Vijay Kumar: Flying Robots | Lex Fridman Podcast #37

1. 0:00 – 15:00

   The following is a…

   1. LFLex Fridman0:00

      The following is a conversation with Vijay Kumar. He's one of the top roboticists in the world, a professor at the University of Pennsylvania, a dean of Penn Engineering, former director of GRASP Lab, or the General Robotics Automation Sensing and Perception Laboratory at Penn that was established back in 1979. That's 40 years ago. Vijay is perhaps best known for his work in multi-robot systems, robot swarms, and micro aerial vehicles, robots that elegantly cooperate in flight under all the uncertainty and challenges that the real-world conditions present. This is the Artificial Intelligence Podcast. If you enjoy it, subscribe on YouTube, give it five stars on iTunes, support it on Patreon, or simply connect with me on Twitter at Lex Fridman, spelled F-R-I-D-M-A-N. And now, here's my conversation with Vijay Kumar. What is the first robot you've ever built or were a part of building?

   2. VKVijay Kumar1:03

      Way back when I was in graduate school, I was part of a fairly big project that involved building a very large hexapod. This weighed close to 7,000 pounds, and it was powered by hydraulic actuation, or was actuated by hydraulics with 18 motors, hydraulic motors, each controlled by an Intel 8085, uh, processor and an Inte- 8086 co-processor. And so imagine this huge, uh, monster that had 18 joints, each controlled by an independent computer, and there was a 19th computer that actually did the coordination between these 18 joints. So I was part of this project and my thesis work was how do you coordinate the 18 legs, and in particular, the-the pressures in the hydraulic cylinders to get efficient locomotion.

   3. LFLex Fridman2:09

      It sounds like a giant mess. So how difficult is it to make all the motors communicate? Presumably, you have to send signals hundreds of times a second, or at least-

   4. VKVijay Kumar2:18

      Yeah, so this was not my work, but the-the folks who worked on this wrote what I believe to be the first multiprocessor operating system. This was-

   5. LFLex Fridman2:27

      Mm-hmm.

   6. VKVijay Kumar2:27

      ... in the '80s. And you have to make sure that, uh, obviously messages got across from one joint to another. You have to remember, the-the clock speeds on those computers were about half a megahertz.

   7. LFLex Fridman2:39

      (laughs) Right.

   8. VKVijay Kumar2:40

      So.

   9. LFLex Fridman2:41

      The '80s. So not to romanticize the notion, but how did it make you feel to make-to see that robot move?

   10. VKVijay Kumar2:51

       It was amazing. In hindsight, it looks like, well, we built this thing which really should have been much smaller. And of course, today's robots are much smaller. You look at, you know, Boston Dynamics or Ghost Robotics, a spinoff from-from Penn. But back then, you were stuck with the substrate you had, the compute you had, so things were unnecessarily big. But at the same time, uh, and this is just human psychology, somehow bigger means grander. You know, people never have the same appreciation for nanotechnology or nano devices as they do for the space shuttle or the Boeing 747.

   11. LFLex Fridman3:30

       Yeah, you've actually done quite a good job at illustrating that small is beautiful.

   12. VKVijay Kumar3:35

       Yeah.

   13. LFLex Fridman3:36

       In terms of robotics. (laughs)

   14. VKVijay Kumar3:37

       Yeah.

   15. LFLex Fridman3:37

       So what is, uh, on that topic is the most beautiful or elegant robot in motion that you've ever seen? Not to pick favorites or whatever, but something that just inspires you, that you remember.

   16. VKVijay Kumar3:51

       Well, I think thing that I'm-I'm most proud of that my students have done is really think about, uh, small UAVs that can maneuver in constrained spaces, and, uh, p- in particular, their ability to coordinate with each other and form three-dimensional patterns. So once you can do that, uh, you can, uh, essentially create 3D objects in the sky, and you can deform these objects on the fly. So in some sense, your toolbox of what you can create is suddenly got enhanced.

   17. LFLex Fridman4:25

       Mm-hmm.

