Pod Insights Lex Fridman Podcast #114 – Russ Tedrake: Underactuated Robotics, Control, Dynamics and Touch About this episode Russ Tedrake is a roboticist and professor at MIT and vice president of robotics research at TRI. He works on control of robots in interesting, complicated, underactuated, stochastic, difficult to model situations.
Support this podcast by supporting our sponsors. Click links, get discount:
– Magic Spoon: https://magicspoon.com/lex & use code LEX at checkout
– BetterHelp: https://betterhelp.com/lex
– ExpressVPN: https://www.expressvpn.com/lexpod
If you would like to get more information about this podcast go to https://lexfridman.com/ai or connect with @lexfridman on Twitter https://twitter.com/lexfridman, LinkedIn https://www.linkedin.com/in/lexfridman/, Facebook https://www.facebook.com/lexfridman, Medium https://medium.com/@lexfridman, or YouTube https://www.youtube.com/lexfridman where you can watch the video versions of these conversations. If you enjoy the podcast, please rate it 5 stars on Apple Podcasts https://podcasts.apple.com/us/podcast/artificial-intelligence/id1434243584, follow on Spotify https://open.spotify.com/show/2MAi0BvDc6GTFvKFPXnkCL, or support it on Patreon https://www.patreon.com/lexfridman.
Here’s the outline of the episode. On some podcast players you should be able to click the timestamp to jump to that time.
OUTLINE:
00:00 – Introduction
04:29 – Passive dynamic walking
09:40 – Animal movement
13:34 – Control vs Dynamics
15:49 – Bipedal walking
20:56 – Running barefoot
33:01 – Think rigorously with machine learning
44:05 – DARPA Robotics Challenge
1:07:14 – When will a robot become UFC champion
1:18:32 – Black Mirror Robot Dog
1:34:01 – Robot control
1:47:00 – Simulating robots
2:00:33 – Home robotics
2:03:40 – Soft robotics
2:07:25 – Underactuated robotics
2:20:42 – Touch
2:28:55 – Book recommendations
2:40:08 – Advice to young people
2:44:20 – Meaning of life
Transcript 27,104 words · 2 speakers
Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.
0:00 Lex Fridman? The following is a conversation with Russ Tadrick, a roboticist and professor at MIT and vice president of robotics research at Toyota Research Institute, or TRI. He works on control of robots in interesting, complicated, underactuated, stochastic, difficult-to-model situations. He's a great teacher and a great person, one of my favorites at MIT. We'll get into a lot of topics in this conversation, from his time leading MIT's DOPRA Robotics Challenge Team, to the awesome fact that he often runs close to a marathon a day to and from work barefoot. For a world-class roboticist interested in elegant, efficient control of underactuated
0:45 Lex Fridman? dynamical systems like the human body, this fact makes Russ one of the most fascinating people I know. Quick summary of the ads: three sponsors: Magic Spoon Cereal, BetterHelp, and ExpressVPN. Please consider supporting this podcast by going to magic spoon.com/lex and using code Lex at checkout, going to betterhelp.com/lex, and signing up at expressvpn.com/lexpod. Click the links in the description, buy the stuff, get the discount, it really is the best way to support this podcast. If you enjoy this thing, subscribe on YouTube, review it with five stars on Apple Podcasts,
1:26 Lex Fridman? support it on Patreon, or connect with me on Twitter at Lex Fridman. As usual, I'll do a few minutes of ads now and never any ads in the middle that can break the flow of the conversation. This episode is supported by Magic Spoon, low-carb keto-friendly cereal. I've been on a mix of keto or carnivore diet for a very long time now. That means eating very little carbs. I used to love cereal, obviously most of crazy amounts of sugar, which is terrible for you, so I quit years ago. But Magic Spoon is a totally new thing: zero sugar, 11 grams of protein, and only three net grams of carbs. It tastes delicious. It has a bunch of flavors, they're all good, but if you know-
2:10 Lex Fridman? Know what's good for you, you'll go with cocoa, my favorite flavor and the flavor of champions. Click the magic spoon.com slash Lex link in the description. Use code Lex at checkout to get the discount and to let them know I sent you. So buy all of their cereal. It's delicious and good for you. You won't regret it. The show is also sponsored by BetterHelp spelled H E L P. Help. Check it out at betterhelp.com slash Lex. They figure out what you need and match you with a licensed professional therapist in under 48 hours. It's not a crisis line. It's not self-help. It is professional counseling done securely online. As you may know, I'm a bit from the David Goggins line of creatures and still have
2:55 Lex Fridman? some demons to contend with, usually on long runs or all-nighters full of self-doubt. I think suffering is essential for creation, but you can suffer beautifully in a way that doesn't destroy you. For most people, I think a good therapist can help in this, so it's at least worth a try. Check out the reviews. They're all good. It's easy, private, affordable, available worldwide. You can communicate by text anytime and schedule weekly audio and video sessions. Check it out at betterhelp.com slash Lex. This show is also sponsored by ExpressVPN. Get it at expressvpn.com slash Lex pod to get a discount and to support this podcast. Have you ever watched The Office?
3:39 Lex Fridman? If you have, you probably know it's based on a UK series also called The Office. Not to steer up trouble, but I personally think the British version is actually more brilliant than the American one, but both are amazing. Anyway, there are actually nine other countries with their own version of The Office. You can get access to them with no geo restriction when you use ExpressVPN. It lets you control where you want sites to think you're located. You can choose from nearly 100 different countries, giving you access to content that isn't available in your region. So again, get it on any device at expressvpn.com slash Lex pod to get an extra three months
4:21 Lex Fridman? free and to support this podcast. And now here's my conversation with Russ Tedjerk.
4:46 Lex Fridman? What is the most beautiful motion of an animal or robot that you've ever seen?
4:53 Speaker 01 I think the most beautiful motion of a robot has to be the passive dynamic walkers. I think there's just something fundamentally beautiful, the ones in particular that Steve Collins built with Andy Ruina at Cornell. A 3D walking machine, so it was not confined to a boom or a plane. That you put it on top of a small ramp, give it a little push. It's powered only by gravity, no controllers, no batteries whatsoever. It just falls down the ramp. And at the time, it looked more natural, more graceful, more human-like than any robot we'd seen to date, powered only by gravity.
5:32 Lex Fridman? How does it work?
5:34 Speaker 01 Well, okay, the simplest model, it's kind of like a slinky. It's like an elaborate slinky. One of the simplest models, we used to think about it, is actually a rimless wheel. So imagine taking a bicycle wheel, but take the rim off. So it's now just got a bunch of spokes. If you give that a push, it still wants to roll down the ramp. But every time its foot, its spoke comes around and hits the ground, it loses a little energy. Every time it takes a step forward, it gains a little energy. Those things can come into perfect balance. And actually, they want to, it's a stable phenomenon. If it's going too slow, it'll speed up. If it's going too fast, it'll slow down. And it comes into a stable periodic motion.
6:16 Speaker 01 Now, you can take that rimless wheel, which doesn't look very much like a human walking, take all the extra spokes away, put a hinge in the middle. Now it's two legs. That's what I call our compass gate walker. That can still, you give it a little push, starts falling down a ramp. Looks a little bit more like walking, at least it's a biped. But what Steve and Andy and Ted McGee started the whole exercise, but what Steve and Andy did was they took it to this beautiful conclusion. Where they built something that had knees, arms, a torso, the arms swung naturally. Give it a little push and that looked like a stroll through the park.
6:55 Lex Fridman? How do you design something like that? I mean, is that art or science?
6:59 Speaker 01 It's on the boundary. I think there's a science to getting close to the solution. I think there's certainly art in the way that they they made a beautiful robot. But but then the finesse, because because this was work, they were working with a system that wasn't perfectly modeled, wasn't perfectly controlled. There's all these little tricks that you have to tune the suction cups at the knees, for instance, so that they stick, but then they release at just the right time, or there's all these little tricks of the trade. Which really are art, but it was a point. I mean, it made the point. We were at that time, the walking robot, the best walking robot in the world was Honda's Asimo. Absolutely marvel of modern engineering.
7:41 Lex Fridman? This is 90s?
7:42 Speaker 01 This was in 97 when they first released it sort of announced P2 and then it went through, it was Asimo by then in 2004.
7:51 Lex Fridman? It looks like this very cautious walking, like you're walking on on hot coals or something like that.
7:59 Speaker 01 I think it gets a bad rap. Asimo is a beautiful machine. It does walk with its knees bent. Our Atlas walking had its knees bent. But actually Asimo was pretty fantastic, but it wasn't energy efficient. Neither was Atlas when we worked on Atlas.
8:15 Speaker 01 None of our robots that have been that complicated have been very energy efficient.
8:21 Speaker 01 But
8:23 Speaker 01 there was a there's a thing that happens when you do control. When you try to control a system of that complexity. You try to use your motors to basically counteract gravity. Take whatever the world's doing to you and push back. Erase the dynamics of the world and impose the dynamics you want because you can make them simple and analyzable. Mathematically simple. And this was a very sort of beautiful example that you don't have to do that. You can just let go, let physics do most of the work. Right? And you just have to give it a little bit of energy. This one only walked down a ramp. It would never walk on the flat. To walk on the flat, you have to give a little energy at some point.
9:05 Speaker 01 But maybe instead of trying to take the forces imparted to you by the world and replacing them, what we should be doing is letting the world push us around and we go with the flow. Very zen, very zen robot.
9:18 Lex Fridman? Yeah, but okay, so that that sounds very zen. But you can, I can also imagine how many like failed versions they had to go through. Like how many, like, I would say it's probably, would you say it's in the thousands that they've had to have the system fall down before they figured out?
9:36 Speaker 01 I don't know if it's thousands, but it's a lot. It takes some patience. There's no question.
9:42 Lex Fridman? So in that sense, control might help a little bit.
9:45 Speaker 01 Oh, the apps, I think everybody, even at the time, said that the answer is to do that with control. But it was just pointing out that maybe the way we're doing control right now isn't the way we should.
9:58 Lex Fridman? Got it. So what about on the animal side? The ones that figured out how to move efficiently? Is there anything you find inspiring or beautiful in the movement of any?
10:07 Speaker 01 I do have a favorite example.
10:09 Lex Fridman? Okay.
10:11 Speaker 01 So it sort of goes with the passive walking idea. So is there, you know, how, how energy efficient are animals? Okay, there's a great series of experiments by George Lauder at Harvard and Mike Tranafilo at MIT. They were studying fish swimming in a water tunnel. Okay. And one of these, the type of fish they were studying were these rainbow trout. Because they, there was a phenomenon well understood that rainbow trout, when they're swimming upstream at mating season, they kind of hang out behind the rocks. And it looks like, I mean, that's tiring work swimming upstream. They're hanging out behind the rocks. Maybe there's something energetically interesting there. So they tried to recreate that. They put in this water tunnel, a rock, basically, a cylinder
10:54 Speaker 01 that had the same sort of vortex street. The eddies coming off the back of the rock that you would see in a stream. And they put a real fish behind this and watched how it swims. And the amazing thing is that if you watch from above, what the fish swims when it's not behind a rock, it has a particular gait. You can identify the fish, the same way you look at a human looking, walking down the street. You sort of have a sense of how a human walks. The fish has a characteristic gait.
11:22 Speaker 01 You put that fish behind the rock, its gait changes. And what they saw was that it was actually resonating and kind of surfing between the vortices.
11:32 Lex Fridman? Yeah.
11:33 Speaker 01 Now, here was the experiment that really was the clincher. Because there was still, it wasn't clear how much of that was mechanics of the fish? How much of that is control? The brain? So the clincher experiment, and maybe one of my favorites to date, although there are many good experiments. They took, they, this was now a dead fish. They took a dead fish. They put a string that went, that tied the mouth of the fish to the rock, so it couldn't go back and get caught in the grates. And then they asked, what would that dead fish do when it was hanging up behind the rock? And so what you'd expect is it sort of flopped around like a dead fish in the vortex wake, until something sort of amazing happens. And this video is worth putting in.
12:17 Lex Fridman? Yeah.
12:18 Speaker 01 Right?
12:19 Lex Fridman? What happens?
12:20 Speaker 01 The dead fish basically starts swimming upstream. Right? It's completely dead, no brain, no motors, no control, but it somehow, the mechanics of the fish resonate with the vortex street, and it starts swimming upstream. It's one of the best examples ever.
12:37 Lex Fridman? What, who do you give credit for that to? Is that just evolution constantly just figuring out by killing a lot of generations of animals? Like the most efficient motion? Is that, or maybe the physics of our world completely like, it's like if evolution applied not only to animals, but just the entirety of it somehow drives to efficiency? Like nature likes efficiency? I don't know if that question even makes any sense.
13:07 Speaker 01 I understand the question. That's reasonable. I mean, do they co-evolve?
13:11 Lex Fridman? Yeah, somehow co, yeah, like, I don't know if an environment can evolve, but.
13:17 Speaker 01 I mean, there are experiments that people do, careful experiments, that show that animals can adapt to unusual situations and recover efficiency. So there seems like, at least in one direction, I think there is reason to believe that the animal's motor system and probably its mechanics adapt in order to be more efficient. But efficiency isn't the only goal, of course. Sometimes it's too easy to think about only efficiency, but we have to do a lot of other things first, not get eaten, and then, all other things being equal, try to save energy.
13:50 Lex Fridman? By the way, let's draw a distinction between control and mechanics. Like, how would you define each?
13:57 Speaker 01 Yep. I mean, I think part of the point is that we shouldn't draw a line as clearly as we tend to. But on a robot, we have motors and we have the links of the robot, let's say. If the motors are turned off, the robot has some passive dynamics. Okay? Gravity does the work. You can put springs, I would call that mechanics, right? If we have springs and dampers, which our muscles are springs and dampers and tendons. But then you have something that's doing active work, putting energy in, which are your motors on the robot. The controller's job is to send commands to the motor that add new energy into the system. Right? So the mechanics and control interplay somewhere the divide is around, you know, did you decide
14:42 Speaker 01 to send some commands to your motor or did you just leave the motors off and let them do their work?
14:47 Lex Fridman? Would you say, is most of nature on the dynamic side or the control side? So like, if you look at biological systems, or if, you know, we're living in a pandemic now, like, do you think a virus is a, do you think is a dynamic system? Or is there a lot of control, intelligence?
15:10 Speaker 01 I think it's both, but I think we maybe have underestimated how important the dynamics are. Right? I mean, even our bodies, the mechanics of our bodies, certainly with exercise, they evolve. But so I actually, I lost a finger in early 2000s. And it's my fifth metacarpal. And it turns out you use that a lot in ways you don't expect when you're opening jars. Even when I'm just walking around, if I bump it on something, there's a bone there that was used to taking contact. My fourth metacarpal wasn't used to taking contact. It used to hurt, still does a little bit. But actually, my bone has remodeled, right?
15:51 Speaker 01 You get the, over the, over a couple of years, the geometry, the mechanics of that bone changed to address the new circumstances. So the idea that somehow it's only our brain that's adapting or evolving is not right.
16:07 Lex Fridman? Maybe sticking on evolution for a bit, because it's tended to create some interesting things. Bipedal walking. Do you, why the heck did evolution give us? I think we're, are we the only mammals that walk on two feet?
16:23 Speaker 01 No, I mean, there's a bunch of animals that do it a bit.
16:27 Lex Fridman? A bit.
16:27 Speaker 01 There's a, I think we are the most successful bipeds.
16:30 Lex Fridman? I think some, I think I read somewhere that the reason the, you know, evolution made us walk on two feet is because there's an advantage to being able to carry food back to the tribe or something like that. It's like you can carry, it's kind of this communal cooperative thing. So like to carry stuff back to, to a place of shelter and so on, to share with others. Do you understand at all the value of walking on two feet from both a robotics and a human perspective?
17:06 Speaker 01 Yeah, there are some great books written about evolution of, walking, evolution of the human body. I think it's easy, though, to make
17:16 Speaker 01 bad evolutionary arguments.
17:17 Lex Fridman? Sure. Most of them are probably bad, but what else can we do?
17:23 Speaker 01 I mean, I think
17:25 Speaker 01 a lot of what dominated our evolution probably was not.
17:31 Speaker 01 The things that worked well sort of in the steady state. You know, when things are, when things are good, but, but. For instance, people talk about what we should eat now because our ancestors were meat eaters or, or whatever.
17:44 Lex Fridman? Oh yeah, I love that.
17:46 Speaker 01 Yeah. But probably, you know, the reason that one pre, pre Homo sapiens species versus another survived was not because of whether they ate well when there was lots of food. But when the ice age came, you know, probably one of them happened to be in the wrong place. One of them happened to forage a food that was okay, even, even when the glaciers came or something like that. I mean.
