11. Commercial-grade Autonomous Mowers, Safety, and Dogfooding, with CBQ
In this episode, Audrow Nash speaks to Charles Brian Quinn (aka, CBQ), CEO and a Co-Founder of Greenzie. Greenzie make an autonomous driving system for commercial lawn mowers. We talk about Greenzie's autonomous mowing system, how Greenzie has worked with manufacturers to up-fit their system into comercial mowers, how Greenzie does dog-fooding, safety and standards, and about CBQ's experiences bootstrapping and with venture capital.
- 0:00:00 - Start
- 0:00:51 - Introducing CBQ and Greenzie
- 0:02:40 - Why go by initials?
- 0:03:22 - Describing the Greenzie autonomous system
- 0:08:51 - Working with mower manufacturers to up-fit their system
- 0:15:22 - Software on autonomous system
- 0:21:21 - Mapping the lawn
- 0:28:03 - Handling poor GPS signal
- 0:33:28 - Perception pipeline
- 0:38:58 - Having a human use their mowers
- 0:45:15 - Standards in the off-road space
- 0:50:18 - The value of standards bodies
- 0:55:00 - Depth cameras in the autonomous system
- 0:58:37 - LIDAR and being venture backed
- 1:02:24 - Replacing depth cameras with LIDAR? + Tesla and computer vision
- 1:03:50 - Ruggedized computer
- 1:06:36 - Microcontrollers, testing, and visualizing data
- 1:12:03 - Deploying software updates
- 1:17:33 - Safety
- 1:20:57 - Testing for deployment + dogfooding
- 1:24:54 - Training people to work with their autonomous system
- 1:29:54 - Greenzie’s business model
- 1:35:13 - Bootstrapping a startup versus venture capital
- 1:39:23 - What CBQ learned from bootstrapping
- 1:47:38 - Future of Greenzie
- 1:51:09 - Advice to someone starting their career
- 1:54:02 - Links and social media
The transcript is for informational purposes and is not guaranteed to be correct.
(0:00:02) Audrow Nash
This is a conversation with Charles Brian Quinn, also known as CB Q, who is the CEO and co founder of green Z. Greens. He makes an autonomous driving system for commercial lawn mowers. In this interview, we talk about greens these autonomous mowing system, how they've worked with manufacturers to upfit their system into commercial mowers, how greens he does dogfooding and about CPQ his experience with bootstrapping, and raising venture capital in startups. This is the SENS think act Podcast. I'm Audrow Nash. Thank you to our founding sponsor, Open Robotics. And now, here is my conversation with CPQ. Hi, CPQ Would you introduce yourself?
(0:00:54) Charles Brian Quinn
Hey, Audrow Good to be here on the podcast. I am CPQ I go by my initials Charles Brian Quinn, and then the co founder and CEO of green Z. Greens he had our our big mission is to free humans from repetitive outdoor labor. And we're starting in the green industry. We have a product that helps create self driving commercial zero turn lawn mowers. So we help big landscaping crews that maintain the largest crop in the United States by square footage to help them reduce their cost of labor,
(0:01:27) Audrow Nash
the cost of living grass by largest crop that is,
(0:01:31) Charles Brian Quinn
if you think about it, you know, I know you've had great people on your podcast that are doing farming and but if you look at square footage in terms I mean, grass is a crop that the we maintain across the United States in terms of watering, cutting, maintaining, cultivating, in terms of square footage about about 3x corn, which would be the next and so there's people who do that that industry, the green industry we call it is pretty big industry and not a lot of people want to sit stand or push a mower for eight hours in the hot sun, especially here in Atlanta, Georgia, where we're based. And all over the US there's a shortage of labor. And that translates as you know, in supply and demand to higher sort of demands on that and and again, when when it doesn't people don't want to do it. And it's also dangerous, dirty, repetitive, monotonous, you know, things that we we all know our robots are very good and capable of and don't care about, then it is probably a good place for us to help supplement and add robotic workers to these crews, and our software that's based on ROS does that.
(0:02:36) Audrow Nash
Awesome. See, you brought up a lot of things I want to start. So first, you kind of unrelated to your mower. You mentioned there's a story behind CPQ and why you prefer that
(0:02:49) Charles Brian Quinn
out there. Yeah, I've just always gone by my initials starting from high school. And so it's even become my little moniker, you know, on every sort of side seq, which is CPQ I used to even have a license plate See viki.com And since 99, so I've been gone for a while. So yeah, and it's funny and professionally to a lot of people were like, hey, you know, CPQ and they're like, who? And it's like Charles and they're like, oh, yeah, CBK it's kind of a moniker that both professionally and friendly. I go by. So Andre Audrow were close enough. Now you can call me CPQ.
(0:03:23) Audrow Nash
Funny. Okay, so now tell me about the greens, the mower or your setup?
(0:03:29) Charles Brian Quinn
Yeah, absolutely. So we it's important to note that what we do is we are an automated driving sort of system, right? We are basically a software package that's enabled by a set of, we call them off the shelf sensors. As you know, Robotics has gotten very far in the past, Gosh, 20 3050 years, even more recently with the introduction of the Robotic Operating System. And so with the standardization these a lot of the reps and things like you know, data structures, like point clouds and ROS enhancement proposals are like being standards for the ROS community. An easy one would be like, hey, use meters as opposed to, you know, inches, right? Like, that's a very good rep, one of the three I believe, says, you know, there's some good ones out there. And so with all that, what we've found is that the time is now to take some of these sensors, like the real sense camera, and use that to basically do a function or task and so green z, we build software. That software is enabled by a set of sensors and we certify those sensors, we call it being a robotic ready, that's part of our robotic Ready program. So we help these mowers become robotic ready. And once they have the sensors, they can then run our software and our software adds self driving. So, we we are trying to like I said reduce the cost of labor. So when you think about autonomous and the behaviors and things that make something autonomous. It is sort of self directed at x You know, again, it's sensing thinking, perceiving and acting on the world. And so what we do is we have a sensor stack that does that for a very particular part of the process that landscapers do, and that these mowers do, we call it sometimes we call it cutting out the middle. And that's kind of a unique term that landscapers kind of kind of resonates with. Because when you get to a job site, you know, there's a certain set of tasks to do to make, you know, the property look beautiful or safe. If you're, you know, mowing a hospital facility that has a helipad, you know, or right of way for safety, or on roadways, or industrial, you know, a lot, a lot of safety reasons why you want to keep that, that maintain that property maintained, as well as make it look beautiful, then there's a tougher task you do. And so our software helps automate some of that. And, again, by doing that we help reduce the cost of labor for those landscapers, which is why they like our robotic workers, but a lot of people assume we have mowers and we don't, they're some of our competitors, who are wonderful, and happy to mention them here. Companies like Saif do are building a automated mower, and that we unfortunately do not we actually build a a kit, basically. And we do it at the factory. So we help manufacturers and OEMs produce self driving equipment that's comes from the factory. Both strategies, I think are noble. And I think that it's tough to compete. You know, especially talk about John Deere, who I know that one has been on your podcast, it's tough to compete with them, they produce lawn equipment, I've been doing so for hundreds of years. So they've got a lot of learning ahead of them and distribution and all that stuff. But so what we do is, again, add sensors, and a sensor suite package and our software that goes on these existing commercial mowers to add autonomy. Gotcha. Yeah, it's it seems like a clever approach, especially for a startup to work with a company that actually makes them ours, and then kind of retrofit that with your autonomous system. Yeah. And the word like a lower barrier than it is for sure. You know, in talking about lower barrier, when we first started, we did try and like retrofit, like posts sort of sale and so we go get these mowers and, and put all these things on them. And I'll never forget the first time we did it, everything broke. And then we're like, well, well, let's just make it more robust. Right? And so we tried, and what do you mean, everything broke out, bro. You know, like, when you think about how these are used, I remember the first demo, I saw ED, right, who's the CEO, right manufacturing, who is one of our current manufacturing partners that were partner with to bring out our first product. I remember seeing him demo, and he's nonchalantly talking as he's demoing. And he drives off the curb, and then like drives back on it and drives back on it and off of it, and the mower is just bouncing off the curb, repeatedly. Yeah. And he puts down to the deck and the deck, like hits it and bumps up. And I was like, oh my goodness, like the amount of vibration ruggedization required to keep what we had originally had, we just cert put these servers with an eMag clutch to basically actuate the the the left wheel and the right wheel. And it worked. But you know, it was very fragile and delicate. Absolutely. And you know, and it's funny, like, it's not that they're our end user customers are rough on the equipment, it's just that they have a job to do, and not a lot of time to do it. And so the you know, they're they move fast, they roll over the curb, they run it back into the truck and are on to the next site. So but retrofitting was very difficult. And so we immediately moved it from sort of this post retrofit to at the factory, that way we can use the design principles, design it in with the mower and get that support.
(0:08:51) Audrow Nash
How does that work? It's like, so do you have to go to the company and say, Hey, we needed at this stage? And just tell me a bit about that. Because that's interesting.
(0:08:59) Charles Brian Quinn
Yeah. So this is part of my consulting background. You know, in a previous life, I, we I helped some of the big companies like GE Lighting, and some other companies do software that went with hardware. And one of the ways you do it is you go to the factory, where that thing is produced as close as possible to the line. They call the assembly line or manufacturing line. And by doing the upfitting is what we call it. You call it retrofitting, but
(0:09:27) Audrow Nash
it's up fitting that way. You think about it, like when you buy a guitar go has it a little different than retrofitting, because you're not getting it all the way in. Like you're not getting it from the retailer where it's entirely set up for the user. You're getting it part of the way and then you're adding things and changing things. Yeah,
(0:09:45) Charles Brian Quinn
we call it a good way to look at it. If you think about it. If you go to the Let's assume you went to the Ford dealer to go get a truck. When you go they have some base models. You know the F 150 which is the most popular are selling truck and we have a couple of Ford Yep. And if you go and you say I want this one, they're like, great. And you say, You know what would be awesome, those, I would love one with a V eight, like turbo diesel, and they go great, we don't have any, but we could get that upgrade package like we can do that. And we get that from the factory, like we'll put in that order that it'll come down the line, we'll put it on there for you. And you can get even more custom than that. But so that's the idea is that this is a feature, we call it a autonomous mowing that we built that you could up fit or upgrade and order. And then it comes from the factory. So what we've done is work with, right. And I'm working with a couple others right now, that where we go and we do that, that outfitting as close to as I said the factory as possible so that they come off the line. And then when they go to the you know, because manufacturers are people who do this, the end user customers buy their equipment from outdoor power equipment, so much like a dealer. It's kind of like a dealership, but for outdoor power equipment. They sell these things to do this kind of activities. They have those mowers already there. And then they activate them just like I guess OnStar or Sirius XM Radio, if you've ever done that process that's similar to us, except you're doing software that does autonomy, autonomous driving, that's cool. Okay, is there.
(0:11:16) Audrow Nash
So when you approached the company that makes the mower and you want to add these custom features, I assume they don't have like an autonomous mower package. So I assume you have to work with them to do that.
(0:11:28) Charles Brian Quinn
Yeah. You know, when we started the company, we were sort of like people were like, you know, we already have robot mowers, right. And so if you look at the idea of a robot mower, those are those little Roomba like machines that and they've been around since the 1970s. That patent is has been there, I think since Yeah. 70. And so you put a boundary wire in the yard. And so the big commercial mowers were like, Hey, what is this? You know, and how is this different? And, you know, we had to do a little bit of convincing to tell them no, no, this is self driving assisted sort of like almost like Lane Assist. And when we start using those terms, they're like, oh, like my new truck? has you know that where it keeps them in the lane? Probably? Yeah, it definitely helped. And so we said, hey, this is self driving, but for these big commercial mowers, where it takes over on part of the operation, and they said, well, that's not possible now is it? And we said, well, look over here, and we built prototypes, and we did the retrofitting. And we did all these things. And you know, and I'll get back to that. But that's actually the one of the thesis of the business is that we have been iterating since we started and the term iterate is very important to us. It means do learn, improve, and repeat. And the process of iteration has helped us tremendously. So I think it's, it's interesting, as an entrepreneur, I look back and say, Oh, it's always been this way. But I can guarantee you that, you know, we've been through several iterations where we probably thought certain things, and then we learned and did and now the new reality is that that is what we do. So, you know, every entrepreneur will tell you, Oh, yeah, I knew everything to do with the business. Yeah, they don't actually what they do say is they say, Well, we learned a lot. So a lot of them talk about, like learning through failing, right, failing fast, right? So we were doing a lot of that in the beginning. And so that's how we got there. To answer your question, yes, when we go to manufacture, that is, you know, the, the now what we do is we pitch and we tell them about this robotic ready, which is now been proven and commercialized with a couple of partners already. So there are there are a few systems out there, I would say that are competitive. X mark is a big manufacturer who makes Toro are sorry, Toro, who owns X mark and, and so they have one that they've been working on for a while. And then they even made an acquisition in our space, which was amazing. And I'm so thankful for that, you know, normally when, when, when, when a competitor is acquired by a big manufacturer, it's actually an incredible opportunity. You know, like a lot of companies are like, Oh, that's scary, because the big guy like has it now. They slow down. No, isn't that I mean, it's honestly that. I mean, I live in a world of abundance. And so yeah, investors and everybody, and there's always enough for everybody to do. And so when that happened precedent, well, yeah, that any legitimizes you and it also helps every other manufacturer who doesn't have that, like will pick up the phone and say, Hey, I see that you do this, right. If you know, there are 46 outdoor power manufacturers, and you may actually be hearing some one of them on the background. Apologies. That's in our test lab. But if one of those 46 Like starts to think that they get ahead, then the other 45 are gonna be like, hey, and there may be another one, you know, a new one comes online, you know, 4648, you know, so you're saying new companies, yeah, new manufacturers or other sort of entrants to the market. But I think competition is wonderful. It's definitely legitimising and it's a rising tide lifts all boats. I believe that and I believe that, you know, my entire life.
