK has its roots in surveying. I mean, total stations, the concept that a surveyor needs to pull the stick around, needs to know within a couple centimeters of where some point is so they can accurately understand a given site. And again, you mentioned it, meters for a cell phone today, combining that into a location point and feedback for a device to know where it is in space as it moves around a property. Are you talk a little bit more in plain English about what that means for a developer?

37:31Yeah. 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, you know, GPS is pretty good and like it does what I need. And that's most of the time true. was 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.

38:13and 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 for humans too and we've 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 thing. 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.

38:59And so we see both of those becoming just more prevalent applications. The one that really of glue my mind was we actually have some customers that are doing this as well on animals. And so knowing like, you know, 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 the issue of your dogs, like invisible fences working properly. 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. I mean, the other problem that I've heard from some developers is in ag, 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.

39:54And again, signals bouncing around now, suddenly things are a little bit confused as to exactly where you are. Or does this solve that? Or how does RTK and the other technologies evolve? Yeah, it's a great question. And this is why like PointOne 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, 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 lighter scanner a normal use of perception we actually can use to help integrate that solution forward in time and the idea is like well, how do you blend that with RTK?

40:53And that problem is actually much harder to do well. There's obviously very simple ways that you could do it where you have something that just switches, which is what a lot of people try, and then you end up with this handoff problem. So you end up, 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.

41:35Aaron Nathan: You mentioned other technologies. How do you see RTK in relation to approaches like SLAM and Vision or newer ones like Elio? 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 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.

42:22That 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 robot vacuums 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.

43:12And 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. Well, one of them is a camera looking at lanes on the highway and saying, like, keep the car in between the two vines of paint. That's basically, you know, the algorithm.

43:50Aaron Nathan: And then the other one is saying, I have this high definition map that came from, you know, a different company like Usher DP, right? And that's effectively like GPS waypoints that define the center 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 rum view and uh now you have these completely two independent sources that tell you this is exactly where i am and now that gives you a high degree of confidence to make a safe decision about should i change lanes or exit the highway or any of these you know directions so um yeah i guess like i'm a little bit of a broken record, but it's always about how do I use all the things together as opposed to be in competition with a different technology.

44:44Aaron Nathan: Well, and you mentioned the absolute frame concept. What happens when many robots or systems are working from the same map? Does it work across platforms like drones that are moving at one speed and cars moving at another and delivery robots moving at another? How does that work together? Yeah. So our technology is agnostic to the platform. But I need to be a little bit careful in how we say that because we do actually take advantage of the fact that we know that we're locating a drone or we're locating a tractor or a car, whatever the actual physics of the underlying thing is. The important part is this absolute frame is like a grid that we all agree on that defines the location and also things like speed and direction.

45:34of things. And the reason that's kind of a cool concept is you think about like a port where you have like a bunch of, let's say, forklifts driving around and they're all moving these big containers. They may not have like great visibility about where they're about to go. So your camera, your LIDAR may be blocked. There's this whole world where they actually can communicate in real time their positions and their directions and actually say, oh, I'm going to slow down because I can see, quote unquote, this collision happening purely just by observing like the almost video game view of the world.

46:13And I think that this is where, you know, the current state of robotics is that each robotic company goes to a site and builds a map. And that's like needed because we're so early. And so the eventual solution, though, is there will absolutely be interop between these things. And I don't think it's going to be just because like, it's nice to have, I think it's actually going to drive like the core thing that robotics are supposed to do, which is to drive efficiency and throughput and all these things. So yeah, I mean, in my mind, that's an inevitable future. And it's why location to me, it's like it has to be on this shared common grid and it can't be each robot company figuring out its own thing.

47:05It's just inherently less efficient. Let's talk a little bit about some of the markets then that you're serving. We've dropped a few of them already. Tell us some of the other interesting use cases for the technology. And I don't know if you're able to share some of the companies that have deployed 0.1 nav into their platforms. Yeah. I mean, so we are, um, you know, the investor pitch is a 0.1s in everything that moves. And, um, we're, we're trying to really actually make that the case. Um, so when we look at our markets, you know, there is the traditional things you mentioned like survey. Um, what we do is so, uh, at scale that we've started to disrupt that market even.