18:15 Lex Fridman? There's a million variables that contributed and we can't, and are actually the amount of information we're, we're working with and telling these stories, these evolutionary stories is, is very little. So yeah, just like you said, it seems like if you, if you study history, it seems like history turns on like these little events that, that otherwise would seem meaningless. But in a grant, like when you, in retrospect were turning points.
18:44 Speaker 01 Absolutely.
18:45 Lex Fridman? And that, that's probably how like somebody got hit in the head with a rock because somebody slept with the wrong person back in the cave days and somebody get, get angry and that turned, you know, warring tribes can combine with the environment, all those millions of things and the meat eating, which I get a lot of criticism because I, I don't know, I don't know what your dietary processes are like, but these days I've been eating only meat, which is, there's, there's a large community of people who say, yeah, probably make evolutionary arguments and say, you're doing a great job. There's probably an even larger community of people, including my mom, who says it's deeply unhealthy, it's wrong, but I just feel good doing it.
19:27 Lex Fridman? But you're right, I, these evolutionary arguments can be flawed, but is there anything interesting to pull out for?
19:33 Speaker 01 There's a great book, by the way, well, a series of books by Nicholas Taleb about Fooled by Randomness and Black Swan. Highly recommend them, but yeah, they make the point nicely that probably it was a few random events that, yes, maybe it was someone getting hit by a rock, as you say.
19:56 Lex Fridman? That said, do you think, I don't know how to ask this question or how to talk about this, but there's something elegant and beautiful about moving on two feet. Obviously biased because I'm human. But from a robotics perspective too, you work with robots on two feet. Is it, is it all useful to build robots that are on two feet as opposed to four? Is there something useful about it?
20:19 Speaker 01 The most, I mean, the reason I spent a long time working on bipedal walking was because it was hard and it was, it challenged control theory in ways that I thought were important. I wouldn't have ever tried to convince you that you should start a company around bipeds or something like this. There are people that make pretty compelling arguments, right? I think the most compelling one is that the world is built for the human form. And if you want a robot to work in the world we have today, then, you know, having a human form is a pretty good way to go. There are, there are places that a biped can go that would be hard for other form factors to go, even natural places.
21:04 Speaker 01 But, you know, at some point in the long run, we'll be building our environments for our robots, probably, and so maybe that argument falls aside.
21:13 Lex Fridman? So you famously run barefoot. Do you still run barefoot?
21:19 Speaker 01 I still run barefoot.
21:20 Lex Fridman? That's so awesome.
21:21 Speaker 01 Much to my wife's chagrin.
21:24 Lex Fridman? Do you want to make an evolutionary argument for why running barefoot is advantageous? What have you learned about human and robot movement in general from running barefoot? Human or robot and or?
21:40 Speaker 01 Well, you know, it happened the other way, right? So I was studying walking robots and I was, there's a great conference called the Dynamic Walking Conference where it brings together both the biomechanics community and the walking robots community. And so I had been going to this for years and hearing talks by people who study barefoot running and other, the mechanics of running.
22:05 Speaker 01 So I did eventually read Born to Run. Most people read Born to Run in the
22:08 Lex Fridman? First then.
22:09 Speaker 01 Right. The other thing I had going for me is actually that I I wouldn't I wasn't a runner before. And I learned to run after I had learned about barefoot running, or I mean, started running longer distances. So I didn't have to unlearn. And I'm definitely I'm a big fan of it for me, but I'm not gonna I tend to not try to convince other people. There's people who run beautifully with shoes on, and that's good. But here's why it makes sense for me. It's all about the long term game, right? So I think it's just too easy to run 10 miles, feel pretty good, and then you get home at night and you realize my knees hurt. I did something wrong, right?
22:54 Speaker 01 If you take your shoes off, then if you hit hard with your foot at all, then it hurts. You don't like run 10 miles and then and then realize you've done something some damage. You have immediate feedback telling you that you've done something that's that's maybe suboptimal. And you change your gait. I mean, it's even subconscious. If I right now, having run many miles barefoot, if I put a shoe on, my gait changes in a way that I think is not as good. So so it makes me land softer. And I think my my goals for running are to do it for as long as I can into old age, not to win any races. And so for me, this is a, you know, a way to protect myself.
23:40 Lex Fridman? Yeah, I think, first of all, I've tried running barefoot many years ago, probably the other way, just just just reading Born to Run. But just to understand, because I felt like I couldn't put in the miles that I wanted to. And it feels like running for me, and I think for a lot of people, was one of those activities that we do often, and we never really try to learn to do correctly. Like, it's funny, there's so many activities we do every day, like brushing our teeth. Right? I think a lot of us, at least me, probably have never deeply studied how to properly brush
24:22 Lex Fridman? my teeth, right? Or wash, as now with the pandemic, or how to properly wash our hands. We do it every day, but we haven't really studied, like, am I doing this correctly? But running felt like one of those things that it was absurd not to study how to do correctly because it's the source of so much pain and suffering. Like, I hate running, but I do it. I do it because I hate it, but it, I feel good afterwards. But I think it feels like you need to learn how to do it properly. So that's where barefoot running came in. And then I quickly realized that my gait was completely wrong. I was taking huge, like, steps and landing hard on the heel, all those elements. And so, yeah, from that, I actually
25:04 Lex Fridman? learned to take really small steps. Look, I already forgot the number, but I feel like it was 180 a minute or something like that. And I remember I was, I actually just took songs that are 180 beats per minute and then like tried to run at that beat, just to teach myself. It took, it took a long time. And I feel like after a while, you learn to run, you adjust it properly without going all the way to barefoot. But I feel like barefoot is the legit way to do it. I mean, I think a lot of people would be really curious about it. Can you, if they're interested in trying, what would you, how would you recommend they start or try or explore?
25:47 Speaker 01 Slowly. That's the biggest thing people do is they are excellent runners and they're used to running long distances or running fast and they take their shoes off and they hurt themselves instantly trying to do something that they were used to doing. I think I lucked out in the sense that I, I couldn't run very far when I first started trying. And I run with minimal shoes too. I mean, I will, you know, bring along a pair of actually like aqua socks or something like this. I can just slip on or running sandals. I've tried all of them.
26:17 Lex Fridman? What's the difference between a minimal shoe and nothing at all? What's like feeling wise, what does it feel like?
26:24 Speaker 01 There is, I mean, I noticed my gait changing, right? So, I mean, your, your foot has as many muscles and sensors as your hand does, right?
26:34 Lex Fridman? Sensors, oh, okay.
26:37 Speaker 01 And we do amazing things with our hands. And we stick our foot in a big, solid shoe, right? So there's, I think, you know, when you're barefoot, you're, you're just giving yourself more proprioception. And that's why you're more aware of some of the gait flaws and stuff like this. Now, you have less protection too, so.
26:57 Lex Fridman? Rocks and stuff.
26:59 Speaker 01 I mean, yeah, so, so I think people are, who are afraid of barefoot running, they worry about getting cuts or getting stepping on rocks. First of all, even if that was a concern, I think those are all like, very short term. You know, if I get a scratch or something, it'll heal in a week. If I blow out my knees, I'm done running forever. So I will trade the short term for the long term anytime. But even then, you know, this, again, to my wife's chagrin, your feet get tough, right? And.
27:25 Lex Fridman? Calist, okay.
27:26 Speaker 01 Yeah, I can run over almost anything now.
27:30 Lex Fridman? I mean, what, maybe, can you talk about? Is there hint, like, is there tips or tricks that you have? Suggestions about, like, if I wanted to try it?
27:43 Speaker 01 You know, there, there is a good book, actually. There's probably more good books since I read them. But Ken Bob, Barefoot Ken Bob Saxton.
27:54 Speaker 01 He's an interesting guy. But I think his book captures the right way to describe running, barefoot running to somebody, better than any other I've seen.
28:05 Lex Fridman? So you run pretty good distances and you bike and is, is there, you know, if we talk about bucket list items, is there something crazy on your bucket list athletically that you hope to do one day?
28:21 Speaker 01 I mean, my commute is already a little crazy.
28:24 Lex Fridman? What are we talking about here? What, what, what distance are we talking about?
28:28 Speaker 01 Well, I live about 12 miles from MIT. But you can find lots of different ways to get there. So I mean, I've run there for a long, many years, I biked there.
28:37 Lex Fridman? Both ways?
28:38 Speaker 01 Yeah, but normally I would try to run in and then bike home, bike in, run home.
28:43 Lex Fridman? But you have run there and back before?
28:45 Speaker 01 Sure.
28:45 Lex Fridman? Barefoot?
28:46 Speaker 01 Yeah, uh, yeah, or with minimal shoes or whatever that.
28:49 Lex Fridman? 12, 12 times two?
28:51 Speaker 01 Yeah.
28:51 Lex Fridman? Okay.
28:52 Speaker 01 It's became kind of a game of how can I get to work? I've rollerbladed, I've done all kinds of weird stuff, but my favorite one these days, I've been taking the Charles River to work. So I can put in a little rowboat, not so far from my house, but the Charles River takes a long way to get to MIT. So I can spend a long time getting there. And it's, you know, it's not about, I don't know, it's just about, uh, I've had people ask me, how can you justify taking that time? But for me, it's just a magical time to think, to compress, decompress. You know, especially I'll wake up, do a lot of work in the morning and then I kind of have to just let that settle before I'm ready for all my meetings.
29:37 Speaker 01 And then on the way home, it's a great time to let it sort of let that settle.
29:41 Lex Fridman? You, you lead a, like a, a large group of people. I mean, you're, is there days where you're like, oh shit, I gotta get to work in an hour?
29:55 Lex Fridman? Like, I mean, uh, is, is there, is there a tension there where, and like, if we look at the grand scheme of things, just like you said, long term, that meeting probably doesn't matter. Like you can always say, I'll just, I'll run and let the meeting happen, how it happens. Like what, uh, how do you,
30:17 Lex Fridman? that Zen, how do you, uh, what do you do with that tension between the real world saying urgently, you need to be there? This is important. Everything is melting down. How are we going to fix this robot? There's this, uh, critical meeting and then there's this, the Zen beauty of just running, the simplicity of it, you along with nature.
30:38 Lex Fridman? What do you do with that?
30:39 Speaker 01 I would say I'm not a fast runner particularly. Probably my fastest splits ever was when I had to get to daycare on time because they were going to charge me, you know, some, some dollar per minute that I was late. I've run some fast splits to daycare. But that those times are past now. I think work, you can find a work-life balance in that way. I think you just have to. I think I am better at work because I take time to think on the way in. So I plan my day around it. And I rarely feel that those are really in at odds.
31:17 Lex Fridman? So what the bucket list item? If we're talking 12 times two or approaching a marathon. What have you run an ultra marathon before? Do you do races? Is there what's?
31:35 Speaker 01 To win.
31:36 Lex Fridman? Not to.
31:38 Speaker 01 I'm not going to like take a dinghy across the Atlantic or something if that's what you want. But, uh, but if someone does and wants to write a book, I would totally read it because I I'm a sucker for that kind of thing. No, I do have some fun things that I will try. I like to, when I travel, I almost always bike to Logan Airport and fold up a little folding bike and then take it with me and bike to wherever I'm going. And it's taken me or I'll take a stand up paddleboard these days on, on the airplane and then I'll try to paddle around where I'm going or whatever. And I've done some crazy things, but, um, but not for the, you know, I've, I now talk, I don't know if you know who David Goggins is by any chance? Not well, but yeah.
32:15 Lex Fridman? But I, I talk to him now every day. So he's the person who made me do this stupid challenge. So he, he's insane and he does things for the purpose in, in the best kind of way. He does things like for the explicit purpose of suffering. Like he picks the thing that like whatever he thinks he can do, he does more. So is that, do you have that thing in you or are you?
32:44 Speaker 01 I think it's become the opposite. It's a
32:47 Lex Fridman? So you're like that dynamical system that the walker, the efficient.
32:51 Speaker 01 Yeah, it's a leave no pain, right? You should end feeling better than you started.
32:57 Lex Fridman? Okay.
32:58 Speaker 01 But it's mostly, I think, and COVID has tested this because I've lost my commute. I think I'm perfectly happy walking around, around town with my wife and kids, if they could get them to go. And it's more about just getting outside and getting away from the keyboard for some time, just to let things compress.
33:19 Lex Fridman? Let's go into robotics a little bit. What to you is the most beautiful idea in robotics? Whether we're talking about control or whether we're talking about optimization, the math side of things, or the engineering side of things, or the philosophical side of things?
33:37 Speaker 01 I think I've been lucky to experience something that not so many roboticists have experienced, which is to hang out with some really amazing control theorists. And
33:55 Speaker 01 the clarity of thought that some of the more mathematical control theory can bring to even very complex, messy looking problems
34:06 Speaker 01 is really, it really had a big impact on me and, and I had a day even just a couple of weeks ago where I had spent the day on a Zoom robotics conference, having great conversations with lots of people, felt really good about the ideas that were flowing and, and the like. And then I had a, you know, late afternoon meeting with a, one of my favorite control theorists and
34:35 Speaker 01 and we went from these, from these abstract discussions about maybes and what ifs and, and what a great idea to these super precise statements about systems that aren't that much more simple or abstract than ones I care about deeply. And the contrast of that is,
34:59 Speaker 01 I don't know, it really gets me. I think.
35:03 Speaker 01 People underestimate maybe the power of clear thinking. And so, for instance, deep learning is amazing.
35:17 Speaker 01 I use it heavily in our work. I think it's changed the world unquestionable.
35:23 Speaker 01 It makes it easy to get things to work without thinking as critically about it. So I think one of the challenges as an educator is to think about how do we make sure people get a taste of the more rigorous thinking that I think goes along with with some different approaches.
35:41 Lex Fridman? Yeah, so that's really interesting. So understanding like the fundamentals, the first principles of the of the problem, or in this case, it's mechanics, like how a thing moves, how a thing behaves, like all the forces involved, like really getting a deep understanding of that. I mean, from physics, the first principle thing come from physics. And here it's literally physics.
36:09 Lex Fridman? Yeah, and this applies in deep learning, this applies to not just, I mean, it applies so cleanly in robotics, but it also applies to just in any data set. I find this true, I mean, driving as well. There's a lot of folks in it that work on autonomous vehicles that don't study driving
36:34 Lex Fridman? like deeply. I might be coming a little bit from the psychology side, but I remember I spent a ridiculous number of hours at lunch at this like lawn chair and I would sit somewhere somewhere in MIT's campus, there's a few interesting intersections, and we just watched people cross. So we're studying pedestrian behavior. And I felt like as we record a lot of video to try and then there's the computer vision extracts their movement, how they move their head and so on. But like every time I felt like I didn't understand enough. I just, I felt like I wasn't understanding what, how are people signaling to each other? What are they thinking?
37:20 Lex Fridman? How cognizant are they of their fear of death? Like, what we like, what's the game, what's the underlying game theory here? What are, what are the incentives? And then I finally found a live stream of an intersection that's like high def that I just, I would watch. So I wouldn't have to sit out there, but that's interesting. So like, I feel.
37:40 Speaker 01 That's tough. That's a tough example because, I mean, the learning.
37:44 Lex Fridman? Humans are involved.
37:45 Speaker 01 Not just because human, but I think the learning mantra is that basically the statistics of the data will tell me things I need to know, right? And, you know, for the example you gave of all the nuances of, you know, eye contact or hand gestures or whatever that are happening for these subtle interactions between pedestrians and traffic. Right? Maybe the data will tell this, they'll tell that story. I maybe even I, uh, one level more meta than, than what you're saying. For a particular problem, I think it might be the case that data should tell us the story.
38:24 Speaker 01 But I think there's a rigorous thinking that is just an essential skill for a mathematician or an engineer that I just don't want to lose it. There are, there are certainly super rigorous, rigorous control, or sorry, machine learning people. I just think deep learning makes it so easy to do some things that our next generation are not immediately rewarded for going through some of the more rigorous approaches. And then I wonder where that takes us. I, well, I'm, I'm actually optimistic about it. I just want to do my part to try to steer that rigorous thinking.
39:05 Lex Fridman? So there's like two questions I want to ask. Do you have sort of a good example of rigorous thinking where it's easy to get lazy? And not do the rigorous thinking? And the other question I have is like, do you have advice of how to practice rigorous thinking? And, you know, in all the computer science disciplines that we've mentioned?
