In this episode, Audrow Nash speaks to Tim Chung, Program Manager in the Tactical Technology Office at the Defense Advanced Research Projects Agency (DARPA), on the DARPA Subterranean (SubT) Challenge. The SubT Challenge is a robotics challenge that aims to develop innovative technologies that would augment operations underground. In this conversation, they talk about the motivation of the SubT Challenge, its systems (hardware) and virtual (simulation) challenges, how the resulting technology has been shared with the world, on benchmarking the robotics behaviors in simulation, on the challenge of scoping the SubT Challenge, and on building the final environment for the systems challenge.

Start

Introducing Tim and the SubT Challenge

Systems and Virtual competitions

Team makeup

Challenges of networking

Motivation for this challenge

Four tech areas of focus

Sharing the results

Virtual challenge

Applying benchmarking setup elsewhere

Final course for SubT System’s challenge

Scoping the SubT challenge

Role of DARPA in technology

What’s next for DARPA?

Links to share

This is a conversation with Tim Chung, who is a program manager in the Tactical Defense Office at the Defense Advanced Research Projects Agency, also known as DARPA. We speak about the DARPA subterranean challenge or SubT, which is a robotics challenge that aims to develop innovative technologies to augment operations underground. I was excited about this interview, as I have heard a lot about the sub D challenge around the edges here at Open Robotics. But it wasn't one of the projects that I'm working on. So I was happy for this opportunity to learn more. From the interviewer, it seems like the SubT challenge was a great success, and that the challenge stimulated a lot of great work. You'll hear more from Tim during this interview. I also found it fascinating to talk about how DARPA picks their robotics challenges, and very importantly, how they scope the difficulty of these challenges. This is the sense think act Podcast. I'm Audrow. Nash. Thank you to our founding sponsor, Open Robotics. And now, here is my conversation with Tim Chung. I Tim, would you introduce yourself?

Sure. Hi. My name is Tim Chung. I'm a program manager at the Defense Advanced Research Projects Agency, or DARPA. And I'm the program manager for a couple of programs that involve robotics and autonomy.

And so this interview is mostly going to be about the subterranean challenge. Would you tell me a bit about that?

Sure. DARPA subterranean challenge is all about inspiring folks from all around the world to discover revolutionary technologies for robotics, so that they can help in diverse underground settings for time critical missions.

And so this competition has already occurred, correct? Yeah, what is right, what did it look like? Like, what kind of challenges were involved?

Yeah, so I like to describe the DARPA SubT challenge, as we call it, as kind of like this underground scavenger hunt slash triathlon for robots. So the general idea here that we've heard time and time again, from many of the folks like those first responders that need to go into really challenging environments is, you know, how come this one piece of component technology works in the, in the one tunnel or the or the one parking garage that I tested it in, but not in all the others that I have to take this equipment into? And so the SubT challenge was about how do we get robotic technologies to work across many different types of underground settings. And that includes human made tunnels like mines for mine search and rescue, urban underground. That's everything from subway tunnels to infrastructure, like storm drains, to parking garages, and even naturally occurring cave network. So for the cave rescue type settings. How would you get robots to be the best triathlete? Not just the best runner cyclist, but you really want that well rounded, robust, capable set of teams or robots that go do this. And the problem that we posed in the safety challenges, this underground scavenger hunt, DARPA goes into these environments, places, objects of interest, and it's up to these teams of robots to go out and find them and report them back to their human teammates.

What would be an object of interest? I could say, what's an example?

Yeah, so we really intentionally set up a whole array of artifacts, as we like to call them. So you might think, for example, we put a survivor artifact. This is a mannequin. So it looks like a survivor. It has that visual appearance, but it also was a thermal mannequin. So it has a thermal signature that's human like, wow. And it even had a voice box. So you could have voice recordings or sound recordings in there. And so those robots going in to look for the survivor artifacts. Of course, most typically carry cameras, that kind of makes sense. But if you wanted to do a little bit better, or use other cues, maybe you're going to have a thermal camera on board, or a set of microphones. And that's just one example of the 10 types of artifacts that we placed in these courses. We had a cell phone in there that on the camera, probably really hard to find, but with its Wi Fi, in Hotspot mode on cool and Bluetooth and discoverable mode. Now you can start listening for RF signatures for signs of life. We even had something we call the gas artifacts. And this gas artifact clearly has no visual signature, but instead, in this case, we're, of course being saved. So we use co2 carbon dioxide. But you can imagine that, that these robots equipped with co2 sensors, gas sensors could be used to figure out where there's good air versus bad air or noxious chemicals that might endanger those responders going into these And then environments. And so this quite wide array of types of artifacts meant that you can't just send in one robot with one type of sensor, but in fact, likely benefit from teams or robots carrying an array of sensors to kind of cross cue and help each other out much like we do as humans, or you

could I mean, so I could imagine one robot that has like every sensor possible, but maybe this isn't the best strategy. So then you said, teams of robots, what does a team of robots look like?

Yeah, well, one of the things that we have telegraphed early on in this whole competition, and this is the combination of multiple years of teams coming together to build and ultimately break some of their robots. But we said attrition is not only possible, but likely in these types of really challenging environment, terrain and other things. So for any team that came with that one glorious robot, loaded out with all of its sensors, and that's really putting all your eggs in one basket. And so, you know, thinking through what that means for your strategy for your, your competition, gameplay, if you will, really led many of our teams to think about diversifying their robot portfolio. And that not only means two types of sensors that go on different types of robots, but how they even use them in terms of like the positions on the team or the roles on the team. So all of that coming together, you had all sorts of robot types that can get into crawl into different spaces, maybe fly into high verticals or other open areas, some had legs that could walk upstairs or downstairs or traverse. Adding more rugged terrain, tracks, wheels, you name it. That's what the challenge is all about is to go and highlight that the problem is this, bring your best and brightest solutions to figure out what solves these problems.

And I'd like to just think about the kind of make explicit to like, difficult robotics challenges that are involved in this competition. So like, whether it was like, Can you speak a bit about it, like I mentioned, like mud and reflective surfaces, and like all sorts of other things. But what were some of the challenges that were especially difficult for robots in this situation?

Yeah, you name some of them, for sure. I think having been crawled through a number of tunnels and urban settings and caves myself, you know, I can testify, I can testify that these are the types of challenge elements that made it hard for humans, let alone robots to navigate. So some of those you already mentioned, the types of surfaces, mud, moisture, puddles, water, you never know, we might be able to see your tell if the puddle depth is just an inch, and I'm going to be able to step on right through. But the reflectivity of that and the difficulty that robots might have, that makes it a really daunting kind of, you know, survival question of whether or not to step foot or roll into a potential puddle, or, you know, potential hole. Yeah, lighting, lighting is a major issue. So oftentimes he or only relying on the lighting you bring yourself. A lot of times there's dust or fog, or certainly in emergency settings, you can imagine things like smoke, including many of your sensors. So thinking through what kind of paradigms you would use to be able to navigate when you really can't see, again, in the context of cameras, so DARPA used smoke machines to go and learn from sections of these environments, so that we would intentionally stress test some of that. And then you start to learn, you know, things like what types of sensors are transparent to certain types of dust or a if I fly my multi rotors, my flying vehicles, they're going to kick up dust as they're flying through. Yeah, as was the case in these minds. And that can hose your senses as well. So self inflicted something problems as well. So verticality, I'll throw that one out. So the three dimensional nature's a really big player in these underground settings, because you're not just going out, but you're also going down or up. And so elevator shafts to stairwells of varying types to scrambling up older piles to wow, other opportunities to look in these wide open caverns that you might find a real real, you know, like a real diverse set of those kinds of challenge elements. And never knowing what's around that next corner is, is perhaps the most daunting challenge for most of these robots.

Yeah, sure. How did you how were teams structured so I know there was the hardware and the software come or the systems and simulation components of this. But for the hardware one, how did you say a team can have some certain number? How do you organize what robots a team could have? And was there standardization?

Sure, well, as you mentioned, there's the systems competition and the virtual competition. And there were our our sister competitions, where one could build and design and break robots. And the other, you would do all of that in the cloud in a simulator. And so in the context of the parameters, which we defined the challenge, it was, quite frankly, quite loosely defined intentionally. In some cases. It's the you know, without constraining the design or solution space, sometimes that's where you find those really creative or solutions, innovative solutions, right. And so this is specifically for the hardware. The system, yeah, version of the competition now. Yeah, that's right. And so we would specify that the type of environment is a coal mine, and highlight that most robots, if you want to reach all parts of the course need to be able to fit through a one by one meter area. So something like a manhole cover, if you elected to bring much larger robots, then yeah, you still might be able to access parts of the course. But you're probably going to be leaving some points on the table, if you can't access some other segments of the course. And then beyond that, quite frankly, DARPA, you know, left it to the competitors imaginations, to identify not only what they might face, but what robot types or technologies would be advantageous for them to bring two to conquer that kind of an environment. So there was no limit on the number of robots, there was very little limit on the style of robots. There were some safety considerations on maybe exotic fuel types or what have you. But other than that, teams were able to use existing available platforms, and then really just keep on sensors or payloads, radios, or what have you on top. Or we did have teams that design robots from scratch, really thinking through the nuances of these underground environments in their build design power. So yeah, what, you know, clean sheet approach to trying to solve a really hard technical problem as a kind of a mechanism here for identifying interesting solutions that, you know, frankly, we might not have seen or thought about. And we too narrowly defined the problem.

Gotcha. Was there like a budget constraint for the teams? Or was there was it like open budget?

You can kind of buy by and bring whatever you will for the systems competition? Yeah, it really was kind of open teams could and in fact, many didn't seek out external sponsorships or donated hardware. One of our teams found some repurpose some robots that he found on Craigslist. Wow, that's crazy, was able to turn those into ground robotic suite. Right. And so being really creative with both the the the resources that you have, and the solutions you want to bring to bear. Yeah, that's where a lot of that creativity came.

Gotcha. Well, so what was the what did some of the teams look like? Like? How would you describe some of the robots maybe that show kind of the diversity of teams of robots that were entered?

Yeah. Well, what was really exciting from my perspective about this empty challenge is we had constructed it in kind of a iterative development manner. And so we started off, for example, in a coal mine, and we call it our tunnel circuit. So, of course, this human made tunnels, thinking about the mine rescue type scenarios, consulting with mine, rescue responders, and so forth. We went to a coal mine. And then approximately six months after that, we went to an unfinished nuclear power plant, and that was our urban circuit, and then working and exploring the possibility of kind of transforming a cave into a test course. But of course, we did have to cancel that due to COVID. But then, the final events allowed us to bring together all three of those types of environments together. And well, I'm sure we'll have a chance to talk about that here in a bit. But we fabricated this course that allowed teams to test their robots against all three of these environment types all in this magnificent course that that DARPA fabricated. And so, the reason I bring that up is because you saw there was no one form factor for a team, there was this continuous growth or evolution, if you will, who will have both the individual technologies, but also the team compositions. And so we saw a lot of robots that were wheeled, and we tried to see some flying robots in the tunnels circuit in the coal mines. And I can say that the wheeled robots did well, and the flying robots did not. And that was a great learning point. Whereas we pivot to the urban circuit. Now these are expansive think everything from warehouses to elevator shafts to other things that these drones really helped allow robots in Canada teams to go and explore places that just the ground robotically would never have been able to do. And then also saw the showcasing of legged robots, these quadruped Ed robots, so that they could go up and down stairs with a fair bit more ease than some of their wheeled counterparts. And so you kind of see this progression of both tailoring the fleets right who's going to be in your starting lineup might be a little bit shaped by the type of environment you're going to send these fleets of robots into. But by and large, that continued learning process culminated in the final event, where I'd say you saw a pretty healthy mix of air grounds, wheeled and legged. We even had marsupial robots, so ground robots carrying aerial robots on their on their back, piggybacking them, it's so cool to other parts of the course. And really, that, that diversity, the fact that there's not one and have common makeup of a team, I think is a hallmark of kind of the, you know, the the what we're going for in a challenge of being able to tease out all these various ways to attack this problem.

Now, how do you, I guess, so you have these teams, these teams all have the hardware. They go and the competition is about finding the markers, or what we find them the points that artifact artifacts, artifacts, and also it was about what total distance covered or something like this with this, these were the two significant indicators of performance,

or Yeah, so work, we yeah, we, you know, we kept it as simple as you have a fixed amount of time, you have an hour. And you have to go and find these artifacts. And what we mean by that is you have to be able to return the location and the type of the artifact that you found, you know, you have to do that location positioning to within five meters. So the idea here is, yeah, so you go into these places, you have no GPS, I should have, you know, maybe stated that upfront. And so you're moving through these environments, and you know, it's pretty easy to get twisted and turned around and get lost. And so being able to report out where you found that survivor artifact, for example, to within five meters of global position. So that if you had to send in humans and would know, that location, it'd be pinpointed within, nominally within arm's reach. That's the kind of notional metrics for firefighters, you want to get them within arm's reach, because it's going to be smoke filled, and they need to be able to reach out, touch the thing that they got sent into to go find. So within five meters, you have to go find that out, and it's not sufficient to have found it. But you have to get to get that information back out. Right? You have to get it correct, of course, what type it is, but then you have to report it out. And if you successfully report out the physician to within that five meters and the correct time, then you get a point. And so the aims that find the most artifacts in that hour, are the ones that take home. Yeah. It to do the victory lap at

the prize. And it was the prize was for the what was the prize for the competition?

Yeah, so we had cash prizes. This is one of the hallmarks of these DARPA Grand Challenges. And so for that systems competition, building the robots in such the top place to come $2 million. Wow, to their credit, that's awesome. And Wow, very good. Like publicity and everything to which is wonderful. Yeah. All right. It's the glory of winning the challenge for DARPA.

So the robots going back to finding the artifacts. They would you're not providing the robots a map of the minds or of the environment beforehand. They're building it while they're going through it. Is

that correct? Yeah, that's absolutely correct. In fact, that's one of the hallmarks of how we constructed the SubT challenge. Neither robot nor human knew the man on these competitor teams has set foot inside this course and know anything really about And so it really is about exploring the unknown environment and then exploiting it to go and find those artifacts quickly and returning that

information. Gotcha. So the robots are building a map while they're going in it. And this is why you can get twisted up. So if the robots building in an accurate map, say it's like a crew accumulating error as it's building the man, yeah, absolutely, then the map might be inaccurate, inaccurate. And then you could, you could say, I found something, I found it here. But because it found it, and the map is distorted, the location is wrong. And they would get no points because of a distorted map. Gotcha. That's right. Now, one thing that I imagined because it's or that I've seen discussed in watching some of the videos about SubT, one of the major challenges was networking. Can you talk a bit about this?