47:46So we have, uh, some customers there. One of them is MLID and we just announced, you know, So those survey polls that you see, they just come directly with point one from the factory. So it's like you don't really need to do anything. It's like a batteries included experience, highly disruptive to that market. The other markets we see are in like consumer. So you're starting to see these autonomous lawnmowers that you'll be able to buy in like Combeco, Lowe's. They're going to have our technology on them and it's going to be mowing your lawn like next year. It's kind of a wild capability. In agriculture, we have lots of different customers doing everything from planting seeds to taking weeds out.

48:29One of the ones I really like is Burrow. They've almost built a platform that is a physical platform. And so their robot will move around and do all kinds of different tasks on the farm, follow people around. And, you know, they use this, obviously, to make sure that that robot is able to stay right in between, you know, the rows of crops or wherever it is it's advocating. Drones is a big one. We see that in two major use cases. One is really in the world of public safety. So companies like Skydio use our drones. And then in delivery, you know, we have customers there, several delivery customers.

49:12You know, people I'm sure have heard of like Zipline and they're using us for that delivery function. And it's, I think the coolest thing about it is just how many different markets we end up seeing this. Construction and mining is another one that we have lots of customers in. And the number of use cases just keeps growing. production on motive. We're even going to be launching motorcycles next year. Just it's, I mean, that notion of everything that moves is becoming true. I mean, I'm curious, you talk about disintermediating the surveying. Does it mean that you don't need to deploy a total station on site anymore to get the accuracy you need?

49:59I mean, so total stations specifically serve like the millimeter market, which like that's a little bit, you know, beyond where we want to go. So there's still a use case for total stations. Yes. But what's funny is like people will actually use our technology with the total station because the total station technically is a, because you millimeters relative to wherever you put it. And then like now you get millimeters to that point. Right. But how do you know, like if that point is correct? So as another example, the customer Civ Robotics, and they literally have a robot that runs around and it just like puts a stake in the ground where they're supposed to drive a pylon to put building, you know, so you really want to make sure you get that right.

50:41And those are the kinds of things where I guess technically that's like a survey stroke construction application, but it's also bringing robotics. And I think this is really, we're starting to see a convergence of these technologies. And I think it's super exciting. Now, a lot of teams can get a pilot working, but when they start to scale, and you and I attended the RobOpsCon last week. And so very, very interesting to talk about situations with scale. So what are some of the things that sort of need to happen when you go from that initial pilot to a production with Point Nav or other sort of location?

51:30technologies. Yeah, I mean, there's, I'd say two categories of things when you get to percussion, there's, you know, the relationship with your vendors, like if we're working with a robotic mower company, let's say, and what's the relationship between us and that mower company, we've designed the product around having these tools that let you make kind of observability decisions at scale, because it's one thing to have a portal you log into, and you can see one robot's health. But how do you do it when you have like 100 ,000 robots operating and then you wanted to see like, is there an issue in the whole of France?

52:09So these are considerations that we've actually already built into our platform and then exposed APIs that allow our customers to now bring that into their dashboards. Because the thing that comes with scale is all those weird problems that happen, you know, once in a blue moon, they happen a lot because you have just a lot of things in the field. And so the customer service organization actually gets a ton of value by working with us because they can directly integrate into our system and see what we see. And that results in just having, you know, quicker ticket resolution, better understanding of the overall what's happening.

52:55And that's just one example. The other example is like when you are selling that many robots, you actually have to start thinking about how do I provision these things? Like how do I build them in a factory? How are they tested? And so again, it goes back to like be very thoughtful about the kind of like life cycle of this building of a robot and making sure that we have the correct APIs to support all that. And you know, when a robot arrives at your customer, they're going to turn it on and it's going to work. And that takes a lot of forethought. It takes vendors that are going to work with you very well.