39:33 Speaker 01 Yeah, I mean, there are times where problems that can be solved with well-known, mature methods could also be solved with with a deep learning approach. And there's an argument that you must use learning even for the parts we already think we know, because if the human has touched it, then you've you've biased the system and you've suddenly put a bottleneck in there that is your own mental model. But something like inverting a matrix, you know, I think we know how to do that pretty well, even if it's a pretty big matrix, and we understand that pretty well. And you could train a deep network to do it, but you shouldn't, probably.
40:13 Lex Fridman? So so in that sense, rigorous thinking is understanding the the scope and limitations of the methods of the methods that we have, like how to use the tools of mathematics properly.
40:27 Speaker 01 Yeah, I think, you know, taking a class on analysis is all I'm sort of arguing is to take a chance to stop and and force yourself to think rigorously about even, you know, the rational numbers or something, you know, it doesn't have to be the end all problem. But that exercise of clear thinking, I think, goes a long way, and I just want to make sure we we keep preaching it.
40:52 Lex Fridman? We don't lose it.
40:52 Speaker 01 Yeah.
40:53 Lex Fridman? But do you think when you're doing like rigorous thinking or like maybe trying to write down equations or sort of explicitly like formally describe a system, do you think we naturally simplify things too much? Is that a danger you run into? Like, in order to be able to understand something about the system mathematically, we make it too much of a toy example?
41:18 Speaker 01 But I think that's the good stuff, right?
41:20 Lex Fridman? That's how you understand the fundamentals?
41:23 Speaker 01 I think so. I think maybe even that's a key to intelligence or something. But, I mean, OK, what if Newton and Galileo had deep learning? And and they had done a bunch of experiments, and they told the world, here's your weights of your neural network, I've we've solved the problem.
41:40 Lex Fridman? Yeah.
41:40 Speaker 01 You know, where would we be today? I don't I don't think we'd be as far as we as we are. There's something to be said about having the simplest explanation for a phenomenon. So I don't doubt that we can train neural networks to predict even physical, you know, F equals MA type equations.
42:03 Speaker 01 But I maybe I want another Newton to come along because I think there's more to do in terms of coming up with the simple models for more complicated tasks.
42:16 Lex Fridman? Yeah, let's not offend AI systems from 50 years from now that are listening to this that are probably better at might be better coming up with F equals MA equations themselves.
42:30 Speaker 01 Oh, sorry. I actually think learning is probably a route to achieving this. But the representation matters, right? And I think having a function that takes my inputs to outputs that is arbitrarily complex may not be the end goal. I think there's still, you know, the most simple or parsimonious explanation for the data. Simple doesn't mean low dimensional. That's one thing I think that we've a lesson that we've learned. So, you know, a standard way to do model reduction or system identification and controls is to the typical formulation is that you try to find the minimal state dimension realization
43:10 Speaker 01 of a system that hits some error bounds or something like that. And that's maybe not. I think we're learning that that was that state dimension is not the right metric.
43:23 Lex Fridman? Of complexity.
43:23 Speaker 01 Of complexity. But for me, I think a lot about contact, the mechanics of contact. Robot hand is picking up an object or something. And when I write down the equations of motion for that, they're they look incredibly complex, not because actually not so much because of the dynamics of the hand when it's moving, but it's just the interactions and when they turn on and off. Right? So having a high dimensional, you know, but simple description of what's happening out here is fine. But if when I actually start touching, if I write down a different dynamical system for every polygon on my robot hand and every polygon on the object, whether it's in contact or not with all the combinatorics that explodes
44:07 Speaker 01 there, then that's too complex. So I need to somehow summarize that with a more intuitive physics.
44:17 Speaker 01 Way of thinking and yeah, I'm very optimistic that machine learning will get us there.
44:22 Lex Fridman? First of all, I mean, I'll probably do it in the introduction, but you're one of the great robotics people at MIT. You're a professor at MIT. You teach a lot of amazing courses. You run a large group and you have an important history for MIT, I think, as being a part of the DARPA Robotics Challenge. Can you maybe first say, what is the DARPA Robotics Challenge and then tell your story around it, your journey with it?
44:53 Speaker 01 Yeah, sure. So the DARPA Robotics Challenge, it came on the tails of the DARPA Grand Challenge and DARPA Urban Challenge, which were the challenges that brought us, put a spotlight on self-driving cars. Gil Pratt was at DARPA and pitched a new challenge that involved disaster response. It didn't explicitly require humanoids, although humanoids came into the picture. This happened shortly after the Fukushima disaster in Japan and our challenge was motivated roughly by that because that was a case where if we had had robots that
45:38 Speaker 01 were ready to be sent in, there's a chance that we could have averted disaster. And certainly after the, in the disaster response, there were times where we would have loved to have sent robots in. So in practice, what we ended up with was a grand challenge, a DARPA Robotics Challenge, where Boston Dynamics was to make humanoid robots. People like me and the amazing team at MIT were competing first in a simulation challenge to try to be one of the ones that wins the right to work on one of the Boston Dynamics humanoids
46:20 Speaker 01 in order to compete in the final challenge, which was a physical challenge.
46:25 Lex Fridman? And at that point, it was already, so it was decided that's humanoid robots.
46:29 Speaker 01 So there were, there were two tracks. There were, you could enter as a hardware team where you brought your own robot. Or you could enter through the virtual robotics challenge as a software team that would try to win the right to use one of the Boston Dynamics robots.
46:43 Lex Fridman? Which are called Atlas.
46:44 Speaker 01 Atlas.
46:45 Lex Fridman? Humanoid robots.
46:45 Speaker 01 Yeah, it was a 400 pound marvel, but a, you know, pretty big scary looking robot.
46:52 Lex Fridman? Expensive too.
46:53 Speaker 01 Expensive.
46:54 Lex Fridman? At the time, yeah. Okay, so, uh, I mean, how did you feel the prospect of this kind of challenge? I mean, it seems, you know, autonomous vehicles, yeah, I guess that sounds hard, but not really. From a robotics perspective, it's like, didn't they do it in the eighties? Is the kind of feeling I would have, uh, like when you first look at the problem and it's on wheels. But like humanoid robots, that sounds really hard. So what, like, what are the, psychologically speaking, what were you feeling? Excited, scared? Why the heck did you get yourself involved in this kind of messy challenge?
47:36 Speaker 01 We didn't really know for sure what we were signing up for. In the sense that you could have had something that, as it was described in the call for participation, that could have put a huge emphasis on the dynamics of walking and not falling down and walking over rough terrain. Or the same description, because the robot had to go into this disaster area and turn valves and, and pick up a drill. It cut the hole through a wall. It had to do some interesting things. The challenge could have really highlighted perception and autonomous planning. Or it ended up that, you know, locomoting over a complex terrain played a pretty big role in the competition. So.
48:22 Lex Fridman? And the degree of autonomy wasn't clear.
48:25 Speaker 01 The decreaved autonomy was always a central part of the discussion. So what wasn't clear was how we would be able, how far we'd be able to get with it. So the idea was always that you want semi-autonomy, that you want the robot to have enough compute that you can have a degraded network link to a human. And so the same way you, we had degraded networks at many natural disasters. You'd send your robot in, you'd be able to get a few bits back and forth, but you don't get to have enough potentially to fully operate the robot, every joint of the robot. So, and then the question was, and the gamesmanship of the organizers was to figure out what we're capable of,
49:07 Speaker 01 push us as far as we could so that it would differentiate the teams that put more autonomy on the robot and had a few clicks and just said, go there, do this, go there, do this, versus someone who's picking every footstep or something like that.
49:22 Lex Fridman? So what were some memories, painful, triumphant from the experience? Like what was that journey? Maybe if you can dig in a little deeper, maybe even on the technical side, on the team side, that, that whole process of, from the early idea stages to actually competing.
49:45 Speaker 01 I mean, this was a defining experience for me. I, it was, it came at the right time for me in my career. I had gotten tenure before I was due a sabbatical and most people do something, you know, relaxing and restorative for a sabbatical.
49:59 Lex Fridman? So you got tenure before the, before this?
50:01 Speaker 01 Yeah, yeah, yeah. It was a good time for me. I had, I had, we had a bunch of algorithms that we were very happy with. We wanted to see how far we could push them. And this was a chance to really test our mettle, to do more proper software engineering. The team, we all just worked our butts off. We, you know, we're in that lab almost all the time.
50:23 Speaker 01 Okay, so there, I mean, there were some, of course, high highs and low lows throughout that anytime you're, you know, not sleeping and devoting your life to a 400 pound humanoid. I remember actually one funny moment where we're all super tired and so Atlas had to walk across cinder blocks. That was one of the obstacles. And I remember Atlas was powered down and hanging limp, you know, on the, on its harness. And the, the humans were there like laying, you know, picking up and laying the brick down so that the robot could walk over it. And I thought, what is wrong with this? You know, we've got a robot just watching us do all the manual labor so that it can take its little stroll across the train. But
51:06 Speaker 01 I mean, even the, even the virtual robotics challenge was, was super nerve wracking and dramatic. I remember, so, so we were using gazebo as a simulator on the cloud. And there was all these interesting challenges. I think the investment that OSR's FC, whatever they were called at that time, Brian Gurkey's team at Open Source Robotics, they were pushing on the capabilities of gazebo in order to scale it to the complexity of these challenges. So, you know, up to the virtual competition. So the virtual competition was you will sign on at a certain time and we'll have a network connection to another machine on the cloud
51:49 Speaker 01 that is running the simulator of your robot. And your controller will run on this computer, this controller, this computer and, and the physics will run on the other and you have to, to connect. Now, the physics, they wanted it to run at real time rates because there was an element of human interaction and humans could, if you do want to teleop, it works way better if it's at frame rate.
52:12 Lex Fridman? Oh, cool.
52:13 Speaker 01 But it was very hard to simulate these, these complex scenes at real time rate. So right up to like days before the competition, the simulator wasn't quite at real time rate. And that was great for me because my controller was solving a bit, pretty big optimization problem. And it wasn't quite at real time rate. So I was fine. I was keeping up with the simulator. We were both running at about point seven. And I remember getting this email, and by the way, the perception folks on our team hated that they knew that if my controller was too slow, the robot was going to fall down. And no matter how good their perception system was, if I can't make my controller faster. Anyways, we get this email like three days before the virtual competition.
52:57 Speaker 01 You know, it's for all the marbles. We're going to either get a humanoid robot or we're not. And we get an email saying, good news, we made the robot, the simulator faster. It's now one point. And I, we were, I was just like, oh, man, what are we going to do here? So that came in late at night for me.
53:16 Lex Fridman? A few days ahead.
53:17 Speaker 01 A few days ahead. I went over, there was, it happened at Frank Pimenter, who's a very, very sharp. He's a student at the time, working on optimization. He was still in lab. Frank, we need to make the quadratic programming solver faster. Not like a little faster. It's actually, you know. And we wrote a new solver for that QP together that night.
53:45 Lex Fridman? A new solver. So there's a really hard optimization problem that you're constantly solving. You didn't make the optimization problem simpler? You wrote a new solver?
53:55 Speaker 01 So, I mean, your observation is almost spot on. What we did was what everybody, I mean, people know how to do this, but we had not yet done this idea of warm starting. So we are solving a big optimization problem at every time step. But if you're running fast enough, the optimization problem you're solving on the last time step is pretty similar to the optimization you're going to solve with the next. We had, of course, had told our commercial solver to use warm starting. But even the interface to that commercial solver was causing us these delays. So what we did was we basically wrote, we called it fast QP at the time. We wrote a very lightweight, very fast layer, which would basically check if nearby solutions
54:39 Speaker 01 to the quadratic program, which were very easily checked, could stabilize the robot. And if they couldn't, we would fall back to the solver.
54:47 Lex Fridman? You couldn't really test this well, right?
54:50 Speaker 01 Um, so we always knew that if we fell back to, if we, it got to the point where if for some reason, things slowed down and we fell back to the original solver, the robot would actually literally fall down.
55:03 Speaker 01 So it was, it was a harrowing sort of edge we're, ledge we're sort of on. But, I mean, actually, like the, the 400 pound humanoid could come crashing to the ground if you, if you, if your solver's not fast enough. But, you know, we had lots of good experiences.
55:19 Lex Fridman? So can I ask you a weird question? I, I get about the idea of hard work. So, um, actually, people like students of yours that I've interacted with and just in robotics, people in general. But they, uh, they have moments, at moments have worked harder than, uh, most people I know in terms of, if you look at different disciplines of how hard people work, but they're also like the happiest. Like, just like, I don't know.
55:55 Lex Fridman? It's the same thing with like running, people that push themselves to like the limit. They all also seem to be like the most like full of life somehow. And I get often criticized like you're not getting enough sleep. What are you doing to your body? Blah, blah, blah, like this kind of stuff. And I usually just kind of respond like I'm, I'm doing what I love. I'm passionate about it. I love it. I feel like it's, uh, it's invigorating. I actually think, I don't think the lack of sleep is what hurts you. I think what hurts you is, uh, stress and lack of doing things that you're passionate about. But in this world, yeah, I mean, can you comment about, uh,
56:36 Lex Fridman? why the heck robotics people are, uh, willing to push themselves to that degree? Is there value in that? And why are they so happy?
56:47 Speaker 01 I think, I think you got it right. I mean, I think the causality is not that we work hard. And I think other disciplines work very hard too. But it's, I don't think it's that we work hard and therefore we are happy. I think we found something that we're truly passionate about.
57:05 Speaker 01 It makes us very happy. And then we get a little involved with it and spend a lot of time on it. What a luxury to have something that you want to spend all your time on, right?
57:16 Lex Fridman? We could talk about this for many hours, but maybe if we could pick, is there something on the technical side, on the approach that you took that's interesting? That turned out to be a terrible failure or a success that you carry into your work today? About all the different ideas that were involved in making, whether in the simulation or in the real world, making this semi-autonomous system work?
57:44 Speaker 01 I mean, it really did teach me something fundamental about what it's going to take to get robustness out of a system of this complexity. I would say the DARPA challenge really was foundational in my thinking. I think the autonomous driving community thinks about this. I think lots of people thinking about safety critical systems that might have machine learning in the loop are thinking about these questions. For me, the DARPA challenge was the moment where I realized, you know, we've spent every waking minute running this robot. And again, for the physical competition, days before the competition, we saw the robot fall down in a way it had never fallen down before. I thought, you know, how could we have found that? You know, we only have one robot.
58:28 Speaker 01 It's running almost all the time. We just didn't have enough hours in the day to test that robot. Something has to change, right? And then I think that, I mean, I would say that the team that won was from KaiS, was the team that had two robots and was able to do not only incredible engineering, just absolutely top rate engineering, but also they were able to test at a rate and discipline that we didn't keep up with.
58:56 Lex Fridman? What does testing look like? What are we talking about here? Like, what's a loop of test? Like, from start to finish, what is a loop of testing?
59:05 Speaker 01 Yeah, I mean, I think. There's a whole philosophy to testing. There's the unit tests and you can do that on a hardware. You can do that in a small piece of code. You write one function. You should write a test that that checks that function's input and outputs. You should also write an integration test at the other extreme of of running the whole system together, you know, where that that try to turn on all of the different functions that you've you think are correct. It's much harder to write the specifications for a system level test, especially if that system is as complicated as a humanoid robot, but the philosophy is sort of the same. On the real robot, it's it's no different, but on a real robot, it's impossible to run the same experiment twice. So if you if you see a failure,
59:49 Speaker 01 you hope you caught something in the logs that tell you what happened, but you'd probably never be able to run exactly that experiment again. And right now, I think our philosophy is just basically Monte Carlo estimation is just run as many experiments as we can, maybe try to set up the environment to to make the things we are worried about happen as often as possible. But really, we're relying on somewhat random search in order to test. Maybe that's all we'll ever be able to. But I think, you know, because there's an argument that the things that'll get you are the the things that are really nuanced in the world. And it'd be very hard to, for instance, put back in a simulation.
1:00:33 Lex Fridman? Yeah, the I guess the edge cases. What was the the hardest thing? Like, so you said, walking over rough terrain, like the just taking footsteps. I mean, people there's it's so dramatic and painful in a certain kind of way to watch these videos from the DRC of robots falling.
1:00:54 Speaker 01 Yep.
1:00:55 Lex Fridman? I just so heartbreaking. I don't know. Maybe it's because for me, at least, we anthropomorphize the robot. Of course, it's also funny for some reason, like humans falling is funny for I don't it's some dark reason. I'm not sure why it is so, but it's also like tragic and painful. And so speaking of which, I mean, what what made the robots fall and fail in your view?