(0:14:57) Audrow Nash
Yeah, it also seems like it makes it It easy the space grows. Yes, there is a larger events in it so educate, it's easier to harness all that. Yeah, yeah. And parts may be become more easily procured and
(0:15:12) Charles Brian Quinn
things like this. And then you get stuff like, you know, like, maybe standards are created, right that are there to help you too, as well.
(0:15:20) Audrow Nash
Uh huh. So what is your autonomous driving system? What's it composed of? You mentioned a lot of sensors. And it probably has a big computer with it. And it has some things to interact with existing mower hardware, but tell me a bit about it.
(0:15:35) Charles Brian Quinn
Sure. So we're big fans of ROS. And they're not like operating systems. So and we're big fans of open source. So while there are parts of our stack, a few nodes that we probably won't open source, just because they're not going to be useful to the overall community. specific use case exactly. I see. But you know, if you look at like, say, robot localization, which we use, you know, it's funny, we were out there, I guess, couple years ago, two years ago, and in the field, and we were mowing for a customer. And I'll remind me to tell you about that becoming an actual becoming the customer and doing it ourselves. We still do that. Now. We learned a lot. We call that eating around dog food. But I'll come back. Yeah. But we were talking about robot localization, we were using this package and won one field, we would be mowing, and all of a sudden, we'd get to this one area, and the mower would shoot and say, Hey, I've got to head 50 miles that way, for my waypoint, and we were like, that is a bug. And we're like, that is really weird. And whenever flow error, it has to do with UTM boundaries. Are you familiar with, you know? So in,
(0:16:42) Audrow Nash
I don't even know what is UTM stands for? Yeah, so I
(0:16:44) Charles Brian Quinn
think it's a universal time Merkin teal, and we can look it up. I apologize. But what it has to do with is, latitude and longitude are all straight lines. So you know, if you're going on Google Maps, you'll maybe notice that you can get Google maps of like, you know, it's a 33 or 90, and it's all in degrees, right? So you can do any location on the planet, you can have a certain it is a sphere band. So you got so right, so why can't really wrap a sphere in a rectangle, right? There's some area that's adjusting for that. Correct. So we, we we most of the lot of problem to run into, yeah, mostly libraries take a area and they'll do it in bounding boxes. And so you'll be in a UTM quadrant. And so once you're in that quadrant, the the space goes from sort of, you know, it stays in that sort of area, right. And then once you move outside that boundary, that UTM boundary, and there are like, obviously 50 or so of those, you know, as you talked about the latitude longitude and the US, I think there's like five or six that you go across. Okay, don't correct me if I'm wrong on that. But there's quite a few. And we just happened to be on it, that one site happened to be on a UTM boundary. So when it crossed that boundary, it reset to the other UTM, which was 50 miles away. So anyway, we found that bug, and it was great, we worked with more to push up a PR and, you know, and push it back to the community. And now we're about localization can go across UTM boundaries. So big fans and open source been doing in my entire life. And we'd love to keep doing that as long as as long as it exists, which I hope is forever. And and so you'd ask us about our stack big fans of robot localization. So we use a lot of the base base stuff, we're not trying to reinvent the wheel. So standard cost maps, we're big fans of ROS control. We have hardware interfaces, which really help us with, you know, left wheel right wheel, differential drive. What else do we use? We use a lot of the standard data. You know, I
(0:18:39) Audrow Nash
guess they're missing depth by using ROS 1 or ROS 2.
(0:18:42) Charles Brian Quinn
We are currently our current generation stack is on ROS 1. And I think we're on melodic, and I think we have a noetic running around downstairs, that works just perfectly fine. And so we may upgrade our entire fleet to that. And then ROS T we've evaluated some of the packages we're using aren't quite there yet. And we've been working closely with some of you guys at Open Robotics, the Michael Carroll who said, close we're close. As soon as we are we would love to upgrade and we can even do that in field. So but we're enjoying the ROS 1 ecosystem. But yeah, so you asked what's our sensor stack and sort of package look like but autonomous mowing is a suite of ROS nodes that do a function and that function is autonomous mounting. So if you can imagine our system feels like an appliance. So it is a ruggedized computer and I think you need to go to our site. We're pretty open with like everything we use. It's an x86. I actually just gave a talk at ROS con. This last one on how to boot to ROS and seven seconds where I took this machine and really minimize the colonel and use the ubuntu LTS and kind of minimize that install with the precede to make it very minimize it boots up very quickly. Super fast. And I and just go straight into ROS, using System D, which we're big fans of, we like a lot of the Unix stuff. And so where there's a lot of custom stuff we don't, we're sort of not big fans of it. So yeah, we use a lot of like sort of trusted stuff like system D networking and open VPN and some of the sort of standard standard stuff that's been around for a while. It's very modular, extremely big fans of node based, you know, single responsibility, tiny things that do one thing very, very well, liberal and the input that they accept, very specific in the output that they do. And so a lot of design principles for software that we like about ROS. And our stack does that very, very well. It also interfaces with a web app that we've built, that our customers love. And that's built in Ruby on Rails, which we love, and is probably the best for doing rapid web application development. And, you know, there's a bunch of stuff behind the scenes there. But I won't go into all the details. But all that does a very specific function, and that is landscapers by our product, they take the motor out, they press map, they mow a area of the area, they want it to sort of finish the job for them, they press go on a little remote, and it basically just finishes and Stripe still fills in everything. So they do the border. And from there, you fill it in autonomously, exactly.
(0:21:19) Audrow Nash
Okay. Let's see. So for all of the what kind of sensors are you using for this whole? So when you map it? Is that are using GPS? Or? Yeah, so what kind of thing are using?
(0:21:35) Charles Brian Quinn
Yeah, so I'll start with control and get all the way sort of there. It starts with control. And in order to be, you know, I have a theory about robotics that a lot of people when they envision robots, they think of the Willow Garage, sort of PR to like, has to be humanoid. But in reality, you know, robots are in robotics as a way to I think automate and customize what would normally be considered a human level task. And so there's a lot of ways you can do it. When you think about self driving cars, they are in in terms, sort of a robotics. So the first thing you have to do is get good control. And so what we do is with let we need control of left wheel, right wheel, because these are differential drive, and a lot of them have caster wheels on the front. So they while they have bias, they don't really matter and are controlled. And so we start with left wheel and right wheel control. And we've been able to do that with a drive by wire system. And so that starts with with ROS control and having a canvas adapter. And so we use can which is on you know, very
(0:22:31) Audrow Nash
cool was on his cannon? Oh, yeah,
(0:22:34) Charles Brian Quinn
I think it's already gonna do you know it right. What is it? It's the automotive protocol. Right? Yeah,
(0:22:39) Audrow Nash
I know, it is the automotive protocol. I don't know
(0:22:41) Charles Brian Quinn
what exactly stands for. But it is a protocol, we could probably look up the acronym. But it is a protocol that a lot of cars use. And it's very small, it's very high speed. And good for redundancy. Yes, it's built in. And so we have that can interface layer that allows us to left wheel right wheel. So once we have that we then need to read. So we use encoders. This standard Hall Effect sensor encoders. And on our electric platform, we can read that straight from the wheel itself, they have encoders built in. And the reason you'll need to know that is no velocity. And so when you're able
(0:23:13) Audrow Nash
to say hey, you do your own mapping with this, you're not you're not necessarily using GPS, you're using odometry, large, right, and then maybe sensors and things.
(0:23:22) Charles Brian Quinn
So you're exactly right. So we're slowing down for
(0:23:26) Audrow Nash
just a second just to speak about a hall effect sensor. So it's a magnetic sensor, and you can count the ticks as a wheel spins. So maybe you have one magnets, or you could have a bunch of magnets and you can count do you do? What's it called where they're 90 degrees out of phase? If you have to, let's say that you can figure out the directionality. Yes, that's exactly correct. Because one way it's traveling 90 degrees over to get the next bump. And one way it's traveling 270 degrees or three fourths of a rotation or three fourths of a phase? I guess
(0:23:54) Charles Brian Quinn
that's correct. And you can get some telephones have the gear backwards. Exactly. So they have gear teeth that they're reading. And so then if you know, the tick count, you know, and you could just do the math to say how many wheels and velocity? Yeah, so yeah, exactly.
(0:24:10) Audrow Nash
And you were saying sensor fusion? Because if you're using raw odometry, like just seeing how many times your wheels spin, there's slip and all sorts of things that all accumulate as errors. So you're dealing with that through some sort of sensor fusion?
(0:24:24) Charles Brian Quinn
Yeah, so you're exactly right. When we first started, if you just use our DOM, or odometry, on a very nice platform that doesn't have a lot of slip, you go out, you turn left, you turn, right, you turn again, you get that square and in you know what'll end up happening is you'll be like this right? And it won't be distorting. And what I'm saying is you can't for those who can't see, it's like a you know, unconnected square right? Because of the slip. And so what we do is we fuse that with an IMU. And so we have a high grade IMU we've evaluated many, many many IMU use small ones we liked I happen to like some of the vector NAB stuff because it's nocturnally calibrated alias that for the gyroscope. So they don't even notice all of the sensor data from it. But yes, we do fuse a lot of the components from it. Yeah, the gyroscope, which tells it which direction you're facing? Yep. Yeah. So I did something like this in grad school, it was like some course where you use the sensor fusion of the inertial measurement unit, and the odometry. And it gets much more accurate, which is pretty amazing. So you're doing now we fuse that along with GPS, and we do high accuracy GPS, we have the ability to run on standard GPS, but we prefer and for some of our customers for the straight lines and tracking that they want to do. And a lot of the fields that we are we have RTK GPS, and are just gonna have real time kinematic. And what that means is, is if you think about normal EPA accurate, yes. And I think you've had people in your podcast talk about this before. But
(0:26:02) Audrow Nash
you may not have this podcast, previous one, I think so yeah, you get crazy.
(0:26:08) Charles Brian Quinn
You get correction data. So you can get a very accurate centimeter level. So we fuse all that now I can tell you that our sensor fusion is pretty heavily biased towards the RTK GPS, because the quality of it is just super accurate. Those are
(0:26:21) Audrow Nash
so if I remember correctly, and maybe the price has come down, those are like $20,000, or something to get a good RTK GPS isn't correct
(0:26:31) Charles Brian Quinn
or and we first started down, it has come down quite a bit. And when we first started exciting, I remember we were using an RTK setup that had a base station. And you're right, it was 1000s of dollars for this one and 1000s for the one on the machine. And gosh, just recently, I saw that. And a lot of it's been enabled by a company called ublox. And essentially, they have a chipset called the F nine and F nine P and that has taken the cost down to in saying I think we just got another sensor for I'll admit it, I think we just got our most recent RTK for like 129 bucks, and I'm like, Oh my God, that's crazy. And so the real the real kicker, though is that the data, Correctional Service really matters. And that's where you're seeing a lot of the innovation. So there's a service out there called SEF. There's service out there called Point perfect, that provides what we call n trip, which is I forget what that stands for, I think it's a network transport protocol. And so instead of having a base station, what they do is they're basically like a cellphone network and every 50 kilometers from the, you know, from certain high density areas, they put their own base station, they calibrate it with other sort of known areas. And then they can send out that correctional data over the Internet. And so you don't have to have a base station. That's nominal. And you already have that data. It's gotten really good, low latency, you know, super high availability. And with that correctional data, it's been really good and very good for our business.
(0:28:02) Audrow Nash
Do you ever? I don't know with RTK GPS, but do you ever run into situations where you're mowing a field and it doesn't have good GPS coverage? Absolutely.