53:34I mean, it's, I could tell you like, just as a personal experience, we work with a lot of the cellular companies and it is extremely difficult to put a sim card in something and then know that it's going to work when you ship it to a customer and they turn it on and a lot of these systems and robotics almost work the same way because it's like the physical world is a lot of variables and so you just really have to make sure that you're arming the customer with as much information as you possibly can the other part of scale i did want to mention is just geographic scale and so being able to show up to markets and have things work.

54:11And we've obviously built a ton of infrastructure. It's one of our core pillars of the business. But we still have places that don't have coverage. If you're doing the open pit mine in Northern Canada, we may not have coverage there yet. So we've actually figured out how do we work with customers to have deployable coverage where they can actually bring their own technicians to go and actually install equipment to make the Point One service work there. And it becomes managed. It's like a really amazing experience for them. And we've actually now had some customers come back and say, hey, this is game changing for our business because we can completely take the infrastructure problem off the table for them too.

54:55Aaron Nathan: Talking about building the business side of things, Point One NAB brings together expertise across GNSS, networking, autonomy, robotics. Most companies are good at maybe one of them. How did all this come together? Yeah, I mean, I think, so generally speaking, I think this is true of most robotics companies is robotics requires you to be good at a lot of things because it is a physical problem. So you have to have like mechanical engineers who know how to build and assemble and like have things not rattle apart. You know, you have to have electrical engineers that know how to build circuit boards and all these kinds of things.

55:34And then you obviously need software engineers who know how to actually write the code that makes these things work. And software engineering spans everything from, you know, low-level microcontroller firmware up to at-scale cloud software. And then on top of all that, there's all the operations behind it, which is often forgotten about. And so we very early were able to assemble a team that were expert in doing a lot of these different verticals and had also experienced like kind of like cross-functionally working with those different expertises like in their past lives. lives. And so I think it's the team is like the short answer of that.

56:18And it's very powerful when you can have a small team of people that know how to do a lot of different things because we don't have as many things fall through the cracks. And so it's built like this very tightly coupled organization and i think it's part of why we've been able to build so much without you mean to raise a billion dollars or something crazy well and point one's been around for about 10 years

56:48Aaron Nathan: so you've been putting in the work and putting in the effort even going back to the challenge that you mentioned earlier but um what why is it growing so fast right now what's what's going on what's in the water that everyone's drinking? Yeah. I mean, it's definitely been an inflection point. And I think there's a few factors that contribute to it. I mean, first of all, like the nature of our business, especially the early parts of RTK, or that you needed to get to a certain level of scale to be able to service like a consumer business, right? Like when you buy your mower at Home Depot, I can't like guess if we're going to have coverage when you take it home.

57:29We just have to know that. And so there was a level of critical scale that we hit. And that was a big transition for us about, I'd say, like three years ago, where we had one of the largest professionally run corrections networks out there. now the other thing that we've done and seen is that physical ai or you know whatever you love to call it now um it's gone from something that was like hey we can do all these cool demos in the lab to these things are actually working and delivering value and we're seeing it i think in two contexts there are some consumer use cases like the lawnmowers that are at scale i would argue that not self-driving cars quite yet because those are still relatively small, but the high levels of advanced driver assistance that we see has been another huge area of consumer.

58:22And then when you go into the industrial sector, which is where the vast majority of our customers are, it's just like these point solutions have just delivered so much value, like in agriculture, being able to do like weeding really well for lettuce you know it's like that's a big deal and so we uh we just see that like the applications are working and so that's putting demand on us and it's resulted like just in the last year uh i think we've 10x the number of customers that we actually have um and that's that's just like a really amazing uh stat especially given like i don't think the market slowing down.

59:02If anything, it's continuing to accelerate. The other piece that's really interesting for us is that all of these customers, the deployments are still relatively small in the industrial sector, but they're growing very quickly. They're seeing this high level of adoption as they're moving from pilots to actual being rolled out across local facilities, etc.