   18. VKVijay Kumar4:27

       And before that, we did the two-dimensional version of this, so we had, uh, ground robots forming patterns and-and so on. So that-that was not as impressive, that was not as beautiful. But if you do it in 3D, suspended in midair, and you've got to go back to 2011 when we did this, um, now it's actually pretty standard to do these things eight years later, um, but back then, it was a big accomplishment.

   19. LFLex Fridman4:49

       So the distributed cooperation is where-is where beauty emerges, in your eyes?

   20. VKVijay Kumar4:55

       Well, I think beauty to an engineer is very different from-from beauty to, you know, someone who's looking at robots from the outside, if you will.

   21. LFLex Fridman5:02

       Yeah.

   22. VKVijay Kumar5:03

       But what I meant there, so before we said that grand is associated with size, and, um, another way of thinking about this is just the physical shape, and the idea that you can create physical shapes in midair and have them deform, uh, that's beautiful.

   23. LFLex Fridman5:21

       But the individual components, the agility is beautiful too, right?

   24. VKVijay Kumar5:24

       That is true too.

   25. LFLex Fridman5:25

       So the-the aggressive move.

   26. VKVijay Kumar5:26

       So then how-how quickly can you actually manipulate these three-dimensional shapes and the individual components? Yes, you're right.

   27. LFLex Fridman5:32

       Uh, by the way, you said UAV, unmanned aerial vehicle. Well, what's a good term for drones, UAVs, quadcopters? Is there a term that's stan- being standardized?

   28. VKVijay Kumar5:44

       I don't know if there is. Everybody wants to use the word drones. And I've often said this, drones to me is a pejorative word. It-it signifies something that's, uh, that's dumb-

   29. LFLex Fridman5:54

       Hmm.

   30. VKVijay Kumar5:54

       ... that's pre-programmed, that does one little thing. And robots are anything but drones. So I actually don't like that word, but that's what everybody uses.You could call it unpiloted.
2. 15:00 – 30:00

   Yeah. So let's step…

   1. VKVijay Kumar15:00

      the cost of individuals would really become insignificant.

   2. LFLex Fridman15:04

      Yeah. So let's step back at a high-level view, the impossible question of what kind of, and as an overview, what kind of autonomous flying vehicles are there, in general?

   3. VKVijay Kumar15:16

      I think the ones that, uh, receive a lot of notoriety are obviously the military vehicles. Military vehicles are controlled by a base station, but have, uh, uh, a lot of human supervision, but they have limited in- autonomy, which is the ability to go from point A to point B, and even the more sophisticated now, f- sophisticated vehicles can do autonomous, uh, takeoff and landing.

   4. LFLex Fridman15:41

      And those usually have wings, and they're heavy, and they-

   5. VKVijay Kumar15:44

      Usually, they're wings, but then there's nothing preventing us from doing this for helicopters as well. There are, um, I mean, there are many military organizations that have autonomous helicopters in the same vein. And by the way, you, you look at autopilots in airplanes, and it's, it's actually very similar. In fact, I can... One interesting question we can ask is, uh, if you look at all the air safety violations or all the crashes that occurred-

   6. LFLex Fridman16:13

      Yeah.

   7. VKVijay Kumar16:14

      ... would they have happened if the plane were truly autonomous? And I think you'll find that, in many of the cases, you know, because of pilot error, we make silly decisions. And so, in some sense, even in air traffic, commercial air traffic, there's a lot of applications, uh, although we only see, um, autonomy being enabled at very high altitudes, uh, when, when the, the, the pilot, the, the, the, the plane is on autopilot.

   8. LFLex Fridman16:41

      There's still a role for the human, and tho- that kind of, uh, autonomy is, uh, you're kind of implying, I don't know what the right word is, but it's a little dumb- dumber than it could be.

   9. VKVijay Kumar16:53

      Uh, right.

   10. LFLex Fridman16:53

       It's simpler and naive.

   11. VKVijay Kumar16:54

       So, so in the lab, of course, we can, we can, we can afford to be a lot more aggressive.