(0:28:14) Charles Brian Quinn
So we've had to design a lot around that. And what happens is in localization, at least in the way we've done it, which is the best practices, you know, by you know, roboticist, you've done this before, you have what's called continuous and you have your discrete, and I think I'm getting that right. But in continuous, you've got things like, that are just going continuously. And so that's
(0:28:37) Audrow Nash
odometry. And that's the wheels spinning, okay? And knowing how far they spend, right? In
(0:28:41) Charles Brian Quinn
your discrete, you can have jumps, right? And so, in a good localization system, what will happen is, when you have when your discrete jumps, like, let's say your GPS shifts, and you know, it runs out or it's there's no connectivity, or whatever, and it says, oh, you know, I really thought you were here and you're moving along and boom, you're over here. A good localization system will go, I don't think so I, I had all this momentum in my ETF sort of saying bias that I was saying I was going five meters a second this way. Yet. Now when when you say me, I'm over here, I'm gonna ignore that and and yet back in.
(0:29:19) Audrow Nash
So you use probabilistic methods like an extended Kalman filter and ukef, as you were saying, exactly. And so what that does is you have a pretty good idea, like you have a probability distribution that says I'm most likely here. And if you get some information that says, I'm way over here, it's like, well, it's probably not very likely it takes that information into account. And then it adjusts its belief accordingly, but if you tune it in a way, it probably won't listen to that very hard, or very significantly.
(0:29:48) Charles Brian Quinn
And what ends up happening the thing that's worse actually is not GPS going out, per se, it's the thing that will mess you up. Is it is it changing and you should between a high accuracy and a low accuracy. So we've actually designed our system such that when it starts, if you get a high accuracy fix, like we go, and we're like, great. And then if we lose it, which has happened, you go down, you know, big hill and go down, and there's no coverage down here. And it just, it's starting to go out. If the system loses it, the mower will pause, our software will pause and say, hey, something's up. seconds ago was the last time I got a high accuracy. And so the mower pauses, and it'll kind of wait, maybe it's just like fluid, maybe it's a fluke or something. And so sometimes the motor will just kick back and start going, it'll get that fixed back. But if it can't, you know, there is a chance for the operator, at least with the mobile interface that we've built to say, you know, what, go ahead and turn off the low accuracy or high accuracy, and there may be a small shift in the map. And so it's not enough to make a huge difference based on what we've learned. But it is enough that you could say, hey, just turn it off. Because what what's, what stinks is how, again, going in between them, and it's constantly shifting is what will mess you up. But again, yeah, sensor fusion, what we do think about it, like we basically use our coordinate system in ROS, right? You have 00, right, which is where a robot starts, and then we record right. And so we're using all this data to determine where we think, you know, the next point is, you know, on the map and coordinate space, and we're using all these other systems. So the robot doesn't think it's at, you know, lat launch. It's using lat lodge as a data point,
(0:31:25) Audrow Nash
internal coordinate system. Yeah. Yeah, you transform it into your primary reference system.
(0:31:32) Charles Brian Quinn
And as all robotics is, right, it's a transform series of sensors all connected with a universal descriptive robot format. You RDF you. And that's, we love you RDF. We use this a lot as well, because it's all just transforms all the way down.
(0:31:47) Audrow Nash
Yeah. Funny. So if you so for your robot, where you're driving it, and you haven't heard it, and 50 seconds from the GPS, which is your really good source of information for driving it around. Do you have so if you're using a probabilistic way of reasoning about where it is, does that uncertainty just it keeps, so it received one good information? And then it drives using odometry? And yeah, using odometry. And then, so the uncertainty continues to grow as it goes. And at some point, you say, This is too uncertain, I'm gonna wait for a better GPS, or then you trigger this has have the operators switch the GPS, from high to low, or whatever it might be.
(0:32:31) Charles Brian Quinn
Generally, I don't know the, the correct answer to this. But what's interesting is, I think, when you think about cars, and how they drive so far, you know, that that where that bias could really go, and you talked about even going through UTM boundaries and things like that, that's where a lot of that will grow. In the areas that we're doing even like, like the the large acreage, even, it's enough to do a full day of mowing, and you're totally okay, running on that same localization and, and being able to cover that field. And we're good enough, then we haven't run into really any of those. And what's interesting is, at that, that's great, you reset, you turn off, you go to the next site you turn back on. And so since it's not long running, like the second truck, or a truck going across the US and really accumulating so much bias, we've been okay. Knock, yeah, so the error doesn't stack up that significantly and so sign I'm aware of.
(0:33:23) Audrow Nash
Awesome. Okay, so then, what? What other sensors do you have? So you have odometry, you have some depth cameras and things like this? What else? So or how is the how are the depth cameras use
(0:33:41) Charles Brian Quinn
your perception pipeline we're really proud of we are. I'm a big fan of AI and ML, and I think it's gonna happen. But I'm actually not, we're not using it, I believe it's gonna happen. I believe that some of the AI and ML modeling and some of the training and the networks that are being developed out there are going to revolutionize a lot of the tasks that we have to do algorithmically or programmatically. And I truly believe that. However, I think that right now, it's a bit of a black box approach. And you know, that the the amount of data required to really train it up for what we would consider to be good enough, prohibitive. It is and,
(0:34:23) Audrow Nash
and so we need like a million examples of someone walking in front of it or something
(0:34:27) Charles Brian Quinn
like that. And everybody corrects me says, Oh, we've got synthetic data. And I'm like, Well, you know, synthetic data is synthetic data, like you can only like change the color of a, you know, seven times and it doesn't really add that much.
(0:34:39) Audrow Nash
In distribution mismatches between simulated data and real data are huge a lot of times,
(0:34:45) Charles Brian Quinn
I mean, I know because we've been mowing in the field and you'd be surprised that the stuff we really ever Yeah. So what we've done is we've taken a really, I guess, a pretty unique and this goes back to our design principles approach of really keeping it simple. And so what we have is a lightning fast C++ pipeline that does, you know, ransack, which is stands for I don't, I can't remember random sampling. Yes. And what it does is it tries to consensus, right? So it tries to find the ground plane. And, and then anything above the ground plane is an obstacle. So, this is not like we're trying to classify and say You said, so I, the way I described our customers is they're like, visit detect, like kids. And I'm like, you know, it does not make a distinction between a garden gnome and a kid. If it sees something above the ground plane, it's going to stop
(0:35:33) Audrow Nash
it'll success to go back slightly for ransack and talk about a little bit about that. So you, you have your depth camera, your depth camera points over the ground. And then what you're going to do is check a bunch of, it's going to give you points at different depths, kind of. So from this, you're going to try to fit with a math equation, a plane on that. So a 2d surface, and the one that matches the majority of the points is the one you're gonna select. And that's it's a fast algorithm. Yeah, so the thing that's on top of that are deviating from it, you're like, This is something thing. Yeah, is what I understand.
(0:36:12) Charles Brian Quinn
Yeah, and not to get into all the details, but we have some special fun sauce, we do around line fit, and some of the other stuff on stuff to make it really fast and accurate. And, and then again, all that's translated into just a standard cost map. And the cost map would be, hey, you know, a, when they see something that is a, you know, tree or vertical plane or anything above that, that that is not part of that, that that surface, then it says, Hey, I can't go there. And so it creates a very large infinite cost map, you know, to say, like, kind of out there. Yeah, exactly.
(0:36:49) Audrow Nash
Okay, how do you deal with like? So I imagine like the way you want to handle a kid, in close distance to the mower, and the way you want to handle a pole would be very different. How do you, like if I, if there's poles in my lawn, or in my field here,
(0:37:06) Charles Brian Quinn
you want to go around them? Whereas the other kids want to stop? Right? Yeah, what's interesting is when you think about, and this is natural as as humans to sort of say, like, let's solve the entire domain, right, like, let's do it just like a human would. And what's interesting is, having developed this company, you know, from iterative and from these basis is sort of like, how do I solve the first immediate problem, which is a job to be done, and get as far as you can get, as far as
(0:37:33) Audrow Nash
that iterating, you're speaking about exactly,
(0:37:36) Charles Brian Quinn
is that when you get when you actually talk to customers? They're like, Do you know what they're like, I'm good at going around things. Like, you know, by the way, like, I can go right around a tree, I know where the the brushes, or the pine straw or whatever it is, or the roots there like I can do that. What I need help with is just the sort of big valueless. Exactly. And so what we've done is we've, we've built our system is such that it is made for those open areas. And so when a lot of people do that, they're like, Well, I probably can't use it. Because you know, I, you know, I, you know, I do this one that just has trees everywhere. And we're like, great. The good news is the mower still works like you normally do. Yeah, you know, like, I don't turn on cruise control, the moment I get out of my driveway, I hope you don't either. I only do it when it starts to get really repetitive and boring. And I'm like, I'm on the highway, let me turn on cruise control. And so it's the same functionality that we've developed, right? Yeah,
(0:38:31) Audrow Nash
cruise control is a very good metaphor for those. Yeah, see, because you use it when you have a spot that's incredibly monotonous. Like, it's just this big, open thing that's going to take a bunch of passes. And thus, a big open field, that's going to take a lot of back and forth. And so that's when you use it. But for the highly custom stuff, like if you had a bunch of poles or trees to go around, in which case you don't engage cruise control, you keep the robot. And so your systems are made so that a human operator can just jump on it. Like you're not modifying the spot where the human works,
(0:39:06) Charles Brian Quinn
right. And that's been very critical. Even when when we first developed it, I remember a customer early on telling me, you know, Hey, your system may be great and may never break, but this is my livelihood. So there always needs to be a way to disconnect. And so that's one of the features we design and the robotic ready. If you look at our website, there's a switch from manual to autonomous and, you know, it's funny, you and I both know that it's probably not needed in the future at one point. But it is a physical safety blanket type thing when you do this, the entire system is cut off, that could have autonomous control. And so there's no way for the system to take over and sort of issue commands to the wheels and that's a very fun thing for our customers that are relieving, you know a safety blanket that they like, and it's also a productivity thing like they can always sort of say, and when you say jump on to I want to be careful to say that that when the motor is going autonomous because we have sort of 360 cameras, if you run up to it, even from the back, it'll stop. If you even somehow were able to get up and dodge it or whatever, be a ninja. And it wasn't meaning this. But yeah, but it's fun to talk about, like, if you were to jump on the back, a lot of the mowers have a thing, you stand on a platform operator presence, if you get on that, like we used to allow people to ride on it while it was autonomous, and now we don't, because it's not a safety thing. But it was fun, you can ride on it while the matter was going to be pretty cool. But now if somebody is on there, it won't allow that. Right? So you know, we've had our customers try and put their safety people on it. And there's videos of them, like running up to it, jumping on it, and just stopping immediately. We're like, don't do that. And they're like, Well, you gotta test it. I was like, okay, funny.
(0:40:44) Audrow Nash
So it almost to me, it seems like a clever approach to do this, where you have the ability to toggle between the two, because it seems like if you're making a fully autonomous mower, and you're building the entire mower for the fully autonomous case, so you're not making a spot for the human to sit and work on it, for the drive it, it makes it so you have to solve every hard problem. And I think that that's probably like, there's a lot of them, I'm sure you can speak to like, how do you know if I don't know, you can go over these routes or go around all the things. But then having the human do these hard ones, that seems very
(0:41:21) Charles Brian Quinn
clever too good example would be like high grass, right? You know, so like, there's a big, you know, brush of grass. And we ran into this, right? Like, you know, one of our customers got a little behind, because they don't have enough labor. And they came out, they're like, Hey, listen, like this field is like knee high grass, like I was supposed to hit it last three weeks before, and I didn't, it's like way up here. And we're like, instead of the mower was like, like, can't go here can't go here. Like, even we have a feature for avoidance, which you know, and feel they can just have it go around. And so it's just constantly trying to go around everything. And he's like, it looks like it's drunk. And we look at the cameras. And so we look through the RGB. And we're like, whoa. And so we did design a feature for relaxed obstacle detection. And so we raised the ground plane of the ransack. And so we do let him operate with a higher, but but when we do that, again, this is all about jobs to be done. So we trust our operators, they're trained, they're certified to do it. And we, you know, train them on this. And we said, hey, listen, when you press this button, it'll relax it, you know, you better be sure that there's nothing in there. And when he did, he was like, works great. And we rolled that out, you know, two weeks later, and he was like, This is wonderful. Thank you. Can you can you add this feature? And we're like, Yep, sure can. So we keep going with them. And that's kind of how we run. Which you're right. It's, it's, it's the iterative approach, right? And you You hit the nail on the head, which is, how do we augment human capabilities, you know, especially were in these highly repetitive, dangerous, dull, dirty, monotonous things that robots are very good at and likened to, and then how do we keep the person able to do the creative, you know, unique, beautiful, and things that humans will always be good at and should be good. And, you know, that to me is the future. It's, it's what I love, like, why I do this, and why I get up every day.
