0:00:00.564,0:00:05.207
My job is to design, build and study[br]robots that communicate with people.

0:00:05.231,0:00:08.850
But this story doesn't start with robotics[br]at all, it starts with animation.

0:00:08.874,0:00:11.243
When I first saw Pixar's "Luxo Jr.,"

0:00:11.267,0:00:13.973
I was amazed by how much[br]emotion they could put

0:00:13.997,0:00:16.825
into something as trivial as a desk lamp.

0:00:17.477,0:00:19.822
I mean, look at them --[br]at the end of this movie,

0:00:19.846,0:00:22.625
you actually feel something[br]for two pieces of furniture.

0:00:22.649,0:00:23.930
(Laughter)

0:00:23.954,0:00:25.982
And I said, I have[br]to learn how to do this.

0:00:26.006,0:00:28.233
So I made a really bad career decision.

0:00:28.257,0:00:29.451
(Laughter)

0:00:29.475,0:00:31.668
And that's what my mom[br]was like when I did it.

0:00:31.692,0:00:33.833
(Laughter)

0:00:33.857,0:00:37.278
I left a very cozy tech job in Israel[br]at a nice software company

0:00:37.302,0:00:39.594
and I moved to New York[br]to study animation.

0:00:39.618,0:00:40.769
And there I lived

0:00:40.793,0:00:43.611
in a collapsing apartment building[br]in Harlem with roommates.

0:00:43.635,0:00:45.659
I'm not using this phrase[br]metaphorically --

0:00:45.683,0:00:48.412
the ceiling actually collapsed[br]one day in our living room.

0:00:48.436,0:00:51.678
Whenever they did news stories[br]about building violations in New York,

0:00:51.702,0:00:54.118
they would put the report[br]in front of our building,

0:00:54.142,0:00:56.879
as kind of, like, a backdrop[br]to show how bad things are.

0:00:56.903,0:00:58.840
Anyway, during the day, I went to school

0:00:58.864,0:01:02.291
and at night I would sit and draw[br]frame by frame of pencil animation.

0:01:02.315,0:01:04.500
And I learned two surprising lessons.

0:01:04.524,0:01:09.014
One of them was that[br]when you want to arouse emotions,

0:01:09.038,0:01:11.213
it doesn't matter so much[br]how something looks;

0:01:11.237,0:01:14.435
it's all in the motion, in the timing[br]of how the thing moves.

0:01:14.816,0:01:18.006
And the second was something[br]one of our teachers told us.

0:01:18.030,0:01:20.323
He actually did the weasel in "Ice Age."

0:01:20.662,0:01:24.519
And he said, "As an animator,[br]you're not a director -- you're an actor."

0:01:24.895,0:01:27.918
So, if you want to find[br]the right motion for a character,

0:01:27.942,0:01:30.387
don't think about it --[br]go use your body to find it.

0:01:30.411,0:01:33.344
Stand in front of a mirror,[br]act it out in front of a camera --

0:01:33.368,0:01:36.306
whatever you need -- and then[br]put it back in your character.

0:01:36.696,0:01:39.908
A year later I found myself at MIT[br]in the Robotic Life Group.

0:01:39.932,0:01:42.790
It was one of the first groups[br]researching the relationships

0:01:42.814,0:01:44.128
between humans and robots.

0:01:44.152,0:01:48.108
And I still had this dream[br]to make an actual, physical Luxo Jr. lamp.

0:01:48.132,0:01:51.124
But I found that robots didn't move[br]at all in this engaging way

0:01:51.148,0:01:53.323
that I was used to[br]from my animation studies.

0:01:53.347,0:01:55.811
Instead, they were all --[br]how should I put it --

0:01:55.835,0:01:57.289
they were all kind of robotic.

0:01:57.313,0:01:59.187
(Laughter)

0:01:59.211,0:02:02.947
And I thought, what if I took[br]whatever I learned in animation school,

0:02:02.971,0:02:05.574
and used that to design[br]my robotic desk lamp.