59:28Aaron Nathan: All great tailwinds. Yeah, well, you talked about that 10x growth. I know 0.1 raised$35 million in seriously funding by Crosslow Ventures. What does that enable as you continue scaling up? Yeah, so one of the big things that we've been doing is trying to get into more markets. So, obviously, we started here in the US, we're headquartered in San Francisco. And then since then, you know, we've really put a lot of effort into global expansion. So we just actually, uh, announced a large partnership with Orange, who's one of the largest telcos in Europe and frankly, around the world. Um, and you know, we're also doing, uh, you know, business in Asia and like trying to figure out how do we actually, um, solve this problem, not just from a U S perspective, but actually have like a global solution because we've seen actually our technology is most valuable to the biggest companies who actually are thinking at a global scale.

1:00:29And this is really like, I think, a great thing for us as a business because we're now able to go in and say, yes, we have something that will work in the US, in Europe, in Japan, you know, in South Korea, in New Zealand, in Australia. and we're expanding even beyond just that. And I think that's a really powerful value proposition when you're trying to make a product that serves all those markets. Wow. So I'm curious what's next. We've talked about Agrobots is one of the growing markets and where I've seen, as you already said, a lot of companies adopting your technology for the accuracy it gives them in the workflows that they're trying to deploy.

1:01:11But what's around the corner? What excites you about this industry or other industries as well as the growth of the company? Yeah, I mean, there's been amazing advancements, I think, in the overall architecture for how people are building these robotic systems. You know, foundational models are transforming how we think about, you know, just robotics in general. And, you know, several of the companies leading in that field are customers. and we are trying to figure out the right way to bring location in a like maximal useful way in that context and so if you have these kind of like parallel systems which is what we're kind of seeing shake out as the default today where you have some model-based uh you know decision system and then you also have like a more traditional stack of perception planning and acting.

1:02:05Location is ultimately kind of like common between those two pieces of the stack. We are trying to think, how do we bring point one into that ecosystem in a way that's native, I guess you could say. The other piece is just, you know, how do we continue on our North Star vision of making, you know, positioning work everywhere with a high degree of reliability. and uh you know we have a lot of work in our lab that you know is uh not quite yet ready but it is something that uh i'm very excited for the future because uh yeah robotics is not slowing down and i still believe what i believed in 2016 which is that we will have a demand for more robotic systems to have high precision location that we do all the humans and phones combined today any opportunity to bring it indoors?

1:02:56We think we talk about the outdoor location problem, but we also think about warehouses and manufacturing lines under the roof. Is there a future application where this or some other new technology provides the accuracy those robots need? Yeah. I mean, it's a very clear need and we're studying that quite a bit. And, you know, the technologies that are out there today, like ultra wideband or, you know, Bluetooth beaconing, they're great for tracking like, hey, where's the tool or where's the package along the, you know, the palette line or something. but it's not sufficient to navigate a robot.

1:03:36And so, you know, you can imagine a world where our technology works in tandem with, you know, indoor technologies to be able to deliver that, like, common coordinate system I was talking about. But yeah, I think it's an absolutely exciting area. And we are definitely exploring to see, you know, the right way for 0.1 to service not just the outside, but the indoor and the outside and in between. Awesome. Well, hey, one more time before we let you go. Fuse is coming up November 19th. Tell us one more pitch on that event and what folks should expect and who should come. If you are building robotic systems and you use location in any way, which basically unless you have a statically mounted arm, you probably had experienced a lot of these problems.

1:04:30you should be at this event. So November 19th in San Francisco at the Foundry. Our website is fuse.1nav.com. And any listeners here, they can get a 30 % discount. The code is FuseRobotReport. And I'm sure we could put a link in the bio. Absolutely. Yeah. FuseRobotReport, all one word. So thanks for that. Appreciate you extending that to our listeners. And I hope folks, if you're listening, go sign up, be there. It'll be the place to be if you want to learn about the latest in location. So, Aaron, Nathan, thank you so much for joining us and sharing an update on where you guys are. And I look forward to following your guys' success in the future.