(0:43:14) Audrow Nash
It's also the So for all those are great reasons. It's also pragmatic as a startup to, because you're not doing the hardest problem. First, you're not doing every hard problem all at once. Yeah, you're doing just the minimum to provide value in a market, which is fantastic for I mean, like, I mean, I'm thinking about autonomous cars now. And you see huge companies like, say, like Cruz, who has like, I don't know exactly, but like 1000s of engineers working on this problem, to fully automate driving. And a lot of really great things have come out of that. But as a startup, it's hard to do because you don't have 2000 engineers. So solving an easier problem that still provides a lot of value, kind of like what Tesla's doing, in a sense.
(0:44:03) Charles Brian Quinn
Yeah. And again, we're just we're sort of copying a lot of this crazy has been amazing. Our product manager that was just in San Francisco and holidays and was like a solid couple around around he's like, it's incredibly out there everywhere. It's crazy. And you that way Mo Yeah, yep. So it's the only choice here it's just not evenly distributed. And what I tend to think about the off road capabilities, what we're doing in the autonomous space where you know, it's interesting for us is I always tell people is like, hey, when we don't know what to do, we stop. Now, I think as a self driving car, I think when you don't know what to do, like, you can't just stop in the freeway, right? Yeah. Oh, gosh. There has to be a lot more and there's people involved and plenty for us who are in controlled environments like we can in some of the center's we're working with are sort of industrial Right. So there's a controlled environment, you know, you don't have people running around. Hell, it's it's interesting, because people were like, Well, what about schools and kids and it's like, hey, why don't you ask us landscaper, what they do? And have you ever seen a landscaper milling around kids know if the kids are out, they don't know, period and the story like manually. So, you know, so So the automation is capable of doing now and I think that the offered space will continue to have leaps and bounds. I?
(0:45:17) Audrow Nash
What do you mean off road space?
(0:45:19) Charles Brian Quinn
So when you think there's when I think about autonomy, there's a lot of standards right now, if you look at some of the bodies that are certifying on road autonomy through some of the standards, like the ISO 2626262. Yeah. Or what I think it is, it's one of those I just to say, just say this is until it repeats, but you have the
(0:45:37) Audrow Nash
right Ryan therapy from clear path you mentioned next Tuesday, or something like this, often, okay.
(0:45:44) Charles Brian Quinn
And so those are the those are the autonomy levels, right? Level one up to level five were like, level five is just, you know, and level five, kind of interesting, because I've heard people say that level five would be like, You tell your car, like, hey, take me to the beach, and it takes you to work instead. Because it's like, Hey, you actually need to go to work. Like it's truly self directed, right? It's like, No, you don't need to compete. But um, the, the i digress a little bit, but we talked about on river software, there's the standards and in off road, we don't have that, like there isn't a body learning is exactly that that's, that's determining these, we do have is a lot of some of the ones for industrial robotics. And so their standards like ar 1508, which is a robotics for automated machinery, and vehicles. And those are the ones that we're going for those standards. And we've been really lucky, we've working with some external consultants for risk analysis, as well as we've got just hired some validation engineer from from Rivia. And so we have a lot of firepower on that. And I think that are, and we're working with some of the industry as well, some of the outer power industry people directly to help make sure that those are safe standards, but we're doing that in conjunction with our customer, who also like has a job that they want to get done. You know, I tell my team, we have six core values and safety first is first. And number six is customer success. And they're not in real order. You know, they're all important. But if you think about it, like if safety is like the most critical, then the safest thing to do would be to just sit in a insulated bubble and tell our customers you can No, because mowings dangerous, right? That'd be the safest it is. But in the end, there's customer success, and they've got a job to do. And while it is dangerous, we accept those risks. And we the reason we accept this risk is because we've done enough risk analysis to know that like, hey, if I do this safely, and I follow the procedures and the guidelines, the risk is low enough, that I'm safe to do this. And so where we fit is trying to bridge that gap between I've got this job to be done. And I still want to do it safely and with the least amount of risk possible. And I frankly think that when we look back in the in the future, we're gonna look back and say, Wow, can you believe that we had humans sitting standing riding on these things that were prone to rollovers and a huge spinning blade? Yeah. And we'll be like, oh, yeah, we used to used to drive around in cars and smash into each other. Oh,
(0:48:09) Audrow Nash
no, I'm just gonna say, yeah, yeah, the cars are so dangerous, but, and it's funny, because, like, they're still relatively safe, but they are one of the most dangerous, dangerous things in modern society. So I think, like 50 years from now, it'll be like, our parents that we were driving around, like the risk, but
(0:48:31) Charles Brian Quinn
it's the only way to go right now. So
(0:48:33) Audrow Nash
it's true. Yeah, unless you walk or bicycle and bicycling is much more dangerous. And city it is.
(0:48:40) Charles Brian Quinn
Speaking of bicycling, you got to get, you've got to get Brandon from Luxan us on your podcast, the homework that he's been doing with depth a AI and the depth AI platform. These are our cameras that basically run AI ml on them. And they have great ROS drivers. And we're helping a little bit with that open sourcing a lot, but phenomenal and vegan advice. And he started this company because he had some friends who and I won't mess with his story. But they had a some accidents. And he was like, how do we prevent this? And he's like, we got to get a camera that faces behind. And so he tried to prototype one and was like, you know, how do we do this and, and with AI and ML where it is right now he was able to do it. And so he open sourced the platform so that other people are able to do it. And we're actually excited to start implementing that on our next gen, which we've already started. And so in terms of, you know, think about like the real sense and the depth. Cloud is a great protocol for algorithmic but like I said that AI stuff is coming fast. I mean, the stuff that they can even do, they can even output a Deaf cloud using you know, something. Exactly, exactly. And the quality better than stereo and these kinds of things and I've been super impressed and they fast. So we're definitely got to get him on. Because he's, I mean, in terms of robots, they're gonna revolutionize it, I think.
(0:50:06) Audrow Nash
Awesome. I'll look into having him on the podcast. Thank you for the recommendation. One, one thing that I'm wondering, like, where do you see standards bodies being helpful in these? Is it because they establish well defined protocols that are well thought out? And thus they reduce risk? Or where's the value in establishing these standards? Yeah, I probably
(0:50:35) Charles Brian Quinn
not the best person to ask this as an entrepreneur who thinks that all rules are there for somebody else. I'm kidding. The rules are meant to be broken. I don't believe that, but I'll say this, I mean, I benefit from them every single day. You know, like, from, from the headphone jack, I just plugged into to the USB that I had to plug in, and then turn around and then put back and then do it that way. Right. Those are all standards, right? Web Standards. You know, ROS being a standard, the rep, like we talked about, I'm a huge fan of those. And so what I think where, where I think the best things get built, is in a company is leading, and really driving that. And then it isn't all driven by consensus and committee. Now, I'm a big fan of committees, we're on a few. And but where I think that you can get in trouble is trying to design by consensus, I have a rule in our company, and my team will will kill me for saying this. But there's three types of decisions that are made at Green sea. And this is all companies by the way. There's command control. There's consensus. And then with there's consultative, right, so let's go through the three. So in command is when I come come in the room, and I'm like, Hey, guys, or hey, people, Hey, everybody, Hey, person's everybody. We're doing this. And everybody goes, Okay, let's do it. consultative is, His command is pretty good. And sort of wartime and scenarios when you need somebody just come and say, Hey, this is what we're doing. We make decisions. Yeah. consultative is very good. And consultative is very critical, and probably the one you should be doing in business. And the most important, that's the one where, where someone comes in and says, Hey, there's a decision that I'm in charge of making, because I'm responsible for this, you seek expertise, correct. And you said, I'm seeking your consultation on it. But ultimately, I have the call. And that's how all decisions in business should be made. The only decision in business that should be done consensus is where do we go for lunch? Yeah, because I just think that the that watering down of sort of, like, you know, we've got to get all everybody to buy in and fully understand it. You know, if you had to ask everybody, just nothing would get done. And so I do appreciate committees that are the appropriate size, that are in that actually have stakeholders who are committed and not just in it to sort of Express power or sort of lobbying or interest that aren't their own, then I think you have very good standards, and I'm all for that, you know, so again, you get real world, you know, and that's what I like about the ones we're on there. They're not from, you know, people who are just trying to stamp this out or competitive. They are people who are actually like, nd user, you know, who benefit from it. And where I think there's benefits is that, you know, we've seen this in the automotive industry, you know, there are standards bodies that say, like, Hey, here's what we think true sort of autonomy would look like. And these are some of the things we do you know, it's funny, there's a simple one that you know, I got a new car. And when you go to the back, there's a liftgate and there's a button, and all the iconic, iconic RV, is all sort of standardized, right? And so, you know, it seems funny, like it's an SUV, but the the Connor icon or Greg, I forget it, the icon itself is that looks like a card or something, right. And it's a hood closing, but it's I know, when I see that button, I click that, and I know that the hood will close. And that's because of standards help us all. So we all don't have to read the manual every time we do something. They really help with usability safety, and I'm a big fan. I do do sense, though, that there are some that are probably gotten too big or don't have appropriate stakeholders that matter anymore where I think a lot of damage can be done.
(0:54:30) Audrow Nash
How do you determine if it's too big? Oh, or how do you figure out the one size?
(0:54:36) Charles Brian Quinn
Yeah, I'm not the one to determine it. I think it's all context dependent, but I'll quote Yeah, he says, because he seems to be the smartest man on the planet. He says, What is it the pizza rule? Right? So if you can feed a pizza, that group is fine. It's the fine size but anything bigger than that? He's like, get rid of it. So everything is done in feeding. I think it's I think it's the pizza rule and maybe two pizzas. I'll have to look it up.
(0:55:00) Audrow Nash
Something some small number of pizzas. Anyways. Interesting. Okay, going back to your autonomous system a bit more. So you have many depth cameras, they're pointed. So you use odometry, odometry. And GPS. You're doing some sensor fusion there and is fusion. Correct. So we local and global, right? Yep, go ahead. And then you have cameras, depth cameras. So you were mentioning the Intel real sense, which is structured lighting, I believe, or maybe it sends out a laser or something
(0:55:35) Charles Brian Quinn
it does in the outdoor, it probably ignores a lot of the pattern project that happens the IR projection because of just using stereo, or what doesn't it works pretty well said is is stereo depth, right? Yeah. And no, in between them. Yep. And so
(0:55:49) Audrow Nash
you can infer how far away everything is by the disparity in the images taken by both of the cameras and go, Okay, so you have those, those are facing all you have, like, one of them on each corner, or they're all around
(0:56:01) Charles Brian Quinn
the 360. But what's interesting is that there are directions that a mower cannot go just like a car, right? You know, you can't see a car can't suddenly move laterally diagonal back. Yeah. Perfect. Yeah, exactly. Exactly. Yeah, exactly. Not morphic. And so having said that, we have pretty close to 360. But we actually have a bias towards the front being more important, because that's the primary direction that it goes. And so that that sensor is actually a little bit duplicated. If you look at our current one, we have a little bit of overlap. And those are calibrated, like I said, to make sure that we can see. But yeah, so we have very good coverage around the mower, and then in the back. But there's I mean, there are definitely sort of areas, you know, sort of here where it does not move, but the
(0:56:49) Audrow Nash
left and back right kind of thing. Yeah. Yeah. Okay, cuz you're not as worried about someone approaching in the mower, run running them over
(0:56:57) Charles Brian Quinn
for an even go that way. Exactly. And even the turns that it does, as soon as it turns it sees you and he's like, Well, I can't finish that turn, right. I see.
(0:57:07) Audrow Nash
And yeah, these are you said, it's like two wheel drive two, and you can turn in place because the front wheels or casters.
(0:57:14) Charles Brian Quinn
That's right, he's got all that zero turn or turn on a dime. Right. And so what's interesting is when I first we first got the the mower, you know, we're I used to be able to say I was new to landscaping. Now I can't write having been in a while. And so when we would do, we would go out and we'd be like, Oh, cool. Let's just turn and we would just zero turn right there. And when you do it, landscapers will go like, Oh, you just rotted the grass, because it's true. Can you imagine? If you have one wheel that stays stationary, and you pivot the other you especially good? Yeah, you actually tear up the grass. And so our first turns were terrible. You don't say don't put one wheel forward one wheel in reverse. You do now. And that's what our algorithm does, right? So that's what we do is we call it a perfect, they call it the Y turn or the you know, and so you can watch our machine do it, but it goes forward. And then it actually uses its own an inertial I guess. I don't know what you call it, but it's sort of kinematically so that it backs up, and then goes straight, and it lines up those casters perfect. And so it executes what is a very good turn. And when when landscapers see it, they're like, Whoa, it looks like an excuse. That's right. And it doesn't run the grass. And of course it does it every time, which is kind of fun. I mean, if you're in a hurry, you can always just you know, get out of there. Yeah. Well, what's great about a robot, right, is that a robot is one time to do it. And it's like, I'm happy to do that exact same turn every single time.