0:02:05.598,0:02:07.643
So I went and designed frame by frame

0:02:07.667,0:02:11.627
to try to make this robot as graceful[br]and engaging as possible.

0:02:12.199,0:02:15.908
And here when you see the robot[br]interacting with me on a desktop --

0:02:15.932,0:02:17.968
and I'm actually redesigning the robot,

0:02:17.992,0:02:19.796
so, unbeknownst to itself,

0:02:19.820,0:02:22.395
it's kind of digging its own[br]grave by helping me.

0:02:22.419,0:02:24.425
(Laughter)

0:02:24.449,0:02:27.688
I wanted it to be less of a mechanical[br]structure giving me light,

0:02:27.712,0:02:30.730
and more of a helpful,[br]kind of quiet apprentice

0:02:30.754,0:02:33.923
that's always there when you need it[br]and doesn't really interfere.

0:02:33.947,0:02:37.282
And when, for example, I'm looking[br]for a battery that I can't find,

0:02:37.306,0:02:40.253
in a subtle way, it'll show me[br]where the battery is.

0:02:41.872,0:02:43.705
So you can see my confusion here.

0:02:44.442,0:02:45.654
I'm not an actor.

0:02:48.585,0:02:51.618
And I want you to notice[br]how the same mechanical structure

0:02:51.642,0:02:53.729
can, at one point,[br]just by the way it moves,

0:02:53.753,0:02:55.897
seem gentle and caring[br]and in the other case,

0:02:55.921,0:02:58.292
seem violent and confrontational.

0:02:58.316,0:03:01.163
And it's the same structure,[br]just the motion is different.

0:03:07.419,0:03:11.991
Actor: "You want to know something?[br]Well, you want to know something?

0:03:12.015,0:03:13.904
He was already dead!

0:03:13.928,0:03:17.830
Just laying there, eyes glazed over!"

0:03:17.854,0:03:18.875
(Laughter)

0:03:18.899,0:03:21.955
But, moving in a graceful way[br]is just one building block

0:03:21.979,0:03:24.574
of this whole structure[br]called human-robot interaction.

0:03:24.598,0:03:28.051
I was, at the time, doing my PhD,[br]I was working on human-robot teamwork,

0:03:28.075,0:03:30.137
teams of humans and robots[br]working together.

0:03:30.161,0:03:31.796
I was studying the engineering,

0:03:31.820,0:03:34.352
the psychology,[br]the philosophy of teamwork,

0:03:34.376,0:03:35.527
and at the same time,

0:03:35.551,0:03:38.045
I found myself in my own kind[br]of teamwork situation,

0:03:38.069,0:03:40.321
with a good friend of mine,[br]who's actually here.

0:03:40.345,0:03:42.749
And in that situation,[br]we can easily imagine robots

0:03:42.773,0:03:44.673
in the near future being there with us.

0:03:44.697,0:03:46.387
It was after a Passover Seder.

0:03:46.411,0:03:48.466
We were folding up[br]a lot of folding chairs,

0:03:48.490,0:03:51.148
and I was amazed at how quickly[br]we found our own rhythm.

0:03:51.172,0:03:54.282
Everybody did their own part,[br]we didn't have to divide our tasks.

0:03:54.306,0:03:56.752
We didn't have to communicate[br]verbally about this --

0:03:56.776,0:03:57.965
it all just happened.

0:03:57.989,0:04:00.869
And I thought, humans and robots[br]don't look at all like this.

0:04:00.893,0:04:04.024
When humans and robots interact,[br]it's much more like a chess game:

0:04:04.048,0:04:07.169
the human does a thing, the robot[br]analyzes whatever the human did,

0:04:07.193,0:04:09.836
the robot decides what to do next,[br]plans it and does it.

0:04:09.860,0:04:12.215
Then the human waits,[br]until it's their turn again.

0:04:12.239,0:04:14.970
So it's much more like a chess game,[br]and that makes sense,

0:04:14.994,0:04:18.105
because chess is great for mathematicians[br]and computer scientists.

0:04:18.129,0:04:21.557
It's all about information, analysis,[br]decision-making and planning.