1:01:22 Speaker 01 So I can tell you exactly what happened on a we I contributed one of those. Our team contributed one of those spectacular falls. Every one of those falls the has a complicated story. I mean, at one time, the power effectively went out on the robot. Because it had been sitting at the door, waiting for a green light to be able to proceed and its batteries, you know, and therefore it just fell backwards and smashed its head to ground and it was hilarious, but it wasn't because of bad software, right? But for ours, so the hardest part of the challenge, the hardest task, in my view, was getting out of the Polaris. It was actually relatively easy to drive the Polaris.
1:02:00 Lex Fridman? Can you tell the story, sorry to interrupt, the story of the car? People should watch this video. I mean, the thing you've come up with is just brilliant. But anyway, sorry, what's?
1:02:12 Speaker 01 Yeah, we kind of joke, we call it the big robot, little car problem because somehow the race organizers decided to give us a 400 pound humanoid and then they also provided the vehicle, which was a little Polaris and the robot didn't really fit in the car. So you couldn't drive the car with your feet under the steering column. We actually had to straddle the, the main column of the, and have basically one foot in the passenger seat, one foot in the driver's seat and then drive with our left hand. But the hard part was we had to then park the car, get out of the car. It didn't have a door, that was okay, but it's just getting up from crouched, from sitting, when you're
1:02:56 Speaker 01 in this very constrained environment.
1:02:58 Lex Fridman? First of all, I remember after watching those videos, I was much more cognizant of how hard is it, it is for me to get in and out of the car and out of the car especially. Like, it's actually a really difficult control problem.
1:03:11 Speaker 01 Yeah.
1:03:12 Lex Fridman? And I, I'm very cognizant of it when I'm like injured, for whatever reason.
1:03:16 Speaker 01 It's really hard.
1:03:17 Lex Fridman? Yeah. So how did you, how did you approach this problem?
1:03:20 Speaker 01 So we had a, you know, you think of NASA's operations and they have these checklists, you know, pre-launch checklist and the like. We weren't far off from that. We had this big checklist and on the first day of the competition, we were running down our checklist. And one of the things we had to do, we had to turn off the controller, the piece of software that was running, that would drive the left foot of the robot in order to accelerate on the gas. And then we turned on our balancing controller. And the nerves, jitters of the first day of the competition, someone forgot to check that box and turn that controller off. So we used a lot of motion planning to figure out a sort of configuration of the robot that we could get up and over. We relied
1:04:04 Speaker 01 heavily on our balancing controller. And, and basically, there were, when the robot was in one of its most precarious, you know, sort of configurations, trying to sneak its big leg out of the, out of the side, the other controller that thought it was still driving told its left foot to go like this. And, and that wasn't good. But, but it turned disastrous for us because what happened was a little bit of push here. Actually, if we have videos of us, you know, running into the robot with a 10 foot pole and it kind of will recover. But this is a case where there's no space to recover. So a lot of our secondary balancing mechanisms about like take a step to recover, they were all
1:04:49 Speaker 01 disabled because we were in the car and there was no place to step. So we were relying on our just lowest level reflexes. And even then, I think just hitting the foot on the seat, on the, on the floor, we probably could have recovered from it. But the thing that was bad that happened is when we did that and we jostled a little bit, the tailbone of our robot had, was only a little off the seat, it hit the seat. And the other foot came off the ground just a little bit. And nothing in our plans had ever told us what to do if your butt's on the seat and your feet are in the air. Feet in the air. And then, the thing is, once you get off the script, things can go very wrong because even our state estimation, our system that was trying to collect all the data from the
1:05:32 Speaker 01 sensors and understand what's happening with the robot, it didn't know about this situation. So it was predicting things that were just wrong. And then we did a violent shake and fell off in our face first on, out of the robot.
1:05:47 Lex Fridman? Like into the destination.
1:05:49 Speaker 01 That's true. We fell in. We got our point for egress.
1:05:53 Lex Fridman? But so is there any hope for that's interesting. Is there any hope for Atlas to be able to do something when it's just on its butt and feet in the air?
1:06:03 Speaker 01 Absolutely.
1:06:04 Lex Fridman? So you can, what do you?
1:06:05 Speaker 01 No, so that's, that is one of the big challenges. And I think it's still true. You know, Boston Dynamics and, and
1:06:14 Speaker 01 animal and there's this incredible work on, on legged robots happening around the world.
1:06:21 Speaker 01 Most of them still are very good at the case where you're making contact with the world at your feet. And they have typically point feet relatively. They're balls on their feet, for instance. If that, if those robots get in a situation where the elbow hits the wall or something like this, that's a pretty different situation. Now they have layers of mechanisms that will make, I think the, the more mature solutions have, have ways in which the controller won't do stupid things. But a human, for instance, is able to leverage incidental contact in order to accomplish a goal. In fact, I might, if you push me, I might actually put my hand out and make a new, brand new contact. The feet of the robot are doing this on, on quadrupeds, but
1:07:02 Speaker 01 we mostly in robotics are afraid of contact on the rest of our body. Which is crazy. There's this whole field of motion planning, collision free motion planning. And we write very complex algorithms so that the robot can dance around and make sure it doesn't touch the world.
1:07:22 Lex Fridman? So people are just afraid of contact because contact the scene is a difficult.
1:07:26 Speaker 01 It's still a difficult control problem. And sensing problem.
1:07:32 Lex Fridman? Now you're a serious person.
1:07:36 Lex Fridman? I'm a little bit of an idiot and I'm going to ask you some dumb questions. So I do, I do martial arts. So like jiu jitsu, there's, I wrestled my whole life. So let me, let me ask the question. You know, like whenever people learn that I do any kind of AI or like I mentioned, robots and things like that. They say, when are we going to have robots that, you know, that can win in a wrestling match? Or in a fight against a human? So we just mentioned sitting on your butt. Feet in the air, that's a common position jiu jitsu when you're on the ground, you're your down opponent. Like what, how difficult do you think is the problem?
1:08:20 Lex Fridman? And when will we have a robot that can defeat a human in a wrestling match? And we're talking about a lot, like, I don't know if you're familiar with wrestling, but essentially.
1:08:32 Speaker 01 Not very.
1:08:33 Lex Fridman? It's basically the art of contact. It's like, it's because you're, you're, you're picking contact points. And then using like leverage, like to off balance to, to trick people. Like you make them feel like you're doing one thing. And then they, they change their balance. And then you switch what you're doing. And then results in a throw or whatever. So like, it's basically the art of multiple contacts.
1:09:05 Speaker 01 Awesome. It's a nice description of it. So there's also an opponent in there, right? So, so if.
1:09:11 Lex Fridman? Very dynamic.
1:09:12 Speaker 01 Right? If you are wrestling a human and are in a game theoretic situation with a human, that's still hard. But just to speak to the, you know, quickly reasoning about contact part of it, for instance.
1:09:28 Lex Fridman? Yeah, maybe even throwing the game theory out of it, almost like, uh, yeah, almost like a non dynamic opponent.
1:09:34 Speaker 01 Right. There's reasons to be optimistic, but I think our best understanding of those problems are still pretty hard. I have been increasingly focused on manipulation, partly where that's a case where the contact has to be much more rich. And there are some really impressive examples of, of deep learning policies, controllers that, that can appear to do good things through contact. We've even got new examples of, of, you know, deep learning models of predicting what's going to happen to objects as they go through contact. But I think the challenge you just offered there still eludes us, right?
1:10:18 Speaker 01 The, the ability to make a decision based on those models quickly.
1:10:24 Speaker 01 You know, I have to think, though, it's hard for humans too when you get that complicated. I think probably you had maybe a slow motion version of where you learned the basic skills and you've probably gotten better at it and there's much more subtlety. But it might still be hard to actually, you know, really on the fly, take a, you know, model of your humanoid and figure out how to, how to plan the optimal sequence. That might be a problem we never solve.
1:10:53 Lex Fridman? Well, the, I mean, one of the most amazing things to me about the, we could talk about martial arts, we could also talk about dancing, doesn't really matter. To human, I think it's the most interesting study of contact. It's not even the dynamic element of it. It's the, like, when you get good at it, it's so effortless. Like, I can just, I'm very cognizant of the entirety of the learning process being essentially like, learning how to move my body in a way that I could throw very large weights around effortlessly. Like, and I can feel the learning. Like, I'm a huge believer in drilling of techniques.
1:11:38 Lex Fridman? And you can just like feel your, I don't, you're not feeling, you're feeling, I'm sorry, you're learning it intellectually a little bit, but a lot of it is the body learning it somehow, like instinctually. And whatever that learning is, that's really, I'm not even sure if that's equivalent to like a deep learning, learning a controller. I think it's something more, it feels like there's a lot of distributed learning going on.
1:12:08 Speaker 01 Yeah, I think there's hierarchy and composition.
1:12:11 Lex Fridman? Yeah.
1:12:13 Speaker 01 Probably in the systems that we don't capture very well yet. You have layers of control systems, you have reflexes at the bottom layer and you have a, you know, a system that's capable of planning a vacation to some distant country, which is probably, you probably don't have a controller, a policy for every possible destination you'll ever pick, right? But there's something magical in the in-between. And how do you go from these low-level feedback loops to something that feels like a pretty complex set of outcomes?
1:12:49 Speaker 01 You know, my guess is, I think, I think there's evidence that you can plan at some of these levels, right? So Josh Tenenbaum just showed his talk the other day. He's got a game he likes to talk about, I think he calls it the pick three game or something, where he puts a bunch of clutter down in front of a person. And he says, okay, pick three objects, and it might be a telephone, or a shoe, or a Kleenex box, or whatever. And apparently, you pick three items, and then you pick, he says, okay, pick the first one up with your right hand, the second one up with your left hand. Now, using those objects, those now as tools, pick up the third object. Right?
1:13:28 Speaker 01 So that's down at the level of physics and mechanics and contact mechanics that I think we do learning, or we do have policies for, we do control for, almost feedback. But somehow, we're able to still, I mean, I've never picked up a telephone with a shoe and a water bottle before, and somehow, and it takes me a little longer to do that the first time, but most of the time, we can sort of figure that out. So, yeah, I think the amazing thing is this ability to be flexible with our models, plan when we need to, use our well-oiled controllers when we don't, when we're in familiar territory.
1:14:10 Speaker 01 Having models, I think the other thing you just said was something about, I think your awareness of what's happening is even changing as you, as you get, as you improve your expertise, right? So maybe you have a very approximate model of the mechanics to begin with, and as you gain expertise, you get a more refined version of that model. You're aware of muscles, or balanced components that you just weren't even aware of before. So how do you scaffold that?
1:14:38 Lex Fridman? Yeah, plus the fear of injury, the ambition of goals, of excelling, and fear of mortality. Let's see, what else is in there as motivations? Overinflated ego in the beginning, like, and then a crash of confidence in the middle. All of those seem to be essential for the learning process.
1:15:03 Speaker 01 And if all that's good, then you're probably optimizing energy efficiency.
1:15:07 Lex Fridman? Yeah, right, so we have to get that right. So, you know, there was this idea that you would have robots play soccer better.
1:15:18 Lex Fridman? Then human players by 2050, that was the goal. Uh, well, basically was the goal to beat world champion team.
1:15:27 Speaker 01 Yeah.
1:15:27 Lex Fridman? To become a World Cup, be like a World Cup.
1:15:29 Speaker 01 Right.
1:15:29 Lex Fridman? Level team. So are we gonna see that first? Or um, a robot? If you're familiar, there's an organization called UFC for mixed martial arts. Are we gonna see a World Cup championship soccer team that are robots? Or a UFC champion? Mixed martial artists, uh, as a robot?
1:15:50 Speaker 01 I mean, it's very hard to, to say one thing is harder than one, some problems harder than the other. What probably matters is um, who, who, who started the organization that, that, I mean, I think RoboCup has a pretty serious following. And there is a history now of people playing that game, learning about that game, building robots to play that game, building increasingly more human robots. It's got momentum. And so if you want to uh, to have mixed martial arts compete, you better start your, start your organization now, right? Um, I think almost independent of which problem is technically harder, because they're both hard and they're both different.
1:16:28 Lex Fridman? That's a good point. I mean, those videos are just hilarious that like uh, especially the humanoid robots trying to um,
1:16:37 Lex Fridman? trying to play soccer. I mean, they're kind of terrible right now.
1:16:40 Speaker 01 I mean, I guess there is robo sumo wrestling. There's like the robo one competitions. Um, where they do have these robots that go on the table and basically fight. So maybe I'm wrong, maybe.
1:16:50 Lex Fridman? First of all, do you have a year in mind for RoboCup? Just from a robotics perspective, seems like a super exciting possibility that um,
1:17:01 Lex Fridman? like in the physical space, this is what's interesting. Uh, I think the world is captivated. I think it's really exciting. It's um, it inspires just a huge number of people. When a machine beats a human.
1:17:17 Lex Fridman? At a game that humans are really damn good at. So you're talking about chess and go. But that's in the, in the world of digital. I don't think machines have beat humans at a game in the physical space yet, but that would be just.
1:17:34 Speaker 01 You have to make the rules very carefully, right? I mean, if, if, if Atlas kicked me in the shins, I'm down and, uh, you know, and, and game over. So there's, you know, it's, it's very subtle on.
1:17:47 Lex Fridman? Yeah, I think the. I think the fighting one is a weird one. Yeah. Cause you're, you're talking about a machine that's much stronger than you. But yeah, in terms of soccer, basketball, all those kinds.
1:17:56 Speaker 01 Soccer, right? I mean, as soon as there's contact or whatever. And there's, there are some things that the robot will do better. I think. If you really set yourself up to try to see, could robots win the game of soccer as the rules were written? The right thing for the robot to do is to play very differently than a human would play. It's, you're not going to get, you know, the perfect soccer player robot. You're going to get something that exploits the rules, exploits its super actuators, its super low bandwidth, um, you know, feedback loops or whatever. And it's going to play the game differently than you want it to play.
1:18:33 Lex Fridman? Yeah.
1:18:34 Speaker 01 Um, and it, I bet there's ways, there's, I bet there's loopholes, right? We saw that in the, in the DARPA challenge. Uh, that, that it's very hard to write a set of rules that someone can't find, uh, a way to exploit.
1:18:49 Lex Fridman? Let me ask another ridiculous question. I probably, I think this might be the last ridiculous question, but.
1:18:55 Speaker 01 I doubt it.
1:18:58 Lex Fridman? I, I aspire to ask as many ridiculous questions of, uh, of a brilliant MIT professor. Okay. Uh, I don't know if you've seen the Black Mirror.
1:19:10 Speaker 01 It's funny, I never watched the episode. I know when it happened, though. Because I gave a talk to some MIT faculty one day on an unassuming Monday or whatever. I was telling them about the state of robotics. And I showed some video from Boston Dynamics of the quadruped. Spot at the time, it was the early version of Spot. And there was a look of horror that went across the room. And I said, what? You know, I've shown videos like this a lot of times. What happened? And it turns out that this video had got, yeah, this Black Mirror episode had changed the way people watched. Yeah, the videos I was putting out.
1:19:50 Lex Fridman? The way they see these kinds of robots. So I talked to so many people who are just terrified because of that episode, probably of these kinds of robots. They, I almost want to say that you almost kind of like enjoy being terrified. I don't even know what it is about human psychology that kind of imagine doomsday, the destruction of the universe or our society and kind of like enjoy being afraid. I don't want to simplify it, but it feels like they talk about it so often. It almost, there does seem to be an addictive quality to it. I talked to a guy, so there's a guy named Joe Rogan, who's kind of the flag bearer for being terrified of these robots. Do you have a, two questions.
1:20:34 Lex Fridman? One, do you have an understanding of why people are afraid of robots? And the second question is, in Black Mirror, just to tell you the episode, I don't even remember it that much anymore. But these robots, I think they can shoot like a pellet or something. They basically have, it's basically a spot with a gun. And how far are we away from having robots that go rogue like that? You know, basically Spot that goes rogue for some reason and somehow finds a gun?
1:21:08 Speaker 01 Right. So.
1:21:11 Speaker 01 I mean, I'm not a psychologist. I think I don't know exactly why people react the way they do.
1:21:20 Speaker 01 I think, I think we have to be careful about the way robots influence our society and the like. I think that's something that's a responsibility that roboticists need to embrace.
1:21:32 Speaker 01 I don't think robots are going to come after me with a kitchen knife or a pellet gun right away. And I mean, if they were programmed in such a way, but I used to joke with Atlas that
1:21:44 Speaker 01 all I had to do was run for five minutes and its battery would run out. But actually, they've got a very big battery in there by the end. So it was over an hour.