(0:58:36) Audrow Nash
Yeah. Okay. So do you have any other sensors?
(0:58:41) Charles Brian Quinn
On your outside? Let's see. So I think we are. Yeah, so we we've had ultrasonic video on it. Ultra problem with ultrasonics is and that was shortly that some of our machines still have it, but we're not using those. And I'm happy to disclose why that at the speeds inside times we were going it was only turning on for a very minimal amount of the thing because, you know, we're going I would say pretty fast. And we have been insanely happy with the point clouds. And we've actually our newest generation has a lidar that has added a secondary form of redundancy. We're actually using the ouster, and we're super happy with that. And we actually on our current gen, we use the live ox LIDAR as well. And with that, and the depth sensing cameras, we've got our redundancy and it's much better than the the ultrasonics were really fun. Yeah, they're very noisy and at the speed and vibration we were doing they just weren't adding a lot of value. There was no they were not making the system safer, which was the whole point. They were adding complexity to the BOM cost bill of material and so we just we decided to cancel them I would be I'm impressed with some of the new stuff that's coming out. We're always evaluating sensors in our lab downstairs. We have some fun stuff that I probably can't talk about, but there is some unique stuff out there that are in the ultrasonic and sort of i What would you would call closer to that almost audio type spectrum than visible light, right, that I think will be capable. But the neat thing about what we're doing is, again, if it's a structured data and we can use it, then we will incorporate it as part of our standard and spec. But as of right now, those ultrasonics are tremendous. A lot of it. Yeah.
(1:00:23) Audrow Nash
Yeah. And so for LiDAR, are you using? Is it a planar lighter? Or is it one that's sending out a few strips, or
(1:00:29) Charles Brian Quinn
the live box is a unique? One that I think is I am probably not the best to talk about, we have a whole systems team that evaluates a hardware, and I saw a couple of them come in, and I definitely saw the pricing of some of them coming in. We have stuff in our lab. You know, I think we, so we're venture backed. And so what's interesting to me is, and I've never I've been always done bootstrap companies. But in venture, we're trading a capital for speed and growth and, and have making our customers happy. And so what our team does now is and it's real fun to be on the green team, because they don't come to me. They don't come to me period anymore. But they don't come to me and say, you know, hey, there's a $35 IMU and $1,000 IMU, which you know, they buy, they buy two of each one, and we evaluate it, we choose the best one, right and, and we FedEx Ship it like overnight if we can, right because time is of the essence. So yeah, they do that now. And we know that. So I think the one i The ones I've seen are the ouster OSC, Ro 128, which is the highest grade one. And the reason is because, you know, we all were software heads, too. So we're like, let's buy the 128. Because if we, if we can software, make it in software to a 64. Or the lower Rez like we can do that in software? And we can figure out if, you know, yeah, right. So we can always you can always go down lines in data and destroy data, but you can't recreate it. So I've seen some of the you and I've seen some of the initial work on that. And it's been phenomenal, like the amount of you know it with our depth cloud, you can tell what things are like you can see humans and you know, because it's hard to visualize, right? Like as humans were not good at visualizing a depth cloud, even though there are some things to do it with color and things like that, like red is close. And blue is far whatever it may be. But with the the LiDAR, like the amount of data in line scanning that we get with both of those units has been phenomenal. In terms of range.
(1:02:24) Audrow Nash
Interesting. Do you think the LIDAR will ever replace the depth cameras?
(1:02:29) Charles Brian Quinn
I, I'm of course,
(1:02:32) Audrow Nash
redundant system. Yeah, yeah, I'm
(1:02:34) Charles Brian Quinn
a prevalent probabilistic guy, right? You you, you nail that ahead of time. And so I think that the world is full of dirty sensor data. And you should take as much of that dirty sensory data as you can apply probability to do the task at hand. And whatever comes out needs to be the one I don't think that there is an end all be all. Yeah, it's funny. I mean, you look at like the Tesla. And I know that they're all super deep on vision. But yeah, we know I have some friends in the industry have been doing this well, and they're like, hey, like, fog. You know, like, they're like fog. And they're like, so this is like a known thing. So I would not be surprised if, if, if the future is better than than humans. And it should be. It could be. Oh, yeah, totally using sensors and things that we don't have. We just, we happen to see in RGB. So we send that tend to sort of go for that. But there's no reason why the world of a robot shouldn't have be like an insect that can totally see, you know, completely different spectrum than us. Right. Yeah. Infrared seems very useful for a lot of things. Like all sorts of other things.
(1:03:43) Audrow Nash
Okay. That's really cool. The let's see. So, these are your sensors. And then do you have a you have a computer onboard? You mentioned it's an x86 architecture. What is it? Is it like a super powerful computer is the now
(1:04:03) Charles Brian Quinn
here's, there are a couple other things. I mentioned that so the computer is not very powerful, but I would say it probably is. The main thing though, is heat. So they're ruggedized industrial din, rated for fanless for heat and vibration, and those are critical. And by the way, we have hit the limit on those in Texas several times. It do not mess around in Texas. They do not mess around with mowing. They have practice fields on practice fields.
(1:04:31) Audrow Nash
Wow. That's crazy. That field for mowing,
(1:04:34) Charles Brian Quinn
you think it's practice fields for football, but and, and all this, but it has just for mowing? Yeah. Well, we have those. We have those but Yes, but But yeah, and so we'd be out there and it was 105 Fahrenheit, which is I don't know what that is in Celsius. I should because I'm 30 pharmacists close to. Yeah. And so our computers are rated for I think they may be up to 70 or something like that. which is nuts 7070 Celsius, which is like 140. So I may be off and maybe 40 and 140 because I'm not very good at the conversions. Because I have Siri that just tells me. But anyway, the point of the story is that we hit the limit. And our USB bus died and fell off. And so all the cameras were gone. And of course, the mowing is like, stop. But what's funny is we were like, We were apologizing their customer customers, like I'm done to me. They're like in terms of human like, we shouldn't be out here either. Like at when it's 105 humid, and our you know, yeah. So they're like, it's, you know, you're good. You're good. buy our books. So but what is cool is we did fix some of that, you know, when it made it more robust? Yeah, we've had heat shielding. And some of the, you know, exhausts i We got one of those flot FLIR Thermal guns to flir measurements. Yeah. And I was surprised how hot do you think it does get on the at the exhaust point of the engine on a mower in Texas? Like, what's your guess? I don't know. 180 730 coming off, the exhaust says, That's pretty well, I guess. Seven? Yeah, it's very hot. And so we originally had our sort of exhaust sort of blowing towards the back of the computer, and there's this area. And so ours would just heat up to where it stopped. So now we vented it differently. We've added some extra shielding with air, which is another reason why we work we love working with the manufacturers, because they're like, we've been dealing with heat shielding forever. They're like, yeah, what you do. And they just added three things. And they're like, done, and we're like, oh, cool. Check, check.
(1:06:36) Audrow Nash
That was easy. Yeah.
(1:06:37) Charles Brian Quinn
I don't think we're done yet. But there's that now we do. Also, we love microcontrollers. So we're a big fan of, I think we use Arduinos, we use Teensies. I think TNCs are the current generation. And the more we can do our we have another theory about probabilistic robotics. But another theory is that the more we can do at the low level hardware, the safer the system will be. And so anything we can do that that becomes sort of rote and is not in C++ or something high, like at a high level, I would call C++ a high level language, even though you can go low, you know, we can move that down to the microcontroller and have a bonafide you know, thing that when it turns on, that's the only thing it does. And it's dedicated to the really single purpose. So it's the same reason you like nodes. In a sense, you're exactly right. Yep. Okay. Well, I'm super excited about some of the ROS 2 you know, stuff that you can run, you know, oh, yeah, a device where it just outputs a topic. Yeah, embedded, whatever, right. Yeah, that's gonna be really cool.
(1:07:34) Audrow Nash
Why? So, if you're using C? Or do you do things where you're allocating all your memory beforehand? Or?
(1:07:44) Charles Brian Quinn
Excuse me? Yeah, whereas in C++,
(1:07:46) Audrow Nash
oh, you said your C++, okay. Yeah, the I do avoid
(1:07:50) Charles Brian Quinn
microcontrollers, or C, right? And make sure we're doing that in whatever the the microcontroller languages Arduino, ESP, whatever those are. But yeah, we're using C++ for the main stack. We still also use some Python for a lot of the lower level. Statistics are very good. So Mo, our progress monitor and a lot of that stuff that generates graphs and gifts and things like that. Can't be Python for that, for sure. So yeah, again, they all speak ROS topics on the back end. So we're all happy to oblige, right?
(1:08:20) Audrow Nash
When when you put things on microcontrollers, how do you test them?
(1:08:25) Charles Brian Quinn
Good question. A lot of that is kept, you know, sort of very low level, but it does not have the same test suite that our ROS does. Yeah,
(1:08:34) Audrow Nash
cuz you're writing all these things you probably have like a spool for maybe you can run, I don't do this, we
(1:08:41) Charles Brian Quinn
do. We have a lab downstairs, I'd have to go grab our systems engineer who is probably down there doing it now. But a lot of input, a lot of output. I mean, a lot of graphing manual testing to prove that it will work as I expect. And we're huge sponsors of David Piccante. And his work at Platja glare, like, you know, I think we were one of the there's wonderful, we use it every day. So we sent him a little love notes all the time. And I couldn't be happier with that. I mean, that's a majority of our work is actually it's funny, like we sent we put out graphs of like, okay, here's what the lower level microcontroller encoder reads are, you know, here's what it looks like. Now, we replay replay replay a big fan of replaying data. You know, we in terms of testing, we do have a good test suite that I'm very proud of for robotic stack, we use the ROS unit and ROS testing, we throw sensor data at, you know, we have a continuous build server using circle CI and so when when our you know, we commit code, it all goes on a circle CI server, it runs the ROS unit tests and make sure that the basic knowing sort of workflow still works. And we go massive amounts of sensor data, we we, you know, have recorded us going through a field full of obstacles and make sure that it's like yep, yep, yep, yep. Yep. And that nothing you do interferes with the ability for the mower to stop, right? Yeah, for sure. Ah, very cool. But you're right testing. I would love to see ROS get better at this, I think, I think the ROS community would flip out if they saw what US former web developers, the kind of tooling that we have. Oh, yeah, I was super excited that you had the guys from foxglove, which were huge fans of and users of podcasts, which I know, they just raised a big round. And I'm super fans of them and the testing that they're going to do. Because I think they're going to level up our industry a lot, you know, with with real time and sort of, you know, we're, we've got some unique stuff that we're doing and working with them where, you know, an incident happens in the field. And that may be that a sensor, you know, sort of encoded drops, or you know, some other things, and we can tag that. And we can say, alright, what happened, because that's real world data. And by the way, we're there in the field. So you know, they're generating a ton of data. And so we can't go grab the entire bag file, which we used to be, we'd be like, somebody run out there with a hard drive. And like, same thing. Yeah. So we built a pretty cool system that can you can tag it. And then there's a Our Sync type process that runs in the background. Nice, nice as a Unix command that will lower the priority. So that like, the rest of the stuff can also it's very low priority. So right, and so then it'll squirt that data over that 32nd window of that thing to a server, and then we give it to foxglove. And we're, like, visualize that. Because that what happened there, right. Like, why did the mower, see it saw a corrugated fence and thought there was an obstacle straight in front of it when it was, you know, I mean, 30 meters out, right. So stuff like that, right? Yeah, it's been very fun. I digress. But we could definitely get better on the testing side. And if you're interested in that, and find more resources that we'd love to know.
(1:11:40) Audrow Nash
Yeah, for sure. We're getting a little better with ROS 2. Yeah, for some of the testing resources, but I agree, it's a big and especially for like industrial, or, like for company level reliability. Like, we could probably improve a lot as a community total in this space, I think. Let's see. How do you update your systems?