1:05:17I really appreciate it. Thanks, Mike. Thanks, Gene.

1:05:23Great stuff there. Thanks again to Aaron for joining us there. I liked where you said, Mike, location. This is a quote, quote. Location is one of those things you really have to get right early in the design process of your robotic system. Otherwise, everything else downstream kind of falls apart. I think that's a good model for folks listening to this to make sure they follow. Yeah, it's true. And again, like we talked about, you know, what happens to robots when they're in like an orchard, you know, when the robots are occluded from seeing the sky and, you know, GPS becomes spotty. What do the robots need to do?

1:05:59It's one of those things, Steve, when I was managing the mobile robots, the indoor mobile robots, getting lost, needing to be relocalized, was a frequent and still is for many indoor robot systems. And it's even a bigger challenge when that's outdoor. So, again, it was interesting to dive deep on that. And it was a great conversation. Same thing, inspection drones. another use case they always need to know where they are so if you're looking at something you want to know where you are in space so you can relate that and the more accurate you are the better that data is going to be and you know steve one of the last things i want to point out for for point nav is that remember we've been covering the india autonomous challenge for since its inception and they've used point one nav since the beginning of the event five years to go to keep those cars on track.

1:06:52That was one of the great stress cases for this concept of knowing where you are. And even in those race cars, they have two receivers, one at the front of the vehicle and one in the back of the vehicle because that centimeter accuracy was important to know how the vehicle was turning, rate of turn, all that kind of stuff. And I remember one of the biggest crashes, so to speak, one of the vehicles went off off the track because it lost this there was some some problem on board it lost the gps signal and you know the robot was moving you know 150 miles an hour something like that and so sort of spun off the the track and in the corner uh and it was because it lost the it's gps signal didn't know where it was anymore and that caused the whole system to become confused so position is important everything always comes back to the india autonomous challenge for you huh it does man love racing yeah that's funny uh oh again that was a great look under the hood of what's become a ubiquitous sensor for outdoor robotics today and again kudos to you for challenging him on the indoor positioning problem for uh warehouse robots that was good by you yeah i again i think this is a huge market as aaron talked about as they move you know beyond robotics into other areas, autonomous vehicles, and what have you.

1:08:16And again, I think that's why it's time for them to bring all their customers together for that Fuse event that's happening in a few weeks. So it sounds like it's going to be a great event. Yeah, I think this is the first time they're doing this in Silicon Valley. I believe it's in San Francisco. Great lineup of folks there. So make sure you check that out. And make sure you check out the Robotics Summit, Mike. Boston coming June 2nd and 3rd, 2027. Again, we'll have over 5 ,000 people there, over 250 exhibitors. We're looking for partners. We're looking for speakers. We're looking for sponsors.

1:08:49Registration not quite ready to be opened at this point in time. But if you want to get involved, reach out to any one of us here at The Robot Report. We can help get you set up. If you want to be a speaker, make sure you apply. Send in a session proposal as soon as you can. We'll link to it in the show notes. Or you can go to therobotreport.com. You can see it there as well. But again, Robotics Summit Boston. and coming to the Heinz Convention Center in downtown Boston, June 2nd and 3rd, 2027. You'll hear more from us as we get closer to that show. But that's going to do it for episode 269. Thanks again to everybody for tuning into the show.

1:09:24Thanks to Aaron Nathan, the CEO of Point One, for being our guest this week. Again, if you're interested, make sure you check out their Fuse event that's happening on November 19th in Silicon Valley to learn all things about outdoor positioning and navigation. They have a great lineup of speakers that are going to be there. Also, thank you to Intel for sponsoring the podcast this month. New episodes of the Robot Report podcast drop each week. You can find us anywhere you listen to your podcast. Please give us a review. Tell your friends about us. Really help us out. This episode was produced by Mike Oitzman.

1:09:55It was edited by Tyler Kubisti. Our executive producer is Amanda Buhner. I'm Steve Crow. Thanks so much, folks, for tuning in. And we will talk to you again next week.

1:10:07Thank you.