TED日本語 - マーク・レイバート: 走って飛び跳ねて、ドアも開けられるロボット犬「スポット」

(Laughter)

(Laughter)

That's SpotMini. He'll be back in a little while.

I --

(Applause)

I love building robots. And my long-term goal is to build robots that can do what people and animals do. And there's three things in particular that we're interested in. One is balance and dynamic mobility, the second one is mobile manipulation, and the third one is mobile perception.

So, dynamic mobility and balance -- I'm going to do a demo for you. I'm standing here, balancing. I can see you're not very impressed. OK, how about now?

(Laughter)

How about now?

(Applause)

Those simple capabilities mean that people can go almost anywhere on earth, on any kind of terrain. We want to capture that for robots.

What about manipulation? I'm holding this clicker in my hand; I'm not even looking at it, and I can manipulate it without any problem. But even more important, I can move my body while I hold the manipulator, the clicker, and stabilize and coordinate my body, and I can even walk around. And that means I can move around in the world and expand the range of my arms and my hands and really be able to handle almost anything. So that's mobile manipulation. And all of you can do this.

Third is perception. I'm looking at a room with over 1,000 people in it, and my amazing visual system can see every one of you -- you're all stable in space, even when I move my head, even when I move around. That kind of mobile perception is really important for robots that are going to move and act out in the world.

I'm going to give you a little status report on where we are in developing robots toward these ends. The first three robots are all dynamically stabilized robots. This one goes back a little over 10 years ago -- "BigDog." It's got a gyroscope that helps stabilize it. It's got sensors and a control computer.

Here's a Cheetah robot that's running with a galloping gait, where it recycles its energy, it bounces on the ground, and it's computing all the time in order to keep itself stabilized and propelled.

And here's a bigger robot that's got such good locomotion using its legs, that it can go in deep snow. This is about 10 inches deep, and it doesn't really have any trouble.

This is Spot, a new generation of robot -- just slightly older than the one that came out onstage. And we've been asking the question -- you've all heard about drone delivery: Can we deliver packages to your houses with drones? Well, what about plain old legged-robot delivery?

(Laughter)

So we've been taking our robot to our employees' homes to see whether we could get in --

(Laughter)

the various access ways. And believe me, in the Boston area, there's every manner of stairway twists and turns. So it's a real challenge. But we're doing very well, about 70 percent of the way.

And here's mobile manipulation, where we've put an arm on the robot, and it's finding its way through the door. Now,one of the important things about making autonomous robots is to make them not do just exactly what you say, but make them deal with the uncertainty of what happens in the real world. So we have Steve there,one of the engineers, giving the robot a hard time.

(Laughter)

And the fact that the programming still tolerates all that disturbance -- it does what it's supposed to.

Here's another example, where Eric is tugging on the robot as it goes up the stairs. And believe me, getting it to do what it's supposed to do in those circumstances is a real challenge, but the result is something that's going to generalize and make robots much more autonomous than they would be otherwise.

This is Atlas, a humanoid robot. It's a third-generation humanoid that we've been building. I'll tell you a little bit about the hardware design later. And we've been saying: How close to human levels of performance and speed could we get in an ordinary task, like moving boxes around on a conveyor? We're getting up to about two-thirds of the speed that a human operates on average. And this robot is using both hands, it's using its body, it's stepping, so it's really an example of dynamic stability, mobile manipulation and mobile perception. Here --

(Laughter)

We actually have two Atlases.

(Laughter)

Now, everything doesn't go exactly the way it's supposed to.

(Laughter)

(Laughter)

(Laughter)

And here's our latest robot, called "Handle." Handle is interesting, because it's sort of half like an animal, and it's half something else with these leg-like things and wheels. It's got its arms on in kind of a funny way, but it really does some remarkable things. It can carry 100 pounds. It's probably going to lift more than that, but so far we've done 100. It's got some pretty good rough-terrain capability, even though it has wheels. And Handle loves to put on a show.

(Laughter)

(Applause)

I'm going to give you a little bit of robot religion. A lot of people think that a robot is a machine where there's a computer that's telling it what to do, and the computer is listening through its sensors. But that's really only half of the story. The real story is that the computer is on one side, making suggestions to the robot, and on the other side are the physics of the world. And that physics involves gravity, friction, bouncing into things. In order to have a successful robot, my religion is that you have to do a holistic design, where you're designing the software, the hardware and the behavior all at one time, and all these parts really intermesh and cooperate with each other. And when you get the perfect design, you get a real harmony between all those parts interacting with each other. So it's half software and half hardware, plus the behavior.