(1:12:05) Charles Brian Quinn
Very excited and happy to talk about that. We part of my ROS CON talk was a little bit on that. Now. I love the current system that I believe you guys use for packaging, because I am a big fan of it. I think it's what it's cat can plus,
(1:12:21) Audrow Nash
we use cold con cold on we're here with ROS one. So yeah, yeah,
(1:12:25) Charles Brian Quinn
well, there's that. And then blue are the bloom, that's the one I was gonna talk about Bloom is the sort of thing that will create packages, right. Now Debian packages for distribution on Linux. So we evaluated using bloom and tried it for a little while. But what we found is that we were unable to do a lot of the sort of, we couldn't find a way to do meta packages, which we use a lot of where it'll be like, you know, packages, well, and also to pulling in other stuff. So what we did was we went and we also were targeting just Debian so I sorry, ubuntu LTS. And so we don't need to create RPM, or other things, you know, generically, and so we're other Linux distributions or other operating systems, okay. So what we do is we create our own Debbie ends, and we use Debbie and proper, right, so we just straight up, generate them, the Debbie and from, you know, using the Debbie and maintainers guide, and all the tools that exist with change log and all that stuff. And so then we build packages. And then we have a couple of private repos that we mirror ROS upstream. So thank you, I mean, that's a new thing that a lot of people do, right? And and then we mirror you know, ROS security and Eros updates. And so we have our own package server. And so when our mower boots up, it runs apt update, essentially. And if you look at my talk, it actually runs a couple things. It's actually dist upgrade, you know, which is an automated with why right. And so basically all our packages are installed. And then when we do that, the system is still running the current one. And so then when it when you go to reboot it, it'll actually run the new stuff. And so we use a ton of super small postinstall. There's a lot of stuff, neat tricks you can do in some of the like, when after you install something, you can, you can redo your config and kind of fixed files and change variables and stuff. And I haven't found a little bit of that lacking in the sort of automated stuff. So again, when we control the full Debian, we can do a lot of that. And so we've been really excited by that I would love to, I've heard that snaps are good. And I'd be really curious to explore that. I've even tried to connect with some of the people that are working on that. But I'm just again, I'm a low level sort of Unix guy and I've been doing Debian and Ubuntu for so long that when there was a tool out there like apt and Debbie and I was like, just reach for it and say, Okay, let's do this. Yep. But it's been fun. The other fun stuff is there's some neat stuff we used to use a package called rep rep row to to manage them. And then there's another one came along called athlete that allows us to snapshot and mirror these and now we have what's really cool is when you deploy code to our mowers The automated system will run all the tests. It'll, it'll actually generate a bunch of Debbi ins, it goes and installs them automatically on our experimental mowers. So we have a couple of tests on the platform. So on each mower, you're running the tests or your CI, run the test on the CI, which is like a desk, for instance, that mimics the whole install, right? And so, but you're right, it doesn't have a lot of the sensors on it, they're all fake right, then. So you're right. So there needs to be somebody needs to test it. And so what we do is we have a fleet, and I showed you ahead of time, before we were on our lab, where we have a couple hours, some of these mowers are on what we call the experimental branch and experimental is just the Debian wording for hasn't yet been released to production. And we use that term lightly, but they're experimental. And so they run bleeding edge. And so what that means is that when they turn on, they're running main, which was formerly known as GitHub master, right. And so they run main. And so when you commit code, you can go downstairs and you can run it on experimental. And we do we we run around our lab, and you saw the field where we met out back. And so we'll go and run that around and make sure that the all the functionality is there. And as soon as we do enough of that, we then do a release. And release is nothing more than the git pull request that packages up all everything from that's been an experimental for a while we do those every one or two weeks. And what's nice about that is we do release notes, and then we text message our customers with those, you know, improvements and features a lot of our developer, but a lot of them and then we work them both in English and Spanish and make sure that they know that, hey, the Moto is going to be updated next time you turn it on, you know, I think eventually we'll have to just copy the Tesla interface where you can download the update and then apply it. And then you know, there's three options. But for now, we are automating and forcing those upgrades, because everybody is on the same one. And we can do that because we're able to manage, but I'm sure we'll get more sophisticated, but we're really happy with that. And I'd love to open source more in that area. It's just when I go to do it. I'm like, Oh, this is Debbie. And this is apt this is you know,
(1:17:03) Audrow Nash
it's just a process very specific to specific to us. And also, it's
(1:17:07) Charles Brian Quinn
like, it's just a way to use all these open source that's pretty well documented. So
(1:17:12) Audrow Nash
yeah, I feel like like a really well written tutorial or blog posts would be awesome around that kind of thing. Challenge accepted. Because yeah,
(1:17:22) Charles Brian Quinn
I'll definitely make keep doing that the ROS talks, because we definitely enjoy that we were asked to I think this year, and we're big fans and sponsors, I hope to sponsor that bigger level NEXT TIME TO
(1:17:32) Audrow Nash
HELL YEAH. YEAH. So can you talk a bit more about safety in your design? Or like making it robust?
(1:17:41) Charles Brian Quinn
Yeah, absolutely. I think about this all the time. From, you know, the current thing that we're doing, we've gotten a lot better, and we're continuing to get better. You know, safety is our first core value safety first. And so one of the things we're doing right now that I'm very proud of is that we have a PhD risk. A person who just absolutely loves thinking about risk data and is asked just I mean, the amount of data and things he asked for, you know, he's like, how many accidents happened in this way that led to hospitalization through this and he's like, Okay, we put this in our system. And he's got things that he's automated to basically help us make sure that we adhere to the highest level to some of these standards that are out there. And so our current system is pretty well documented in how we adhere to these based on our understanding interpretation. And as we get better understanding, and as we get better sensor data and things, it can be updated, and do iteration. Exactly. And a lot of the work we do is in validating those. So the key areas that I would think that that your audience might be interested on are, we are constantly trying to push the limits of the obstacle detection framework and pipeline, so our customers, what we tell them, and what it actually does is a little different, right? So we err on the side of safety. So our system can detect obstacles of a certain size. And I won't go into that right now. But and what we tell them is it has to be of this size, and we do that for that margin.
(1:19:07) Audrow Nash
So you give them the worst case and you internally, it's something a little better on that,
(1:19:13) Charles Brian Quinn
right. And then what they know is they say, okay, cool, right. And so the biggest one is people are like, Hey, does it detect sprinkler heads? And I'm like, Absolutely not. You know, like, those are too small. And I was like, you know, sometimes as humans even have trouble, like, you know,
(1:19:26) Audrow Nash
(1:19:27) Charles Brian Quinn
And what the neat part is, though, is that when I asked them really like, what what are you getting at? Like, what? And they say, Well, you know, if this thing's going to do the whole thing, it needs to know that like remember, you do the boundary and I was like, why don't you just like do that part yourself? And you go around where you know, those are because you install them? He's like, Oh, yeah, I installed all this finger heads. Right? And then I'm not gonna hit him, right and so and I was like, why don't you just go one lap inside, do a lap and let the mower do that and then you take out a string trimmer edger wieder blower and you do that detailed
(1:19:58) Audrow Nash
work while you do it. Oh, that's awesome. They can parallelize their own
(1:20:01) Charles Brian Quinn
effort. Yeah. And so that's pipelining is huge. In fact, you know, when I talk about, you know, greens, the we take job openings, not jobs, right? There's, there's hundreds, and there's 1000s of job openings, just that one of our customers, you know, for, you know, workers that they don't have and can't find. And so when green Z comes along, it says, I'll take that really boring one. And you can, you can pipeline. So that crew that used to be a three or five person crew can be like one or two people now with a couple of robotic workers, and now they're doing the same work that they were able to do. And they're able to go home, you know, sooner and go talk to the kids and just, you know,
(1:20:39) Audrow Nash
do all that. Yeah, exactly. It's, I mean, it's less work for everyone to do, basically, because the robot is taking over some of it. Yep. At least taking some of it that was already there. And, like, not there aren't enough people for thinking and sound. Yeah. Okay. So with how do you how do you test your robots? So you mentioned that you go, you have this main branch, and you'll go and you test it on your robot in your fields? How do you make sure that something is ready to be deployed to all of the mowers on in your system?
(1:21:17) Charles Brian Quinn
I'm glad you asked this, because this circles back to something I said, let's talk about in the future, and that is that we eat our own dog food. And what I mean by that is that we are current subcontractors to a couple of our customers so we are mowers I'm, I'm wearing the outfit. I actually have a uniform, I wear this I have five of these shirts, and I'm wearing the lawn mowing shoes. And, and we have a safety glasses in here. And, but and we have trailers and trucks, and we met. So today we went and we have a couple customers, they have sites and we say hey, you know, can we go out? And they're like, absolutely. I mean, they're every time. Yeah, you know. And the good news is, you know, we carry the insurance and liability to it and the training were OSHA certified and or OSHA training, excuse me, I don't think there's a certification. But and we follow all their guidelines. And we product and OSHA is the is the Occupational Safety and Health Administration. They're the ones who would, would dictate that when you're doing this activity that you have, and I won't show you my shoes, but they're closed toed. Right. So composite or steel toe, that when you're in the
(1:22:26) Audrow Nash
standards body for worker safety correctively our worker conditions are something okay.
(1:22:32) Charles Brian Quinn
And by by joining and being there that they'll report on incidents and things that are unsafe. Yeah, exactly. In order to understand they're very big in construction, right. This is why when you go to a construction site, if you're not wearing your helmet, your hard hat, you know, you can OSHA can get you in trouble. So But I digress a little bit, so we as subcontractors we go out. And that's pretty critical for us. But from a product standpoint, it's also No, but what we do is when we go out and we do the work to be done with that's the day after is usually when we do our releases will go and we say, you know, we tried to push it before, we're like, oh, that's just a small fix, let's just put it into production. The good news is we can issue fixes pretty quick, like we've got a system for doing that we can hotfix and do a branch off stable and do a hotfix. And we've had to do this before, you know, luckily, some of them aren't like critical, you know, that the test suite will cup cut that out, right. But it might be some small fix that gets out there. But in doing so by by actually doing the job to be done. We are effectively and experience, right. And we're making sure that what I would call is sort of the eye it's it's more eyes on the bugs make sort of bugs shallow, that's the cathedral bizarre approach, right is that, you know, as our customers see these things, and as we see them, like we can fix them. And so I tell our team, you know, and we've strived to do this, but we strive to make sure that we can release early and often and quickly. And I think that that is probably our kicker. So we even have DevOps, time DevOps that just helps us with developer tooling, developer happiness, logging, and making sure that our stuff is just fast to go out. And I think that's just critical. We'll just probably continue to build that practice internally. But to answer your question, how do we know when it's ready to go is when we feel comfortable, and we've used it ourselves, and we've mowed lawns with it, and it still works, and it passes all our tests. We package it up. And we what's interesting is that we just do a release off stable. And we package it all up, bump the version numbers and then hit go. And it automatically deploys into all across our fleet. And so then that's when we do our text message to the to the customers and say, Hey, next time you turn it on, you know,
(1:24:43) Audrow Nash
these are the changes that will be applied. Yeah. And most
(1:24:45) Charles Brian Quinn
of the time, they're excited. They're like, Oh, cool. I asked for that feature last week. And we're like, yep, there it is.
(1:24:50) Audrow Nash
That's awesome. Do you I guess, how do you train people to use your system? Like, how is it?
(1:24:59) Charles Brian Quinn
Yeah, right. Yeah. We're, we're venture backed, and so we're very hands on. In fact, we'll we I've, I've hired some people who are robotic technicians who speak English and Spanish better Spanish than I than I do. And they go on site and are doing a lot of that. And we're building up that practice as well. We are, I'm a big fan of the quote, what is it good artists copy? What is it emulate? Great artists feel? Oh, yeah. And so what we did is I asked our customers, like, who has the best training? And they said, you know, and I won't say who it is, because we're gonna copy him. And, and I said, Great, we're gonna do University. And I said, like, let's just, I mean, honestly, I mean, I, we're not gonna steal everything, because it's just totally different. But
(1:25:44) Audrow Nash
it's dropping the decisions. Yeah. It's like, they did a lot of things through iteration. You're just kind of grabbing that and starting there.
(1:25:52) Charles Brian Quinn
Yeah. And honestly, I think hopefully, that will leverage and level up the industry by not starting from ground zero, right. And so we have a very good training program that is very hands on. And we've gotten very good at it. In fact, our I'm very proud of the work that our team does, they've, they've delivered it several times. In fact, when we first started, one of the things we did that it was very unique was we did training before we even had anything, which was awesome. We invited landscapers to come train on what we had now. And they'd ask questions like, Well, what do you do about and we're like, how to get to the thing? Yeah, or, or we'd be like that we do it with them. And then they'd be like, I'm confused by x. And we'd be like, re explain that. Right. And so we did a lot. We've done a lot. And so now if you were to go out with our gentleman, who does the train one of our gentlemen, who does the training right now, he's very good at it, and even does some really things that are unique. Some of our investors have been in the green industry for why a while and they talk about training, being very specific, where you tell them what you're gonna tell them, then you tell them, tell them tell them and then you tell them why and then you told them, yes. And so we do a lot of that. And then it's a lot of it is from example, and sort of building on. So there's like a base case, like, what we do is we used to kind of go into like safety and all sort of stuff. And we're like, you know, what, just show the basic use case, then starts talking about some of the things that could happen and trigger those things to happen. And then the other thing we do that's really nice, too, is that we trigger some some things like, for instance, we very intentional about when we start going we say oh, you know, something happened, he pauses the MO or whatever. And then he says, What would you do, and we have them call support. We have a 787 P support line, that's text, message and phone. And that's staffed by our CIT level one engineers, which is in some of us now, which is we all do support. We all have shifts? And so we'll answer it and we'll say, Oh, cool. Looks like you've got this. Thanks for calling. You can call any time. The answer is this. We know what it is hit resume, and you should be able to do it. And they go, Oh, that was easy. And so we hopefully then they, you know, because if we just showed up, and we're like, oh, you can call support for anything. I mean, yeah, I do it. But if we have them do it in a case where it's really easy, and it makes them feel good. And we say thank you and do all these things. You know, and then we're ready for it that they go, Oh, well, that was fun, you know, and then we also are watching. So we congratulate him, like we'll send them a text and be like, hey, great first map. It's kind of like they're in on the project. That sounds thing. You nailed it. Yeah. And so it's, I'm very proud of our training. And that's some of my background was in a lot of that technical training, like making the complex, simple. And so very proud of our work in that. And I think we have a lot to do and a lot of work to do there. But we're pretty good at it, I think.
