The Rise of Personal Robots | Cynthia Breazeal | TED Talks

159,306 views ・ 2011-02-08

TED


Please double-click on the English subtitles below to play the video.

00:15
Ever since I was a little girl
0
15260
3000
00:18
seeing "Star Wars" for the first time,
1
18260
2000
00:20
I've been fascinated by this idea
2
20260
2000
00:22
of personal robots.
3
22260
2000
00:24
And as a little girl,
4
24260
2000
00:26
I loved the idea of a robot that interacted with us
5
26260
2000
00:28
much more like a helpful, trusted sidekick --
6
28260
3000
00:31
something that would delight us, enrich our lives
7
31260
2000
00:33
and help us save a galaxy or two.
8
33260
3000
00:37
I knew robots like that didn't really exist,
9
37260
3000
00:40
but I knew I wanted to build them.
10
40260
2000
00:42
So 20 years pass --
11
42260
2000
00:44
I am now a graduate student at MIT
12
44260
2000
00:46
studying artificial intelligence,
13
46260
2000
00:48
the year is 1997,
14
48260
2000
00:50
and NASA has just landed the first robot on Mars.
15
50260
3000
00:53
But robots are still not in our home, ironically.
16
53260
3000
00:56
And I remember thinking about
17
56260
2000
00:58
all the reasons why that was the case.
18
58260
2000
01:00
But one really struck me.
19
60260
2000
01:02
Robotics had really been about interacting with things,
20
62260
3000
01:05
not with people --
21
65260
2000
01:07
certainly not in a social way that would be natural for us
22
67260
2000
01:09
and would really help people accept robots
23
69260
2000
01:11
into our daily lives.
24
71260
2000
01:13
For me, that was the white space; that's what robots could not do yet.
25
73260
3000
01:16
And so that year, I started to build this robot, Kismet,
26
76260
3000
01:19
the world's first social robot.
27
79260
3000
01:22
Three years later --
28
82260
2000
01:24
a lot of programming,
29
84260
2000
01:26
working with other graduate students in the lab --
30
86260
2000
01:28
Kismet was ready to start interacting with people.
31
88260
2000
01:30
(Video) Scientist: I want to show you something.
32
90260
2000
01:32
Kismet: (Nonsense)
33
92260
2000
01:34
Scientist: This is a watch that my girlfriend gave me.
34
94260
3000
01:37
Kismet: (Nonsense)
35
97260
2000
01:39
Scientist: Yeah, look, it's got a little blue light in it too.
36
99260
2000
01:41
I almost lost it this week.
37
101260
3000
01:44
Cynthia Breazeal: So Kismet interacted with people
38
104260
3000
01:47
like kind of a non-verbal child or pre-verbal child,
39
107260
3000
01:50
which I assume was fitting because it was really the first of its kind.
40
110260
3000
01:53
It didn't speak language, but it didn't matter.
41
113260
2000
01:55
This little robot was somehow able
42
115260
2000
01:57
to tap into something deeply social within us --
43
117260
3000
02:00
and with that, the promise of an entirely new way
44
120260
2000
02:02
we could interact with robots.
45
122260
2000
02:04
So over the past several years
46
124260
2000
02:06
I've been continuing to explore this interpersonal dimension of robots,
47
126260
2000
02:08
now at the media lab
48
128260
2000
02:10
with my own team of incredibly talented students.
49
130260
2000
02:12
And one of my favorite robots is Leonardo.
50
132260
3000
02:15
We developed Leonardo in collaboration with Stan Winston Studio.
51
135260
3000
02:18
And so I want to show you a special moment for me of Leo.
52
138260
3000
02:21
This is Matt Berlin interacting with Leo,
53
141260
2000
02:23
introducing Leo to a new object.
54
143260
2000
02:25
And because it's new, Leo doesn't really know what to make of it.
55
145260
3000
02:28
But sort of like us, he can actually learn about it
56
148260
2000
02:30
from watching Matt's reaction.
57
150260
3000
02:33
(Video) Matt Berlin: Hello, Leo.
58
153260
2000
02:38
Leo, this is Cookie Monster.
59
158260
3000
02:44
Can you find Cookie Monster?
60
164260
3000
02:52
Leo, Cookie Monster is very bad.