0:04:21.581,0:04:25.311
But I wanted my robot[br]to be less of a chess player,

0:04:25.335,0:04:27.128
and more like a doer

0:04:27.152,0:04:29.153
that just clicks and works together.

0:04:29.177,0:04:32.546
So I made my second[br]horrible career choice:

0:04:32.570,0:04:35.123
I decided to study acting for a semester.

0:04:35.147,0:04:38.066
I took off from the PhD,[br]I went to acting classes.

0:04:38.090,0:04:40.128
I actually participated in a play --

0:04:40.152,0:04:42.454
I hope there’s no video[br]of that around still.

0:04:42.478,0:04:43.516
(Laughter)

0:04:43.540,0:04:45.834
And I got every book[br]I could find about acting,

0:04:45.858,0:04:48.987
including one from the 19th century[br]that I got from the library.

0:04:49.011,0:04:52.624
And I was really amazed, because my name[br]was the second name on the list --

0:04:52.648,0:04:54.648
the previous name was in 1889.

0:04:54.672,0:04:55.687
(Laughter)

0:04:55.711,0:04:57.960
And this book was[br]kind of waiting for 100 years

0:04:57.984,0:05:00.316
to be rediscovered for robotics.

0:05:00.340,0:05:01.916
And this book shows actors

0:05:01.940,0:05:04.178
how to move every muscle in the body

0:05:04.202,0:05:06.918
to match every kind of emotion[br]that they want to express.

0:05:06.942,0:05:09.968
But the real revelation was[br]when I learned about method acting.

0:05:09.992,0:05:12.245
It became very popular[br]in the 20th century.

0:05:12.269,0:05:13.420
And method acting said

0:05:13.444,0:05:15.744
you don't have to plan[br]every muscle in your body;

0:05:15.768,0:05:18.713
instead, you have to use your body[br]to find the right movement.

0:05:18.737,0:05:21.617
You have to use your sense memory[br]to reconstruct the emotions

0:05:21.641,0:05:24.679
and kind of think with your body[br]to find the right expression --

0:05:24.703,0:05:26.578
improvise, play off your scene partner.

0:05:26.602,0:05:28.047
And this came at the same time

0:05:28.071,0:05:31.177
as I was reading about this trend[br]in cognitive psychology,

0:05:31.201,0:05:34.453
called embodied cognition,[br]which also talks about the same ideas.

0:05:34.477,0:05:35.992
We use our bodies to think;

0:05:36.016,0:05:38.973
we don't just think with our brains[br]and use our bodies to move,

0:05:38.997,0:05:40.915
but our bodies feed back into our brain

0:05:40.939,0:05:43.104
to generate the way that we behave.

0:05:43.128,0:05:44.724
And it was like a lightning bolt.

0:05:44.748,0:05:45.962
I went back to my office,

0:05:45.986,0:05:48.391
I wrote this paper,[br]which I never really published,

0:05:48.415,0:05:50.947
called "Acting Lessons[br]for Artificial Intelligence."

0:05:50.971,0:05:52.352
And I even took another month

0:05:52.376,0:05:54.820
to do what was then the first theater play

0:05:54.844,0:05:56.797
with a human and a robot acting together.

0:05:56.821,0:05:59.214
That's what you saw[br]before with the actors.

0:06:00.564,0:06:01.715
And I thought:

0:06:01.739,0:06:04.676
How can we make an artificial[br]intelligence model --

0:06:04.700,0:06:06.683
a computer, computational model --

0:06:06.707,0:06:09.214
that will model some of these[br]ideas of improvisation,

0:06:09.238,0:06:11.068
of taking risks, of taking chances,

0:06:11.092,0:06:12.619
even of making mistakes?

0:06:12.643,0:06:15.256
Maybe it can make for better[br]robotic teammates.

0:06:15.280,0:06:17.884
So I worked for quite[br]a long time on these models

0:06:17.908,0:06:20.303
and I implemented them[br]on a number of robots.

0:06:20.327,0:06:22.628
Here you can see a very early example

0:06:22.652,0:06:26.231
with the robots trying to use[br]this embodied artificial intelligence

0:06:26.255,0:06:28.718
to try to match my movements[br]as closely as possible.