Yeah, sure. I think this is probably one of the understated types of problems, when you go into these underground environments, that no amount of testing in a lab or in even the basement of a university building, will really get you the feel of RF, the radio frequency of underground environments, because it's just so tightly coupled to everything from the thickness of the concrete, whether they're steel girders, or you know, rebar, if there's, you know, metallic, you know, metals in the in the soil, you know, all of those, if it rains that morning, it that plays a role. And so because of those dependencies Sue so hard to really think about communications in a robust way. Now, that was one of the four technology areas that the subsea challenge was deeply interested in. And so we did see teams really get in some cases, both surprised and confounded by how they're calm solutions were working under ground. So we saw a lot of different approaches, we had some teams come up with tethered robots that they would deploy from the outside, and tethers long as they could to maintain connectivity. And that robot, imagine, yeah, it's a long cable. I certainly twisted it will get snagged it would be a tangle hazard. And so there are many, many good reasons why not to use a tether, but some were able to make good use of that. There were others that used breadcrumbs. So now I'm carrying breadcrumb relay nodes on on the robot. And as they traverse either fixed amount of distance, and to like console and Gretel, they were at corner. Drop. Yeah, that's right. So they would drop.

Yeah. breadcrumb comms nodes. And that would allow them to relay their communications from robots robot or robots a base station. And then you had other models of comms, which was, you know, I'm gonna live without communications, I'm gonna go, I'm gonna go off the grid for a little while do my searching, scouting, mapping, finding. And then after either a set amount of time, or maybe I have really good data that I don't want to lose, I'm going to come back into columns, and then try to dump it, you know, to my teammate, or, or to the base station. So there are all sorts of columns technologies, but also come strategies that emerged as a way to deal with the difficulties of RF of communicating underground, is there.

So I guess there's a lot of structural things that make it really hard to do radio frequencies in these like tunnels and things like this, like you turn a corner, and then the signal kind of just doesn't bounce down the hall back down back through the corner, and so you can't get it out. And so that's why there were all these difficult. This was this was such a difficulty. Right?

Yeah, yeah, exactly. And that's a good rule of thumb. You know, if you turn the corner, your signal goes down dramatically. Yep. And, you know, if you've ever had those kinds of problems, getting your cell service, working in a subway station, or, you know, something like that, you know, that RF just doesn't propagate as well underground and through the earth. And so that's something that the teams really had to wrestle with.

Yeah, I'm curious about. So the motivation for this competition. Part of it, it's first responders and things like this. Can you talk a bit more about this? Sure.

Well, I'd say it was highly motivated at many of the robotics technologies We have as well as some of the component technologies, whether it's sensors or radios.

You still there? Yep. Still, yeah, you're saying so many of the robotics technology seems to freeze.

Yeah, there's so many other robotics technologies that we had, you know, four years ago. You know, even the component technologies at radios or component sensors, they were, you know, frankly, limited in how robust they were how resilient, they were to that vast, very diverse set of underground settings. And so that's kind of know, from a technology point of view, we viewed this DARPA subterranean challenge as a way to spotlight and accelerate technology development, not just of these individual small component technologies, but in fact, how we think about integrating all of them into resilient systems of technologies. And I think that's kind of the technology motivation. But when we come back to it operationally, you know, if there is this period of time where an emergency response scenario is occurring, and the incident commanders marshaling our forces and trying to figure out what resources he has available, wouldn't it be great in that kind of roughly one to, say, four hour time period, you know, that, that golden hour, if you will, or she knows enough to send in humans, you know, at the at great risk, wouldn't it be great to send it robots, if we could do that, and pinpoint where the survivors are located, or trapped or otherwise, or even if it's what kind of equipment these first responders should be carrying in with them. That was kind of the key takeaway, if you can tell me that I should be bringing in shoring equipment, because the ceiling might collapse. And that will prolong and reduce risk to the responders that have to operate in that environment. It'd be great that the firefighter didn't have to go in there first, figure that out, come all the way back out, and then carry in all of that equipment. Same with re breathing equipments, and things of that nature. So just being able to we like to call it actionable situational awareness. Yeah, it's it's not just not just the map, which is really helpful. And in fact, you know, a lot of folks just kind of would be grateful just to even have a map. Yeah, but DARPA likes to go well beyond what is needed today, and anticipate what would be really beneficial in the future. And this notion of actionable situational awareness, is this idea of being able to provide the incident commander, who's about to send in her teams of humans, the best possible set of information like hazards, where key objects of interest are like those survivors, where you know, where blind corners might be, where she might lose comms, all of those points are very relevant. And that's the kind of information we really want it to be able to develop the technologies to be able to provide or in the long run, so that really served as the motivating operational setting. Yeah. And I think it's been exciting to see how this technology is mature to try to meet that Mark,

for sure. To me, it seems like the two hardest parts of this competition for robotics teams would be first, the networking, and then also just the mobility, getting around in these environments, because I think, like, you can find different sensor pack, and maybe I'm mistaken in this. But I imagine you can find different sensors that are good in different environments. But they may have big, they may be bulky, they may have three power requirements, whatever it might be. But it seems like given the constraint of these tunnels, or these environments, where cons aren't really good, it's like, the big benefits of this challenge would be testing actual robot hardware in these environments to see how well it can do. And maybe like, what approaches might be a bit more robust. And then the second part would be okay, now that we have these robots moving around, how do we get them communicating their information out? Or connecting? So I mean, like, you could have kind of done robots that aren't doing much of the compute other than like, their localization. And whatever you're doing, they're sending information all the way back outside, for processing and kind of keeping a global state of the situation or whatever it would be. It seems like kind of the two areas that are pushed most by this competition.

So So you nailed them. And so in fact, we had four tech areas that we predominantly focused on the first. The first ones you've already mentioned, it's the networking. Mobility is the second one. You got to be able to get to these places, of course, but the other two areas that I'd also highlight are the autonomy the decision making of these robots in the face of significant uncertainty. And fourth and final was the perception piece. So how do you tie together? Not just like you said, the sensors, but what you do with that information? How do you fuse different sensing views, right? Those myriad sensors that you might be carrying? How do they provide you with a common picture of what is actually happening in this environment? And so all for autonomy, mobility, networking, and perception, we kind of really need to all come together, for sure. And we found the most successful teams were the ones that really thought about it holistically, and they didn't, again, rely solely on an autonomy solution to solve all of their networking problems, or didn't, you know, invest all of their dollars in the best radios and forego thinking about sensors in perception? So?

Yeah, it's like four dimensions, really? And yeah, to be successful in this company?

I think that's a twist. Yeah, that's a true statement.

I think I need to change the name of this podcast to have something about networking. Because something thinking acting are kind of They're analogous to three of those. But then, yeah, working systems, robots, and have fun.

And, and that's kind of another insight coming from this competition has been the role of teams, not just, you know, we might think of robots and humans as teammates, and you have robots and robots as teammates. And so just like you said, the name of this podcast, is this additional element where, in addition to what autonomy, perception and mobility I might have, as an individual player, how do I leverage the team so that I can cover all the bases appropriately, so that maybe I don't need, you know, it's like the relay races, I don't need to be the best cyclist. If I know, I'm a good runner, and my teammates are a good cyclist, oh, they can help augment what I might be deficient in. And so that, that kind of level of flexibility, kind of the, the design choices that that just explodes. The design space, really. And, you know, I think that's really one of the fascinating pieces. And so communication, communicating, teaming is that additional angle, additional perspective that the teams really needed to think about and not again, not just on transmitting bits, over wireless signals, but in fact, what information to which teammate when to send this information, stuff like that. And it turned out to be a really interesting dynamic to the way this research progressed.

Yeah. And it's interesting, it kind of catches my attention, because you were saying triathlon earlier. And I didn't quite understand. But now it's like, there are mixed events that each mode of robot may be best at. And so it's like, if one robot say a flying robot is really good at going up elevator shafts, which might be a very important thing in this competition, then that robot is specialized for that, but it's not going to be good for exploring in general, because it might kick up a bunch of dust. And that could be prohibitive to its sensors, so then it can't do its job. Well, this kind of thing. It's a triathlon, because it has many events at which of which different modes of robot may do better. Yes, yeah.

And yeah, exactly right. And even calling it a triathlon kind of glosses over the fact that our urban environments, when you think urban, or your listeners are thinking about urban, they might have many different mental pictures of what urban underground might actually be. Some might be thinking about the sewer system, or others might be thinking about the metro rail or others are thinking about where they park their car, in the, you know, in the basement lot. And so that, that even within a single so called event, right, like, like running, it's like running in a very different very courts and trying to figure out how

best suited you're running. You're running. Yeah, I don't know, upstairs, you're running. Like there's a ton of different environments. Exactly. It's like a Tough Mudder. In a sense.

That's not that sounds like a future DARPA program, right? Yeah.

Gotcha. How did you? How do you disseminate the results of this? Because I imagine a lot of teams came up with clever solutions. There was probably some push in terms of algorithms or ways of doing things. How do they results get pushed and folded back into the public.

Yeah. So that's one of the things I'm probably most proud of from a kind of a community sense is that the subsea challenge competitors, you know, they are competitors, they're all vying for that top prize. But in the end, they were all wreck, you know, recognizing that this is a an opportunity as a community to leap ahead and change that, you know, potential trajectory of, of this research in robotics. And so many of these teams have gone to great lengths to open source their code, to share data extensively. In fact, one of the limitations of trying to, you know, with, with our off the shelf, image classifier, so object recognition, you can get off the shelf classifiers. But what do you need, you need a lot of training data, Well, turns out finding training data in underground environments and various lighting out there for that, that's just like, you know, I left it Yeah. And so, you know, finding that and aggregating that, and even even collecting such data is also very intensive, and time and labor. And so we found teams actually sharing their datasets by collecting so they had this kind of pool of data that they could train, and improve collectively. And I think that was kind of just one small example of how communal and collaborative that this community ended up being. And so all of that to say, even amidst helping each other, you know, whether it's lending, monitors, and screwdrivers all the way to sharing open source code and data, I'd say all of the members of the subsea community has really embraced this idea of, of sharing it, and, and helping this community grow. So you can go to their listing of repositories they've shared, not only in their publications, but also in their online videos. They've shared their research, they've shared their code share their data, many of the researchers have gone on to work on follow on projects that are leveraging the technologies that they developed in sub T's, in some case, working with former competitors, now, actual collaborators on these projects. And so a lot of that has kind of kind of made it out to the wild. And those are just the research product projects. There's also a pretty big effort amongst these teams to kind of take these pardons technologies, those that have been tested in the crucible of the darkness of T challenge, and turn them into commercial products. And so we've seen startup companies spin out from these competitor teams, productization, of even some of these components, technologies, you can in fact, so go and buy these sensor integrated sensor packages, that you can slap on the hood of your car, or carry in your backpack, and get a nominal kind of imaging, mapping capabilities. That's now as a product. And a lot of that really came out from the SubT challenge. And so again, being able to make that impact, not just the research community with code, but in fact really turning us around and impacting the, you know, safety community in the security community in the mining industry, in the construction site industry. And you know, all those kinds of folks that can really benefit from these, even the component technologies have already started to see that impact from from getting the research, but also the technology out into the wild. It's been awesome. For sure. Yeah, that is super cool.

How did the so another part of this that we haven't really talked about? Is the simulation or the virtual competition? Would you tell me a bit about this and how it relates?

Yeah, so we designed the virtual competition of the SubT challenge to be an opportunity for us to kind of explore some of these What if cases, and that's one of the incredible values of using virtual environments to study advanced technologies. And so whereas in the system's competitions, we might take over a coal mine or an unfinished nuclear power plant, you only going to get one such course you know, one such environment. And despite having a lot of variability within that, one course, there might be a whole lot of other things we might want to study in the virtual environment gave us those opportunities to do that. To give you an example, you know, if you wanted to, you could use in the virtual competition, we enabled this ability to create your own world, you could procedurally generate your tunnel like environments or procedurally generate your own cave like environment, specify some parameters it would be Have you long and narrow? Or, you know, highly vertical? Or, you know, kind of

Yeah. And and that gives teams on competing in the virtual competition, this opportunity to test against a wide range of worlds far greater than one would find yet a single test site to kind of avoid overfitting to the problem to avoid studying to that one specific test. And so this virtual competition really kind of embraced that we, instead of testing against one virtual world, in many cases, we're testing against half a dozen upwards of eight worlds, in some cases to see how well a given fixed solution would work against a varying set of environments. So the way this works, we invested heavily in a next gen simulation capability, ignition, Zeebo, our SubT simulator. And that's the simulation

environment made by Open Robotics where I'm working. That's right.

Yeah, that's right. So Open Robotics, provided that virtual environment capability and advanced the state of robotics simulation, I'd say. And in that simulator, we're able to run that in the cloud using our cloud based simulation infrastructure that we also developed. And so now teams are able to develop containerized solutions. So bundle their robotic software, if you will, and upload it to the cloud and run their software against our simulation environments, not knowing what the simulated world would look like is, of course, we are managing all that in the cloud.

Yeah. You have your tests, basically, which this is how well does it do in the cloud environment? Okay.