61
172260
3000
02:56
He's very bad, Leo.
62
176260
2000
03:00
Cookie Monster is very, very bad.
63
180260
3000
03:07
He's a scary monster.
64
187260
2000
03:09
He wants to get your cookies.
65
189260
2000
03:12
(Laughter)
66
192260
2000
03:14
CB: All right, so Leo and Cookie
67
194260
3000
03:17
might have gotten off to a little bit of a rough start,
68
197260
2000
03:19
but they get along great now.
69
199260
3000
03:22
So what I've learned
70
202260
2000
03:24
through building these systems
71
204260
2000
03:26
is that robots are actually
72
206260
2000
03:28
a really intriguing social technology,
73
208260
2000
03:30
where it's actually their ability
74
210260
2000
03:32
to push our social buttons
75
212260
2000
03:34
and to interact with us like a partner
76
214260
2000
03:36
that is a core part of their functionality.
77
216260
3000
03:39
And with that shift in thinking, we can now start to imagine
78
219260
2000
03:41
new questions, new possibilities for robots
79
221260
3000
03:44
that we might not have thought about otherwise.
80
224260
3000
03:47
But what do I mean when I say "push our social buttons?"
81
227260
2000
03:49
Well, one of the things that we've learned
82
229260
2000
03:51
is that, if we design these robots to communicate with us
83
231260
2000
03:53
using the same body language,
84
233260
2000
03:55
the same sort of non-verbal cues that people use --
85
235260
2000
03:57
like Nexi, our humanoid robot, is doing here --
86
237260
3000
04:00
what we find is that people respond to robots
87
240260
2000
04:02
a lot like they respond to people.
88
242260
2000
04:04
People use these cues to determine things like how persuasive someone is,
89
244260
3000
04:07
how likable, how engaging,
90
247260
2000
04:09
how trustworthy.
91
249260
2000
04:11
It turns out it's the same for robots.
92
251260
2000
04:13
It's turning out now
93
253260
2000
04:15
that robots are actually becoming a really interesting new scientific tool
94
255260
3000
04:18
to understand human behavior.
95
258260
2000
04:20
To answer questions like, how is it that, from a brief encounter,
96
260260
3000
04:23
we're able to make an estimate of how trustworthy another person is?
97
263260
3000
04:26
Mimicry's believed to play a role, but how?
98
266260
3000
04:29
Is it the mimicking of particular gestures that matters?
99
269260
3000
04:32
It turns out it's really hard
100
272260
2000
04:34
to learn this or understand this from watching people
101
274260
2000
04:36
because when we interact we do all of these cues automatically.
102
276260
3000
04:39
We can't carefully control them because they're subconscious for us.
103
279260
2000
04:41
But with the robot, you can.
104
281260
2000
04:43
And so in this video here --
105
283260
2000
04:45
this is a video taken from David DeSteno's lab at Northeastern University.
106
285260
3000
04:48
He's a psychologist we've been collaborating with.
107
288260
2000
04:50
There's actually a scientist carefully controlling Nexi's cues
108
290260
3000
04:53
to be able to study this question.
109
293260
3000
04:56
And the bottom line is -- the reason why this works is
110
296260
2000
04:58
because it turns out people just behave like people
111
298260
2000
05:00
even when interacting with a robot.
112
300260
3000
05:03
So given that key insight,
113
303260
2000
05:05
we can now start to imagine
114
305260
2000
05:07
new kinds of applications for robots.
115
307260
3000
05:10
For instance, if robots do respond to our non-verbal cues,
116
310260
3000
05:13
maybe they would be a cool, new communication technology.
117
313260
4000
05:17
So imagine this:
118
317260
2000
05:19
What about a robot accessory for your cellphone?
119
319260
2000
05:21
You call your friend, she puts her handset in a robot,
120
321260
2000
05:23
and, bam! You're a MeBot --
121
323260
2000
05:25
you can make eye contact, you can talk with your friends,
122
325260
3000
05:28
you can move around, you can gesture --
123
328260
2000
05:30
maybe the next best thing to really being there, or is it?
124
330260
3000
05:33
To explore this question,
125
333260
2000
05:35
my student, Siggy Adalgeirsson, did a study
126
335260
3000
05:38
where we brought human participants, people, into our lab
127
338260
3000
05:41
to do a collaborative task
128
341260
2000
05:43
with a remote collaborator.