   12. LFLex Fridman16:59

       Right.

   13. VKVijay Kumar16:59

       And the question we try to ask is, um, can we make robots that would be able to make decisions without any kind of external infrastructure?

   14. LFLex Fridman17:13

       Right.

   15. VKVijay Kumar17:13

       So what does that mean? So the most common piece of infrastructure that airplanes use today is GPS. Uh, GPS is also the most brittle form of information. Um, if you have driven in a city, tried to use GPS navigation, you know, in tall buildings, you immediately lose GPS. Um, and so that's not a very sophisticated way of building autonomy. I think the second piece of infrastructure they rely on is communications. Again, it's very easy to jam communications. In fact, if you use wifi, you know that wifi signals drop out, cell signals drop out, so to rely on something like that is not, is not good. The third form of infrastructure we, we use, and I hate to call it infrastructure, but, but it is that in the sense of robots, is people.

   16. LFLex Fridman18:06

       (laughs)

   17. VKVijay Kumar18:06

       So you could rely on somebody to pilot you. (laughs)

   18. LFLex Fridman18:09

       Right.

   19. VKVijay Kumar18:09

       Uh, and so the question you wanna ask is if there are no pilots, if there's no communications with any base station-

   20. LFLex Fridman18:15

       Yeah.

   21. VKVijay Kumar18:16

       ... if there's no knowledge of position-... and if there's no a priori map, a priori knowledge-

   22. LFLex Fridman18:22

       Yeah.

   23. VKVijay Kumar18:22

       ... of what the environment looks like, a priori model of what might happen in the future, can robots navigate? So that is true autonomy.

   24. LFLex Fridman18:31

       Right. So that's, that's true autonomies. And we're talking about, you mentioned, like military applications of drones. Okay, so what else is there? You talk about agile, autonomous flying robots, aerial robots. So that's a different kind of... It's not winged, it's not big. At least, it's small.

   25. VKVijay Kumar18:48

       So I use the word agility mostly, or at least we're motivated to do agile robots, mostly because robots can operate and should be operating in constrained environments.

   26. LFLex Fridman19:01

       Mm-hmm.

   27. VKVijay Kumar19:02

       And if you want to operate the way a Global Hawk o- operates, I mean, the kinds of conditions in which you operate are very, very restrictive. If you go, want to go inside a building, for example, for search and rescue, or to locate an active shooter, or you want to navigate under the canopy in an orchard to look at health of plants or to, to look for, count, to count fruits-

   28. LFLex Fridman19:28

       Mm-hmm.

   29. VKVijay Kumar19:28

       ... to measure the tree, the tree trunks, uh, these are things we do, by the way. Uh-

   30. LFLex Fridman19:33

       Yeah. Yeah, some cool agriculture stuff you've shown in, in the past. It's really awesome.
3. 30:00 – 45:00

   Mm-hmm. …

   1. VKVijay Kumar30:00

      to fly through a constrained space, the first time you try it, you'll invariably... you might get it wrong-

   2. LFLex Fridman30:08

      Mm-hmm.

   3. VKVijay Kumar30:09

      ... if, if the task is challenging. And the reason is, to get it perfectly right, you have to model everything in the environment.

   4. LFLex Fridman30:16

      Right.

   5. VKVijay Kumar30:17

      And flying is notoriously hard to model. There are aerodynamic effects that we constantly discover, uh-... even just before I was talking to you, I was talking to a student about how blades flap when they fly.

   6. LFLex Fridman30:36

      Huh. Wow.

   7. VKVijay Kumar30:37

      And that ends up changing how a rotorcraft is accelerated in the angular direction.

   8. LFLex Fridman30:45

      So these are like micro flaps or something? It's mo- it's-

   9. VKVijay Kumar30:48

      It's not micro flaps. So we assume that each blade is, is rigid but actually it flaps a little bit.

   10. LFLex Fridman30:53

       Oh.

   11. VKVijay Kumar30:53

       It bends.

   12. LFLex Fridman30:54

       Interesting. Yeah.