0:06:28.742,0:06:30.205
It's sort of like a game.

0:06:30.530,0:06:31.739
Let's look at it.

0:06:35.652,0:06:39.191
You can see when I psych[br]it out, it gets fooled.

0:06:39.698,0:06:42.293
And it's a little bit[br]like what you might see actors do

0:06:42.317,0:06:43.951
when they try to mirror each other

0:06:43.975,0:06:46.340
to find the right synchrony between them.

0:06:46.364,0:06:48.196
And then, I did another experiment,

0:06:48.220,0:06:52.279
and I got people off the street[br]to use the robotic desk lamp,

0:06:52.303,0:06:55.405
and try out this idea[br]of embodied artificial intelligence.

0:06:55.921,0:07:00.519
So, I actually used two kinds[br]of brains for the same robot.

0:07:00.543,0:07:02.495
The robot is the same lamp that you saw,

0:07:02.519,0:07:03.858
and I put two brains in it.

0:07:03.882,0:07:05.609
For one half of the people,

0:07:05.633,0:07:08.569
I put in a brain[br]that's kind of the traditional,

0:07:08.593,0:07:09.822
calculated robotic brain.

0:07:09.846,0:07:12.486
It waits for its turn,[br]it analyzes everything, it plans.

0:07:12.510,0:07:14.192
Let's call it the calculated brain.

0:07:14.216,0:07:17.463
The other got more the stage[br]actor, risk-taker brain.

0:07:17.487,0:07:19.609
Let's call it the adventurous brain.

0:07:19.633,0:07:22.570
It sometimes acts without knowing[br]everything it has to know.

0:07:22.594,0:07:24.886
It sometimes makes mistakes[br]and corrects them.

0:07:24.910,0:07:28.828
And I had them do this very tedious task[br]that took almost 20 minutes,

0:07:28.852,0:07:30.328
and they had to work together,

0:07:30.352,0:07:32.905
somehow simulating, like, a factory job

0:07:32.929,0:07:35.016
of repetitively doing the same thing.

0:07:35.445,0:07:38.776
What I found is that people[br]actually loved the adventurous robot.

0:07:38.800,0:07:40.577
They thought it was more intelligent,

0:07:40.601,0:07:42.707
more committed,[br]a better member of the team,

0:07:42.731,0:07:44.796
contributed to the success[br]of the team more.

0:07:44.820,0:07:46.528
They even called it "he" and "she,"

0:07:46.552,0:07:48.673
whereas people with the calculated brain

0:07:48.697,0:07:51.499
called it "it," and nobody[br]ever called it "he" or "she."

0:07:51.876,0:07:55.169
When they talked about it after the task,[br]with the adventurous brain,

0:07:55.193,0:07:58.976
they said, "By the end, we were good[br]friends and high-fived mentally."

0:07:59.397,0:08:00.690
Whatever that means.

0:08:00.714,0:08:02.620
(Laughter)

0:08:02.644,0:08:03.997
Sounds painful.

0:08:04.021,0:08:06.759
Whereas the people[br]with the calculated brain

0:08:06.783,0:08:09.141
said it was just like a lazy apprentice.

0:08:09.165,0:08:11.910
It only did what it was supposed[br]to do and nothing more,

0:08:11.934,0:08:14.283
which is almost what people[br]expect robots to do,

0:08:14.307,0:08:17.862
so I was surprised that people[br]had higher expectations of robots

0:08:17.886,0:08:21.392
than what anybody in robotics[br]thought robots should be doing.

0:08:22.027,0:08:24.042
And in a way, I thought,[br]maybe it's time --

0:08:24.066,0:08:27.028
just like method acting[br]changed the way people thought

0:08:27.052,0:08:28.648
about acting in the 19th century,

0:08:28.672,0:08:31.749
from going from the very calculated,[br]planned way of behaving,

0:08:31.773,0:08:35.271
to a more intuitive, risk-taking,[br]embodied way of behaving --

0:08:35.295,0:08:38.491
maybe it's time for robots[br]to have the same kind of revolution.