129
343260
2000
05:45
The task involved things
130
345260
2000
05:47
like looking at a set of objects on the table,
131
347260
2000
05:49
discussing them in terms of their importance and relevance to performing a certain task --
132
349260
3000
05:52
this ended up being a survival task --
133
352260
2000
05:54
and then rating them in terms
134
354260
2000
05:56
of how valuable and important they thought they were.
135
356260
2000
05:58
The remote collaborator was an experimenter from our group
136
358260
3000
06:01
who used one of three different technologies
137
361260
2000
06:03
to interact with the participants.
138
363260
2000
06:05
The first was just the screen.
139
365260
2000
06:07
This is just like video conferencing today.
140
367260
3000
06:10
The next was to add mobility -- so, have the screen on a mobile base.
141
370260
3000
06:13
This is like, if you're familiar with any of the telepresence robots today --
142
373260
3000
06:16
this is mirroring that situation.
143
376260
3000
06:19
And then the fully expressive MeBot.
144
379260
2000
06:21
So after the interaction,
145
381260
2000
06:23
we asked people to rate their quality of interaction
146
383260
3000
06:26
with the technology, with a remote collaborator
147
386260
2000
06:28
through this technology, in a number of different ways.
148
388260
3000
06:31
We looked at psychological involvement --
149
391260
2000
06:33
how much empathy did you feel for the other person?
150
393260
2000
06:35
We looked at overall engagement.
151
395260
2000
06:37
We looked at their desire to cooperate.
152
397260
2000
06:39
And this is what we see when they use just the screen.
153
399260
3000
06:42
It turns out, when you add mobility -- the ability to roll around the table --
154
402260
3000
06:45
you get a little more of a boost.
155
405260
2000
06:47
And you get even more of a boost when you add the full expression.
156
407260
3000
06:50
So it seems like this physical, social embodiment
157
410260
2000
06:52
actually really makes a difference.
158
412260
2000
06:54
Now let's try to put this into a little bit of context.
159
414260
3000
06:57
Today we know that families are living further and further apart,
160
417260
3000
07:00
and that definitely takes a toll on family relationships
161
420260
2000
07:02
and family bonds over distance.
162
422260
2000
07:04
For me, I have three young boys,
163
424260
2000
07:06
and I want them to have a really good relationship
164
426260
2000
07:08
with their grandparents.
165
428260
2000
07:10
But my parents live thousands of miles away,
166
430260
2000
07:12
so they just don't get to see each other that often.
167
432260
2000
07:14
We try Skype, we try phone calls,
168
434260
2000
07:16
but my boys are little -- they don't really want to talk;
169
436260
2000
07:18
they want to play.
170
438260
2000
07:20
So I love the idea of thinking about robots
171
440260
2000
07:22
as a new kind of distance-play technology.
172
442260
3000
07:25
I imagine a time not too far from now --
173
445260
3000
07:28
my mom can go to her computer,
174
448260
2000
07:30
open up a browser and jack into a little robot.
175
450260
2000
07:32
And as grandma-bot,
176
452260
3000
07:35
she can now play, really play,
177
455260
2000
07:37
with my sons, with her grandsons,
178
457260
2000
07:39
in the real world with his real toys.
179
459260
3000
07:42
I could imagine grandmothers being able to do social-plays
180
462260
2000
07:44
with their granddaughters, with their friends,
181
464260
2000
07:46
and to be able to share all kinds of other activities around the house,
182
466260
2000
07:48
like sharing a bedtime story.
183
468260
2000
07:50
And through this technology,
184
470260
2000
07:52
being able to be an active participant
185
472260
2000
07:54
in their grandchildren's lives
186
474260
2000
07:56
in a way that's not possible today.
187
476260
2000
07:58
Let's think about some other domains,
188
478260
2000
08:00
like maybe health.
189
480260
2000
08:02
So in the United States today,
190
482260
2000
08:04
over 65 percent of people are either overweight or obese,
191
484260
3000
08:07
and now it's a big problem with our children as well.
