The Exchanges

Q I love it. And so before you go into that, tell us a little bit more about your background and academic career. You, you, you, you studied computer science then or what?

A Yeah, sure. I'll, I'll go way back. So I was actually a computer science and philosophy double major as an undergraduate. I went to a, a small liberal arts school, um, called Bowdoin college in Brunswick, Maine. Um, after that, uh, I did a little bit of work in, in robotics as an engineer at a robotics company, and then studied neurobiology for a couple of years at Duke university, uh, before deciding to go back to grad school. So. Um, at the time I was very interested in, in how the human brain worked. Um, but, uh, ultimately I decided I wanted to design intelligence systems and, um, put them out into the world. And so I started to, to study machine learning and robotics in grad school, um, and got my PhD at Carnegie Mellon university doing that.

AI assessment note: “I was actually a computer science and philosophy double major as an undergraduate.”

Q And I have to admit, when I first heard about Overland, I said, wait a second, I thought that was already solved in Tesla and everyone else's way ahead, but it turns out it's a very different problem in some ways to really perfectly solve driving on just like random train anywhere versus driving on a road, right?

A That's right. So on-road self-driving is very hard. Um, Uh, the major challenge there is not, you know, how do you actually traverse terrain? I mean, you're driving on roads which are engineered to be a very easy to drive on. Um, the challenge is dealing with all of the different, uh, agents that are in the environment. So think about other cars, bicyclists, pedestrians, um, understanding where they are and their intent. So that makes on-road self-driving very hard. But off-road self-driving, uh, has really a different focus, which is on the traversability of terrain. So, Um, you have to perceive the terrain around you. You have to represent that somehow, uh, and then find ways for your vehicle to move reliably through the terrain without rolling over or crashing.

AI assessment note: “off-road self-driving, uh, has really a different focus, which is on the traversability of terrain”

Q philosophy? I want to ask this because, you know, a lot of the people I've worked with, we have this term philosopher builder we like, right? So, so Alex Karp, Peter Thiel, you know, we're, we're very advanced philosophers, Charles Koch, She calls himself as philosopher in chief, the biggest private business in America. So it's cool. You have a philosophy background as well. How does that tie into this?

A Yeah. So I only have an undergrad degree in philosophy, unlike Alex Carb, who's got a PhD, but, um, you know, I think ultimately it comes to thinking about, you know, how the human mind works, um, you know, how humans understand the world and really trying to, to delve into that. I actually think computer science and philosophy are pretty closely related. So, um, you might study logic and formal systems in philosophy, and then that's related to the foundations of Um, computation. Uh, and then also when you think about, um, you know, philosophy of mind and, you know, how that might relate to, to AI, I think there are some connections there as well. And so, um, as I moved from philosophy into, you know, more practical things like computer science and robotics, um, I still sort of think about what we do is almost like applied philosophy, uh, where, you know, you're thinking about these deep questions and you're trying to realize that, um, in the real world through engineering.

AI assessment note: “I still sort of think about what we do is almost like applied philosophy”

Q won the competition, but you're the only one left. Everyone I've talked to, I can say it for you. Everyone I've talked to in the DOD, you know, has said really great things and is really excited. You guys are the best they say. So, you know, you're, you're iterating multiple times per week with software and hardware, different environments. Like how, how come you got to be the best?

A Yeah, so, um, I think you are starting to kind of hit on some of our secret sauce. I don't mind saying it because it's a hard system to replicate. So basically, um, you know, we, one of the things about robotics is it's basically software and hardware working together, and then field robotics, um, and, you know, robotics in some of the domains that we're talking about requires that software and hardware to work really well in complex environments. Um, people who are just kind of starting work in robotics often think that you can just do things in, in simulation. Uh, but they quickly learned that it is really important to actually run your software on the robot. And then especially in field robotics, run that robot in the terrain.

AI assessment note: “you are starting to kind of hit on some of our secret sauce”

Q ahead, but for, for, for me, I'd say like, like one concept, like for Sironic with the stuff in the water is, is, is follow and monitor that, that Shepard. Another concept would be Everyone wants to meet here. Everyone wants to defend this unit. Like, what are, how are you thinking of other concepts you'd want to be able to command these swarms to do and to help you?

A Yeah, for sure. So, um, a very basic one is just surveillance. So trying to get an asset out, um, in front in order to investigate some area. So you can do route reconnaissance, for example, which, um, where you move an autonomous asset along a route, um, you use the cameras on board in order to, um, determine what might be out there. Um, so things like that. And then just in general, um, you're, we're thinking about how to actually push these Um, autonomous systems out in front of the forward line of troops, um, to be able to do other things like provide security or provide, um, electronic warfare, uh, nodes or, um, uh, uh, re-trans nodes, so basically like communication nodes, so set up communication networks. There's a lot of different things that you can actually use these uncrewed vehicles for, uh, that help, um, warfighters to, to operate in pretty complex terrain.

AI assessment note: “a very basic one is just surveillance. So trying to get an asset out”

Q What, what are you most excited about that you're building the next year? Is there anything in particular like, oh, this is so cool.

A Uh, so we've just started, um, we've just announced Overwatch, which allows for command and control of multiple, um, assets. So, um, we're going to start to be showing that a lot more, um, being able to coordinate, uh, multiple robots, um, multiple autonomous robots, uh, in a variety of, of difficult terrain. And we're also starting to wade into hardware. So, uh, over the last several years, we've learned quite a bit about how to build and maintain Vehicles, which can move very fast through very difficult terrain. And so we're bringing some of that production in house and we'll be excited to, to, um, reveal some of that in, in, in a few months, but, um, it's, it's exciting stuff for sure.

AI assessment note: “we've just announced Overwatch, which allows for command and control of multiple”