1:21:54 Speaker 01 I think the fear is a bit cultural, though, because I mean, you notice that, like, I think in my age in the US, we grew up watching Terminator. Right? If I had grown up at the same time in Japan, I probably would have been watching Astro Boy. And there's a very different reaction to robots in different countries. Right? So I don't know if it's a human innate fear of metal marvels or if it's
1:22:22 Speaker 01 something that we've done to ourselves with our sci fi.
1:22:26 Lex Fridman? Yeah, the stories we tell ourselves through, through movies, through just
1:22:32 Lex Fridman? through popular media. But if I were to tell, you know, if you were my therapist and I said, I'm really terrified that we're going to have these robots very soon that will hurt us. Like, how do you approach making me feel better? Like, why shouldn't people be afraid? There's a, I think there's a video that went viral.
1:23:01 Lex Fridman? Recently, everything, everything with Spot in Boston, it goes viral in general. But usually it's like really cool stuff, like they're doing flips and stuff or like sad stuff. Atlas being hit with a boomstick or something like that. But there's a video where I think one of the new productions, Spot Robots, which are awesome. It was like patrolling somewhere in like in some country. And like people immediately were like saying like, this is like the dystopian future. Like the surveillance state. For some reason, like you can just have a camera, like something about Spot being able to walk on four feet. With like really terrified people.
1:23:43 Lex Fridman? So like, what, what do you say to those people? I think there is a legitimate fear there because so much of our future is uncertain. But at the same time, technically speaking, it seems like we're not there yet. So what do you say?
1:24:01 Speaker 01 I mean, I think technology is complicated. It can be used in many ways. I think there are purely software
1:24:12 Speaker 01 attacks that somebody could use to do great damage. Maybe they have already. You know, I think wheeled robots could be used in bad ways too.
1:24:25 Lex Fridman? Drones.
1:24:26 Speaker 01 Drones, right?
1:24:30 Speaker 01 I don't think that, let's see. I don't want to be building technology just because I'm compelled to build technology and I don't think about it. But I would consider myself a technological optimist, I guess, in the sense that
1:24:48 Speaker 01 I think we should continue to create and evolve and our world will change. And if we will introduce new challenges, we'll screw something up maybe. But I think also we'll invent ourselves out of those challenges and life will go on.
1:25:06 Lex Fridman? See, it's interesting because you didn't mention like this is technically too hard.
1:25:11 Speaker 01 I don't think robots are, I think people attribute a robot that looks like an animal as maybe having a level of self-awareness or consciousness or something that they don't have yet, right? So it's not, I think our ability to anthropomorphize those robots is probably, we're assuming that they have a level of intelligence that they don't yet have, and that might be part of the fear. So in that sense, it's too hard. But, you know, there are many scary things in the world, right? So I think we're right to ask those questions, we're right to think about the implications of our work.
1:25:52 Lex Fridman? Right. In the, in the, in the short term, as we're working on it, for sure. Is there something long-term that scares you about our future with AI and robots? A lot of folks, from Elon Musk to Sam Harris, to a lot of folks talk about the, you know, existential threats about artificial intelligence. Oftentimes, robots kind of inspire that the most because of the anthropomorphism. Do you have any fears?
1:26:24 Speaker 01 It's an important question. I actually, I think I like Rod Brooks' answer maybe the best on this. I think, and it's not the only answer he's given over the years, but maybe one of my favorites is, he says, it's not going to be, he's got a book, Flesh and Machines, I believe. It's not going to be the robots versus the people. We're all going to be robot people. Because, you know, we already have smartphones, some of us have serious technology implanted in our bodies already, whether we have a hearing
1:27:00 Speaker 01 aid, or a pacemaker, or anything like this. People with amputations might have prosthetics. That's a trend, I think, that is likely to continue. I mean, this is now wild speculation. But, I mean, when do we get to cognitive implants and the like?
1:27:23 Lex Fridman? Yeah, with Neuralink, brain-computer interfaces. That's interesting. So there's a, there's a dance between humans and robots that's going to be.
1:27:33 Lex Fridman? It's going to be impossible to be scared of the other out there, the robot, because the robot will be part of us, essentially. It'd be so intricately sort of part of our society.
1:27:46 Speaker 01 Yeah, and it might not even be implanted part of us, but just it's so much of part of our, yeah, our society.
1:27:54 Lex Fridman? So in that sense, the smartphone is already the robot we should be afraid of. Yeah, I mean, yeah, and that all the usual fears arise of the misinformation, the manipulation, all those kinds of things that, um,
1:28:12 Lex Fridman? that the problems are all the same. They're all, they're human problems, essentially, it feels like.
1:28:17 Speaker 01 Yeah, I mean, I think the, the way we interact with each other online is changing the value we put on, you know, personal interaction. And that's a crazy big change that's going to happen and rip through our, has already been ripping through our society, right? And that has implications that are massive. I don't know if they should be scared of it or go with the flow, but I don't see, you know, some battle lines between humans and robots being the first thing to worry about.
1:28:46 Lex Fridman? I mean, I do want to just, as a kind of comment, maybe you can comment about your just feelings about Boston Dynamics in general. But, you know, I love science, I love engineering. I think there's so many beautiful ideas in it. And when I look at Boston Dynamics or legged robots in general, I think they inspire people curiosity and feelings in general, excitement about engineering more than almost anything else in popular culture. And I think that's such an exciting, like, responsibility and possibility for robotics. And Boston Dynamics is riding that wave pretty damn well.
1:29:27 Lex Fridman? Like, they found it, they've discovered that hunger and curiosity in the people, and they're doing magic with it. I don't care if the, I mean, I guess is their company, they have to make money, right? But they're already doing incredible work in inspiring the world about technology. I mean, do you have, do you have thoughts about Boston Dynamics? Maybe others, your own work in robotics and inspiring the world in that way?
1:29:54 Speaker 01 I completely agree. I think Boston Dynamics is absolutely awesome. I think I show my kids those videos, you know, and the best thing that happens is sometimes they've already seen them, you know, right? I think I just think it's a pinnacle of success in robotics that is just one of the best things that's happened. Absolutely, completely agree.
1:30:19 Lex Fridman? One of the heartbreaking things to me is how many robotics companies fail. How hard it is to make money with a robotics company. Like iRobot went through hell just to arrive at a Roomba to figure out one product. And then there's so many home robotics companies like G-Bo and Anki, Anki, the cutest toy, that's a great robot, I thought, went down. I'm forgetting a bunch of them, but a bunch of robotics companies fail.
1:30:54 Speaker 01 Sure.
1:30:55 Lex Fridman? Roz Company, Rethink Robotics. Like, do you have anything hopeful to say about the possibility of making money with robots?
1:31:07 Speaker 01 Oh, I think you can't just look at the failures. You can, I mean, Boston Dynamics is a success. There's lots of companies that are still doing amazingly good work in robotics. I mean, this is the capitalist ecology or something, right? I think you have many companies, you have many startups and they push each other forward and many of them fail and some of them get through. And that's sort of the natural
1:31:32 Lex Fridman? Way of things.
1:31:33 Speaker 01 Way of those things. I don't know that is robotics really that much worse. I feel the pain that you feel too. Every time I read one of these, I sometimes it's friends and I definitely wish it went better, went differently. But I think it's healthy and good to have bursts of ideas, bursts of activities, ideas, if they are really aggressive, they should fail sometimes.
1:32:02 Speaker 01 Certainly, that's the research mantra, right? If you're succeeding at every problem you attempt, then you're not choosing aggressively enough.
1:32:10 Lex Fridman? Is it exciting to you, the new spot?
1:32:13 Speaker 01 Oh, it's so good.
1:32:14 Lex Fridman? When are you getting him as a pet? It?
1:32:17 Speaker 01 Yeah, I mean, I have to dig up 75K right now.
1:32:20 Lex Fridman? I mean, it's so cool that there's a price tag. You can go and then actually buy it and.
1:32:25 Speaker 01 I have a Skydio R1. Love it. So, um, no, I would, I would, I would absolutely be a customer.
1:32:35 Lex Fridman? I wonder what your kids would think about it.
1:32:37 Speaker 01 I actually, um, Zach from Boston Dynamics would let my kid drive in one of their demos one time, and that was just so good, so good.
1:32:48 Lex Fridman? And again.
1:32:49 Speaker 01 Forever be grateful for that.
1:32:51 Lex Fridman? And there's something magical about the anthropomorphization of that arm. It adds another level of human connection. I'm not sure we understand from a control aspect, the value of anthropomorphization.
1:33:08 Lex Fridman? I think that's an understudied and under-understood engineering problem. There's been a psycho, psychologists have been studying it. I think it's part, like manipulating our mind to believe things is a valuable engineering. Like, this is another degree of freedom that can be controlled.
1:33:26 Speaker 01 I like that. Yeah, I think that's right. I think, you know, there's something that humans seem to do, or maybe my dangerous introspection, is, uh, I think we are able to make very simple models that assume a lot about the world very quickly. And then it takes us a lot more time, like your wrestling. You know, you probably thought you knew what you were doing with wrestling and you were fairly functional as a complete wrestler. And then you slowly got more expertise. So maybe it's natural that our first, first level of defense against seeing a new robot is to think of it in our existing models of how humans and animals behave.
1:34:09 Speaker 01 And it's just, and as you spend more time with it, then you'll develop more sophisticated models that will appreciate the differences.
1:34:17 Lex Fridman? Exactly. Can you say, what does it take to control a robot? Like what is the control problem of a robot? And in general, what is a robot in your view? Like, how do you think of this system?
1:34:32 Speaker 01 What is a robot?
1:34:33 Lex Fridman? What is a robot?
1:34:34 Speaker 01 I think robotics-
1:34:35 Lex Fridman? Ridiculous questions.
1:34:37 Speaker 01 No, no, it's good. I mean, there's standard definitions of combining computation with some ability to do mechanical work. I think that gets us pretty close. But I think robotics has this problem that once things really work, we don't call them robots anymore. Like, my dishwasher at home is pretty sophisticated.
1:35:01 Speaker 01 Beautiful mechanisms. There's actually a pretty good computer, probably a couple of chips in there doing amazing things. We don't think of that as a robot anymore. Which isn't fair, because then roughly it means that robotics always has to solve the next problem and doesn't get to celebrate its past successes. I mean, even factory room floor robots are super successful. They're amazing. But that's not the ones, I mean, people think of them as robots, but they don't. If you ask what are the successes of robotics? Somehow, it doesn't come to your mind immediately.
1:35:34 Lex Fridman? So the definition of robot is a system with some level of automation that fails frequently?
1:35:40 Speaker 01 Something like, it's the computation plus mechanical work and unsolved problem.
1:35:47 Lex Fridman? Unsolved problem, yeah. So from a perspective of control and mechanics, dynamics, what is a robot?
1:35:57 Speaker 01 So there are many different types of robots. The control that you need for
1:36:03 Speaker 01 a Jibo robot, you know, some robot that's sitting on your countertop and interacting with you, but not touching you, for instance, is very different than what you need for an autonomous car or an autonomous drone. It's very different than what you need for a robot that's gonna walk or pick things up with its hands, right? My passion has always been for the places where you're interacting more, you're doing more dynamic interactions with the world. So, walking, now manipulation.
1:36:35 Speaker 01 And the control problems there are beautiful. I think contact is one thing that differentiates them from many of the control problems we've solved classically, right? The modern control grew up stabilizing fighter jets that were passively unstable. And there's like amazing success stories from control all over the place. Power grid, I mean, there's all kinds of, it's everywhere that we don't even realize, just like AI is now. So you mentioned contact, like what's contact? So an airplane is an extremely complex system or a spacecraft landing or whatever. But at least it has the luxury of things change relatively continuously.
1:37:20 Speaker 01 That's an oversimplification. But if I make a small change in the command I send to my actuator, then the path that the robot will take tends to change only by a small amount. And there's a feedback mechanism here. And there's a feedback mechanism. And thinking about this as locally, like a linear system, for instance, I can use more linear algebra tools to study systems like that, generalizations of linear algebra to these smooth systems. What is contact? The robot has something very discontinuous that happens when it makes or breaks, when it starts touching the world.
1:38:02 Speaker 01 And even the way it touches or the order of contacts can change the outcome in potentially unpredictable ways. Not unpredictable, but complex ways. I do think there's a little bit of, a lot of people will say that contact is hard in robotics, even to simulate. And I think there's a little bit of a, there's truth to that, but maybe a misunderstanding around that.
1:38:30 Speaker 01 So what is limiting is that when we think about our robots and we write our simulators, we often make an assumption that that objects are rigid.
1:38:43 Speaker 01 And when it comes down, you know, that they, that their mass moves all, you know, it stays in a constant position relative to each other itself.
1:38:54 Speaker 01 And that leads to some paradoxes when you go to try to talk about rigid body mechanics and contact. And so for instance, if I have a three-legged stool with just a, imagine it comes to a point at the, at the legs, so it's only touching the world at a point. If I draw my physics, my high school physics diagram of this system, then there's a couple of things that I'm given by, by elementary physics. I know if the system, if the table is at rest, if it's not moving, zero velocities. That means that the normal force, all the forces are in balance. So the, the force of gravity is being countered by the forces that the ground is pushing on my table legs.
1:39:37 Speaker 01 I also know, since it's not rotating, that there, that the moments have to balance. And since it can, in, it's a three-dimensional table, it could fall in any direction, it actually tells me uniquely what those three normal forces have to be. If I have four legs on my table, four-legged table, and they were perfectly machined to be exactly the right same height, and they're set down and the table's not moving, then the basic conservation laws don't tell me, there are many solutions for the forces that the ground could be putting on my legs, that would still result, result in the table not moving. Now, the reason, that seems fine, I could just pick one.
1:40:21 Speaker 01 But it gets funny now, because if you think about friction, what we, what we think about with friction is we, our, our standard model says, the amount of force that you're, that the table will push back, if I were to now try to push my table sideways, I guess I have a table here, is proportional to the normal force. So if I have, if I'm very, barely touching and I push, I'll slide, but if I'm pushing more and I push, I will, I'll slide less. It's called Coulomb friction, is our standard model. Now, if you don't know what the normal force is on the four legs, and you push the table, then you don't know what the friction forces are going to be.
1:40:59 Lex Fridman? Right.
1:41:00 Speaker 01 And so you can't actually tell, the laws just don't, aren't explicit yet, about which way the table's going to go. It could veer off to the left, it could veer off to the right, it could go straight. So the rigid body assumption of contact leaves us with some paradoxes, which are annoying for, for writing simulators and for writing controllers.
1:41:23 Speaker 01 We still do that sometimes because soft contact is potentially harder numerically or whatever, and the best simulators do both or do some combination of the two. But anyways, because of these kind of paradoxes, there's all kinds of paradoxes in contact, mostly due to these rigid body assumptions. It becomes very hard to write the same kind of control laws that we've been able to be successful with for fighter jets. We haven't been as successful writing those controllers or manipulation.
1:41:54 Lex Fridman? And so you don't know what's going to happen at the point of contact, at the moment of contact.
1:41:59 Speaker 01 There are situations absolutely where our laws don't tell us. So the standard approach, that's okay. I mean, instead of having a differential equation, you end up with a differential inclusion, it's called. It's a set valued equation. It says that I'm in this configuration, I have these forces applied on me, and there's a set of things that could happen, right?
1:42:22 Lex Fridman? And those aren't continuous, I mean, what, so when you're saying like non-smooth?
1:42:28 Speaker 01 Yep.
1:42:29 Lex Fridman? They're not only not smooth, but this is discontinuous?
1:42:32 Speaker 01 The non-smooth comes in when I make or break a new contact first, or when I transition from stick to slip. So you typically have static friction, and then you'll start sliding, and that'll be a discontinuous change in velocity, for instance, especially if you come to rest or then...
1:42:50 Lex Fridman? That's so fascinating. Okay, so what do you do? Sorry, I interrupted you.
1:42:55 Speaker 01 It's fine.
1:42:58 Lex Fridman? What's the hope under so much uncertainty about what's going to happen? What are you supposed to do?
1:43:03 Speaker 01 I mean, control has an answer for this. Robust control is one approach, but roughly, you can write controllers which try to still perform the right task despite all the things that could possibly happen. The world might want the table to go this way and this way, but if I write a controller that pushes a little bit more and pushes a little bit, I can certainly make the table go in the direction I want. It just puts a little bit more of a burden on the control system, right? And this discontinuities do change the control system because the way we write it down right now...
1:43:38 Speaker 01 Every different control configuration, including sticking or sliding or parts of my body that are in contact or not, looks like a different system. And I think of them, I reason about them separately or differently. And the combinatorics of that blow up, right? So I just don't have enough time to compute all the possible contact configurations of my humanoid. Interestingly, I, I mean, I'm a humanoid. I have lots of degrees of freedom, lots of joints. I only, I've only been around for a handful of years. It's getting up there, but I haven't had time in my life to visit all of the states in my system.