Yeah. And so the other fun part of this is we constructed what we call the sub t tech repo. Think of this as like your, you know, your storefront, your web based storefront, you can go and add robots to cart. And what I'm doing here is I'll give each competitor 1000 SubT credits. Yep. And you go to this storefront, this tech repo, and each of these robots that we have virtual models of cost you some number of sub D credits, yeah, up to that kind of salary cap tees of, you know, NAC league analogy here, you get to build, mix and match the types of robots that you want to add to your team subject to this budget of 1000s of t credits. And these different robots are all different sorts, they have different sensor payloads, they might have, again, wheeled or flying or kind of all the different different modalities you might explore. And so it boils down down to these teams, thinking about where they want to spend their 70 credits, and the number of robots they want to add to their team. And then designing their autonomy and perception solutions to best match the virtual robot teams that they're constructing. And so in this way, you really get to kind of explore what are the best composition of teams? What if, given this cost constraint? He asked earlier? If they're, you know, budget limitations for

that? Yeah, cuz I heard about the virtual, the budget. Yeah, the virtual one. Yeah. So I was wondering if there was something similar in the hardware and how that would work, because it's quite complex, if they're building hardware was my thing. Right,

right. And so we wanted to abstract away some of the, you know, constraints of having to embody some of the software based side of things, and free up that develop, you know, the development to explore some of these other scenarios. The other really big difference between the systems and the virtual competition, was that in the system's competition, these robots have to report out where these artifacts are located. And they can coordinate with a human supervisor, a single human, to act as a teammate amongst a fleet of robots. And that human supervisor, is typically the one that's forwarding the artifact reports to DARPA to get scored. And so you now have this partnership, you can have the human supervisor, kind of interact with the teams of robots and have the robots go take a closer look at things or maybe show a an image or review and high man's like, go over there probably or whatever. That's right. Yeah. And they did. And that was really great partnership. But in the virtual competition. These robots are fully autonomous. You have uploaded your software to the cloud. It's one set of software that has to get run against all of these different types of virtual environments. And there's no human back and forth and so really being able to explore complete autonomy of The solution where you don't get the chance to, you know, back your robot out manually, even if you do it, you know, that gave us again, studying what this what if scenario in the future where you didn't have the luxury of having a human supervisor, or the levels of autonomy got to the point where you could deploy these robots to good effect in these really diverse environments. So now we have, you know, brackets, you have the system competition, highlighting where we are, we push the state of the art in applied realized technologies. And we also have the the solution space of what can be done in the completely autonomous regime where it's software only. And now we can quantifiably say how far are we from complete autonomy, autonomous solutions, or we can quantify it to some degree, the value of the human teammate. And so the virtual consecration is benchmarking ability. Right now we have comparative analysis between systems and virtual. And we did this all throughout the whole competition, where we had tunnel circuit in both systems, virtual, urban in both systems and virtual in cave, we couldn't do the system's competition. But man did the virtual competition really shine through in the in the face of the global lockdown, where now we had teams flocking to the virtual competition, because they still were thirsty to develop their technologies. And so we had numerous systems, competitors, crossover into the virtual competition, in fact, and carry that through to really good effect. So it was a lot of fun on the virtual side to kind of help us imagine what future technologies could be while also being closely coupled to where the current state of the art of the technology was, as well.

Yeah, I find it to me the most exciting part about that, as you said, with the benchmarking, it's that so like, I'm thinking about, like the advancement of technology and say, like the computer image or computer vision space, like we established image net, and it's a benchmark in a sense, so that people can more fairly compare what they're how their algorithm performs. And so what you see is people keep trying it, and then the performance keeps going up. And robotics, especially on like a behavioral level, has not really anything similar to my knowledge, except for what you're describing here, which is really cool, where you can have some sort of, so you have your challenge. And you have a way that people can try by basically upload their algorithm to it. And it runs it given their robots and and all of this, to see the performance, and you can see the performance over time. That's really, really interesting and very exciting to me.

Yeah, totally with you. I think this idea of being able to set those benchmarks allows for us as a community to see how well we're doing right and see that progress. And it's exciting to see that progress. And to be able to do that in near real time with this side by side systems and virtual competition, I think, you know, was really, really cool. And I'll highlight two more things. One is we took systems robots, so robots from the system's competition, and went ahead and scan them, generate 3d models of them. So controller code that were contributed by the competitor teams, and validated it against their sensor spec sheets and battery durations. And you know, quite laboriously. But now, in that SubT tech repo, this is these virtual robot models that are digital twins of their systems, real world robots. Now live in the tech repo. And now virtual competitors, they might not have had the resources to build their own robots, but they can actually go and use a systems embedded robot models in their virtual fleet.

Yeah, and that's very cool. If anyone had an especially good idea for like, how to, like a morphologie. That's really, really good. And now, I can play with that more as a community. Right off. Yeah,

exactly. Right. So I'm going to pull the fantasy league analogy. Again, you know, if it's a virtual competition, gave you the flexibility to mix and match across the league. With a systems competition was kind of like the, you know, like the NFL, right? You kind of have to pick your roster at the beginning of the season, you kind of play the players that are on your roster, because it really is too difficult to go back and do clean sheet design after each one of these competition events to start from scratch, so you're kind of trying to do that systems thinking for the systems teams holistically. But man in virtual you get to mix and match. Play around, see, if you want to be an all ground team or an all air team or, you know, beg and borrow from different, try different styles of robots, you can do that. And many of the competitors were able to do that exploration. And there's still, of course, significant exploration left to do. And then also highlight that there's a virtual testbed, the SubT virtual testbed, which encompasses the simulator, and the tech repo, all of that is publicly available and open source. And so, okay, yeah, you can still go, despite the competition being over, we know that the value to the community is so important that DARPA is keeping up the testbed open for a period to come, you can still go to SubT challenge that world and learn how to how to develop a SubT solution and upload it to the cloud and run it, you know, and get free free reps in for Yeah. For your simulate, you know, your simulation solutions. And so I think, yeah, the availability is another testament to, you know, how we really cherish the the community really are interested in fostering the growth of the community, because that's at the end of the day, what's going to turn around and develop those technologies that are, you know, first responders and warfighters and others are going to be able to make use of or precisely the technologies that these people that the community develops and matures?

Yes, for sure. Do you imagine that the the framework that you guys have developed which hosts this the high level testing and benchmarking of this challenge to imagine that this can be applied to other different like, basically, the whole infrastructure that you've built? Do you think it can be applied to other robotics challenges, say robots like moving around in hospital and be inefficient or any, any rope, any tasks that robots might be very good for? To have this provide like a standard benchmark, so you can look at it over time, and compare more fairly, the algorithms and approaches?

Yeah, hands down. I'm a, I'm a believer in this type of a model of being able to not only test at scale, but also open up the innovation space, by lowering the barriers to entry. And simulation is a great way, you know, to avoid having to lay out capital expenses to build a fleet of robot and oh, by the way, have access to a hospital or the underground mines or the moon or wherever your setting might be. So absolutely think this back end infrastructure absolutely critical, as a, as a method as a set of tools to, to help out. And in fact, I'm pleased to say that, in fact, we are seeing this precise infrastructure being used in other robotics development settings already. So the impact is already near and dear. And stay tuned to see some of those competition events making use of this kind of infrastructure.

And is that infrastructure? Is that in the SubT tech repo that you've been mentioning? Or is it Yeah, somewhere

else? Yeah. Yeah. So the tech repo is the the source code, if you will, of all, the majority of everything we talked about is already available, you can go to get a, I believe, under OSR. F, and see the SubT project there. You know, nearly everything that we've talked about is already located there. So there are a handful of resources under github.com/sub T challenge, and you'll be able to find a number of resources there as well.

Awesome. I didn't know because I haven't. The sub T has never been one of my projects. So I'm not that aware of what where everything lives in this kind of thing. It's awesome to hear that it already is all online and people can access it. And that people are also using this infrastructure to benchmark other tests in simulation. I think that's really, really exciting.

Yeah, it's gonna be great when kind of the impact to not just the subterranean robotics community, which admittedly is just one sliver of the community. But being able to open this up, you suggested kind of hospital environments or maritime settings or other types of environments where we really want to explore more broadly, I do think that, you know, this investment will pay significant dividends for many, many years to come for the robot's community.

Thank you, right. Let's see. So we are running out of time, and by that I mean, like 20 more minutes or so and I have a lot of things that I want to talk About in this, but you you mentioned the final events and that we do you'd like to talk about that and kind of how you fabricated this big environment? Would you tell me a little bit more?

Yeah. So, you know, I think one of the visions for the subsea challenge from the get go was to have teams of robots, that and, you know, unhindered by the fact that you might face all three of these environments. Now, the challenge, and I've crossed crisscross the country to try to find a place that has tunnels, urban caves, all next to one another, all co located all connected in a meaningful way, if any of your listeners have mine, please, please let us know. So instead, as DARPA intends to do is, you know, because we are always seeking those breakthroughs. We transformed a limestone cavern and built a one of a kind course, kind of think, almost like Hollywood set design with the level of realism that, you know, is, you know, very compelling for both human and robot, to the degree where we're getting inspiration from caves and mines and sites that we've seen, we replicated New York City metro station, all the way to steam tunnels, and old rustic abandoned mines to large caverns that are either show caverns that you might go to as a tourist to the, you know, the raw caverns or the untouched ones that have a very different feel as well. And so we were able to take all of those different sites that we had been to or found to be really compelling, and fabricated, we built that we had warehouse structures connected to a metro station connected to a featureless hallway. And that's just a fraction of the urban setting, we had small places where you had to crawl on your hands and knees often over the different segments and places where I'm certain many dozens of times, if I hadn't had a helmet on, if you walk away with a lot of bumps and bruises, you know, just trying to build a place where we can test and push the boundaries of autonomy, mobility, networking, and perception was a phenomenal experience to, to do that. And in having to build that course, going back to where it all started with all of our stakeholders, all the end users of people who this was going to who we would have to have them believe that these environments were realistic enough, right? So we did go back and say, Hey, what are the pieces that you need to see, to be able to say that you believe this technology is relevant to you. And we were able to do that to good effect. And whether and since we were building it ourselves, we in fact, had different segments of the course take on different personalities. And so in total, even though we had three subdomains, the tunnel urban cave, we in fact had, like 60 different segments, kind of like going on a on almost a Disney ride through different parts of the subterranean world, is what we were able to pose to these robots now facing all of that difficulty, really, really, really allowed for testing the diversity. And we went to great lengths, I'd say to hone that realism. We talked earlier about communications, and networking. But I'll tell you, we went through various types of RF shielding and pains and other things baked into the walls of, of, of this course, to be able to replicate the kind of the RF propagation in underground environments. And so I'm pleased to say that I think we did a good job of trying to replicate not just the look and feel but the RF, the radio frequency, the wireless transmission all the way to you know, the little things like amount of water moistures, slick surfaces, Rubble, gravel, you know, all that kind of stuff. Really, really proud of this one of a kind opportunity to, you know, raise the bar for the robotics community writ large, for sure. Yeah, it

sounds like such a great test environment that's so funny that you like the shielding and things so you could get the RF properties you wanted in the environment. Amazing. So I assume that will be used In future competitions or how so actually How did it go? In the finals? You use this environment, correct? Yeah, that's right. How did it go? How was it?

Yeah, I think I think it was really great. I think, you know, one of the benchmarks for me as the DARPA Program Manager here is, was it hard enough, right? Does it push the boundaries, it needs to be hard, so that not everyone gets 100. But we don't want it to be impossibly hard, because then we're not going to know where the boundaries are, where the envelope is. And so being able to design this course, in a way that had the level of difficulty variants, that allowed some pieces of technology to really be showcased, and others, you know, you found where their limitations were, you know, that was really great about the the environment. I'll say, also, from the kind of the government's perspective, the DARPA team, we are in the command post, as you know, this is not something that our competitors get a really good glimpse of, because you're all behind the scenes. But in our command post, we had instrumented this course, with everything from cameras, of course, so we could see where robots might be. But we had things like motion detectors, we had triggers, all of our artifacts were instrumented so we could make sure that they're consistently Halloween house. Yeah. Yeah, that's right. Yeah. And so we could orchestrate kind of like movie style, movies and style, like, and so we had dynamic obstacles. And so these would be triggered when robots entered a particular area, and then section of the course would collapse behind them now blocking their way home, they would need to find a new way they would not be able to follow their that's amazing, around the home. And so that was built into the course as well. actuated, from, you know, from these types of signals that we had instrumented this course with, and so does a Hollywood set up. Yeah, in many ways it was. And it was always done with a technology objective in mind. And that's the cool part about it is and showing this collapse was something that was very relevant to many of our, for example, mine rescue personnel, because that's one of the hard things is debris collapses, or debris, integrity checks of the environment. And so collapsing, part of this was near and dear to them. But for us, we are interested in testing the autonomy, the ability to recognize that your map has changed. And then your way home is no longer viable, you got to find another way home. And so there was a really fun way, a really tight way of coupling, the operational kind of need and insight with the technology that we were trying to push in this one, of course, was explicitly designed, you know, from from CAD drawing all the way to graphic artists painting inside the course. So to be able to deliver that type of tight coupling between operational and technical objectives.

Gosh, that sounds amazing. Do you have is there like a YouTube of like a walkthrough of this course? I haven't seen it.

Yeah, there are. So you can go to DARPA TV, that's the YouTube channel. And all of our videos have been placed there. There are walkthroughs of every course that we DARPA has transformed into a competition course. So you can go and do a walkthrough of Hardrock, like a gold mine, coal mine, that nuclear power plant, and then of course, our grand finale, final event course there multiple walkthrough videos. And then this might be a good opportunity to share that DARPA also collected very high resolution, high accuracy datasets of these environments, to the point where we could dance, of course, because we're also scoring the artifact position reports. So we were down at the, you know, millimeter scale of accuracy. And we've released that as a public data set as well. So if you were unable to test in the final event course, well, you can actually go to the SubT tech repo on the virtual side and get a mesh 3d rendering a 3d version of the final event world and, and see what it looks like for your robots as well. And fun fact here, one of the final event, virtual competition worlds was in fact, a 3d virtual world of the system's competition final event world. So kind of bringing everything full circle Now you get this chance to test how the system's competitors were testing in this, again, unique one time world. And at the same time, we're running virtual competitors do the same as that course, having developed this 3d model of the course, with all the, all the pain, the same pain points as the real robots had to face, but not in a virtual domain. And so all of that's been publicly released, we can see the video, but if you want the point cloud, you can download the Point Cloud yourself and work with it, or the mesh, 3d virtual mesh file is available. So you can, you know, do put in your own simulators, if you wish, or loaded up in the SubT simulator and, and drive some robots around.

So cool. What a great public offering. That's so it's so neat, that people have access to all of this. Let's see. So I have a few things that I want to talk about. And we have like, really 10 minutes left or so would it be all right? If we run a little longer is it? Yeah, absolutely. Okay. So one thing that's very interesting to me, and I really, really wanted to talk about this. So I'm very happy. We can run a little long. But can you tell it's like one of the huge challenges, I believe in setting this whole thing up, which we talked about before, is figuring out how to scope these challenges, because you want to make it so it's not like like, as you were just saying, you don't want all the teams to fail, because it's too hard. And then it drives no innovation, because no one can do anything. But you don't want to make it too easy. Also, can you just talk a bit about scoping the entire SubT challenge? Yeah. Yeah, I think process of that.