We've done some work lately on the hardware, where we tried to go -- the picture on the left is a conventional design, where you have parts that are all bolted together, conductors, tubes, connectors. And on the right is a more integrated thing; it's supposed to look like an anatomy drawing. Using the miracle of 3-D printing, we're starting to build parts of robots that look a lot more like the anatomy of an animal. So that's an upper-leg part that has hydraulic pathways -- actuators, filters -- all embedded, all printed as one piece, and the whole structure is developed with a knowledge of what the loads and behavior are going to be, which is available from data recorded from robots and simulations and things like that.

So it's a data-driven hardware design. And using processes like that, not only the upper leg but some other things, we've gotten our robots to go from big, behemoth, bulky, slow, bad robots -- that one on the right, weighing almost 400 pounds -- down to the one in the middle which was just in the video, weighs about 190 pounds, just a little bit more than me, and we have a new one, which is working but I'm not going to show it to you yet, on the left, which weighs just 165 pounds, with all the same strength and capabilities. So these things are really getting better very quickly.

So it's time for Spot to come back out, and we're going to demonstrate a little bit of mobility, dexterity and perception. This is Seth Davis, who's my robot wrangler today, and he's giving Spot some general direction by steering it around, but all the coordination of the legs and the sensors is done by the robot's computers on board. The robot can walk with a number of different gaits; it's got a gyro, or a solid-state gyro, an IMU on board. Obviously, it's got a battery, and things like that. One of the cool things about a legged robot is, it's omnidirectional. In addition to going forward, it can go sideways, it can turn in place. And this robot is a little bit of a show-off. It loves to use its dynamic gaits, like running --

(Laughter)

And it's got one more.

(Laughter)

Now if it were really a show-off, it would be hopping on one foot, but, you know.

Now, Spot has a set of cameras here, stereo cameras, and we have a feed up in the center. It's kind of dark out in the audience, but it's going to use those cameras in order to look at the terrain right in front of it, while it goes over these obstacles back here. For this demo, Seth is steering, but the robot's doing all its own terrain planning. This is a terrain map, where the data from the cameras is being developed in real time, showing the red spots, which are where it doesn't want to step, and the green spots are the good places. And here it's treating them like stepping-stones. So it's trying to stay up on the blocks, and it adjusts its stride, and there's a ton of planning that has to go into an operation like that, and it does all that planning in real time, where it adjusts the steps a little bit longer or a little bit shorter.

Now we're going to change it into a different mode, where it's just going to treat the blocks like terrain and decide whether to step up or down as it goes. So this is using dynamic balance and mobile perception, because it has to coordinate what it sees along with how it's moving.

The other thing Spot has is a robot arm. Some of you may see that as a head and a neck, but believe me, it's an arm. Seth is driving it around. He's actually driving the hand and the body is following. So the two are coordinated in the way I was talking about before -- in the way people can do that. In fact,one of the cool things Spot can do we call, "chicken-head mode," and it keeps its head in one place in space, and it moves its body all around. There's a variation of this that's called "twerking" --

(Laughter)

but we're not going to use that today.

(Laughter)

So, Spot: I'm feeling a little thirsty. Could you get me a soda? For this demo, Seth is not doing any driving. We have a LIDAR on the back of the robot, and it's using these props we've put on the stage to localize itself. It's gone over to that location. Now it's using a camera that's in its hand to find the cup, picks it up -- and again, Seth's not driving. We've planned out a path for it to go -- it looked like it was going off the path -- and now Seth's going to take over control again, because I'm a little bit chicken about having it do this by itself. Thank you, Spot.

(Applause)

So, Spot: How do you feel about having just finished your TED performance?

(Laughter)

Me, too!

(Laughter)

Thank you all, and thanks to the team at Boston Dynamics, who did all the hard work behind this.

(Applause)

Helen Walters: Marc, come back in the middle. Thank you so much. Come over here, I have questions.

So, you mentioned the UPS and the package delivery. What are the other applications that you see for your robots?

Marc Raibert: You know, I think that robots that have the capabilities I've been talking about are going to be incredibly useful. About a year ago, I went to Fukushima to see what the situation was there, and there's just a huge need for machines that can go into some of the dirty places and help remediate that.

I think it won't be too long until we have robots like this in our homes, and one of the big needs is to take care of the aging and invalids. I think that it won't be too long till we're using robots to help take care of our parents, or probably more likely, have our children help take care of us. And there's a bunch of other things. I think the sky's the limit. Many of the ideas we haven't thought of yet, and people like you will help us think of new applications.

HW: So what about the dark side? What about the military? Are they interested?

MR: Sure, the military has been a big funder of robotics. I don't think the military is the dark side myself, but I think, as with all advanced technology, it can be used for all kinds of things.

HW: Awesome. Thank you so much.

MR: OK, you're welcome.

Thank you.

(Applause)