0:08:39.994,0:08:43.593
A few years later, I was at my next[br]research job at Georgia Tech in Atlanta,

0:08:43.617,0:08:46.441
and I was working in a group[br]dealing with robotic musicians.

0:08:46.465,0:08:48.825
And I thought, music:[br]that's the perfect place

0:08:48.849,0:08:52.992
to look at teamwork, coordination,[br]timing, improvisation --

0:08:53.016,0:08:55.459
and we just got this robot[br]playing marimba.

0:08:55.483,0:08:57.739
And the marimba, for everybody like me,

0:08:57.763,0:09:00.502
it was this huge, wooden xylophone.

0:09:00.526,0:09:02.589
And when I was looking at this,

0:09:02.613,0:09:05.611
I looked at other works[br]in human-robot improvisation --

0:09:05.635,0:09:08.382
yes, there are other works[br]in human-robot improvisation --

0:09:08.406,0:09:10.755
and they were also a little bit[br]like a chess game.

0:09:10.779,0:09:11.930
The human would play,

0:09:11.954,0:09:14.127
the robot analyzed what was played,

0:09:14.151,0:09:16.230
and would improvise their own part.

0:09:16.254,0:09:19.392
So, this is what musicians called[br]a call-and-response interaction,

0:09:19.416,0:09:23.163
and it also fits very well[br]robots and artificial intelligence.

0:09:23.187,0:09:26.440
But I thought, if I use the same ideas[br]I used in the theater play

0:09:26.464,0:09:28.208
and in the teamwork studies,

0:09:28.232,0:09:31.882
maybe I can make the robots[br]jam together like a band.

0:09:31.906,0:09:36.174
Everybody's riffing off each other,[br]nobody is stopping for a moment.

0:09:36.198,0:09:39.072
And so I tried to do the same[br]things, this time with music,

0:09:39.096,0:09:41.930
where the robot doesn't really know[br]what it's about to play,

0:09:41.954,0:09:44.971
it just sort of moves its body[br]and uses opportunities to play,

0:09:44.995,0:09:47.534
and does what my jazz teacher[br]when I was 17 taught me.

0:09:47.558,0:09:48.955
She said, when you improvise,

0:09:48.979,0:09:51.995
sometimes you don't know[br]what you're doing, and you still do it.

0:09:52.019,0:09:55.345
So I tried to make a robot that doesn't[br]actually know what it's doing,

0:09:55.369,0:09:56.590
but is still doing it.

0:09:56.614,0:09:59.125
So let's look at a few seconds[br]from this performance,

0:09:59.149,0:10:01.276
where the robot listens[br]to the human musician

0:10:01.300,0:10:02.465
and improvises.

0:10:02.489,0:10:05.464
And then, look how the human[br]musician also responds

0:10:05.488,0:10:06.761
to what the robot is doing

0:10:06.785,0:10:09.429
and picking up from its behavior,

0:10:09.453,0:10:13.409
and at some point can even be surprised[br]by what the robot came up with.

0:10:13.433,0:10:15.627
(Music)

0:10:55.618,0:10:57.618
(Music ends)

0:10:59.134,0:11:04.868
(Applause)

0:11:04.892,0:11:07.142
Being a musician[br]is not just about making notes,

0:11:07.166,0:11:09.514
otherwise nobody[br]would ever go see a live show.

0:11:09.538,0:11:11.660
Musicians also communicate[br]with their bodies,

0:11:11.684,0:11:13.701
with other band members,[br]with the audience,

0:11:13.725,0:11:15.739
they use their bodies[br]to express the music.

0:11:15.763,0:11:18.460
And I thought, we already have[br]a robot musician on stage,

0:11:18.484,0:11:20.796
why not make it be[br]a full-fledged musician?

0:11:20.820,0:11:23.494
And I started designing[br]a socially expressive head

0:11:23.518,0:11:24.861
for the robot.