Yeah, you know, I think it boils back down to the really doing our homework and kind of getting, I think that's what DARPA is all about is not only gauging where the current state of technology is, and not only kind of trying to understand the trend lines of where technology might be gradually going, but understanding the levers where if we were to exercise, some, you know, nudge here, hope they're tested that, that we would actually bend the curve of the trajectory, and accelerate where technology is gonna go. I think that's what DARPA is, a foundational mission is to try to create a kind of technological surprise. And so by doing our homework, both on terms of where the technology is, but also what the end users really needed, kind of doing that, that you know, where we want to be, right. And we want to skate to that, to where the puck is going to be, combined with knowing where we were, you know, I think it really was a laborious process to tune and tweak the evolution of the challenge to be able to arrive, as well as we have to this end result of having advanced as much as we had. And so I'll tell a story here, at one of our very early events, we transformed the a gold mine into a test course, and this was not for competition, it was really just a test. It was an integration test, really. So we invited competitors if they wanted to, to come out and test and we had done it up much like a competition course. And this was really to give teams a first look at what DARPA had in store for them. And so when we conducted this, teams went in, and you can safely say they got their butts kicked, right, I think they realize that, you know, it's a little things that we'll get to, in addition to the big things that they were worried about. And one of the things that it became a tradition afterwards. But we took all of our competitors on a walking tour of the entirety of the course that we had laid out that DARPA had laid out. And whereas most teams maybe made it, I'll be generous and say, the best team made it 10% into this first test course. Yeah. When we went on the walking tour, and showed them how far and how expansive this course really was. You could very easily imagine that there are those out there who would say, Man, this is impossible. What is DARPA thinking? They'll never, you know, no one can ever accomplish this. And yes, they did say that to some degree, like this is impossible, man. But no, what really kind of stuck with me is that the prevailing sentiment after that walk about two are in that very first course, was not that this can't be done, but that we didn't do it. But man, somebody believes in us that, you know, DARPA must believe that this is possible because otherwise why would they have crawled up that One ladder in the far reaches of his mind, why would they have kind of probably twisted ankles to climb up to that location, replace that cell phone company, all the, you know, 80 pound man, again, three kilometers into this course, if they didn't think that this was possible and that spark, I think for them of setting the bar really high, you know, and saying yes, we think that in due time you accelerate the technology to get to this point, you will be able to conquer a good portion of this course in the future. And that trajectory, I think, has continued to manifest throughout the challenge. And so by the time they got to their final event, you have many teams on record saying that you asked if you ask them three years ago, or four years ago, that they could have conquered or handled any part of this final event course they'd say, Absolutely not. For the fact that we're here, in truth be told, by the way, you know, I don't think we talked about it. DARPA placed a fixed number of artifacts in these courses. And so for the final event, we placed 40 artifacts in nearly half a mile of underground terrain that we had built. And the highest scoring teams scored 23 points, 23 artifacts. So you might say to him, hey, that's kind of a failing grade, right? That's kind of like, well, 50% is just over 50%. And you're saying you did a great job? Well, yeah, that's a phenomenal job, given the difficulty level that we know is where we want to be right. And so again, it's really been showcasing that the technology still has a lot of headroom to grow. But to be able to quantify the level of impacts, right, we're able to cover this massive environment in about an hour with robots that, frankly, took an order of magnitude, even two orders of magnitude longer with my human team to go gather that high precision data, you know, it took them a fair bit longer to be able to go and do what robots are doing in under an hour under duress, never having seen the courts before. That's a market improvement that we can point to and say, four years ago, we might not have been able to do it, if not, for this high bar that DARPA sets. And I think calibration process is a iterative thing that we've fine tuned, I think, here at DARPA,

I think it would be more worrying if people got all 40 already. That would mean the challenge was not hard enough today, because it's a benchmark. I mean, if you look at, again, going back to like image net, it'd be like 50% level when they were starting, and then it's like a free thing up 70% Now, maybe, or 80, or whatever it is, but it starts pretty low, and then you have plenty of room to improve, because you have a hard challenge and getting all of it, especially in that like limited period of time. Right? Like that's a real challenge. Yeah, it's very interesting.

Yeah, wholly agree. And think that there's, you know, really promising work to get to be done and to be a

component, for sure. And you were mentioning, mentioning, DARPA has this very iterative process for scoping, like difficulty of these things. Can you talk a bit about that, because that's really interesting to me.

Sure. And so specifically, for the sub D challenge, we had designed it, so that we would have those opportunities to, to to learn as we go. So by virtue of how we constructed the SubT challenge, we held that first event where teams first saw what DARPA had in store, but then, about six months after there was the tunnel circuit, where we conducted our first event focusing on tunnel environments, in this case, a coal mine. And then we broke that up into again, six months after an urban setting. And so the teams knew that if they were going to be competitive at the final event, where they were anticipating that all three of these environments would all get mashed together, then they should be thinking about their designs from the get go, that can survive, quite frankly, tunnel urban cave, all the way to the very ends. And so we saw teams to kind of internalize this, this need for resilience in their early kind of design scoping. And so they went to the tunnel and man, Were there a lot of really hard lessons learned at the tunnel a bit, but what you saw was a learning not just by team, but across teams. An example is that a using a a sensor on the outside to be able to help correct as robots still within line of sight of the mouth of the tunnel. You know, we had a team that was using that and so they could extend how far their accuracy was, you know, subject to drift they could they could extend And how far they were by using this total station sensor to, to correct for any drift. And yeah, that's, that's clever and so even even at the tunnel circuit he saw teams going out and trying to find and they found a local university and borrowed one of these little stations and tried to use it and by the Urban circuit, you had more teams using such a technology. Same goes for legged robots say, legged robots didn't do so well at the tunnel circuit. But at the Urban circuit where there were stairs and curbs and other things, man, those legged robots really shine. And so at the final event, you saw a lot of legged robots coming to the fore. And so that's what I mean, by the iteration, there was multiple opportunities for these teams to come field go through the the rigor of a competition events, but that wasn't the end of it, they would have to go home, lick their wounds, and then come back and do it again. And then, of course, break some more robots and learn what it means to have to operate in the cold, called nuclear power plant or the human limestone cavern or, you know, all of those kinds of things. We baked in that iteration and the kinds of opportunity to learn quickly and often into the stuff the challenge. And I think, as a roboticist, myself, I think that's where you learn the most by thinking and then doing right thinking of doing breaking, learning, and then thinking and doing it again. And Field Robotics, I think is, you know, needs that and sometimes trying to do robotics in the field, especially at the scales that the sub the challenge was interested in really hard, logistically, you know, it takes a lot of time, a lot of people power to get to transport robots and get things set up. But, you know, sub The challenge really gave all these teams, not only the excuse, but the incentive to have to go and test in the wild. And many of the teams, especially the top performing teams, really took that to heart found, you know, and partner with local caver clubs, local gaming, clubs to go and gain access to their caves and practice, or, you know, all of those kinds of opportunities, I think, came about, with many, many lessons learned a lot, a lot of a lot of broken robots, but a whole cadre of field roboticists and the next generation, I'd say, Field Robotics is coming out, having been battle tested in the subsea challenge.

That's really cool. So that makes me curious about kind of the long term role of DARPA in all of this. So you're, you're mentioning like one thing. Very interesting, as you're mentioning, training the next generation of Field Robotics, roboticists, can you just talk a bit more about the role of DARPA? Yeah, as you see kind of on a bigger picture?

Sure. Well, you know, at its heart, DARPA is always going to be about bringing about technological surprise, and those breakthrough technologies that will have broad impact overall, and whether that's deep investments that will lead to breakthroughs when we need them. And an example of that is that mRNA vaccine approach that in the time COVID, was investments by DARPA early on to identify that kind of methodology in the time of need, where it would arise. And so identifying, you know, those opportunities where, even if you don't need it today, but you might need it in the future. That's what DARPA is all about. And I think, recognizing that the state of the technology for robotics Field Robotics wasn't where we wanted it to be in the future. That's what DARPA was eager to inspire, and incentivize, and then help shape that future trajectory. As far as building the community. I really love the DARPA Challenge model for innovation, where, you know, we have a couple of different ways that we seek out revolutionary ideas. But the challenge model is just one type of those and, and I really love it, because it also gives us an opportunity to think about solving a problem without having defines the solution. When you do that, and the community hasn't yet informed around that problem area, or the solution space. The DARPA Challenge is fantastic for being able to plant the seed and nurture this community that's now going to go off and do great things right. So the DARPA first started Grand Challenge, self driving cars to the desert or in the urban environments, you know, had planted the seed for a lot of the of the self driving tech investments today. And I imagine that many of the types of technologies that we've discovered and invested in for the SubT challenge will have that long term impact. While also, and I'm excited to say, have a very near term impact for many of our end users as well, given how we structured this this challenge to kind of think about marrying, you know, what the what the what the end user needs tomorrow, not just many years from now. So I think being able to span that has been a real hallmark of the DARPA subterranean challenge of understanding what the near problem is, as well as anticipating and planting the seed for the communities to address the fire problems as well.

Awesome. Let's see. So I think I don't know how it works. But what's next? Yeah, like, what next with this SubT challenge next with maybe another, I suppose Grand Challenges take a long time to think about and I don't know, things can be revealed. But what's next? Yeah,

well, I'll say that the SubT challenge has concluded. And while we have all of those resources, all of the Open Source Repositories, all the things that we talked about, available out there, it's my wish that folks, you know, take it and run with it, they can reinvent or recreate or invent the new, different types of approaches to solving some of these types of problems. And so I think that what we see already in the community is kind of we've spun up the firewall, and now it's operating on its own momentum. And it's really invigorating and inspiring to see all these folks already out there. You know, organizing amongst themselves the the ability to have this kind of an impact. And being a resource. As far as DARPA is concerned, I think, you know, if any of your listeners have ideas for Grand Challenges, that's an opportunity here, I think DARPA is always on the lookout for those types of problems, those kind of technology questions that are out there that don't have or would benefit from not having a pre defined solution, kind of a direction to go, you know that there's a breakthrough waiting to happen. But you don't quite have a finger on where that breakthrough is going to come from. And a challenge model is great. And so DARPA, I am certain that the DARPA Challenge model is here to stay. It will, as it at, like all things at DARPA, continued to evolve and tailor itself to the technology of interest. But now, I'm excited to say that, you know, which DARPA Challenge model is demonstrated, at least with sub t, that it's a it's an exciting way to both drive a community and drive technology development.

So wrapping up, do you have any links, websites, anything to share? I know the SubT website. So I'll include that in the post anything, anything else to highlight?

Yeah, I think, you know, if you go to one of the repositories, we mentioned earlier that a GitHub repo slash SubT challenge, there, you'll see a project there, just called simply SubT resources. But this is where it's kind of the one stop shop for all of the references, links to software that the competitors themselves have now released. So you can see that the datasets that both DARPA have provided, as well as many that SubT community has developed and curated, are there, links to papers and other materials are there. So you know, I encourage folks to go check that out. And then of course, the DARPA TV YouTube channel has many, many videos that you can go learn about the sub D challenge, its impact and why it matters, as well as learn about all the teams as well. So I think those are a great place to start. And if you're interested in learning more about DARPA, I think darpa.mil is a is a fantastic landing point for any of your listeners.

Cool. It's been a pleasure. Thank you so much.

Thanks for listening to my conversation with Tim Chung. Thank you again to our founding sponsor, open robotics. See you next time.

The SubT Challenge's Website

Tim's LinkedIn

DARPAtv's YouTube Channel

SubT's Repository on OSRF

DARPA Subterranean Challenge

Sharing Between Competitors

On the DARPA Challenge Model

Motivation for the SubT Challenge

On Setting the DARPA Challenge's Difficulty

On Benchmarking Robotics Behavior

On Using the Benchmarking Framework

In this episode, Audrow Nash speaks to Dan O'Mara, who is the founder and COO of Circuit Launch and Mechlabs. Circuit Launch is a space for hardware entrepreneurs to work in Oakland, California, and Mechlabs is a project-based course to learn robotics. This interview is mostly about Mechlabs, but talks about the origins of Circuit Launch, including how it is not a maker or coworking space and its business model. For Mechlabs, we talk about several of its aspects that make it different than a university education in robotics, including how there are mentors not instructors, how projects are scoped, and how people are invited to work on what is most interesting to them. We also talk about the future of Mechlabs and how it fits with current universities.

Introducing Dan and Circuit Launch

Not coworking or a makerspace

Coming to current business model

Mentors not instructors

Introducing Reachy

Scoping projects

Scaling their education program

If companies paid people to learn

Marker 30

Importance of having students write documentation

Requirements

Comparing to today’s universities

Role of education

Expansion plans

Getting in touch

This is a conversation with Dan O'Mara, who is a founder and the COO of Circuit Launch and Mechlabs, Circuit Launches a space for hardware entrepreneurs in Oakland, California. And Mechlabs is a project-based course for robotics education. What does a robotics education look like to you? Dan jokes during the interview that if you're at a university that you need to major in electrical engineering, mechanical engineering and computer science, to get a robotics education, some universities do have a dedicated robotics program, but it's a big commitment, both in terms of time and money. And what if you already have a degree, even an engineering? Should you go back to school? I have friends and family considering this question. And I feel like there's a gap here, where a group of would-be roboticists don't know how to get started. And this seems to be one of the spots where mech lab fits well. I also find it interesting that Mechlabs basically does the opposite of what universities do on several levels, as you'll see during this interview, and that doing so has worked well for them. They are, as Dan says, during the interview, creating a program that they wanted to learn from. I'm Audrow Nash, this is the Sense Think Act Podcast. Thank you to our founding sponsor Open Robotics. And now, here's my conversation with Dan O'Mara. Dan, would you introduce yourself?

Sure, I'm Dan O'Mara, the COO of Circuit Launch and Mechlabs, we are a basically a community space for robotics and hardware engineering, with corking shared labs, as well as a educational program for mechatronics.

I don't want to talk about both of those things. Let's start with Circuit Launch, would you tell me kind of the story of Circuit Launch how it's come to what it is?