(1:28:36) Audrow Nash
Yeah. How long? How long does it take to train someone before they're up and running?
(1:28:41) Charles Brian Quinn
It used? We used to advocate for a couple of days. And I'd be surprised. I think the last training we did, one of our guys shows up and he's like, he's like they got it like after an hour. He's like, Yeah, he's like, and so now what we do is we hang out with them, and help them because they need help. Yeah, just see if they need any do site selection and stuff like that, which is crazy. So we've gotten really good with the pre work and sort of pre material. And then when we come on site, it's very quick. As you can imagine, these are experienced operators. And we've gotten some of the analogies very good like you you've done and the system itself has gotten really simple. It's it's basically an appliance right, so yeah, you know, there's one like cruise control. I mean, yeah, I mean, they go when I got a new car, they didn't train me on cruise control. I was just like, Oh, there's the two buttons for it. Got it. Right. It's it's trying to make it like that. Right. And I didn't used to be like that used to be I mean, you used to watch us we'd have a laptop and we'd be like, alright, yeah, ROS launch your BBs open. Yeah. Oh, yeah. Yeah,
(1:29:46) Audrow Nash
it's crazy. Okay. So, how many of these do you have? Like how many mowers are I actually I'm curious about the business model. So you're venture backed at the moment but it will it be a subscription based thing? Will people own these robots? Or how will it or people, people own autonomous system in the mower?
(1:30:09) Charles Brian Quinn
Yeah, I'm happy to share all this, we're pretty open book with almost everything except for probably my, if my employees are on a pip, that's probably the only thing I won't share and their salary. What's that? A performance improvement plan, that just means you're in trouble. And so I think that the joke is that I, we're pretty open book about a lot of stuff in our business, we're not like a stealth mode startup, and we never have been. So it's just easier to just be open on it is, you don't have to remember what you told people. And so for our business model, currently, we're trying to meet our customers with how they pay, or how they charge. And so knowing is a seasonal business. And when you think about seasonal workers, and robotic workers, there's a cost associated with those workers. If I wanted to have a worker, you know, I might pay them a yearly, you know, you think about the cost and years because a lot of these companies that do commercial have these contracts that last for a year, and they're like, Okay, we're gonna need, you know, X ray people on this crew and Right, exactly, well, 3d, we're on this crew, right. And so our costs are pretty simple, in that we charge how our customers pay how they get paid. And so it's a one monthly fee for our software. Now, the the mower itself is, like I said, upfitted. And so what's great about that, though, is that the manufacturer is able to do that. And what's great about that is that they've been able to put their procurement in their economies of scale on these things. So I guarantee you that they're getting better pricing on a Hall Effect encoder, from, you know, from Honeywell than we were able to get, right? Because when when we call, we're like, can we get 100? And they're like, you know, and when they call, they're like, can we get 50,000? And by the way, here's our procurement person, and we probably already ordered from you anyway. And they're like, Great, yeah, we can add that to your next order. And so there is some new stuff, but you know, they've obviously gotten better pricing on that. And again, more manufacturers and OEM producers are better at the storing and producing of that equipment at the facility where they do it. And so we don't we, you know, we don't have a big manufacturing facility where we do
(1:32:13) Audrow Nash
you don't need it, you just do the software, and the testing and sensor suites, like, figuring it
(1:32:19) Charles Brian Quinn
out exactly. And and constantly iterating on on the next generation and our sort of what we call upgrades and field. Right. And so yeah, so in terms of charging the business model, I would not be surprised if we move to a robotics as a service. And I know that's a pretty popular route to call it. And some of our customers are asking for it. So we would love to work with some of our partners on doing that. Could you imagine a day where if you're a landscaper, and you say hey, I know from May to October, or April to October, you know, however many months that is 878 months? And we said what if we could give you a mower and a robotic worker that lives on that mower? For one fee, and 2500 I'm making up a number I'm on and they go, that's a dang good deal. Because, you know, like, if you think about the person and the mower, and they start to do the math, and they're like, whoa, that's like, you know, six or seven an hour in terms of labor, and we're like, great, you know, like not to be coy or anything. But like that said, you know, you can't hire person for that. I mean, no person would want to work for seven an hour, right? But a robotic worker, and also it
(1:33:24) Audrow Nash
can work through the heat and all the like, and also won't get tired
(1:33:27) Charles Brian Quinn
quality. Yeah. And And also, we do get pushback because they're like, Well, what about in January, like right now when you know, some of our customers only known a little bit or not at all, if they're in the Northeast, and I go, Well, what do you do now? And they're like, you know, fire them or get seasonal workers or have them do something else? And I'm like, well, guess what, your robotic worker on your mower on March 1, is ready to mow? And you know, even if you put him on the shelf, you know, put him aside and weatherize they'll be ready to move. And yeah, guess what he's gotten like 50 updates since then. Yeah, is better. And like has more features and functionality from all these people we were known in Florida has been training in the OFF time. Exactly. Robotic workers. Yeah. And what's cool is that they don't get it yet until they see it and experience it. And then they're like, Wow, they're like, this is software. Like, I've got software on my mower, and a robotic worker that's continually getting better. And it's hard to see, like, you know, it's hard to tell somebody, but when they see it, and experience it, they get really, like addicted to it, right. So our early customers are, are gonna win big because they've been early adopters. And they've seen us through some of the challenges of things, but they've also experienced some pretty big wins. And so I think that business model will continue, but I'm also open to changing it, you know, like we're very, very customer oriented, customer focused and obsessed. And so if they need something else, we'll do it for them. You know, and I think that the, we are we are taking we are using a lot of capital right now to do speed and to shore up and so like, you know, when the customer asked for something, we just do it. And when we hit those economies To scale, I think we'll have those general SAS margins that are pretty high, when we're just delivering a service. And we don't have to go out and do training and you know, all that other stuff, which is we're on the path towards doing.
(1:35:11) Audrow Nash
Yeah. What do you so you said that this is you've always been bootstrapping in the past. And this is the first time you're taking venture capital. Would you tell me a bit about your experience with this? And oh, yeah, just talk on it for a bit.
(1:35:24) Charles Brian Quinn
I love both. I think that there's room and time to do both. I think, if you don't have to raise money, you shouldn't. You know, it is I think there's a very good use cases, when you're doing something is funny. My co founder, David is really funny. He's, he's an interesting guy. And he has a quote that I'll repeat, he says, you know, starting a business is hard. There's all kinds of challenges people business, the the market, you know, there's timing, there's all kinds of stuff he's like, so if the whole thing is hard, anyway, why not just start a big one? Right. And I and I was like, You're right, right? Like, you know, why not? He's like, why not just go after something massive, like that's, you know, huge and impactful and game changing. And, you know, it's funny, because that's kind of his investment thesis, right? Like, he won't invest in like, gambling or whatever, you know, like, it's just not, you know, it's like a bootstrap. Yeah, it has to be big. And, and so it's, and so there's a time and place for that now, bootstrapping, I absolutely love because there's something brilliant and amazing about selling something, delivering it, getting paid, and using that money to grow. And I've done that, and and, you know, you know, service businesses are great for that, you know, restaurants would be good for that, you know, where you're just building one and then use the profits from one that go to the another and some robotics companies could probably, you know, do that through some model. But if you are going after something big, and there's a leap of faith, more, there's a lot of things that have to happen, and a lot of bets that you are capable of doing and know like if you know something that the rest of the world doesn't, and I do and I happen to know, and that is that I think software is going to eat the outdoor power equipment industry, and totally the most powerful thing on these devices, then then I would, I personally would pay a lot of money now to be the operating system of the future. And so I'll trade today's dollars, hands down tomorrow's. And so that's what Yeah, and so placing a bet very heavily. Oh, yeah. And what's what's interesting is, is the mindset shift from going from Bootstrap to venture has been tough for me. Because in the Bootstrap, you know, a lot of questions I would ask would be like, how do we pay for that. And, you know, like, right now, like next month, or the, you know, in 90 days, net 90, when, when, when bills are due, you want to stay positive the whole time, basically, right. And, and now, what I'm doing is I'm constantly, I'm constantly trying to build a valuable company and an asset. And I use that using capital. And so I do a lot of things that are hard that scale and doing a lot of things that are very unscalable. Now to prove that is scalable later. And what I mean by that is like, we eventually would like for manufacturers, sorry for the outdoor equipment dealers to do a lot of the fixes for us. And so what I do is I go above and beyond to make sure that it is easy, and that they're incentivized to do it. And so I pay, you know, more than their sort of normal rate, so that they're not, they don't feel like, Oh, who's this company? And why are they asking me to like, put a new camera on here. And I'm like, Hey, like, I want you to, you know, I'm going to use my venture dollars to make to figure this out and get better at it.
(1:38:43) Audrow Nash
So you get lots of feedback from them, so you can improve the process, and eventually, it will be less painful thing for future ones. Think. Interesting. Don't see where
(1:38:53) Charles Brian Quinn
I'm sure I've, yeah, go ahead. I was gonna say, and bootstrapping adventure, I'm sure there's a lot more people who can talk more about it. And I know we're running out of time, and I'm happy to go into way more detail. But I also don't know too much. I'm still fumbling along as I go. I wouldn't say that I've mastered it, we have raised quite a bit of funds. And every time I tell my friends, I'm like, Oh, I'm just not good at this. They're like, look at the results seem to be doing okay, but I guess I'm harder on myself than I am on on anybody else. Right. So.
(1:39:20) Audrow Nash
Gotcha. Let's see. So we're a little over the scheduled time is Are you okay to talk a little longer? Yeah. Okay. I would love to hear more about your, your bootstrap bootstrapping experience. And then kind of like if there's anything that you have learned there that you can bring to this venture capital experience.
(1:39:44) Charles Brian Quinn
Yeah. So fundamentally, the the impact the differences of like building a business that is bootstrapped meaning we had sold a product, deliver that product, get paid and then repeat versus the venture which is, in my mind, could be something like that, but it's It's probably trading a lot of it's basically going into, like what I would call a negative sort of, if you look at, I guess the best way to describe it is, there's a cost of acquisition for each customer that can get rather large. And so at some point, you're basically see this thing where it looks like your company is just burning money. And every new customer you acquire causes you to take this, we call it the J curve. And David Scott talks a lot about this, he talks about recurring revenue businesses, that J curve goes way down. And every time you do it, it really just looks like you're just burning cash. But what's the neat part? Is it that some point that Jay, you know, can do this and every recurring business, you know, a lot of people are like, well, so and so doesn't make any money. And you're like, well, that's not really the best way right now. Right? Correct. Because they're creating these economies of scale. And every customer they acquire, it might cost 12 grand to acquire that customer. But every year, they make 12 grand, and the margin on that 12 grand the profit on that 12 grand is very high, the marginal dollars you do once you acquire them. And then they also don't think about net expansion, which is where each customer might add more, right? So you've cost to acquire the network,
(1:41:09) Audrow Nash
that kind of thing, right? So it gets exponentially better to use the service or something.
(1:41:14) Charles Brian Quinn
And so what I would say is that the lessons that I learned bootstrapping, were just the basic ones, like I still rely on a lot of them, like how do I build a good culture? How do I hire retain? How do I fire people? You know, that I don't like talking about that. But you know, it's something that you know, you have to do to put the right people on the bus and all those lessons I learned using our own money, like I have to do now even though I have venture money, I still do that. Right. Like, and I think that that's where I think you've talked about it a lot. The analogy I think you gave in the agriculture one is that like too much money can mess you up, right? If you don't have any constraints, like that can be terrible. So one of the things that we've done differently in venture and maybe this will turn out to be a dumb, dumb move. But I have raised sequentially, sort of small incremental rounds, as opposed to giant ones. And so we don't like advertise, like, oh, we raised 16 million, like we've never raised a $6 million round. And we've done that, because even though we take a little bit of dilution on that, like, what I've said is that, in bootstrapping, I have built a grape. And I've eaten the grape, right? And so grape is pretty good. But if you're hungry, it's cool to build a watermelon and eat a slice. And so when you think about that, like, that's what we're doing with green tea and venture backed is that, would you rather have a full grape? Or would you rather have a slice of a watermelon? And by the way, the other slices all go to investors, and people who are actively taking risk with you. And you know, and we've done a really good job, I think of recruiting in on our cap table, we call it, you know, our
(1:42:51) Audrow Nash
investor capitalization table. Yeah,
(1:42:53) Charles Brian Quinn
they're all people who are green industry, robotics, distributors, dealers, also our various
(1:42:59) Audrow Nash
Smart Money, basically, yeah.