   13. VKVijay Kumar30:55

       And so the models rely on the fact, on the, on, on an assumption that they're, they're actually rigid. But that's not true. If you're flying really quickly, these effects become significant. If you're flying close to the ground, you get pushed off by the ground, right? Something which every pilot knows when, when he tries to land or she tries to land.

   14. LFLex Fridman31:16

       Mm-hmm.

   15. VKVijay Kumar31:16

       This is, this is called the ground effect. Something very few pilots think about is what happens when you go close to a ceiling or you get sucked into a ceiling. There are very few aircrafts that fly close to any kind of ceiling. Likewise, when you go close to, close to a wall, uh, there are these wall effects. Um, and if you've gone on a train and you pass another train that's traveling the opposite direction, you feel the buffeting. And so these kinds of micro climates-

   16. LFLex Fridman31:45

       Mm-hmm.

   17. VKVijay Kumar31:45

       ... affect our UAVs significantly. So if you want-

   18. LFLex Fridman31:48

       And they're impossible to model, essentially (overlapping)

   19. VKVijay Kumar31:50

       I wouldn't say they're-

   20. LFLex Fridman31:51

       ... explicitly.

   21. VKVijay Kumar31:51

       ... impossible to model, but the level of sophistication you would need in the model and the software would be tremendous. Uh, plus to get everything right would be awfully tedious. So the way we do this is over time, we figure out how to adapt to these conditions. Um, so we've, early on, we used a form of learning that we call iterative learning. Uh, so this idea if you wanna perform a task, um, there are a few things that you need to change-

   22. LFLex Fridman32:22

       Mm-hmm.

   23. VKVijay Kumar32:23

       ... uh, and iterate over, few parameters, that over time, you can, you can, you can figure out. So I could call it policy gradient reinforcement learning.

   24. LFLex Fridman32:33

       (laughs)

   25. VKVijay Kumar32:34

       But actually it was just iterative learning.

   26. LFLex Fridman32:35

       Iterative learning.

   27. VKVijay Kumar32:36

       Um, and so this was there way back. I think what's interesting is, if, if you look at autonomous vehicles today, learning occurs, could occur in two pieces. One is perception. Understanding the world. Second is action, taking actions. Everything that I've seen that is successful is in the perception side of things. So in computer vision, we've made amazing strides in the last 10 years. So recognizing objects, actually detecting objects, classifying them, uh, uh, uh, and, and tagging them in some sense, annotating them. This is all done through machine learning. On the action side on the other hand, I don't know of any examples where there are fielded systems where we actually learn the right behavior.

   28. LFLex Fridman33:21

       Outside a single demonstration of success that you know-

   29. VKVijay Kumar33:23

       Oh, in the laboratory, this is the Holy Grail. Can you do end-to-end learning? Can you go from pixels to motorbo- motor currents? This is really, really hard. And I think if you loo- go forward, the right way to think about these things is, uh, data-driven approaches, learning-based approaches, in concert with model-based approaches, which is the traditional way of doing things.

   30. LFLex Fridman33:48

       Right.
4. 45:00 – 56:31

   Mm-hmm. …

   1. VKVijay Kumar45:00

      and how humans interact with robots-

   2. LFLex Fridman45:01

      Mm-hmm.

   3. VKVijay Kumar45:02

      ... you know, we think of these in sort of three different ways. One is the human commanding the robot. The second is the human collaborating with the robot. So, for example, we work on how a robot can actually pick up things with a human and carry things.

   4. LFLex Fridman45:18

      With a human, yeah.

   5. VKVijay Kumar45:18

      That's, like, true collaboration. And, uh, third, we think about humans as bystanders. Self-driving cars, what's the human's role and how does- how do self-driving cars acknowledge the presence of humans?

   6. LFLex Fridman45:32

      Right.

   7. VKVijay Kumar45:32

      Um, so I think all of these things are different scenarios. It depends on what kind of humans, what kind of task, and I think it's very difficult to say that there's a general theory that we all have for this. But at the same time, it's also silly to say that we- we should think about robots independent of humans.