Sure, I think Circuit Launch grew up in the bay area here as a space coming off the the tail end of like the fall of tech shop, and the understanding of like that, there were all of these entrepreneurs and people in this area who are doing hardware, electronics and robotics, and like, this is the Bay Area, we don't have space to do that, where you can run a business like this kind of in your garage and a lot of other places. But eventually, you do need some type of space to build things in a workshop and lab tools and all of the that stuff. And we just realized that there are all these entrepreneurs who are doing, you know, new companies, like because of the start of Kickstarter, and all of the great robotics technologies that are starting to become a lot more available. And we need, you know, they need space, they need shirt labs, they need facilities, they need that any you know, I make a joke that you know, we're not we work we don't have you know, we don't provide scented candles with your your members. We're a little messy, chic, we, you know, bow, you know, one of the things that really resonated on our marketing language and website is it's like, you know, do you want to put a soldering iron on your desk come work here, like this is where we, you know, we want you who are building stuff making stuff. During that I mean, we have we have one person right now has a metal lathe that he snuck onto his desk, basically. And so in the upstairs area, so like that, we realized that there is such a need for like a community and a place where you can work and you can share with other roboticists and other electronics, hardware specialists and, and everything and build a business. And so that's what we really focused on. We said entrepreneurs who are building hardware and robotics businesses, we want to have a space for them. And we want to make this work. And so that was the original side of it. We partnered with our building owner, which is also another crucial part of our business model, to be able to provide that space and to be able to make that so that we weren't going to just grow big, and then all of a sudden the building owner, you know, creates a lease situation where we could. And it was it was a wonderful match made in heaven. We found an incredible business building for about 32,000 square feet. And we've started building our community from just a few people. And we used to let you know any kind of company come in and now we're over 95% specifically, robotics not even like, like we used to do like oh, you know, if you're a lawyer that works in the patent space, you can come here if you're a you know, you do some software, somewhat something you could come in like there, and now it's just really our community has become all about robotics, which is great. And that's really what we're, we're we're creating and fostering and now people want to build their companies from marine robotics to you know, IoT devices to Krub the we have a company that just won the the department energy E robot prize From the robots, they're a carpet cleaning robot. So it's just all of these, these people came. And, you know, we rebuilt it. And they came. And that's really the kind of the story. And we've, we've been constantly working with startups to be like, give them what they need, which is sometimes the ability to have a desk, sometimes the ability to expand into an office. And then sometimes it's the ability to go bankrupt and have all of your employees start new businesses and new companies and go into little other places and downsize things. So that flexible space was what we really knew that our community needed. And then market tested it. And now we have a really flourishing awesome community that we're leveraging to create a, you know, an education program on top of and get more people, robotics experience and projects and mentorship and everything else.

We're 100% occupied just 95% Robotics 95% Robotics. Where,

yeah, that's so exciting. Yeah, cuz I was there with Hello, buddy. Two, three summers ago, as an intern for them. And it was really wonderful to be in the space. Like, I loved all the robotics that was going on around. And I think I don't remember numbers, but it was it didn't I don't think we were, I don't think it was 100% occupied two or three years ago. Now. That's wonderful. Gosh, and we just went to the block party, or you just had the block party, and it was wonderful to see the turnout for that

robot, block party. Barbecue, we do that every, we're now that's our second one in six months, their second one, you know, in a year. So we've done we're hope planning to do those every six months, and it's been now we had 40 Different robotics companies and vendors and demos all come out. And with the job fair, and everything, it was really

fun of it. Yeah. So I mean, from my perspective, it kind of seems like it's part co working space. And then part makerspace, with like laser printers and CNC machines, and I don't know all these things. And then the focus on community.

So that, like, from our marketing side of point, we're trying to, kind of, in many ways, kill off those two terms, coworker, and robot and makerspace. And it's interesting, because that, that's really about where really, so the the co working side, obviously, we're shared offices, you can read desks and offices, that mean, it's co working. Yeah, but, you know, co working really kind of doesn't explain the fact that you have great labs and tools and 3d printers and, you know, an electronics bench and a soldering bench and that you can, you know, if you want to put a 3d printer on your, your dedicated desk, you know, you can put a 3d printer on your dedicated desk and run it all night long, right? All of that. And so that's really why we, you know, co working is very much this sense of, like, that's a dead business because of we work, right. And so we want

to I mean, there's no more potential for a company to start there. Because we were kind of in applies that.

Well, not even monopolize, but just that, you know, people aren't interested in the like, coworking has a bad rap because of it from an investment profile and everything else, right. And we're so much more than that. Like you, we don't want to be pigeon holed into the idea of just like, you know, you're you're we're all working together. And it's like, we have a full lap and facilities and we want to, you know, in a community there, which is so much more valuable than Makerspace side of it. Another business that is kind of doomed to fail for most most people's minds, right, especially after Tech Shop. Right?

Oh, okay. So, Tech Shop was. And that's partly because the space you're in fits more with what we're doing. Like we, we don't want to be a makerspace we want to be an on a shared Fab Lab, by intellect. It's mainly the difference is the level of entrepreneurs and robotics companies, rather than hobbyists and makers, right? Yeah. And not to say that we don't want makers and hobbyists, we were happy to take them. But we also realized that we want we want people cutting edge industry professionals in our space and doing right. And so Tech Shop was kind of the first big Makerspace like, I mean, make in magazine, they all kind of evolved with tech shop to be one of the largest, most well known makerspaces, you know, in the world, and Tech Shop, grew on this very unsustainable model. And then they made a lot of mistakes. And obviously, we don't want to go into that, but they went bankrupt. And then all of these makers and professionals and entrepreneurs who, who realized, hey, shared laboratories and shared resources is a it's a good thing and an economically viable thing for my business. And now I don't have have that

so what we do, and part of what tech shops issues, whereas they didn't support their entrepreneurs enough, they supported their hobbies and makers. But the problem with that is that there is a limited amount of money you can make off of a hobbyist, because there are always going to be, you know, where an entrepreneur is somebody who can be able to support a community and be able to invest in new tools, and have all of those things in a creates, and then build larger office, you know, and be in bigger offices and support a space because that, you know, having monthly memberships have just a small amount and can't, it can be hard to run an industrial space with all of these resources on whatever. So having those those places for entrepreneurs, and that's where we realize it's like, if we point ourselves towards the helping entrepreneurs and helping small businesses go from like a small desk all the way up to a larger office and help them you know, introduce them into networking and funding and all of these things. Like I think we're we're a little bit more akin to an incubator than we are a makerspace. Except we don't take, we don't take that percentage of equity from anybody, we just want people to pay for space and join our community. And then that in itself, has so many dividends.

Definitely. Very interesting. Yeah, I've been. So I've gone to a ton of makerspaces. Because I find them quite useful. I just trying to be involved with hardware. And I often see they're incredibly underfunded, they're lacking, like, kind of like, the really knowledgeable people, like they'll get burned out, because they're helping everyone and then they end up leaving. And then often because of maybe the weird funding situation, they're very political often, which is kind of like stepping into a toxic environment, I just wanted to use a 3d printer, this kind of thing.

Yeah, and it is hard, we found that, you know, we love our maker community, don't get me wrong, I don't want to say anything bad about the makers, and the hobbyists who come and use definitely is wonderful. But entrepreneurs are a lot more hands off. Like, I don't have to teach the most basic, like, everyone, when you when we focus on entrepreneurs, and robotics companies, everyone is an expert in something, right. And this will even come back to when we are when we're talking about education side of things, right? Because it's very much a pure we a pure learning system as well. Yeah. And that if everyone's coming as a an expert in something, they've learned how to learn, right. And the same thing with a space where if people are coming in, they have a large expertise in this one thing, they probably they don't know how to do all this other stuff. But the fact that they can learn it and do it, well is something that is is very likely, and they don't you don't do a lot of hand holding, right? Where I find that with some of the makerspaces particularly tech shop, I found that they they had the their their staff were called Dream coaches. Right. But they were minimum wage, people who maybe learned how to use the machines a day before everyone else. Right. And, and the amount of help that ever all of the members needed on all of the machines and how to do things, and all of that stuff that wasn't part of their business model that was just supplied as your membership for free. And they're understaffed. People, right. So yeah, it becomes really hard to run a space when you are educating every single person, the best makerspaces I found are they do have ways like where you say are very community are very like, like politics side, because the community has to provide that. Yeah. Not, you know, the tears and not the makerspace variable. But you have to create the community that does that, in many ways. We've, we've done that to a large degree, because then that, you know, but it's no longer how to use the laser cutter, it's how to get your batteries certified for shipping, how to get FCC certified for saying, and that's where, you know, if we had created a space that was kind of like makerspaces for that, you know, it's a lot to leave handhold every single person through, so that, you know, I'm just continually impressed by our community of just how high level they are. And then because of that, they understand what it means to have a shared facility and it doesn't mean that we still don't get messes and issues and politics and all that

you know, it's when when a community is of a community of experts and everyone is kind of doing things that and learning to level up their businesses and their self and then being in that community of doing together the the the ability to share that is incredible. Right and where and the best makerspaces do that with the hobbyist level twos is they get their their members to Have other members and it's not expected to be like management teaches you everything.

Yeah. Let's see. So that I mean, it's a very interesting, I really liked the model. How did you? How did you come to this model of like so coworking has its perks, but it's kind of saturated by Upwork. Or it's, like hard to improve upon that. And then makerspaces have their kind of business model level issues. How did you come to this idea of targeting people, not not targeting people, but like focusing on entrepreneurs? As opposed? Like, how did you come on the business model that we've just kind of described?

Well, that from the very beginning, like we all saw what tech shop was doing, and knew that we wanted something more, because they didn't, they didn't serve the entrepreneurial like makerspaces don't serve entrepreneurs very well, right? Because it's like, well, it's got everybody's gotta have some time on the tool. Well, sometimes an entrepreneur needs all the time 100 tools, right? And you have to be able to provide some of that, that ability of ways to to work that out. And so we, from the very beginning, we were like, well, you know, I'm involved in hardware, one of our founders were involved in hardware, and like, this is, this is what we do and what we need. And so we were like, well, there are other people who are there, this is what a good space like, this would be great, because we were like, also, let's use the resource of from the building owner having the space. And so we built this all out from the carpets to the drop ceiling and everything, and saying, like, you need to have space, and you need to be able to have that customer group and find that niche. And that's where we really, we saw that this niche was underserved. And, you know, we took a big bet that this would be that there would be enough people here. And now you know, it's like we have a waiting list for most of our wonderful tables. And we're happy to hear that. It's wonderful for for that and we want to expand and we're you know, we are currently looking for for more funding for our round as well. And we're looking to put more Circuit Launchers out there. And specifically, the the tie in to education was is that after we built this community, people were like, Well, how did everyone here learn how to do robotics? Yeah, right. I want to do this, how do I do this? And we're like, go to school.

And they're like, well, but but that they're not teaching robotics. They're just there, you know, I what degree do I get? I think well, you should go get an A, you should go get a computer science degree in mechanical engineering degree and an electrical engineering degree. And all of

us learned business, if you want to do a stolen,

you should learn business, too. Yeah. And like, maybe there's not enough time in the world to be able to learn all those things. So we we said, we were like, Okay, we need a mechatronics education program, that immediately gets people using the latest technology. And the latest things in building robots is the first step.

And from a very pragmatic perspective to like, this is one of the things about having entrepreneurs and it like they probably won't be wasting your time, because they are, they have skin in the game, and their money is slowly depleting. And this kind of thing, while they're trying to get interest and grow. Like Time is of the essence for them. So they're gonna do whatever is most pragmatic for them. Well, that that was actually

the model that like, led us to this type of learning, right? But entrepreneurs are not necessarily our target market are the learning curves, for the learning side of it was because most of most entrepreneurs are too. Like, there's a couple things. They're too busy to do the thing like they can only focus on the thing that they need the next step. Yeah, so unless there's some type of immediate coaching or whatever that they need, then the business model really is if you need that type of doesn't like good design services and prototyping services, get them connected with other people in the network, right. But there's a whole group, if you want to work in robotics, and you don't have a job and you're not willing to like, be the entrepreneur, like I want to work for a company or I want to build a robot, you know, or I want to learn to get better in my job, or upskill or do those things. There's all of those people, and that's kind of our market for Mechlabs, which is it's our education program.