0:11:24.885,0:11:26.955
The head doesn’t actually[br]touch the marimba,

0:11:26.979,0:11:28.938
it just expresses what the music is like.

0:11:28.962,0:11:31.458
These are some napkin sketches[br]from a bar in Atlanta

0:11:31.482,0:11:34.025
that was dangerously[br]located exactly halfway

0:11:34.049,0:11:35.860
between my lab and my home.

0:11:35.884,0:11:39.822
So I spent, I would say, on average,[br]three to four hours a day there.

0:11:39.846,0:11:41.033
I think.

0:11:41.057,0:11:42.584
(Laughter)

0:11:42.917,0:11:45.799
And I went back to my animation[br]tools and tried to figure out

0:11:45.823,0:11:48.193
not just what a robotic[br]musician would look like,

0:11:48.217,0:11:50.842
but especially what a robotic[br]musician would move like,

0:11:50.866,0:11:54.268
to sort of show that it doesn't like[br]what the other person is playing --

0:11:54.292,0:11:58.117
and maybe show whatever beat[br]it's feeling at the moment.

0:11:58.141,0:12:02.644
So we ended up actually getting the money[br]to build this robot, which was nice.

0:12:02.668,0:12:05.272
I'm going to show you now[br]the same kind of performance,

0:12:05.296,0:12:07.336
this time with a socially expressive head.

0:12:07.360,0:12:09.160
And notice one thing --

0:12:09.184,0:12:10.855
how the robot is really showing us

0:12:10.879,0:12:12.785
the beat it's picking up from the human,

0:12:12.809,0:12:16.736
while also giving the human a sense[br]that the robot knows what it's doing.

0:12:16.760,0:12:18.680
And also how it changes the way it moves

0:12:18.704,0:12:20.656
as soon as it starts its own solo.

0:12:20.680,0:12:24.576
(Music)

0:12:24.600,0:12:27.620
Now it's looking at me,[br]showing that it's listening.

0:12:27.644,0:12:30.367
(Music)

0:12:49.181,0:12:52.102
Now look at the final chord[br]of the piece again.

0:12:52.126,0:12:55.043
And this time the robot[br]communicates with its body

0:12:55.067,0:12:57.180
when it's busy doing its own thing,

0:12:57.204,0:13:02.055
and when it's ready to coordinate[br]the final chord with me.

0:13:02.079,0:13:04.816
(Music)

0:13:09.783,0:13:11.783
(Music ending)

0:13:14.103,0:13:15.104
(Final chord)

0:13:15.128,0:13:20.882
(Applause)

0:13:20.906,0:13:22.061
Thanks.

0:13:22.085,0:13:23.666
I hope you see

0:13:23.690,0:13:28.086
how much this part of the body[br]that doesn't touch the instrument

0:13:28.110,0:13:30.702
actually helps[br]with the musical performance.

0:13:31.160,0:13:33.169
And at some point -- we are in Atlanta,

0:13:33.193,0:13:36.443
so obviously some rapper[br]will come into our lab at some point --

0:13:36.467,0:13:41.260
and we had this rapper come in and do[br]a little jam with the robot.

0:13:41.284,0:13:45.332
Here you can see the robot[br]basically responding to the beat.

0:13:45.356,0:13:46.507
Notice two things:

0:13:46.531,0:13:50.140
one, how irresistible it is to join[br]the robot while it's moving its head.

0:13:50.164,0:13:52.767
You kind of want to move[br]your own head when it does it.

0:13:52.791,0:13:56.377
And second, even though the rapper[br]is really focused on his iPhone,

0:13:56.401,0:13:59.511
as soon as the robot turns[br]to him, he turns back.

0:13:59.535,0:14:02.171
So even though it's just[br]in the periphery of his vision,

0:14:02.195,0:14:04.315
in the corner of his eye,[br]it's very powerful.

0:14:04.339,0:14:06.173
And the reason is that we can't ignore

0:14:06.197,0:14:08.221
physical things moving in our environment.

0:14:08.245,0:14:09.415
We are wired for that.