(1:43:03) Charles Brian Quinn
I call him and I'm like, Hey, how many mowers were sold in there? And they're like, Well, you know, you're not supposed to know this, that. But here you go. And they don't say that. They say, actually, here's what I can tell you. And here's what I know. And here's, here's this, and here's what you need to talk to. And here's seven other connections. And, you know, call me later. And I'll have that for you. And I've been thinking about this, and they are proactive, and so we have a very good, that's the other thing that I think is unique is that we're bringing along a lot of people with us, which is really fun. To me, there's, there's a bit of, and what's cool, too, is I'm lucky in that I was able to participate in some of our rounds, which is rare. I think, for an entrepreneur, I have had some some success before. And so, and I always bet on myself. So I lead one of the rounds, which is kind of fun, you know, to say, Okay,
(1:43:46) Audrow Nash
what does it mean? What does it mean? You let around was it mean, you're the person that goes around talking and trying to raise investment.
(1:43:52) Charles Brian Quinn
So I'm always trying to go around and raise investment, that's actually my job as CEO. So I'm gonna do it for what for this round, I went to my, with my investors and said, Hey, things are looking really well for the company. I believe that we have hit our next milestone, because we did. And I said, I'm leading this next round, meaning I'm putting in a million dollars in my own money on this next round. Yeah. And I think we need this and does anybody want to come in with me? And the fun part about that is what happens is that I didn't get to put in a million. I only put in half that but the there's all SEC D regulation, you go look it up. So I'm not like I'm bragging about it or anything. But yeah, you know, so so, but I did get to be the largest investor in that and then the reason it went down is because all my other investors were like, I'm in put me down for more, you know, like, we're in with you let's go and and and, and they aren't always like that, you know, a lot of them are like, hey, like, these metrics are bad. Like, you need more you know, this, you need more that? Yeah, they're prioritizing something different, but it is good that I do have an investor cap table that does believe in us and we've had the For sure that will up. And we've been able to recruit others as well. But that is a that is a fun game that I am not good at yet. But I have gotten better at it through failure. And the last the last round was very good. And we raised $4 million. Very excited by that. Thank you. We didn't really I'm not very good at publicizing those things, because I'm just not good at it. And I honestly think it's kind of like taking on debt. And what do you mean? I don't I don't understand. It's kind of like we take on this capital. And now we have to utilize it, spend it wisely. So I don't know. I do think there's there's something to be said for celebrating and always helping your customers. And so if there's a way to phrase it, that helps your customers, but I'm just not big on the current Zeitgeist right now, where we're like, raising is the thing. Like, it's funny, because the thing that I would like to celebrate, and we celebrate more internally is like, happy customers, you know, sales and that kind of stuff. And so that's not really like celebrated, we don't like a lot of companies don't say like, we just sold a million dollars. Like, yeah, that should be celebrated probably more than the current raises, because raises just mean that, you know,
(1:46:03) Audrow Nash
raises you mean higher valuation and raising heavy rounds.
(1:46:07) Charles Brian Quinn
Yeah. And and also they without context, they don't really mean anything, right? Like, yes,
(1:46:11) Audrow Nash
it's just a lot of people don't share, you know, the dilution, and they might have been on unfavorable terms. Like there's a lot of context necessary, I
(1:46:18) Charles Brian Quinn
believe. And good news is, you know, I can't I won't disclose I won't disclose some of this because not mine to disclose, but we have very good, very good terms on our raise. Very simple. There's not a lot of funny, Craps and convertible,
(1:46:29) Audrow Nash
no lights, crazy, veto power. Any event, sometimes.
(1:46:33) Charles Brian Quinn
My see my co founder is has is the most entrepreneur friendly, I think it's gonna come out that he is and he's had the Midas touch. I think just recently, he's got a couple companies that are worth billions. And so wow. I mean, he's super entrepreneur friendly. And so it's crazy how entrepreneur friendly is, in fact, he's so friendly, on times that he's just like, we'll just what do you want to do? That it actually makes it makes people like me who have high responsibility go, will shoot he just gave me all theirs. I better make this a win. Good. Fair. Yeah. Yeah. And I think that that's neat that I've learned that about really good venture is that they,
(1:47:13) Audrow Nash
you know, it's funny people talk you want to help us succeed. Yeah, rather than just they want to take the maximum cut. Yeah, and kind of screw you it's
(1:47:20) Charles Brian Quinn
been an entrepreneur too. So with that also is a nicety. You know, having been in those shoes, personally, I can't do it. I'm you'll never find me being an investor. I'm terrible at it. I've done it done a little bit, but I'm just not good at it. I like being in the in the in the driver's ed arena.
(1:47:35) Audrow Nash
You're betting on yourself? Yeah. Yeah, I see. What do you think is the the future? Like when you look out? Next year, two years, five years? Where do you see green z going?
(1:47:48) Charles Brian Quinn
Ah, well, we just did a couple of our vision planning. I'm very big on goals and goal setting. I have I just looked at my personal goals from five years ago back that I wrote in 2016. And I think it's incredible. That, you know, Bill Gates said it, I think the quote is true to him. He said, People underestimate what they can do in 10 years, they overestimate what they can do in one. And so I'm a big fan of writing your your goals and the vision, and there's a way to do it. And so if we look, five years out, green tea, and again, that the name is actually interesting, and it may be that green tea is the product just for green. And who knows, I mean, not gonna be
(1:48:25) Audrow Nash
eventually I mean, it's the same kind of, like, you can follow this model in a lot of areas, I imagine. Right now you're making mowing.
(1:48:33) Charles Brian Quinn
But if you go back to what I told you that our big mission is to free humans from repetitive outdoor labor. And that is always been the case. And we will continue to do that. I just learned the other day that there's even self driving trucks get dirty, and 18 wheelers and something they pay some people to go to these things where they park them and then they just do this the up and down spray to spray them with like, you know, to clean the wheels and stuff that's highly repetitive outdoor. And I think it needs to be automated because I think we humans are not made to get carpal tunnel doing this within Oh, yeah. Are they are made to do is say hey, this needs to be clean. And hey, that one doesn't need to and you know, hey, you know,
(1:49:08) Audrow Nash
I'm better all the decision making all this other fun, high level.
(1:49:12) Charles Brian Quinn
So I believe that green tea in five years will be helping free humans from repetitive outdoor labor. And we'll do that for as long as it takes. And I think that that's a big noble task. It's going to take a long time. And so a lot of people always ask are you for sale? And the answer is no, we're not for sale. But how much
(1:49:31) Audrow Nash
use you started in 2018. With bangzi Is it correct? Yeah, that's awesome. You're already getting questions about that. Well, I
(1:49:37) Charles Brian Quinn
mean, everybody does, right. I mean, yeah, at least when you sort of talk to them. Yeah. Big big people or big players or partners and things like that. But yeah, you know, the answer is no, but how much we everything's for sale except for my boy. Right. So, but But the big thing that they have to answer is is will they help us in our mission to free humans from repetitive labor in the answer No, then it's not even on the table. It's not Yeah. Gotcha. So So if we were to, to, to sell, to merge to buy to acquire other companies, they have to be in support of that mission and that big mission to free humans from repetitive outdoor labor. And if they are, let's go, let's do it. So I see us continuing to do that. And I don't know where it'll take us, I think we're small. And so we do a lot of short term planning, we do quarterly OKRs and objective key results. And, and we shoot for we have a yearly goal. And we have some big yearly goals, company objectives that we go for, we have a three year plan to be very specifically on more mower manufacturers, possibly in other turf areas, other sort of platforms. And so I see us doing that, I have a couple other things that probably are more internal and not really exciting to share. But I see that, and I see us also being a big members of the community, I would love to see us open source more and, and I just think that, you know, some of the work we're doing is just doesn't just needs to be out there. And I'd be happy to continue to contribute. I'm a huge fan of open source. I've been doing it my entire life. So it's awesome. It's game changing,
(1:51:08) Audrow Nash
for sure. Last thing, before asking for links and things. What advice would you give to someone who's just starting their career?
(1:51:17) Charles Brian Quinn
Mm hmm. I'm not good at this. My I've had co founders, my, my last co founder was very good at giving advice. And I think he even has a famous blog article on it. So on the career, I think it's funny, a lot of people will tell you, I can only speak from experience. So let's just say that I'm not good at giving advice. That's what kind of what I try and do. I'm not very good at it either. But I would say that finding something you love is dumb. You know, like, you know, when I think at certain levels, you should strive to work hard and learn. And, and, and not make, you know, not not do this thing where they're like, if you do the work you love, you'll never work a day in your life. I was like, man, if you do the work, if you do something you love, you're gonna hate it is the biggest way to like destroy, you're like, I love tennis, you're like, I'm gonna become a tennis instructor. And now you're gonna be like, tennis, for my French. But yeah, the. So I think career advice for somebody starting out is get out there, just do something, like, do something big and do the worst tasks that someone doesn't want to do. You know, like, what that means is like, okay, so if you want to go into finance, great, go figure out how to, you know, make more Bitcoin money off somebody else who doesn't own Bitcoin, that's fine. That's not for me, I don't think that's very exciting. I would say find a company that's doing something noble or good or sustainable. And then go do the worst thing in it, like, go do customer support, right? Like, you know, like, or work the, you know, the worst job. And if you're useful and good, you will learn and you will move quickly. You know, there's plenty of examples of people who've worked in the mailroom of the CEO. And it happens all the time. I have good friends who, you know, worked in businesses who are CEOs now and people are like, Oh, how did you do that? And it's like, well, overnight, it's like, no, of course, not overnight. You know, they did something hard and learned and, and jumped in and did it and, and weren't afraid to say this is hard. And what I'm doing is hard. And it may take a little while. And that's easy for me to say because I'm sort of older and having done that. But yeah, I mean, I worked as a consultant for a long time traveling, you know, Monday through Thursday, working in really weird locations, but it was the amount of learning I could think back on that it was able to help me do to build good products for good customers and do things. It's just, it's, it's amazing. So I don't have any good advice for career you could skip this section. You know, it's very valuable. Go do something noble and hard and boring and, and learn whatever you can from it. That's my advice.
(1:54:00) Audrow Nash
Love that. Oh, yeah.
(1:54:02) Charles Brian Quinn
Last thing is do you have any links or contact info or anything that you'd like to share with our listeners? Absolutely. So Twitter is our more developer robotics focused, pithy jokes, and shout outs to ROS. So that's where we sort of do that. YouTube is pretty good. We have a series called how it works. That's actually pretty good even for roboticist and sort of non roboticists, which I know is your audience sort of emerging. We share a lot about how the product works, which landscapers really love. And so that's booting back up in series. We used to do one a month we've sort of tailed off in December we to do one, we're back on that schedule and committed to it goal setting. And so we'll be doing a bunch of those YouTube videos. I'd say that our YouTube channels fun. We went viral on tick tock, although that's probably not going to go look at that. We have like a couple of YouTube videos with like millions of views which is nuts. Wow. That is nuts. Yeah, I don't understand that one. And Instagram is really good for if you're a landscaper and you want to see how the product works. We're constantly posting stuff from the field. Then like actual mowing, and actual usage of the of the robot, which I think is really fun and good. But yeah, all those channels are good. And our website, you know, it doesn't get updated that often. But you can definitely go there. If you're interested in careers, we, you know, definitely go there. And I think LinkedIn, I haven't figured out yet I need to get better at that one of my investors is very good at that. And I need to ask them to do it. So. But yeah, go to green Z, green z.com, where get green Z or green Z on most channels, you can find us and I think that's it. Yeah, I mean, I think we have some open source tool on GitHub. One of our path planners is out there. It's good for research. For coverage. We did one of the papers and kind of improved it. So you're happy to do that. We have some fun stuff that we're gonna open source soon on the newer one that we did. So we don't maintain that one. Unfortunately, if somebody like to pick up the maintaining on that date, they're welcome to but we have some really other fun stuff.
(1:55:52) Audrow Nash
So all right. Awesome.
(1:55:54) Charles Brian Quinn
Thank you. Thank you for having me. Cheers.
(1:55:57) Audrow Nash
Cheers. Thanks for listening to this conversation with CPQ. Thank you again to our founding sponsor, Open Robotics, and I hope to see you next time