1:44:20 Speaker 01 Certainly all the contact configurations. So if step one is to consider every possible contact configuration that I've ever, I'll ever be in, that's probably, it's probably not a problem I need to solve, right?
1:44:33 Lex Fridman? Just as a small tangent, what's a contact configuration? What like, just so we can enumerate, what are we talking about? How many are there?
1:44:44 Speaker 01 The simplest example maybe would be, imagine a robot with a flat foot. And we think about the phases of gait where the heel strikes and then the four, the front toe strikes and then you can heel up toe off. Those are each different contact configurations. I only had two different contacts, but I ended up with four different contact configurations. Now, of course, I might have, my, my robot might actually have bumps on it or other things. So it could be much more subtle than that, right? But it's just even with one sort of box interacting with the ground already in, in the plane has that many, right? And if I was just even a 3D foot,
1:45:26 Speaker 01 then it probably my left toe might touch just before my right toe and things get subtle. Now, if I'm a dexterous hand and I go to talk about just grabbing a water bottle.
1:45:39 Speaker 01 If every, if I have to enumerate every possible order that my hand came into contact with the, with the bottle, then I'm dead in the water. I might, my, any approach that we were able to get away with that in walking, because we mostly touched the ground within a small number of points, for instance, and we haven't been able to get dexterous hands that way.
1:46:02 Lex Fridman? So you, you've mentioned that people think that contact is really hard and that that's the reason that robotic manipulation is, problem is really hard. Is there any flaws in that thinking?
1:46:23 Speaker 01 So I think simulating contact is one aspect. I know people often say that we don't, that one of the reasons that we have a limit in robotics is because we do not simulate contact accurately in our simulators. And I think that is, the extent to which that's true is partly because our simulators, we haven't got mature enough simulators. There are some things that are still hard, difficult, that we should change. But, but we actually, we know what the governing equations are. They have some foibles, like this indeterminacy, but we should be able to simulate them accurately. We have incredible open source community in
1:47:07 Speaker 01 robotics, but it actually just takes a professional engineering team, a lot of work to write a very good simulator like that.
1:47:15 Lex Fridman? Now, where does, I believe you've written, Drake?
1:47:20 Speaker 01 There's a team of people. I'm, I certainly spent a lot of hours on it myself.
1:47:24 Lex Fridman? Well, what is Drake? And what, what does it take to, to create a simulation environment for, for the kind of difficult control problems we're talking about?
1:47:37 Speaker 01 Right, so Drake is the simulator that I've been working on. There are other good simulators out there. I don't like to think of Drake as just a simulator. Because we write our controllers in Drake. We write our perception systems a little bit in Drake. But we write all of our, you know, low-level control and even planning and optimization.
1:47:57 Lex Fridman? So it has optimization capabilities as well?
1:47:59 Speaker 01 Absolutely, yeah. I mean, Drake is three things roughly. It's an optimization library, which is, sits on, it provides a layer of abstraction in C++ and Python for commercial solvers. You can write linear programs, quadratic programs, you know, semi-definite programs, sums and squares programs, the ones we've used, mixed integer programs. And it will do the work to curate those and send them to whatever the right solver is, for instance, and it provides a level of abstraction. The second thing is, is a system modeling language. A bit like LabVIEW or Simulink, where you can make block diagrams out of complex systems.
1:48:41 Speaker 01 Or it's like Ross in that sense, where you might have lots of Ross nodes that are each doing some part of your system. But to contrast it with Ross, we try to write, if you write a Drake system, then you have to, it asks you to describe a little bit more about the system. If you have any state, for instance, in the system, any variables that are going to persist, you have to declare them. Parameters can be declared and the like. But the advantage of doing that is that you can, if you like, run things all on one process. But you can also do control design against it. You can do, I mean, simple things like rewinding and playing back your simulations.
1:49:24 Speaker 01 For instance, you know, these things, you get some rewards for spending a little bit more upfront cost in describing each system. And I was inspired to do that because I think the complexity of Atlas, for instance, is just so great. And I think although, I mean, Ross has been incredible, absolutely huge fan of what it's done for the robotics community. But it, the ability to rapidly put different pieces together and have a functioning thing is very good. But I do think that it's hard to think clearly about a bag of disparate parts, Mr. Potato Head kind of software stack. And
1:50:07 Speaker 01 If you can, you know, ask a little bit more out of each of those parts, then you can understand the way they work better. You can try to verify them and the like. You can do learning against them. And then one of those systems, the last thing, I said the first two things that Drake is, but the last thing is that there is a set of multi-body equations, rigid body equations, that is trying to provide a system that simulates physics. And that, we also have renderers and other things, but I think the physics component of Drake is special in the sense that we have done excessive amount of engineering to make sure that we've written the equations correctly. Every possible tumbling satellite
1:50:50 Speaker 01 or spinning top or anything that we could possibly write as a test is tested. We are making some, you know, I think fundamental improvements on the way you simulate contact.
1:51:00 Lex Fridman? Yes. What does it take to simulate contact? I mean, it just seems, I mean, there's something just beautiful, the way you were like explaining contact and you were like tapping your fingers on the, on the table while you're, while you're doing it. Just.
1:51:16 Speaker 01 Easily, right?
1:51:18 Lex Fridman? Easily. Just like, just not even like, it was like helping you think, I guess. What I, you have this like awesome demo of loading or unloading a dishwasher, just picking up a plate, grasping it like for the first time. That just seems like so difficult. What, how do you simulate any of that?
1:51:49 Speaker 01 So, so it was really interesting that what happened was that we started getting more professional about our software development during the DARPA Robotics Challenge. I learned the value of software engineering and how to bridle complexity. I guess that's what I want to somehow fight against and bring some of the clear thinking of controls into these complex systems we're building for robots. Shortly after the DARPA Robotics Challenge, Toyota opened a research institute, TRI, Toyota Research Institute. They put one of their, there's three locations, one of them is just down the street from MIT,
1:52:30 Speaker 01 and I helped ramp that up as a part of the end of my sabbatical, I guess. So TRI has given me, the TRI Robotics effort has made this investment in simulation in Drake, and Michael Sherman leads a team there of just absolutely top-notch dynamics experts that are trying to write those simulators that can pick up the dishes. And there's also a team working on manipulation there that is taking problems like loading the dishwasher, and we're using that to study these really hard corner cases kind of problems in manipulation.
1:53:12 Speaker 01 So for me, simulating the dishes, we could actually write a controller, if we just cared about picking up dishes in the sink once, we could write a controller without any simulation whatsoever, and we could call it done. But we want to understand, what is the path you take to actually get to a robot that could perform that for any dish in anybody's kitchen with enough confidence that it could be a commercial product? And it has deep learning perception in the loop, it has complex dynamics in the loop, it has controller, it has a planner, and how do you take all of that complexity and put
1:53:53 Speaker 01 it through this engineering discipline and verification and validation process to actually get enough confidence to deploy? I mean, the DARPA challenge made me realize that that's not something you throw over the fence and hope that somebody will harden it for you, that there are really fundamental challenges in closing that last gap.
1:54:16 Lex Fridman? During the validation and the testing.
1:54:20 Speaker 01 I think it might even change the way we have to think about the way we write systems. What happens if you have the robot running lots of tests? And it screws up, it breaks a dish, right? How do you capture that? I said, you can't run the same simulation or the same experiment twice in a real, on a real robot. Do we have to be able to bring that one-off failure back into simulation in order to change our controllers, study it, make sure it won't happen again? Do we, is it enough to just try to add that to our distribution and understand that on average, we're going to cover that situation again?
1:55:03 Speaker 01 There's like really subtle questions at the corner cases that I think we don't yet have satisfying answers for.
1:55:10 Lex Fridman? Nick, how do you find the corner cases? That's one kind of, is there, do you think it's possible to create a systematized way of discovering corner cases efficiently?
1:55:21 Speaker 01 Yes.
1:55:22 Lex Fridman? In whatever the problem is?
1:55:24 Speaker 01 Yes. I mean, I think we have to get better at that. I mean, control theory has, for decades, talked about active experiment design.
1:55:34 Lex Fridman? What's that?
1:55:36 Speaker 01 So people call it curiosity these days. It's roughly this idea of trying to exploration or exploitation, but in the active experiment design is even, is more specific. You could try to understand the uncertainty in your system, design the experiment that will provide the maximum information to reduce that uncertainty. If you, there's a parameter you want to learn about, what is the optimal trajectory I could execute to learn about that parameter, for instance? Scaling that up to something that has a deep network in the loop and a planning in the loop is tough. We've done some work on, you know, with Matt O'Kelly and Amon Sina, we've worked on some
1:56:19 Speaker 01 falsification algorithms that are trying to do rare event simulation that try to just hammer on your simulator. And if your simulator is good enough, you can, you can spend a lot of time, you can write good algorithms that try to spend most of their time in the corner cases. So you basically imagine you're, you're building an autonomous car and you want to put it in, I don't know, downtown New Delhi all the time, right? And accelerated testing. If you can write sampling strategies which figure out where your controller is performing badly in simulation and start generating lots of examples around that. You know, it's just the space of possible places where that can be, where things can go wrong is
1:57:03 Speaker 01 very big. So it's hard to write those algorithms.
1:57:06 Lex Fridman? Yeah, rare event simulation is just a really compelling notion. If it's possible.
1:57:12 Speaker 01 We joked and we call it, we call it the black swan generator.
1:57:15 Lex Fridman? It's black swan.
1:57:17 Speaker 01 Because you don't just want the rare events, you want the ones that are highly impactful.
1:57:20 Lex Fridman? I mean, that's the most, those are the most sort of profound questions we ask of our world. Like, what's the, what's the worst that can happen? But what we're really asking isn't some kind of like computer science worst case analysis. We're asking like, what are the millions of ways this can go wrong? And that's like our curiosity. We humans, I think, are pretty bad at, we just like run into it. And I think there's a distributed sense because there's now like 7.5 billion of us. And so there's a lot of them and then a lot of them write blog posts about the stupid thing
1:58:03 Lex Fridman? they've done. So we learn in a distributed way. There's, there's some.
1:58:08 Speaker 01 I think that's going to be important for robots too.
1:58:09 Lex Fridman? Yeah.
1:58:10 Speaker 01 I mean, that's, that's another massive theme at Toyota Research for robotics is this fleet learning concept is, you know, the idea that I, as a humanoid, don't have enough time to visit all of my states, right? There's just a, it's very hard for one robot to experience all the things. But that's not actually the problem we have to solve, right? We're going to have fleets of robots that can have very similar appendages. And at some point, maybe collectively, they have enough data that their computational processes should be set up differently than ours, right?
1:58:48 Lex Fridman? It's a, have this vision of just, I mean, all these dishwasher unloading robots.
1:58:55 Lex Fridman? I mean, that robot dropping a plate and a human looking at the robot probably pissed off.
1:59:03 Speaker 01 Yeah.
1:59:04 Lex Fridman? But that's a special moment to record. I think one thing in terms of fleet learning, and I've seen that because I've talked to a lot of folks, just like Tesla users or Tesla drivers, they're another company that's using this kind of fleet learning idea. And one hopeful thing I have about humans is they really enjoy when a system improves, learns. So they enjoy fleet learning and the reason it's hopeful for me is they're willing to put up with something that's kind of dumb right now. And they're like, if it's improving, they almost like enjoy being part of the, like teaching it. Almost like if you have kids, like you're teaching them something.
1:59:49 Speaker 01 Right.
1:59:50 Lex Fridman? I think that's a beautiful thing because that gives me hope that we can put dumb robots out there. As long, I mean, the problem with on the Tesla side with cars, cars can kill you. That's, that makes the problem so much harder. Dishwasher unloading is a little safe. That's why home robotics is, is really exciting. And just to clarify, I mean, for people who might not know, I mean, TRI Toyota Research Institute. So they're, I mean, they're, they're pretty well known for like autonomous vehicle research, but they're also interested in, in home robotics.
2:00:27 Speaker 01 Yep, there's a big, there's a big group working on, multiple groups working on home robotics. It's a major part of the portfolio. There's also a couple of other projects and advanced materials discovery using AI and machine learning to discover new materials for, for car batteries and then the like, for instance. Yeah. And that's been actually incredibly successful team. There's new projects starting up too, so.
2:00:50 Lex Fridman? Do you see a future of where like robots are in our home and like robots that have like actuators that look like arms in our home or like, you know, more like humanoid type robots? Or is this, are we gonna, are we gonna do the same thing that you just mentioned? That, you know, the dishwasher is no longer a robot. We're going to just not even see them as robots. But I mean, what's your vision of the home of the future 10, 20 years from now, 50 years, if you get crazy?
2:01:23 Speaker 01 Yeah, I think we already have Roombas cruising around. We have, you know, Alexas or Google Homes on their, our kitchen counter. It's only a matter of time till they spring arms and start doing something useful like that. So I do think it's coming. I think lots of people have lots of motivations for doing it. It's been super interesting actually learning about Toyota's vision for it, which is about helping people age in place. Because I think that's not necessarily the first entry, the most lucrative entry point. But it's the problem maybe that we really need to solve no matter what.
2:02:07 Speaker 01 And so I think, I think there's a real opportunity. It's a delicate problem. How do you work with people, help people, keep them active, engaged, you know, but improve their quality of life and, and, and help them age in place, for instance.
2:02:25 Lex Fridman? It's interesting because older folks are also, I mean, there's a contrast there because they're not always the, the folks who are the most comfortable with technology, for example. So there's a, there's a, there's a division that's interesting there that you can do so much good with a robot for, for older folks. But there's a, there's a gap to fill of understanding. I mean, it's, it's actually kind of beautiful. Robot is learning about the human and the human is kind of learning about this new robot thing. And it's also with, at least with, like when I talk to my parents about robots,
2:03:08 Lex Fridman? there's a little bit of a blank slate there too. Like you can.
2:03:14 Lex Fridman? I mean, they don't know anything about robotics. So it's completely like wide open. They don't have that. They haven't. My parents haven't seen Black Mirror. So like they, they, there's, it's a blank slate. Here's a cool thing, like, what can it do for me?
2:03:29 Speaker 01 Yeah.
2:03:29 Lex Fridman? So it's an exciting space.
2:03:31 Speaker 01 I think it's a really important space. I do feel like, you know, a few years ago, drones were successful enough in academia. They kind of broke out and started an industry and autonomous cars have been happening. It does feel like manipulation in logistics, of course, first, but in the home shortly after seems like one of the next big things that's going to really pop.
2:03:57 Lex Fridman? So I don't think we talked about it, but now what's soft robotics? So we talked about like rigid bodies. Okay, if we can just linger on this whole touch thing.
2:04:10 Speaker 01 Yeah, so what's soft robotics? So I told you that I really dislike the fact that robots are afraid of touching the world all over their body. So there's a couple of reasons for that. If you, if you look carefully at all the places that robots actually do touch the world, they're almost always soft. They have some sort of pad on their fingers or a rubber sole on their foot. But if you look up and down the arm, we're just pure aluminum or something. So, so that makes it hard, actually. In fact, hitting the table with your, you know, your rigid arm or nearly rigid arm has some of the problems that we talked about in terms of simulation.
2:04:54 Speaker 01 I think it fundamentally changes the mechanics of contact when you're soft, right? You, you turn point contacts into patch contacts, which can have torsional friction. You can have distributed load. If I want to pick up an egg, right? If I pick it up with two points, then in order to put enough force to sustain the weight of the egg, I might have to put a lot of force to break the egg. If I envelop it with a, with contact all, all around, then I can distribute my force across the shell of the egg and have a better chance of not breaking it. So soft robotics is for me a lot about changing the mechanics of contact.
2:05:32 Lex Fridman? Does it make the problem a lot harder?
2:05:38 Speaker 01 Quite the opposite.
2:05:41 Speaker 01 It changes the computational problem. I think because of the, I think our world and our mathematics has biased us towards rigid. But it really should make things better in some ways, right? It's a, I think the, the, the future is unwritten there. But the other thing it can do-
2:06:02 Lex Fridman? Ultimately, sorry to interrupt, but I think ultimately it will make things simpler. If we embrace the softness of the world.
2:06:08 Speaker 01 It makes, um, it makes things smoother, right? So the, the result of small actions is less discontinuous, but it also means potentially less, you know, instantaneously bad, for instance. I won't necessarily contact something and send it flying off.