0:14:09.439,0:14:11.083
So if you have a problem --

0:14:11.107,0:14:15.782
maybe your partner is looking[br]at their iPhone or smartphone too much --

0:14:15.806,0:14:18.640
you might want to have a robot[br]there to get their attention.

0:14:18.664,0:14:19.665
(Laughter)

0:14:19.689,0:14:21.758
(Music)

0:14:34.113,0:14:36.113
(Music ends)

0:14:38.138,0:14:45.086
(Applause)

0:14:45.633,0:14:49.467
Just to introduce the last robot[br]that we've worked on,

0:14:49.491,0:14:51.841
it came out of something[br]surprising that we found:

0:14:51.865,0:14:55.023
Some point people didn't care[br]about the robot being intelligent,

0:14:55.047,0:14:56.449
able to improvise and listen,

0:14:56.473,0:15:00.879
and do all these embodied intelligence[br]things that I spent years developing.

0:15:00.903,0:15:03.584
They really liked that the robot[br]was enjoying the music.

0:15:03.608,0:15:04.609
(Laughter)

0:15:04.633,0:15:07.178
And they didn't say the robot[br]was moving to the music,

0:15:07.202,0:15:08.690
they said "enjoying" the music.

0:15:08.714,0:15:10.840
And we thought,[br]why don't we take this idea,

0:15:10.864,0:15:13.605
and I designed a new piece of furniture.

0:15:13.629,0:15:16.201
This time it wasn't a desk lamp,[br]it was a speaker dock,

0:15:16.225,0:15:18.865
one of those things[br]you plug your smartphone in.

0:15:18.889,0:15:20.039
And I thought,

0:15:20.063,0:15:23.563
what would happen if your speaker dock[br]didn't just play the music for you,

0:15:23.587,0:15:25.633
but would actually enjoy it, too?

0:15:25.657,0:15:29.818
And so again, here are some[br]animation tests from an early stage.

0:15:29.842,0:15:31.226
(Laughter)

0:15:31.835,0:15:34.706
And this is what the final[br]product looked like.

0:15:46.247,0:15:48.428
(Music)

0:16:06.848,0:16:08.848
(Music ends)

0:16:09.461,0:16:12.081
So, a lot of bobbing heads.

0:16:12.105,0:16:15.716
(Applause)

0:16:15.740,0:16:17.630
A lot of bobbing heads in the audience,

0:16:17.654,0:16:20.362
so we can still see[br]robots influence people.

0:16:20.386,0:16:23.171
And it's not just fun and games.

0:16:23.195,0:16:25.396
I think one of the reasons I care so much

0:16:25.420,0:16:27.653
about robots that use[br]their body to communicate

0:16:27.677,0:16:29.383
and use their body to move is --

0:16:29.407,0:16:32.797
I'm going to let you in on a little[br]secret we roboticists are hiding --

0:16:32.821,0:16:35.614
is that every one of you[br]is going to be living with a robot

0:16:35.638,0:16:37.230
at some point in your life.

0:16:37.254,0:16:40.187
Somewhere in your future,[br]there will be a robot in your life.

0:16:40.211,0:16:42.079
If not in yours, your children's lives.

0:16:42.103,0:16:47.093
And I want these robots to be more fluent,[br]more engaging, more graceful

0:16:47.117,0:16:48.846
than currently they seem to be.

0:16:48.870,0:16:52.157
And for that I think maybe robots[br]need to be less like chess players

0:16:52.181,0:16:54.822
and more like stage actors[br]and more like musicians.

0:16:54.846,0:16:57.659
Maybe they should be able[br]to take chances and improvise.

0:16:57.683,0:17:00.707
Maybe they should be able[br]to anticipate what you're about to do.

0:17:00.731,0:17:04.079
Maybe they even need to be able[br]to make mistakes and correct them,

0:17:04.103,0:17:05.991
because in the end, we are human.

0:17:06.015,0:17:09.569
And maybe as humans,[br]robots that are a little less than perfect

0:17:09.593,0:17:11.324
are just perfect for us.

0:17:11.348,0:17:12.507
Thank you.

0:17:12.531,0:17:19.367
(Applause)