   8. LFLex Fridman45:51

      Right.

   9. VKVijay Kumar45:52

      So, to me, human-robot interaction is almost a mandatory aspect of everything we do.

   10. LFLex Fridman45:59

       Yes, so but to which degree? So what- your thoughts, if we jump to autonomous vehicles, for example, there's a- there's a big debate between what- what's called Level 2 and Level 4, so semi-autonomous and autonomous vehicles. And sort of the Tesla approach currently, at least, has a lot of collaboration between human and machine. So the human is supposed to actively supervise the operation of the robot. Part of the safety, uh, definition of how safe a- a robot is, in that case, is how effective is the human in monitoring it? Do you think that's ultimately not a good, uh, approach in sort of having a human in the picture, not as a bystander or, um, part of the infrastructure, but really as part of what's required to make the system safe?

   11. VKVijay Kumar46:51

       This is harder than it sounds.

   12. LFLex Fridman46:53

       Right.

   13. VKVijay Kumar46:53

       I think, you know, if you- if you- if- I mean, I'm sure you've driven the- driven before on highways and so on. It's- it's really very hard to have to relinquish control to a machine and then take over when needed.

   14. LFLex Fridman47:09

       Right.

   15. VKVijay Kumar47:10

       So I think Tesla's approach is interesting 'cause it allows you to periodically establish some kind of contact, uh, with the car. Toyota, on the other hand, is thinking about shared autonomy as a-

   16. LFLex Fridman47:21

       Mm-hmm.

   17. VKVijay Kumar47:22

       ... or collaborative autonomy as a paradigm. If I may argue, these are very, very simple ways of human-robot collaboration 'cause the task is pretty boring. You sit in a vehicle. You go from point A to point B. I think the more interesting thing to me is, uh, for example, search and rescue. I've got a human-

   18. LFLex Fridman47:39

       Right.

   19. VKVijay Kumar47:39

       ... first responder, robot first responders. I gotta do something. It's important. I have to do it in two minutes. The building is burning. There's been an explosion. It's collapsed. How do I do it? I think, to me, those are the interesting things where it's very, very unstructured, and what's the role of the human? What's the role of the robot? Uh, clearly, there's lots of interesting challenges, and as a field, I think we're gonna make a lot of progress in this area.

   20. LFLex Fridman48:05

       Yeah, it's an exciting form of collaboration. You're right. In autonomous driving, the main enemy is just boredom of the human. (laughs)

   21. VKVijay Kumar48:13

       Yes.

   22. LFLex Fridman48:13

       As- as opposed to in rescue operations, it's literally life and death, and, uh, the collaboration enables the effective completion of the mission, so it's exciting.

   23. VKVijay Kumar48:24

       Well, in some sense, you know, we're also doing this. You- you know, you think about the human driving a car, and almost invariably, the human's trying to estimate the state of the car, estimate the state of the environment, and so on. But what if the car were to estimate the state of the human?

   24. LFLex Fridman48:39

       Mm-hmm.

   25. VKVijay Kumar48:40

       So, for example, I'm sure you have a smartphone, and the smartphone, uh, tries to figure out what you're doing and send you reminders.... and oftentimes telling you to drive to a certain place, although you have no intention of going there-

   26. LFLex Fridman48:51

       (laughs)

   27. VKVijay Kumar48:51

       ... because it thinks that that's where you should be, uh, 'cause of some Gmail calendar entry, um, e- or, or, or something like that. And, and, you know, it's trying to f- constantly figure out who you are, what you're doing. If a car were to do that, maybe that would make the driver safer because the car is trying to figure out, is the driver paying attention, looking at his or her eyes, um-

   28. LFLex Fridman49:12

       Mm-hmm. All that kind of stuff.

   29. VKVijay Kumar49:12

       ... looking at saccadic movements. So, I think the potential is there. But from the reverse side, it's not robot modeling, but it's human modeling.

   30. LFLex Fridman49:21

       It's more on the human, right?

Episode duration: 56:46