2:06:30 Speaker 01 The other aspect of it that just happens to dovetail really well is that if, soft robotics tends to be a place where we can embed a lot of sensors too. So if you change your, um, your hardware and make it more soft, then you can potentially have a tactile sensor, which is measuring the deformation.
2:06:47 Speaker 01 So there's a team at TRI that's working on soft hands and, uh, and you get so much more information. If you, you can put a camera behind the skin roughly and, and get fantastic tactile information, which is, um, it's super important, like in manipulation, one of the things that really is frustrating is if you work super hard on your head mounted, on your perception system for your head mounted cameras. And then you've identified an object, you reach down to touch it and the first, the last thing that happens right before, right? The most important time, you stick your hand and you're occluding your head mounted sensors, right? So in all the part that really matters, um, all of your off board sensors are, you know, are occluded.
2:07:30 Speaker 01 And really, if you don't have tactile information, then you're, you're blind in an important way. So it happens that soft robotics and tactile sensing tend to go hand in hand.
2:07:42 Lex Fridman? I think we've kind of talked about it, but, um, you, you taught a course on, under actuated robotics. I believe that was the name of it, actually.
2:07:49 Speaker 01 That's right.
2:07:52 Lex Fridman? Can you talk about it in that context? What is underactuated robotics?
2:07:57 Speaker 01 Right, so underactuated robotics is my graduate course. It's it's online mostly now. So I mean, in the sense that the lectures are
2:08:04 Lex Fridman? versions of it, I think.
2:08:06 Speaker 01 Right, the YouTube
2:08:06 Lex Fridman? Really great, I recommend it highly.
2:08:09 Speaker 01 Look on YouTube for the 2020 versions until March, and then you have to go back to 2019, thanks to COVID.
2:08:18 Speaker 01 No, I've I've poured my heart into that class.
2:08:22 Speaker 01 And lecture one is basically explaining what the word underactuated means. So people are very kind to to show up and then maybe have to learn what the title of the course means over the course of the first lecture.
2:08:32 Lex Fridman? That that first lecture is really good. You should watch it.
2:08:36 Speaker 01 Thanks. It's it's a strange name, but I thought it captured the essence of what control was good at doing and what control was bad at doing. So what do I mean by underactuated? So a mechanical system has many degrees of freedom, for instance. I think of a joint as a degree of freedom. And it has some number of actuators, motors. So if you have a robot that's bolted to the table that has five degrees of freedom and five motors, then you have a fully actuated robot. If you have, if you take away one of those motors, then you have an underactuated robot.
2:09:20 Speaker 01 Now, why on earth? I have a good friend who who likes to tease me. He said, Russ, if you had more research funding, would you work on fully actuated robots?
2:09:29 Lex Fridman? Yeah.
2:09:29 Speaker 01 And the answer is no. The the world gives us underactuated robots, whether we like it or not. I'm a human. I'm an underactuated robot, even though I have more muscles than my big degrees of freedom, because I have, in some places, multiple muscles attached to the same joint.
2:09:48 Speaker 01 But still, there's a really important degree of freedom that I have, which is the location of my center of mass in space, for instance. All right, I'm, I can jump into the air and there's no motor that connects my center of mass to the ground in that case. So I have to think about these, the implications of not having control over everything.
2:10:10 Speaker 01 The passive dynamic walkers are the extreme view of that, where you're taking away all the motors and you have to let physics do the work. But it shows up in all of the walking robots where you have to use some of actuators to push and pull even the degrees of freedom that you don't have an actuator on.
2:10:27 Lex Fridman? That's referring to walking if you're like falling forward. Like, is there a way to walk that's fully actuated?
2:10:33 Speaker 01 So it's a subtle point. When you're, when you're in contact and you have your feet on the ground, there are still limits to what you can do, right? Unless I have suction cups on my feet, I cannot accelerate my center of mass towards the ground faster than gravity because I can't get a force pushing me down.
2:10:54 Speaker 01 Right? But I can still do most of the things that I want to. So you can get away with basically thinking of the system as fully actuated unless you suddenly needed to accelerate down super fast. But as soon as I take a step, I get into the more nuanced territory. And to get to really dynamic robots or airplanes or other things, I think you have to embrace the underactuated dynamics. Manipulation, people think, is manipulation under, underactuated? My, even if my arm is fully actuated, I have a motor. If my goal is to control the position and orientation of this cup, then I don't have an actuator for that directly. So I have to use my actuators over here to control this thing.
2:11:40 Speaker 01 Now it gets even worse, like what if I have to button my shirt? Okay.
2:11:46 Speaker 01 What are the degrees of freedom of my shirt, right? I suddenly, that's a hard question to think about. It kind of makes me queasy as a, thinking about my state space control ideas.
2:11:57 Speaker 01 But actually, those are the problems that make me so excited about manipulation right now is that it, it breaks some of the, it breaks a lot of the foundational control stuff that I've been thinking about.
2:12:08 Lex Fridman? Is there, what are some interesting insights you could say about trying to solve an underactuated, like, control in, in an underactuated system?
2:12:19 Speaker 01 So I think the philosophy there is let physics do more of the work. The technical approach has been optimization. So you typically formulate your decision making for control as an optimization problem. And you use the language of optimal control and sometimes numer- often numerical optimal control in order to make those decisions and balance, you know, these complicated equations of, and in order to control. You don't have to use optimal control to do underactuated systems, but that has been the technical approach that has borne the most fruit in our, at least in our line of work.
2:12:57 Lex Fridman? And there's some, so in underactuated systems, when you say let physics do some of the work, so there's a kind of feedback, feedback loop that observes the state that the physics brought you to. So like you've, there's a, there's a perception there. This is, there's a feedback somehow. Do you, do, um, do you ever loop in like complicated perception systems into this whole picture?
2:13:23 Speaker 01 Right, right around the time of the DARPA challenge, we had a complicated perception system in the DARPA challenge. We also started to embrace perception for our flying vehicles at the time. We had a really good project on trying to make airplanes fly at high speeds through forests. Surtash Karman was on that project and we had, it was a really fun team to, to work on. He's carried it farther, much farther forward since then.
2:13:51 Lex Fridman? And that's using cameras for perception?
2:13:53 Speaker 01 So that was using cameras. That was, at the time, we felt like LiDAR was too, too heavy and too power
2:14:01 Speaker 01 heavy to, to be carried on, on a light UAV and we were using cameras. And that was a big part of it was just how do you do even stereo matching at a fast enough rate with a small camera, a small onboard computer?
2:14:15 Speaker 01 Since then, we have now, so the deep learning revolution unquestionably changed what we can do with perception for robotics and control. So in manipulation, we can address, we can use perception in a, I think, a much deeper way. And we get into not only, I think the first use of it naturally would be to ask your deep learning system to look at the cameras and produce the state, which is like the pose of my thing, for instance. But I think we've quickly found out that that's not always the right thing to do. Why is that? Because what's the state of my shirt? Imagine I've Very noisy, you mean? Or it's
2:14:59 Speaker 01 If the first step of me trying to button my shirt is estimate the full state of my shirt, including like what's happening in the back here, whatever, whatever. That's just not the right specification. There are aspects of the state that are very important to the task. There are many that are unobservable and not important to the task. So you really need, it begs new questions about state representation. Another example that we've been playing with in lab has been just the idea of chopping onions. Okay. Or carrots, turns out to be better. So onions stink up the lab. And they're hard to see in a camera. But
2:15:44 Speaker 01 The details matter, yeah. Details matter, you know? So If I'm moving around a particular object, right, then I think about, oh, it's got a position or an orientation in space. That's the description I want. Now, when I'm chopping an onion, okay, like the first chop comes down. I have now 100 pieces of onion. Does my control system really need to understand the position and orientation and even the shape of the 100 pieces of onion in order to make a decision? Probably not, you know, and if I keep going, I'm just getting more and more is my state space getting bigger as I cut. It's it it's not right.
2:16:23 Speaker 01 So somehow there's a I think there's a richer idea of state. It's not the state that is given to us by Lagrangian mechanics. There is a there is a proper Lagrangian state of the system, but the relevant state for this is some latent state is what we call it in machine learning. But, you know, there's some some different state representation.
2:16:49 Lex Fridman? Some compressed representation, some.
2:16:51 Speaker 01 And that's what I worry about saying compressed, because it doesn't I don't mind that it's low dimensional or not. But it has to be something that's easier to think about.
2:17:02 Lex Fridman? By us humans.
2:17:04 Speaker 01 Or my algorithms.
2:17:06 Lex Fridman? Or the algorithms being like control, optimal.
2:17:10 Speaker 01 So for instance, if the contact mechanics of all of those onion pieces and all the permutations of possible touches between those onion pieces, you know, you can give me a high dimensional state representation, I'm OK if it's linear.
2:17:23 Lex Fridman? Yeah.
2:17:24 Speaker 01 But if I have to think about all the possible shattering combinatorics of that, then my robot's going to sit there thinking and the soup's going to get cold or something.
2:17:34 Lex Fridman? So since you taught the course, it kind of entered my mind, the idea of underactuated is really compelling to see the to see the world in this kind of way. Do you ever, you know, if we talk about onions or you talk about the world with people in it in general, do you see the world as basically an underactuated system? Do you like often look at the world in this way? Or is this overreach?
2:18:04 Speaker 01 Underactuated is a way of life, man. Exactly. I guess that's what I'm asking.
2:18:10 Speaker 01 I do think it's everywhere. I think some, in some places, we already have natural tools to deal with it. You know, it rears its head. I mean, in linear systems, it's not a problem. We just, we just, like, an underactuated linear system is really not sufficiently distinct from a fully actuated linear system. It's, it's a, it's a subtle point about when that becomes a bottleneck and what we know how to do with control. It happens to be a bottleneck, although we've gotten incredibly good solutions now, but for a long time that I felt that that was the key bottleneck in legged robots. And roughly now, the underactuated course is, you know, me trying to tell people everything I can about how to make Atlas do a backflip,
2:18:53 Speaker 01 right? I have a second course now in, that I teach in the other semesters, which is on, on manipulation. And that's where we get into now more of the, that's a newer class. I'm hoping to put it online this fall completely. And that's going to have much more aspects about these perception problems and the state representation questions, and then how do you do control? And the, this thing that's a little bit sad is that, for me at least, is, there's a lot of manipulation tasks that people want to do and should want to do. They could start a company with it and may be very successful, that don't actually require you to think that much about underact, or dynamics at all even, but certainly underactuated dynamics. Once I have,
2:19:37 Speaker 01 if I, if I reach out and grab something, if it, if I can sort of assume it's rigidly attached to my hand, then I can do a lot of interesting, meaningful things with it, without really ever thinking about the dynamics of that object. So they built, we've built systems that kind of
2:19:53 Speaker 01 reduce the need for that, enveloping grasps and the like. But I think the really good problems in manipulation. So I, manipulation, by the way, is more than just pick and place. That's like, a lot of people think of that, just grasping. I don't mean that. I mean, buttoning my shirt. I mean tying shoelaces. How do you program a robot to tie shoelaces? And not just one shoe, but every shoe, right? That's a really good problem. It's tempting to write down like the infinite dimensional state of the, of the laces.
2:20:30 Speaker 01 That's probably not needed to write a good controller. I know we could hand design a controller that would do it. But I don't want that. I want to understand the principles that would allow me to solve another problem that's kind of like that. But I think if we can stay pure in our approach, then the challenge of tying anybody's shoes is a great challenge.
2:20:53 Lex Fridman? That's a great challenge. I mean, and the soft touch comes into play there. That's really interesting. Let me ask another ridiculous question on this topic. How important is touch? We haven't talked much about humans, but I have this argument with my dad. Where like, I think you can fall in love with a robot based on language alone. And he believes that touch is essential. Touch and smell, he says, but. So in terms of robots, you know, connecting with humans. And we can go philosophical in terms of like a deep meaningful connection like love.
2:21:38 Lex Fridman? But even just like collaborating in an interesting way. How important is touch? Like from an engineering perspective and a philosophical one?
2:21:49 Speaker 01 I think it's super important. Let's even just in a practical sense, if we forget about the emotional part of it. But for robots to interact safely while they're doing meaningful mechanical work. In the, you know, close contact with or vicinity of people that need help. I think we have to have them, we have to build them differently. They have to be afraid, not afraid of touching the world. So I think Baymax is just awesome. That's just like the movie of Big Hero Six and the concept of Baymax. That's just awesome. I think we should. And we have some folks at Toyota that are trying to Toyota research that are trying to build Baymax roughly.
2:22:33 Speaker 01 And I think it's just a fantastically good project. I think it will change the way people physically interact. The same way, I mean, you gave a couple of examples earlier, but if I. If the robot that was walking around my home looked more like a teddy bear and a little less like the Terminator. That could change completely the way people perceive it and interact with it. And. Maybe they'll even want to teach it, like you said, right? You could not quite gamify it, but somehow, instead of people judging it and looking at it as if it's not doing as well as a human, they're going to try to help out the cute teddy bear, right? Who knows?
2:23:15 Speaker 01 But I think we're building robots wrong, and being more soft and more contact is important, right?
2:23:24 Lex Fridman? Yeah, like, all the magical moments I can remember with robots. Well, first of all, just visiting your lab and seeing Atlas, but also Spot Mini. When I first saw Spot Mini in person and hung out with him/her-it, I don't have trouble in gendering robots. I feel robotics people really always say it. I kind of like the idea that it's a her or a him. It's a magical moment, but there's no touching. I guess the question I have, have you ever been, like, have you had a human-robot experience where, like, a robot touched you?
2:24:05 Lex Fridman? And like, it was like, wait, like, was there a moment that you've forgotten that a robot is a robot? And like, the anthropomorphization stepped in, and for a second you forgot that it's not human?
2:24:20 Speaker 01 I mean, I think when you're in on the details, then we, of course, anthropomorphized our work with Atlas, but in, you know, in verbal communication and the like, I think we were pretty aware of it as a machine that needed to be respected. I actually, I worry more about the smaller robots that could still, you know, move quickly if programmed wrong, and we have to be careful, actually, about safety and the like right now. And that, if we build our robots correctly, I think then those, a lot of those concerns could go away. And we're seeing that trend. We're seeing the lower-cost, lighter-weight arms now that could be fundamentally safe.
2:25:07 Speaker 01 I mean, I do think touch is so fundamental. Ted Adelson is great. He's a perceptual scientist at MIT, and he studied vision most of his life. And he said, when I had kids, I expected to be fascinated by their perceptual development.
2:25:26 Speaker 01 But what really, what he noticed was felt more impressive, more dominant, was the way that they would touch everything and lick everything and pick things up, stick it on their tongue and whatever. And he said, watching his daughter convinced him that actually he needed to study tactile sensing more. So there's something very important. I think it's a little bit also of the passive versus active part of the world, right? You can passively perceive the world, but it's fundamentally different if you can do an experiment, right? And if you can change the world, and you can learn a lot more than a passive observer.
2:26:09 Speaker 01 So you can, in dialogue, that was your initial example, you could have an active experiment exchange. But I think if you're just a camera watching YouTube, I think that's a very different problem than if you're a robot that can apply force and touch. I think it's important.
2:26:32 Lex Fridman? Yeah, I think it's just an exciting area of research. I think you're probably right that this hasn't been under researched. It's, to me, as a person who's captivated by the idea of human robot interaction, it feels like such a rich opportunity to explore touch. Not even from a safety perspective, but like you said, the emotional too. I mean, safety comes first. But the next step is like...
2:27:01 Lex Fridman? You know, like a real human connection. Even in the world, like even in the industrial setting. It just feels like it's nice for the robot. I don't know, I, you know, you, you might disagree with this, but um. Cause I think it's important to see robots as tools often. But I don't know. I think they're just always going to be more effective. Once you humanize them. Uh, like it's convenient now to think of them as tools. Cause we want to focus on the safety. But I think ultimately to create like a good experience for the worker, for the person. There has to be a human element.
2:27:45 Lex Fridman? I don't know for me, I, I, it feels like, like an industrial robotic arm would be better. If has a human element, I think like rethink robotics had that idea with. Well, the Baxter and having eyes and so on, having. I don't know, I'm a big believer in that.
2:28:00 Speaker 01 I, I. It's not my area, but I am also a big believer.
2:28:06 Lex Fridman? Do you have an emotional connection to Alice? Like, do you miss him?
2:28:12 Speaker 01 I mean, um.
2:28:17 Speaker 01 Yes, I, I, I don't know if I more so than if I had a different science project that I worked on super hard. Right. I, but, um. Yeah, I mean, the, the, the robot, we basically had to do heart surgery on the robot in the final competition. Cause we melted the core. Um, and, uh. And yeah, there was something about watching that robot hanging there. We know we had to compete with it in an hour and it was getting its guts ripped out.