Mechlabs. Yeah, it sounds like so when you focus on the entrepreneurs from the perspective of Circuit Launch, it seems like it's a it's a bit of an exclusive community where you come in and you're an entrepreneur, and you are highly skilled in at least one thing, and you're good at learning and you're pragmatic, and you can pay the bills to occupy desk space. And so that's a good business model for circuit launch, but being kind of exclusionary. Now, it's like how do we get the other people in a position where they might go into this and that's the education program. You got it. Gotcha. I really like that,

that and then the benefit is is that we are filled in a community of mentors. All of those entrepreneurs are, you know, they're in the community, they've done it they are, they're on the bleeding edge of technology and doing cool stuff, right? So it's very easy to find someone who has a lot of skill and expertise to come in and help people and become mentors in a lot of the stuff and to be able to get answers from too for sure, if I have this very hard problem. Now we've created this community that that serves everyone, and they've been serving each other, and a lot. And now it's being able to also serve the, you know, the students that want to come in and be able to learn how to do this as

well. Yeah. How do you incentivize entrepreneurs to be mentors? For this, because you were saying they're very busy. And I just imagine that's a challenge. Or maybe you pay them or maybe it's part of the like, you get your desk at half off, or something like this, if you're a mentor, there's

obviously incentives to self to mentor. I think that in general, you know, so yes, we do pay our mentors that come in, but we have a very different model, like we're not looking for instructors. That's the big difference with our education program. And Mechlabs is a built to learn it program,

so the Mechlabs is the building to learn it program. The idea is, is that you come in and you build a project, if you want to learn ROS, you either pick a project that has ROS in it, or you join a team project that has ROS in it, right. And then you build it. And then as you go along, you're you are either individually or in a team responsible for figuring out how to implement ROS. And so there's the side of that is that then what happens when you get stuck, right? That's why you join a program, traditionally, people just say, well, we're just going to teach you everything you could possibly need to know in an A to Z way. And we're going to start at A and it doesn't matter if you're on B or C and you need it, you need D and other people need to have like it doesn't matter, you're just all going to sit around and wait till you found the information get taught to you. And or in a book in this process, right. And that's what an instructor does, right? They have a curriculum. So we say no lectures, no textbooks, no curriculum, we say, what will happen is the way you're going to learn this, you're on D, someone else's on F. And then this is where it remember when I made the tie that everyone is an expert in something, people all people are that way, we are all human beings, we are all experts in something, we've all done something cool and can share that. So that's when you get the peer learning. So then people come into our program that when they get stuck, they then have an entire team of people who all have a ton of expertise in a lot of things that are in the program and can share their expertise. And, and we have, you know, for people who are like for really deep problems, this is where we can go to like our community of like, of experts that are working on really cutting edge technology and much more deeper technical stuff that is there. And then we ask them, then when they mentor, we're not asking them to build a curriculum. No, they don't need a PowerPoint presentation. They don't need they just come and help. Yep, right? Come for a few hours look where to go and be like, Oh, this is the wrong thing. Exactly. And so they meet zero preparation, their effort and their time commitment becomes a lot more useful. Right? And the and then of course, mentors are what they really like when you're mentoring, especially in Silicon Valley. That word means like giving back because of all the all the mentors and all the platoons. Yeah, right. It's not to say we don't pay our mentors for that. But it is a you know, it's it's expected that this is a community we're all giving back. And then the best part is, you get to work with really bright, upcoming roboticists that you can hire for. Right? And that's a really cool thing when you can say, Oh, wow, this guy is, you know, he's a Python genius, but he's never done an embedded software. Right. I bet I could help him a little bit along and then jump in, and he could help my car. Right? Yeah. Right. So that's where this that when you're all thinking about the ecosystem is what we're building. We're building an ecosystem of entrepreneurs, and the way to become entrepreneurs, the way to become employees of companies that are good and and to accelerate your career and close that loop. Because what we've seen, you know, one of our companies that are here is Silicon Valley robotics. They're an industry organization and BP probably know, the Andhra and all of that. And they, they're amazing. And they've been talking to a lot of the all of the companies that are in robotics, which unfortunately, all kind of are very siloed when they're not in a community. So it can be very hard to know what they need. And it can be hard for them to say, Well, what they need for from employees. Right? Yeah. And what what they're finding is, is that most of their, their applicants are mechanical engineers, right? But what they really need is some as more and they keep hiring, computer science degrees, their computer, they're, they're doing hiring programmers who have somewhere along the way, figured out hardware, right. And so there's, there's a real disconnect of what you can learn in school, and how you can prepare for a job in robotics and actually get the experience and the portfolio and the hands on of all of that. I mean, that's, that's been a real change. And what we've seen in, in people looking in robotics, to accelerate their skills and to get jobs and to be able to learn these things is that there's a disconnect from what industry needs and what traditional education is teaching. And we want to bridge that gap. We want people leaving our programs being like, Hey, I built the the, you know, I integrated the robotics SDK for these servos into a ROS node. And now this whole robot is made with ROS Yeah. And that's my portfolio and so you apply to a job that's like, you know, needs ROS experience, right? Everybody says, I need ROS experience that's on every little thing. But how do you get ROS experience what is out there building a robot, and not just a, you know, a turtle bot, right? We need you need to, to get deeper into some of this ROS language and, and on different things to be able to really be useful on that. And so that's where there's really, like, there are some great programs out there, but the hands on component is what's missing. And so we want people leaving with literally the like, this is what I built. Here's a tutorial that I wrote, here's my GitHub that shows what the code that I did. And there's me instead of just a resume that says, I know some ROS right, and then no one knows what that is. And that that provides people who are looking for jobs, killer way to get into the the industry.

Definitely. Yeah, I can think so I've done some hiring while at open robotics. And it is funny, because it's like the first thing that I go to, it's not like I couldn't care less about the resume. And this is just my approach to it. But go right to the GitHub, and then look at kind of what they've done and try to sauce out what their commits are, and how much of it was just like, like, what they understand from how they're doing it. And that's really nice to be training people in very pragmatic ways on an actual project. I really liked that approach.

And then they get to learn, like, well, how to use GitHub for for hardware. That's, that's not an easy thing, right there. And, and how are all of those things? And then we, you know, we asked people to like one of the minimum requirements every single week, everyone has to write it tutorial. And so they start learning, good communication skills and demonstration, documentation skills, and all of that, that we want to help them demonstrate.

Yeah. Let's see. That's really interesting. One thing so this robot behind you, I'd like to introduce that robot. It was one Belcher in a project by some students that went through this correct.

Yep. So this is Ricci. It's based on an open source robot robotics platform that was developed by Paul and robotics. They, they actually sell the robot that but they've completely open sourced the designs. So we were the first group outside of the developers to actually build a fully working robot, or off of reaching, right. So we originally, so the, there's a lot of, it's kind of grown as we've gone, but we started with the torso and the head, and one arm, and in 12 weeks, we went from not knowing anything about this robot to fully functional working robot, which was amazing, like, and these are students this is not like, you know, some of them had very little robotics experience, and some of them had a little bit more so in 12 weeks to build something that was incredible. Our second session with with Ricci, everyone wanted to work on the software side is the platform. I had, of course I bought all the motors for the extra arm, and everybody wasn't interested in doing the arm that okay, which is fine. That's our program. If you don't like you get to work on the things that you want to work on. It's a match Not the things you it's not a, it's not like that horrible group project you got in school where you're like, Okay, this is the thing you got to do. There's one person who's good at it, let's just make him do it. Right. Yeah, like, that's not what our program is ours very much like, you might be a Python, you know, a whiz. But you want to work on motor control systems in the power, you know, in power delivery and 3d printing and CAD, well, that's great. You provide your, your expertise to the rest of the students wanting to learn Python. And then the other people who have a lot more experienced the MES that are just graduated, they have a lot more experience in some of the, you know, the CAD and all of that. So that's how, how that gets trained. But so our second session, I built the arm because nobody wanted to do it. And so, but everybody else they did, they created, they put it on ROS, they it was on this thing called loops, which was kind of a semi open source, not like it was an odd thing. Never heard of the pollen head choice. Yeah, it's it's a, like a distributed microcontroller system that, you know, has a lot of potential, but because no one in the world could get the microcontrollers. But, Paul, and we were like, well, let's, you know, let's put this on ROS. And like, use the Dynamixel control system. Like, that's great. That seems like to be a good thing. And so we put them over that, put them on a mobile base, and then he became a concierge robot. And he actually walked around told jokes and gave tours and told told people in the pandemic, if they weren't wearing masks, that they want to put a mask on. Oh, funny. So that was the second the third session we did again, Ricci as the platform became a very deep object orientation and grasping techniques like work, so they they rewrote a lot of the control systems for for the the motors, integrated all through ROS worked with April tags, and you know, criminal, you know, creating a computer vision and learning how to be able to grab a block and we set it up so that, you know, if you picked up the block, the robot grabbed it and put it back where it was cool. And so that's kind of their their session is that was a smaller session of, of team. Yeah, there's a lot of became an amazing platform. That's awesome. I like and it's all open source, we publish all of our stuff, and all of the thing and so people who are interested in doing it, and that's a really important component that we found out for our program was the open source part, the open source part. So we first started, as you know, we're growing and building this as we go and figuring out what we wanted our very first pilot was to bill to take a already existing coffee robot that was working, it's a little bit you've seen our coffee robot, definitely. But it's basically the three axis palletizing, two arms that grab cups and things and then put it up to a big super automatic espresso machine and then delivers the cup, right. And it's all done on ROS. But it was done developed by a couple of Crazy Russian developers that are awesome. They were there interesting. It but it it needed a lot of work for for design. And so the person who owned it wanted us to upgrade it, and they're there. And we found that trying to get students to one manage client expectations, too much being in a little like an understanding what they really needed and all of that and ended up becoming really too. And then reverse engineering something is often much harder than just building it the first time. Oh, I'm sure right. And so that's something that I think we've all learned as you go along. But in the beginning, it can be very, like enticing to be like, Well, I have this thing, I can just improve it right? Sometimes it's really just better to kind of

And so that was our very first session, we found that having an and having a closed, like we couldn't publish any of our work. And so ever since then we were like No, no open source right away. Like all of our projects, all of the things need to be like publishable because then you can manage, like you benefit from a community of people most of the time that are working on the open source group. You know, documentation is always hit or miss with all projects, but particularly open source at least, at least they have more information out there than something that's totally was right. Yeah. And so you're gonna look at the code doing as much reverse engineering, you can look at the code, you can download examples, you can work on that. And then you you have a place to be able to say like, you know, that something, at least somebody has done something, it's worked,

right. And you can get an idea of the community around it, too. So you can see if it's supported or not, or like will other people who did

this with no community, like Yeah, he had zero community at first. And so now we get tons of requests all the time, be like, Hey, how did you do this? Or here's, you know, we want to make this too. And so we can then cut Pretty to the community. And then the benefit for that is, is then all of the students learn to, you know, to better documentation and how to better, you know, support an open source and how to work in a community of people and how to do project management and all of the soft skills and kind of important things that you need to know, for running and being a roboticist company, right? Sure, all of that is available in the, you know, the in between building

stuff. And also, I mean, it's all like, the skills are also just very valuable, in general, if you want to do anything. So teaching them how to do that, like, I mean, I use Git every day. And so like learning how to work with people on that, and get feedback and implement the feedback and this kind of thing, very valuable. So that's so cool, that you're exposing them to all of that. Let's see. So you mentioned that they do tutorials for this, or actually, before that, how do you how do you scope a project? Like how do you decide Ricci making it so Ricci grab looks at a fiducial marker, grabs a block moves it somewhere? Like how do you pick a scope? How do you make it not too hard? Or not too easy? Given the students that you're working with?

Yeah, I mean, that's kind of been the interesting thing was, when we had a really, like, scoped out project, we found that we often had more trouble with that and reaching those goals and figuring out what what could be happening, what couldn't happen, then we do in our current system. So currently, what we try to do an overarching project idea whether you know, some of the things on the blocks right now is like, we'd like to do one of the millions or, or improve on the millions of open source Quadra pets out there, we'd like to, that's one of our ideas, we'd like to do some more. You know, like, autonomous driving, cars and tracks, and like the RC car kind of thing, like, those are some of the ones we like to do. We'd like to, we have a Boston Dynamics spot, we'd like to put him on ROS. That's another one. But so there's a perfect example of, you know, we'd like to do the ROS but we'd actually like to, you know, we need to choose a project that one will appeal to a bunch of people who are, are there. So you have like, we have to make it fun and interesting and exciting, right? So it's like if if our courses are, you know, learn inverse kinematics, we will get a small percentage of people, right. However, if we can be like, you know, build your own juggling robot, right. Yeah. But you know, sometimes, you know, you put that out there today. And then as you so let's take that, as example. Like, we're gonna do a juggling robot, right. Okay. So we have to one make sure that we have the budget know what, you know, what kind of actuators we're going to need, what kind of things to be able to even capable do that. And then we put like, maybe that's where we start, right? And say, Okay, we're going to build a juggling robot. And then like, all robots and all companies and everything that you do, you have to say, Okay, well, we're going to have to learn a ton along the way. And then we're going to change the scope as where we go based on what we have and where we need to be. So maybe that robot in the end is only throwing the ball up and catching it, right. And then, you know, maybe we get two hands to do that or there, but it's the beginnings of like, it's juggling, you know, we're, maybe the next session picks it up where we left off. Yeah, right. And then says, Okay, now we want to balls, and then we need to be able to have a vision system for tracking. And we need to be able to do that. And then you implement that. So the the project becomes, you know, make a juggling robot several sessions, and you make broad progress on that. And then part of it is, is to like, we don't, you know, unlike a business where you say, Okay, I'm gonna go hire the most capable people I can find to do these very particular jobs. We have the opposite problem. We want the most capable people in different things, not doing what they're good at. Yeah. Because unless they want to do that, like if people really, they're like, they're really good at this, and they just want to get better at it. Great that we have you too perfect. Yeah, but, and we get a bunch of that. But in general, like we want, if you're really good at something, you know, diversity, probably needing to know some other things and wanting to learn those things. So let's get you focused on that. You can help the other people who are not as good at these things with their Python, if you're a Python coder, or you know if you're a mechanical engineer, they're your cat. Like, there's such traits Yeah. And so the scope really happens based on like, who needs who needs to do what. And if we lock ourselves to the like, while we must get this end product done, right, then it isn't as efficient for for everybody, like, we want to hit our goals, but we're not afraid of also changing where that scope is to say, you know, so that it is achievable. And that you can then learn the things you learn, which is way more important than getting the end result. Yeah, but and so we do sometimes re scope a project.

Like that is a great example. Yeah, yeah,

juggling robot would, you know, maybe it's not a three ball juggling robot that's doing this. But you know, we've developed, you know, one ball and develop the beginnings of a vision system that can track those balls and catch it on another side, and then the next and then it gets bigger and better. As you go along. It's, it's more interesting that way, too.

Definitely. And also really nice for people learning. And also seeing what's possible in this kind of thing. Like, you say, juggling robot, and it's like, oh, that sounds incredibly difficult. But it's like throwing a ball up and down. Just one still difficult, but not like incredibly infeasible. And then like, maybe you go from one arm to the other, and this kind of thing, maybe it's

like air actuated tubes that are on a Trump rail system, right? Some way. Like, you can scope that in different ways, you know, trying to get Ricci to do juggling would be servos are just not, they're not going to that. Yeah, and so you do have to, and part of that, I think is where the scoping of things is actually a really interesting problem. Because you don't, you don't know how to get to the end of the thing you want to try to say this is the thing I want to go do this is you know, what I might need along the way, that's the one thing that you can't do on your own easily, right. That's why you need to join over with mentors, because a mentor will say, hey, you know, don't waste your time using these servos for juggling robot, and then you've just wasted six months of your life trying to get this robot to juggle. Yeah. And so that's why, you know, our programs are like, you know, we have mentors, and we have advisors to say, Hey, this is feasible. This is, you know, why don't we start here? Why don't we scope this in this way? You know, because people come to us for our individualized program, saying, hey, I want to make you know, we had another person come in and be like, I want a trash collecting robot, you know, is what I'd like to make. It's like, I'd like it to be a robot on wheels with an arm that picks up trash, and puts in there, and this is their first project that they had never done robotics before. Yeah. Right. And to have an expert to like say, Well, okay, you need a full base that can put around at least 25 pounds, right of like weight plus the weight of its own robot. And then if you're going to build some type of an extension arm system, you have to be it has to be able to deal with the mechanical torsion and the the reach and the counterbalance. And then you have to be able to carry all of that, like, that is not a it's not a first Prime first robot. Yeah, for sure. And so you say, Okay, well, that what could we start off first? Maybe we could put a trash can on a mobile base, and put a speaker and ask people to help

like that. Yeah, right. But there's a trash can

robot that's like, can you put a little mobile base, and then we can buy really cheap cheap powders and cheap things and, and that little speaker, and then it'd be like, Hey, can you help me pick this up? You've just created, right, it's like, so being creative with that scoping also allows people to choose the project that is right for them. And that's the first thing you do if you're not joining a team program with the project is kind of already scoped out. Our individualized program is you come and you talk to our advisor, and then we help choose a project for you that will achieve your learning goals. Yep. So if you're Where do you want to learn? ROS? Do you wanna learn motor control? Do you want to learn? You know, what are the parts of the robotics you want to learn first? Right, yeah. And then we kind of scope that project for where people are at and to their budgets to, you know, it's like, it's like, yes, I want to build an autonomous car, like, Okay, can you do you have a car? That's our sensors? And like, do we need to buy that? Yeah. So I mean, all of those things come into account. It's why robotics is so challenging, but in the community of program where we can support those components, and they expenses, like on a team project where you know, reaches was $6,000 worth of parts, right? Yeah. So, you know, then that becomes amortized, and everyone to work on and make something really cool.

So one thing that strikes me with this, it seems like so it seems absolutely wonderful, like what are what an absolutely great way for people to learn. I'm wondering, I'm thinking about how it would scale ill, because one thing that it strikes me about, or it strikes me about it is that you really need a knowledgeable, engaged instructor or mentor, I suppose, like someone to facilitate this whole process. What do you call them? Because they're not they're not exactly maybe their mentor.

So, you know, advisor is an easy advisor do that. But we actually created as we create a system so that the mentors and advisors can help run this help run the sessions. Yeah, right. And those sessions are lead. They're very structured in like the what what you do, you know, you have, like our team session, we have a project management, like, you know, Monday, we do our project management, we talked about all the things that were done, we follow kind of a scrum platforms, we've divided we choose our sprint, we get all of the things together. And someone kind of runs that. And we've played around with actually different people running that each time. Oh, I like that, which is also really helpful. And some things or students Yeah. Oh, so the students often run the sessions, right. And then we have collaborative work sessions where everybody's working together. And then we have like a show and tell day, where people are actually, they show what their work is, they get feedback from in person, all of that kind of stuff. And, you know, what's often what's amazing is is though that, like it's with mentorship, everyone thinks like, Oh, I gotta have that really, really highly. It is accessible person or intelligent person to run all of those meetings, and all of that stuff. And the structure helps with a lot of that. And then peers, because a lot of the expertise comes from mostly from their peers, because again, everyone's an expert in something. And the mentors spend less time. And they also don't teach like mentors don't lecture. There's no one anyone lecture. So we train our mentors to simply say, to help them find the thing that they need the next step, right? Because in a world where you can learn anything on the internet streaming thing, it's not, you know, where will you get the information from? I must have the person in the information in their head, it's how you find that information becomes the real challenge, right? Yeah. And mentors become less than the purveyors of information and more the guidance along your own path for you finding the information. Yes, like, you know, I think of my exploration of, you know, I've been building an espresso machine on my bicycle. I'm in middle, like, I'm in the middle robotics area, like I'm an advisor and the technical mentors, but I'm also loved, I have a passion about it, as well. And I'm not an expert in any one thing, right? So I was learning some basic, like, learning to do certain basic electronics, really, I've done a cabinet on maker stuff, but I've never really done basic electronics stuff. And so I was learning, the the beginnings of putting a whole bunch of sensors in my espresso machine, because I'm also a coffee nerd. And I was working on learning how to build a PCB and, and how to wire this all together. And I was like, well, so then I ran across this problem that like microcontrollers. Take, have logic, voltage and power supplies aren't often different than that about and so like, but I was like, so do I need a step down converter? How do I get the signal from my sensor to the voltage and still keep the signal going? And I just had, I was like, how do you search for that? If you don't even know what you're searching for? Right? Yeah, obviously, we had somebody with more electronics experience, like know what you need to look, it's explore voltage divider, and then a bi directional voltage divider. And that's that circuit that was like, Oh, great. They gave me the jargon, that I could go Google to find. And then I can learn it myself. Right? They didn't need to sit there and explain Voltage dividers for me. I don't need that. And so what it does is it puts less like previously, when you talked about how do you incentivize other entrepreneurs to be mentors, is if you take this impetus that they have to explain everything, and do everything for the students that instead all they really have to be available. This is like, Hey, have you explored the concept of a voltage divider? Have you explored the concept of, you know, the Ohms law like what is this is kind of the thing you need next, and then the student goes, looks it up, implements it, and they have a problem with that. And so that's where the change in things and in fact, our mentors, we're not looking for people who are experts in everything. What I'd much rather have in mentors and teach students how to do is to be to learn how to learn. Our best mentors are people who probably could learn the thing that you The students were doing the day before. Right? Like, oh, you're you're, you know, we don't get experts in everything. There's no expert in everything with robotics, right? So instead, I'd much rather have somebody who can look up and say, like, well, I've got the basics of ROS down, I've done a little bit with machine learning and computer vision. But I bet you, we could probably figure out how to integrate a point cloud and be able to get a depth map and be able to create that kind of a thing. Right, you don't have to have someone is that the but a mentor will be able to help lead the students and then they do it with them. And then they all learn together. And that's kind of where I feel like I'm, I guess I'd be considered a mentor, also, because I'm also often in my groups, and learning that, you know, but that's the real change in it. And it takes a a thought change a paradigm shift in this, like, I'm gonna sit here and wait till someone teaches me exactly what I need. Right? That's where what education has taught us, like original education is taught. Yeah, we just have to take the class to get the thing that we eventually someone's telling us what we need. Yeah, it's

it's active. You say, this is the project I'm making? What do I need? Oh, it's run, you know, it's computer language. It's got a, you know, it's running Linux. And Oh, guess what I can control with Python. I guess I should go take a weekend course in Python Crash Course and then write a ROS node. Right? Yeah. And that, that's kind of and then I mean, that's kind of how I learned Python was like, hey, this robot was cool. It ran on Python. I guess I should learn that. But I had not been incentivized to learn it in my entire life. Because I was like, Well, why I don't like websites, I don't want to run a write another website, I've got HTML, that's fine. I don't want to write back. Like, oh, he does cool things, I want to learn Python. And it's the same kind of thing with Project learning where we've been, you know, I'm sure everyone who's listening to this has done this in their life is like it worked on a project, they haven't known something, so they had to go learn it. And if you have that project, like if you're working with robot arms, you know, the linear algebra with for inverse kinematics and all of that stuff, that's a thing you need to kind of know, a lot of times. And so that was something that, you know, all of a sudden, we had everybody like looking up and learning doing doing like linear 100 projects on the side, because they wanted to, to learn those things. That you know, so we believe that instead of going, starting from A to Z, and trying to start with all the foundational you've ever you ever need, and then you will immediately forget and have to relearn anyway, no total, we just say, hey, when you get to the point that you need this, you will be incentivized to learn. And then all of the foundational knowledge that you need, will start coming in and you'll be incentivized when you're actually using. It's a different way people are, you know, they're not, they're not these experts in fields, they're people who got a little bit of everything can probably figure it out along the way.

Yeah, I really like that. It's, it's kind of it's a flip in the hole thinking about how to learn and how to structure groups to do things, which I really like. It's like, you put people to work where they're motivated, because they think it's interesting. And you have them in this group, where they can ask questions, and they can contribute where they want. Yeah. And so because of that, the mentor is really just the person that gets them unstuck. Yeah, occasionally, and that's really low overhead for the mentor, you just need someone who's like, good at thinking, to be the mentor. I really like that. It seems like a great structure. It's like a stable structure for a team to do a productive, dude, do something and learn a lot. That sounds great to me.

Yeah. And it creates a real interesting thing with like, you know, everybody hated group projects. I know I did in, in school, right? And it was because the whole power structure in the way that you were doing things were was really flawed. You know, it was like, Okay, you guys all don't want to do this thing. And I'm gonna make you do this thing. And I'm gonna put you to a bunch of people also, who don't want to do this thing. And what's the easiest way out is you give the person you think that will know, like, who won't say no. And who doesn't want a bad grade on it, you force them to do all the work. Right? It's it's horrible, like social experiment, that bad incentive structure for sure incentive structure, right? Where instead our group's people that come in, and it's like, well, you get to work on the thing you actually want to learn, which is great. And then you become motivated, motivated, you do a lot of work. And if if there's literally no one that wants to work on something, right? That we figure it out, either, you know, everybody gets together and they do this one thing or that thing to get over the hump. Right. Yeah. And we all agree to it. or, you know, use free scope it like, Why does a robot have to have two arms? Yeah, it doesn't. We just bought all the parts. And so I was like, Well, fine. If you guys, you guys don't need a second arm, but I, well, I bought all the parts, so I'll build it for you and make it happen. And they were more interested in the software and the, you know, the control systems rather than the actual hardware at that point. So they weren't forced to do it. And that's really a crucial part is there is no like, it can be flexible, a project is flexible, and it can be developed in a way that everybody's efforts are working towards the thing that is awesome. And then then the things that aren't as awesome, you at least are motivated to do them because you understand why they're important.

Yeah, I think I was thinking about it just now. And it's, I was wondering about like the unsexy tasks, in a sense, like, as you're saying, and what it seems to me is that so say there's this one critic because often the unsexy tasks might be very important. But people don't want to do that. Maybe it's like developer ops kind of thing. And so what I see or what I'm thinking is that with this structure, what happens is everyone learns basic skill, or everyone learns skills in what they're interested in. And then they get to a point where they're fairly good at what they're like they've learned a good bit, they're fairly invested in the idea of continuing and then on their own, maybe, then they can go and they can learn some required infrastructure or best practices or whatever it might be. But this has kind of prepared them by giving them enough skill to get somewhere interesting. So that they might eventually go over the unsexy task, go and complete that one.

And because it's a project, right, you know, it's like if the, if the unsexy task is like, you know, a power control system like, well, nothing is gonna run unless you have so that everybody gets pretty motivated, even for the unsexy tasks to battle notion when it's a bottleneck and that they won't get there. And then and then you're all working collaboratively to split up the tasks that no one wants to do. Right. And, and that people volunteer and actually help out with that. And so And there's usually somebody who, who is excited about learning, like, it is robotics it is, and somebody understands why, you know, or at worst, there's someone who's really good at it, who can hammer it out way quicker than anyone else, then everyone else. Yeah. And then they help other people do that really quick, you know, so all of those things are your tools to be able to create a great group and actually succeed in a project. And, and learn a whole bunch on the way. But the whole point is, is unlike business, where it's you, everybody has their silos, well, what's really created. And that's a bit of a disservice in the robotics industry, what we see is, is a lot of our students are coming that are, you know, automation, engineers, QA, it's all sorts of like, deep company, like people in larger robotic civic roles. Yeah. But they want to learn one's role something else, because they don't have any of opportunity to do that at their work. Because, like, the way companies are set up is like you don't give thought, you know, tasks to somebody who's not good at them, you give them to this person who's really good at them. And then that's all they do. Right? But I mean, you know, it's it, as a business side of things in my brain, I'm always looking for something that somebody might excel at, that they don't currently do. Right? Because then you get happier, better employees that are learning more things, rather than giving only the things that are to the people who are good at, like, we get excited about learning, we want to grow by employees doing new things, and what what else might they be good at that they're not doing right now, then they grow into new positions and stuff. And it's the same thing, you know, with with this group, but it but when you have a lot of people coming from some of these other other companies that aren't doing that they're hungry to learn all the new stuff, and we want to we want to give them that opportunity to to learn the things that they're not good at.

What do you think would happen? If so I understand from a company's perspective, that desire to specialize people and have them do the thing because they're going to be really good at it. And also, you can kind of pit pay them like the minimum amount because the majority of their time is on the most specialized, highest value added thing. Whereas if you pay them to learn about something that's irrelevant to whatever it is that they're most specialize on. You could think of it as last time, but as you're saying, maybe it's they're pivoting into a thing that they're really really good at but they're very happy to do. But I just What would you think if companies were to adopt this approach where maybe like, I don't know, there's some things where it's like 20% of your time is your own for side projects or something, but what what would a company look like that did this? And what do you think the outcome would be?

Well, I think that, you know, as a side thing, like, we have a whole enterprise side that we would love to be able to do and have people doing that. And it's like, that's a really easy way that they can provide that for their students, or for their employees be like, Hey, you guys want to learn to get trained on a whole bunch of other stuff that has nothing to do with it? Like, let's put you through Mechlabs, and then not only you're going to gain a lot of experience, be able to help, and really pull this back to your teams and new a new way of thinking. So that is something we want to provide for companies and enterprise as as well. But I didn't realize that business model. Yeah, I mean, but I do think that that's like companies getting someone very specialized is it's important for for speed and effectiveness, right. Because obviously, if you want to build something and get it to market, you need to be really fast. And and the fastest way to do that is to get a whole bunch of people already know how to do it. But no one truly knows how to do it. If we're actually working on good technology, right? It's all new. No one's done it before, if it's exciting, cool stuff. And so what we want to do is we want to foster the, the AI and we want to foster companies who realize that it's not what the skills that people know, that will make them successful, it's how well that they they can learn. Right? And that's like that metric is something that, you know, we really have to train our companies to look for. And we have to train our people to be able to demonstrate. And that's one metric

how how, how easily, like how quickly you can learn to learn?

Oh, yeah, definitely. I think it's so valuable, right? For sure. And it's something that by keeping that muscle strong, it seems so valuable.

Absolutely. Because you want somebody who can figure things out and learn how to learn a new skill yet, if you put them doing the same thing all the time, that just that they're good at, and they aren't as good at learning. You know, you get your job done, but you don't, like succeed if that job changes.