2:28:45 Lex Fridman? Those are all historic moments. I think if we look back like hundred years from now.
2:28:52 Lex Fridman? Yeah, I think those are important moments in robotics. I mean, these are the early day. You look at like the early days of a lot of scientific disciplines. They look ridiculous, it's full of failure. But it feels like robotics will be important
2:29:06 Speaker 01 I think so.
2:29:06 Lex Fridman? in the coming hundred years.
2:29:08 Speaker 01 I think so.
2:29:09 Lex Fridman? And these are the early days, so. So I think a lot of people are, look at a brilliant person such as yourself and are curious about the intellectual journey they've took. Is there maybe three books, technical fiction, philosophical, that had a big impact in your life that you would recommend perhaps others reading?
2:29:35 Speaker 01 Yeah, so I actually didn't read that much as a kid, but I read fairly voraciously now. There are some recent books that if you're interested in this kind of topic, like AI Superpowers by Caifulli is just a fantastic read. You must read that. Yuval Harari is just, I think that can open your mind.
2:30:01 Lex Fridman? Sapiens.
2:30:02 Speaker 01 Sapiens is the first one, Homo Deus is the second, yeah. We mentioned The Black Swan by Taleb. I think that's a good sort of mind opener. I actually. So there's maybe a more controversial recommendation I could give.
2:30:23 Lex Fridman? Great.
2:30:23 Speaker 01 Well, I'd love.
2:30:24 Lex Fridman? I love such words.
2:30:25 Speaker 01 In some sense, it's so classical, it might surprise you. But I actually recently read Mortimer Adler's How to Read a Book. Not so long, it was a while ago, but some people hate that book. I loved it. I think we're in this time right now where.
2:30:47 Speaker 01 Boy, we're just inundated with research papers that you could read on archive with limited peer review and just this wealth of information. I don't know, I think the passion of what you can get out of a book, a really good book or a really good paper, if you find it, the attitude, the realization that you're only going to find a few that really are worth all your time. But then, once you find them, you should just dig in and understand it very deeply and it's worth, you know, marking it up and, you know, having the hard copy, writing in the side notes, side margins.
2:31:31 Speaker 01 I think that was really, I read it at the right time where I was just feeling just overwhelmed with really low quality stuff, I guess. And similarly, I'm giving more than three now, I'm sorry if I've exceeded my quota.
2:31:52 Lex Fridman? But on that topic, just real quick is, so basically finding a few companions to keep for the rest of your life in terms of papers and books and so on, and those are the ones, like not doing, what is it, FOMO, fear of missing out, constantly trying to update yourself, but really deeply making a life journey of studying a particular paper, essentially, set of papers.
2:32:17 Speaker 01 Yeah, I think when you really find something which, a book that resonates with you might not be the same book that resonates with me, but when you really find one that resonates with you, I think the dialogue that happens, and that's what, I loved that Adler was saying, you know, I think Socrates and Plato say, the written word is never going to capture the beauty of dialogue, right? But Adler says, no, no. A really good book is a dialogue between you and the author, and it crosses time and space. And I don't know, I think it's a very romantic, there's a bunch of like specific advice which
2:32:59 Speaker 01 you can just gloss over, but the romantic view of how to read and really appreciate it is so good. And similarly, teaching.
2:33:14 Speaker 01 I thought a lot about teaching and so Isaac Asimov, great science fiction writer. It's also actually spent a lot of his career writing nonfiction, right? His memoir is fantastic. He was passionate about explaining things, right? He wrote all kinds of books on all kinds of topics in science. He was known as the great explainer and some, you know, I do really resonate with his style and and just his way of talking about, you know, by communicating and explaining to something is a really the way that you learn something. I think I think about problems very differently because of the way I've been given the opportunity to teach them at MIT.
2:33:58 Speaker 01 And we have questions asked, you know, the fear of the lecture, the experience of the lecture and the questions I get and the interactions just forces me to be rock solid on these ideas in a way that if I didn't have that, I don't know, I would be in a different intellectual space.
2:34:15 Lex Fridman? Also, video, does that scare you that your lectures are online? And people like me in sweatpants can sit sipping coffee and watch, watch you give lectures?
2:34:25 Speaker 01 That I think it's great. I do think that something's changed right now, which is, you know, right now we're giving lectures over Zoom. I mean, giving seminars over Zoom and everything. I'm trying to figure out, I think it's a new medium.
2:34:41 Lex Fridman? Do you think it's a possibility? Yeah, I've been, I've been quite cynical about the human to human connection over, over that medium, but I think that's because it's hasn't been explored fully. And teaching is a different thing.
2:35:02 Speaker 01 Every lecture is a, is a, I'm sorry, every seminar even, I think every talk I give, I, you know, is an opportunity to give that differently. I can, I can deliver content directly into your browser. You have a WebGL engine right there. I could, I can throw 3D content into your browser while you're listening to me, right?
2:35:23 Lex Fridman? Yeah.
2:35:24 Speaker 01 And I can assume that you have a, you know, at least a powerful enough laptop or something to watch Zoom while I'm doing that, while I'm giving a lecture. That, that's a, that's a new communication tool that I didn't have last year, right? And I think robotics can potentially benefit a lot from teaching that way.
2:35:43 Speaker 01 We'll see. It's gonna be an experiment this fall.
2:35:45 Lex Fridman? It's interesting.
2:35:45 Speaker 01 I'm thinking a lot about it.
2:35:47 Lex Fridman? Yeah, and also like
2:35:51 Lex Fridman? the, the length of lectures or the length of like, um, there's something so like, I guarantee you, you know, it's like eighty percent of people who started listening to our conversation are still listening to now, which is crazy to me. But so there's a, there's a patience and a interest in long form content. But at the same time, there's a magic to forcing yourself to condense an idea to as short as possible. Uh, as short as possible, like clip, it can be a part of a longer thing, but like just a really beautifully condensed an idea. There's a lot of opportunity there that's easier to do in remote with,
2:36:33 Lex Fridman? I don't know, uh, with editing too. Editing is an interesting thing like what, uh, you know, most professors don't get when they give a lecture, you don't get to go back and edit out parts like crisp, like crisp it up a little bit. Uh, that's also, it can do magic. Like if you remove like five to 10 minutes from an hour lecture, it can, it can actually, it can make something special of a lecture. I've, uh, I've seen that in myself. And, and, and others too, because I edit other people's lectures to extract clips. It's like there's certain tangents that are like that lose, they're not interesting. They're, they're, they're mumbling. They're just not, they're not clarifying.
2:37:15 Lex Fridman? They, they're not helpful at all. And once you remove them, it's just, I don't know. Editing can be magic.
2:37:21 Speaker 01 It takes a lot of time.
2:37:23 Lex Fridman? Yeah, it takes, it depends like what is teaching, you have to ask.
2:37:26 Speaker 01 Yeah.
2:37:29 Lex Fridman? Yeah. Cause I find the editing process is also. Beneficial as for teaching, but also for your own learning. I don't know if, have you watched yourself?
2:37:40 Speaker 01 Yeah, sure.
2:37:41 Lex Fridman? Have you watched those videos?
2:37:42 Speaker 01 I mean, not all of them.
2:37:45 Lex Fridman? It could be, it could be painful.
2:37:46 Speaker 01 Yeah.
2:37:46 Lex Fridman? And to see like how to improve.
2:37:50 Speaker 01 So do you find that, I know you segment your, your podcast. Do you think that helps people with the, the attention span aspect of it? Or is it?
2:37:59 Lex Fridman? Segment like sections like?
2:38:01 Speaker 01 Yeah, we're talking about this topic, whatever.
2:38:03 Lex Fridman? No, no, that just helps me. It's actually bad. So, and you've been incredible. So I'm, I'm learning, like I'm afraid of conversation. This is even today, I'm terrified of talking to you. I mean, it's, it's something I'm trying to remove from myself. There's, there's a guy, I mean, I've learned from a lot of people, but really,
2:38:27 Lex Fridman? there's been a few people who's been inspirational to me in terms of conversation. Whatever people think of him, Joe Rogan has been inspirational to me because comedians have been too. Being able to just have fun and enjoy themselves and lose themselves in conversation. That requires you to be a great storyteller, to be able to pull a lot of different pieces of information together. But mostly just to enjoy yourself in conversations. And I'm trying to learn that. These notes are, you see me looking down. That's like a safety blanket that I'm trying to let go of more and more.
2:39:02 Speaker 01 Cool.
2:39:03 Lex Fridman? So that's, that people love just regular conversation. That's what they, the structure is like, whatever. I would say, I would say maybe like 10 to like, so there's a bunch of, you know, there's probably a couple of thousand PhD students listening to this right now. Right? And they might know what we're talking about. But there is somebody, I guarantee you right now. In Russia, some kid who's just like, who's just smoked some weed, is sitting back and just enjoying the hell out of this conversation, not really understanding. He kind of watched some Boston Dynamics videos, he's just enjoying it. And I salute you, sir.
2:39:47 Lex Fridman? No, but just like, there's so much variety of people that just have curiosity about engineering, about sciences, about mathematics. And, and also, like, I should, I mean, enjoying it is one thing, but also often notice it inspires people to, there's a lot of people who are like in their undergraduate studies trying to figure out what, trying to figure out what to pursue. And these conversations can really spark the direction there of their life. And in terms of robotics, I hope it does, because I'm excited about the possibilities of what robotics brings. On that topic, do you have advice?
2:40:30 Lex Fridman? Like, what advice would you give to a young person about life?
2:40:36 Speaker 01 A young person about life, or a young person about life in robotics?
2:40:40 Lex Fridman? It could be in robotics, it could be in life in general. It could be career, it could be relationship advice, it could be running advice, just like, there, that's one of the things I see, like, we talk to like 20-year-olds, they're, they're like, how do I, how do I do this thing? What, what do I do? If they come up to you, what would you tell them?
2:41:05 Speaker 01 I think it's an interesting time to be a kid these days. Everything points to this being sort of a winner-take-all economy and the like. I think the people that will really excel, in my opinion, are going to be the ones that can think deeply about problems. You have to be able to ask questions agilely and use the internet for everything it's good for and stuff like this. And I think a lot of people will develop those skills. I think the, the leaders, thought leaders, you know, robotics leaders, whatever, are going to be the ones that can do more and they can think very deeply and critically.
2:41:49 Speaker 01 And that's a harder thing to learn. I think one, one path to learning that is through mathematics, through engineering.
2:41:58 Speaker 01 I would encourage people to start math early. I mean, I didn't really start. I mean, I was always in the the better math classes that I could take, but I wasn't pursuing super advanced mathematics or anything like that. Until I got to MIT, I think MIT lit me up and
2:42:18 Speaker 01 really started the life that I'm living now. But yeah, I really want kids to to dig deep, really understand things, building things too. I mean, pull things apart, put them back together. Like, that's just such a good way to really understand things and expect it to be a long journey, right? It's you don't have to know everything. You're never going to know everything.
2:42:46 Lex Fridman? So think deeply and stick with it.
2:42:49 Speaker 01 Enjoy the ride, but just make sure you're not.
2:42:54 Speaker 01 Yeah, just just make sure you're you're you're stopping to think about why things work.
2:43:00 Lex Fridman? It's true. It's it's easy to lose yourself in the in the in the distractions of the world.
2:43:08 Speaker 01 We're overwhelmed with content right now, but you have to stop and pick some of it and really understand.
2:43:15 Lex Fridman? Yeah, on the book point, I've read Animal Farm by George Orwell a ridiculous number of times. So for me, like that book, I don't know if it's a good book in general, but for me, it connects deeply somehow. It somehow connects.
2:43:33 Lex Fridman? So I was born in Soviet Union, so it connects to me to the entirety of the history of the Soviet Union and to World War Two and to the love and hatred and suffering that went on there and the the corrupting nature of power and greed. And just somehow I just that that that book has taught me more about life than like anything else, even though it's just like a silly, like, childlike book about
2:44:01 Speaker 01 Animals.
2:44:01 Lex Fridman? Pigs, like, I don't know why. It just connects and inspires. And the same, there's a few.
2:44:09 Lex Fridman? Yeah, there's a few technical books too on algorithms that just, yeah, you return to often.
2:44:14 Speaker 01 Right.
2:44:15 Lex Fridman? I'm I'm I'm with you.
2:44:19 Lex Fridman? Yeah, there's, I don't, and I've been losing that because of the internet. I've been like going on, I've been going on archive and blog posts and GitHub and, and the new thing and I've, you lose your ability to really master an idea.
2:44:35 Speaker 01 Right.
2:44:36 Lex Fridman? Wow.
2:44:36 Speaker 01 Exactly right.
2:44:38 Lex Fridman? What's a fond memory from childhood?
2:44:42 Lex Fridman? When baby Russ Tedrick.
2:44:46 Speaker 01 Well, I guess I just said that, um,
2:44:50 Speaker 01 at least my current life begins, began when I got to MIT. If I have to go farther than that.
2:44:55 Lex Fridman? Yeah, what was, was there a life before MIT?
2:44:59 Speaker 01 Oh, absolutely, but, but let me actually tell you what happened when I first got to MIT, because that, I think, might be relevant here, but I, you know, I, I had taken a computer engineering degree at Michigan. I enjoyed it immensely, learned a bunch of stuff. I was, I liked computers, I liked how to, liked programming.
2:45:22 Speaker 01 But when I did get to MIT and started working with Sebastian Sung, theoretical physicist, computational neuroscientist.
2:45:31 Speaker 01 The culture here was just different. It demanded more of me, certainly mathematically and in the critical thinking. And I remember the day that I borrowed one of the books from my advisor's office and walked down to the Charles River and was like, I'm getting my butt kicked, you know?
2:45:53 Speaker 01 And I think that's going to happen to everybody who's doing this kind of stuff, right? I think,
2:46:00 Speaker 01 I expected you to ask me the meaning of life. You know, I think that the, um, somehow I think that's, that's got to be part of it, this.
2:46:09 Lex Fridman? Doing hard things?
2:46:12 Speaker 01 Yeah.
2:46:12 Lex Fridman? Did you, uh, did you consider quitting at any point? Did you consider this isn't for me?
2:46:16 Speaker 01 No, never that. I mean, I was, I was working hard, but I was loving it, right? There's, I think the, there's this magical thing where you, uh, you know, I'm lucky to surround myself with people that basically.
2:46:31 Speaker 01 Almost every day, I'll, I'll, I'll see something, I'll be told something or something that I realize, wow, I don't understand that. And if I could just understand that, there's, there's something else to learn, that if I could just learn that thing, I would connect another piece of the puzzle. And, and, you know, I think that is just such an important aspect. And being willing to understand what you can and can't do, and, and loving the journey of going and learning those other things. I think that's the best part.
2:47:04 Lex Fridman? I don't think there's a better way to end it, Russ. You've been an inspiration to me since I showed up at MIT. Your work has been an inspiration to the world. This conversation was amazing. I can't wait to see what you do next with robotics, home robots. I, I hope to see you work in my home one day. So, thanks so much for talking today. It's been awesome.
2:47:25 Speaker 01 Cheers.
2:47:26 Lex Fridman? Thanks for listening to this conversation with Ross Tedrick. And thank you to our sponsors, Magic Spoon Cereal, BetterHelp, and ExpressVPN. Please consider supporting this podcast by going to magic spoon.com/lex and using code Lex at checkout. Go into betterhelp.com/lex and signing up at expressvpn.com/lexpod. Click the links, buy the stuff, get the discount. It really is the best way to support this podcast. If you enjoy this thing, subscribe on YouTube, review it with five stars and up a podcast, support it on Patreon, or connect with me on Twitter at Lex Fridman, spelled somehow without the E, just F R I D M A N.
2:48:10 Lex Fridman? And now, let me leave you with some words from Neil deGrasse Tyson, talking about robots in space and the emphasis we humans put on human-based space exploration. Robots are important. If I donned my pure scientist hat, I would say just send robots. I'll stay down here and get the data. But nobody's ever given a parade for a robot. Nobody's ever named a high school after a robot. So when I don't my public educator hat, I have to recognize the elements of exploration that excite people. It's not only the discoveries and the beautiful photos that come down from the heavens. It's the vicarious participation in discovery itself.
2:48:51 Lex Fridman? Thank you for listening and hope to see you next time.
2:49:13 Lex Fridman? Thank you.
Previous #113 – Manolis Kellis: Human Genome and Evolutionary Dynamics Next #115 – Dileep George: Brain-Inspired AI Page updated October 26, 2026 · transcript and summary are machine-generated