Yeah. And I think also over time, if people are not engaged in their work, they start slowly falling behind, because they were really specialized ones. But the jobs responsibilities are a moving target, and they're moving away from their core competences. Yeah. So

you have to if I'm not learning something new, or like, growing in something that I'm doing in some way, I get really bored. Right, yeah, that's why I've been, you know, I've been a weird employee to hire in many ways, because I went through so many things that are so many has, like my resume, bizarre looking, right. I have a degree in ethnobotany. And I do robot interest now. You know, it's, like, what, but I know, it's bad. And so basically, I just created a, like an education program that can justify the way that I like to learn. That's really what we've done. I just feel like, you know, I'm good at learning things. And I can get to that, like, 80% of competency really quickly, pretty quick, you know, and so I wanted to be able to help people who are interested in not only that, like learning that last top 20%, but also the people who want to get up to that at that first 80% quickly. And, you know, realizing robotics is something that's changing so quick. And like the the last five years, the availability of hardware, that at a low price point that you can start building at has just exploded, right. Yeah, think of all of the like, you know, it's like, right now we're getting little, the, like the Itsy Bitsy and the feathers and the you know, all of the cool stuff from Adafruit, the microcontrollers that not only now use, you know, Arduino and see but they also you could do circuit Python. And so basically, you can take a weekend workshop to learn Python, you can you can take a microcontroller with and use that Python on it, you know, and then in a very short time, you can be writing, we're doing robotics code, and bad code, and making sensors work and building this stuff for you know, so cool. You know, so much less than what we used to have to pay to get into robotics, right? You don't have to have a platform like Ricci to understand robotics anymore. Like you could there's so much more remember when bait like if you'd wanted to make a robot, just a simple base with a couple of wheels, and they hundreds of dollars, you know, and now you can, you know, obviously you get what you pay for it but you can You can buy a $30 kit on Amazon and have a base of a robot that you can put the Asbury pie on, and put ROS on and then beat then put a camera on and you know, under $150, you could actually be having a full like ROS implemented computer vision robot.

Oh, totally. Yeah, no. I just, I just spoke with our friends from Meg Dang, who does the spot mini looking robot mini buffer. And like, that's a quadra pet for $500 that has pretty sophisticated sensors and a Raspberry Pi. Like, that's so cool. That's totally new, like buying a quadra pet at an affordable price. Exactly. Like, unbelievable. Yeah, and you're right, yeah, the explosion of hardware, it's

moving so fast. Right. And right now is the time to get deeper in robotics or learn other things in robotics, because it's so much like the availability of learn this stuff is finally to anyone, you don't have to be, you know, a researcher, you know, when million dollar lab to learn, you know, inverse kinematics with a with arms, you know, 3d printed with a few few stepper motors, and, you know, you could be learning it for less than than $100.

Yeah, it's not going back to thinking about corporations or like larger businesses and having them do something similar to your courses. One, one thing, one challenge that I could imagine is that if the people don't want to be there, because you have, it's sort of a biased group that comes to you for these courses, where they're all really engaged and very excited to do it for themselves, like they're literally paying their own money to spend their time learning and working with you on some projects. How do you imagine it? Would I just What do you think about the idea of people having their company send them to this kind of time? Where they would work on something in line with the projects we've been discussing?

Yeah, absolutely. I mean, the part of it is, is that, you know, as we have to make it fun, we have to make it interesting. That's kind of the point is, is that and that's scoping those projects, right? Yep. So 14 projects, you know, we do have to make a fun and interesting project that people are going to be excited about, right? If someone really doesn't want to be there. Like, we can also think can just sit the corner and read their phone if they want, like, I'm talking. Like, if they want to contribute, they can. And the way our programs are, is there's no one's relying on like the fifth person who's breathing his phone to get the job done. Right. You know, and so we did a program just yesterday for a Brazilian Innovation Tour Company that that brought in about 3030 students all have different corporate backgrounds, who had not no robotics experience, per se. And we brought them in, set them down on a little platform, which is a I don't know if you've seen their polo zumo bots, they are.

Yep, use them as like a sumo thing. Yeah. Robots,

but they have an IMU they have proximity sensors, they have line following they have, they have all of these things, and an example library. And so we basically set them up, I made a quick tutorial on the, you know, on our wiki, and I said, you know, this is, you guys are going to figure this out. So you're going to learn how to connect the robot, you're gonna learn how to install your IDE, you're gonna learn how to, to load it up and understand that all the things that you want to pull your hair out with Arduinos. And like, I don't like it, the Comm port, where do I find the library. And so we made some of the tutorials to make that easier, but we put them through the paces, and then let them explore all the examples. And we said, hey, there might be a fighting robot example, in there somewhere, see if you can figure it out. And they all did. And then we let them decorate the robots. And then and then we had a big tournament of a battling, you know, bots. And so these, you know, and they got a chance, if they wanted to get into the code and learn a little bit of coding, they could do that if they wanted to play around, you know, with the hardware, like they could do that. And so that that's really the thing is, is to like, you know, aim it at wherever, you know, we're not going to get them into the you know, the deep math and deep coding of stuff if it's if that's not where, where they need to be. But having a cool product like if you are Bible is the project, you build it to learn it. If you get a good project, there will be something there that will interest most people and if it really doesn't interest them at all. It doesn't hurt them to be on their phone over there to help in any way that they do. Like we often we occasionally have students that that fall off the, you know, fall off the beaten path a little bit and so that we have to pull them back in, or they don't contribute as much. But the way it works is they get what they need and what they put in.

Oh, definitely. Let's see. So you were speaking about tutorials over earlier? Can you tell me a bit about having students? Because it sounds like it's one of the like, few things that you're taking more of an active stance and encouraging students to do in the program? Would you tell me a bit about that?

Sure. So a lot of it is is like understanding the process of accountability, right? With a project based program? The big question is like, Well, why don't I just do it myself? Right. And rightly, so if that's like, we want you to learn it yourself. And we want you to grow those things like that. And a lot of people can. But we also want to offer the points for like, a, when you get stuck, you have mentors, and you have people who can help you, right. And that's what you don't have doing your product on your own. And we all get stuck, right? The other side of it is is the, you need some kind of structure of accountability, right? We all know that we were, there's no way that we're going to continue going to the gym, if we, if it were a pay by the day kind of thing. Right? The fact that we've paid for them on and we have to go to the gym, that's the only way that really gets us to go to the gym sometimes, right? And so you have to create some levels of structures of accountability. And so documentation is one of those things that we just found. You know, I'd like to say everybody, but there I have some people that like I love documentation that like good to help us with, right? Because most people don't do well with writing documentation. Right? They're great on building stuff, but they don't want to document it. And so part of the, the learning process for, you know, the classic thing is, is the, you know, show and demonstrate and then involve the other person into learning, like, that's the classic way of teaching something, right? Yeah, well, in this situation where, you know, it's a little bit flipped, right, you're learning it along with them. It's like the, the demonstrate and the teach someone else, what you're learning is part of that documentation process. All of those put together creates accountability, it creates a ability for people to ingrain what they've learned, because they have to explain it. And then it's documented so that when other people need that information, it can be there, as well as when we need that information. You know, they say documentation is a love letter to your future self. Yeah, definitely. It is. And so it's super important. And so we that's, that's one of those unsexy things that we, you know, we require people to do. And so that that's just one really important thing we found that really helps on so many levels, that we want to make sure that it's it's part of every single person's like, kind of requirements to that.

Are there any other requirements that you have? Or is that really like? I mean, you show up at certain times, and you have like, these are the hours we'll be all together. But other than that, is there any real hard structure in the whole program?

Well, there's a lot of structure, but requirements, like, don't have any other requirements. We don't have any, like, you know, school is filled with prerequisites, right? You can't take this unless you've taken this and you can't take this. And, you know, I don't know about you, but I opened right up to the back page of the manual. But I want to take all of that, like I really, four or 500 classes. That's what I want

to take those interesting ones. Yeah. Why do I have

to take Intro to Computers? Like, really? Like, I've been using computers, thank you. And like, so we realize, like, there are no prerequisites we do for our team programs, we do choose people that have a we need to have one skill in strong the team that not have been strong, but you need to have a bear like your competence, you have to have some competency in one of the fields that is needed to complete this project. And so, and again, you don't even have to do those things. But we do want to piece in your resource for the group. And so we try to match people in that and if there's really truly a spot that has no competency in that area, that's where we'll bring a mentor and to be able to help sense that there. And so for our team levels, it's the our one requirement is that you have some competency and some level of that and we can be pretty loose with that if you're a maker and you've done a lot of CAD to be 3d print But you've never done anything professionally or you've never done a bunch of other things with it, that's still really valuable. Because we find that you've learned that thing. It's that like, what did you get expert T said, we just want you to have some expertise in something, so that we know that you, you can can do that. And that helps with the team project for the individualized project, there are no requirements, you can come in as green as you could possibly be. And, and it's really amazing, because you do see, you know, it's not just the people who are, you know, experts getting other be like, there's so many things that this person, for example, that person who's really green in robotics, has really good business sense. And this other person who is an electrical engineer, is now learning about basic marketing for the very first time, you can contribute to their basic marketing, right, like, yeah, and that ends up being still really valuable because of this community thing. So we, we just kind of say, forget the prerequisites. You know, most people have some level of something there, and then they can join us, or we can help put them into a group, maybe you're not jumping into the deep object orientation and grasping class, you're working on the mini, you know, DIY pup, you know, mini pumper where you're, you know, just working with Raspberry Pi, that some of those things. So, you know, it's, it's about scoping the people for the prior matching the people for the project to those that we don't, other requirements is just you need to show up at sessions. But we also have a really cool way of doing an asynchronous thanks. So we have even talked about how this whole like you actually asked earlier, how do you scale this, and I don't think we got to that right.

Now I definitely want to talk about it, you can do the

scaling is that this is all a hybrid model. Not only can you be in person, but you can do this completely remote. Right, that's all. So that's how we scale a lot of this group. And we found so it can be literally double the amount of students because we can do half in person and half out of, you know, being completely virtual. And then even so our facility wise of this, even our students who are in person, they don't need to be here doing things all the time. If we're at a meeting, like we're having a Zoom meeting, there's no point in us all being in in one room. And, and so they can all be home and like, you know, in their bathrobe, doing it doing a project planning project. And some people might come into the lab. And so that's how we really scale this is that you create a hands on experience, even if you don't have an experience now and I'd like to tell this quick story about Noelle who is one of our Argentinian students. He lived in Argentina. And he was an automation engineer, but he had never done cat never done any type of cat design. And, you know, just like, like, this is something I want to learn. But I just again, he's like, Well, do I go back to school for this? Do I take a course to learn how to use basics, I've never had anything fun to make. Right. And so now we're like, hey, so the the neck piece of this was originally scoped with the Paul on robotics as this really fascinating but very intricate mechanism where it was a three degree of freedom system that was called the orbiter, it was really cool. It was a little outside of what we were going to build and recreate. So we just put a pan tilt servo in there. But all of this had been designed. And so we needed to actually design the mounting of those servos into the program. So we needed somebody to Cat up the whole structural mechanism to hold that. And so he was like, Oh, I'd love to learn CAD. So I literally went on a, you know, a call with him spent 20 minutes to be like here, this is how you set up your components and your you know, your your components and your parts in Fusion 360 so that you can be successful, here's how you turn on your device, you know, your, your actual changes history so that you can get back to things. And here's like two other tips. Here are the models for the servos that you could put in and this is how you put them in. And now I want you to build this. Right yeah. And it gave him kind of the specs of what what we want to hear the measurements. There's that he you know, he went home and by the very next night had built something. And so he put it on our 3d printers over the air. And so it was literally printing out in the morning when I came in. I come in, I hand it to the team, they assemble it for him, they give him notes. He goes back and re revive designs it and it's like he's hands on calving and 3d printing. He's just not necessarily touching the thing. Which is incredible. So he basically learned to CAD better than most of us in two weeks. That's awesome. Right and manage managed to do all the things that we needed. So that's kind of the process is like, you know, you have something cool that you need somebody who wants to learn it. And even if they're completely virtual, you know, they can buy, you know, a cheaper robot, a servo and a control module and then start working on the code to control that and understanding it, even hands on at their desk, that then that code can go and be uploaded into our project and work in a much bigger system. So yeah, you kind of on a micro level do quite a bit hands on, even if you're not in our lab, then in most of our programming, like a lot of our programmers, that we're mostly interested in just doing the code for the robot, they didn't even come into the lab, they were working with everybody, but we'd have them up on the big screen and talking to them. And they would be uploading code and controlling the robot from their home. That's so cool, right? And being able to test this, while we're all working on this, you know, it becomes like, we aren't limited anymore to in, in, in classroom, you know, experience, the pandemic is taught like this was developed during our pandemic, because we were like, well, we can't wait, we need to create this amazing program for people now. And the pandemic shows just how well we can be able to do that and what the limitations are, as well. But yeah, allows us to create a system where we can scale this. And the actual in you can be hands on without necessarily having to be in a school, nine to five every single day.

Yeah, definitely. Yeah, it's so interesting. To me, it seems like the whole approach that you're taking in this, how do you call it again, Mechi, or with labs, Mechlabs, the whole approach you're taking in the Mechlabs, course, or program? It seems like, I'm comparing it in my head to like universities, or these kinds of things, where it seems like they go against a lot. So for example, people have to take courses they're not motivated to do, you have to learn things that are kind of abstract, and not directly applicable to what you're working on, or what you're even interested in. But it's like a to z learning, as you were saying. They have a rigorous measures in place for accountability, like all the exams, and things like this, and the like hierarchy that forms from all of that. Whereas you guys, and also then they have they have the high paid lectures relatively. They have the intricate infrastructure around like TAs and graders, and all of this kind of thing,

multimillion dollar labs that very few people can access that money. Yeah,

that's totally true, too. And so you guys kind of took everything and you flipped it on its head. And so it's like, people are motivated to do whatever it is, you need very little of an expert's time. Those are your advisors and mentors. The people it's like, if they want to disengage, that's totally fine. But for the most part, they're doing it because they're totally interested in it. Yep. It's very interesting. And then the accountability with documentation, providing it so that it's good for them in the future, it's good for you to build off of their work. And it's helping them kind of skill up in how they communicate, and also in their own understanding, by leveraging the idea that they teach, to learn because they are writing documentation, teaching it to their future selves, or whoever their reader may be. readers may be, it feels very clever to me. With all this, it's like you're working with the grain of human nature very well, as opposed to other structures is how I'm thinking of it now.

2 posts with the hardware tag