192
487260
2000
08:09
And we know that as you get older in life,
193
489260
2000
08:11
if you're obese when you're younger, that can lead to chronic diseases
194
491260
3000
08:14
that not only reduce your quality of life,
195
494260
2000
08:16
but are a tremendous economic burden on our health care system.
196
496260
3000
08:19
But if robots can be engaging,
197
499260
2000
08:21
if we like to cooperate with robots,
198
501260
2000
08:23
if robots are persuasive,
199
503260
2000
08:25
maybe a robot can help you
200
505260
2000
08:27
maintain a diet and exercise program,
201
507260
2000
08:29
maybe they can help you manage your weight.
202
509260
3000
08:32
Sort of like a digital Jiminy --
203
512260
2000
08:34
as in the well-known fairy tale --
204
514260
2000
08:36
a kind of friendly, supportive presence that's always there
205
516260
2000
08:38
to be able to help you make the right decision
206
518260
2000
08:40
in the right way at the right time
207
520260
2000
08:42
to help you form healthy habits.
208
522260
2000
08:44
So we actually explored this idea in our lab.
209
524260
2000
08:46
This is a robot, Autom.
210
526260
2000
08:48
Cory Kidd developed this robot for his doctoral work.
211
528260
3000
08:51
And it was designed to be a robot diet-and-exercise coach.
212
531260
3000
08:54
It had a couple of simple non-verbal skills it could do.
213
534260
2000
08:56
It could make eye contact with you.
214
536260
2000
08:58
It could share information looking down at a screen.
215
538260
2000
09:00
You'd use a screen interface to enter information,
216
540260
2000
09:02
like how many calories you ate that day,
217
542260
2000
09:04
how much exercise you got.
218
544260
2000
09:06
And then it could help track that for you.
219
546260
2000
09:08
And the robot spoke with a synthetic voice
220
548260
2000
09:10
to engage you in a coaching dialogue
221
550260
2000
09:12
modeled after trainers
222
552260
2000
09:14
and patients and so forth.
223
554260
2000
09:16
And it would build a working alliance with you
224
556260
2000
09:18
through that dialogue.
225
558260
2000
09:20
It could help you set goals and track your progress,
226
560260
2000
09:22
and it would help motivate you.
227
562260
2000
09:24
So an interesting question is,
228
564260
2000
09:26
does the social embodiment really matter? Does it matter that it's a robot?
229
566260
3000
09:29
Is it really just the quality of advice and information that matters?
230
569260
3000
09:32
To explore that question,
231
572260
2000
09:34
we did a study in the Boston area
232
574260
2000
09:36
where we put one of three interventions in people's homes
233
576260
3000
09:39
for a period of several weeks.
234
579260
2000
09:41
One case was the robot you saw there, Autom.
235
581260
3000
09:44
Another was a computer that ran the same touch-screen interface,
236
584260
3000
09:47
ran exactly the same dialogues.
237
587260
2000
09:49
The quality of advice was identical.
238
589260
2000
09:51
And the third was just a pen and paper log,
239
591260
2000
09:53
because that's the standard intervention you typically get
240
593260
2000
09:55
when you start a diet-and-exercise program.
241
595260
3000
09:58
So one of the things we really wanted to look at
242
598260
3000
10:01
was not how much weight people lost,
243
601260
3000
10:04
but really how long they interacted with the robot.
244
604260
3000
10:07
Because the challenge is not losing weight, it's actually keeping it off.
245
607260
3000
10:10
And the longer you could interact with one of these interventions,
246
610260
3000
10:13
well that's indicative, potentially, of longer-term success.
247
613260
3000
10:16
So the first thing I want to look at is how long,
248
616260
2000
10:18
how long did people interact with these systems.
249
618260
2000
10:20
It turns out that people interacted with the robot
250
620260
2000
10:22
significantly more,
251
622260
2000
10:24
even though the quality of the advice was identical to the computer.
252
624260
3000
10:28
When it asked people to rate it on terms of the quality of the working alliance,
253
628260
3000
10:31
people rated the robot higher
254
631260
2000
10:33
and they trusted the robot more.
255
633260
2000
10:35
(Laughter)
256
635260
2000
10:37
And when you look at emotional engagement,
257
637260
2000
10:39
it was completely different.
258
639260
2000
10:41
People would name the robots.
259
641260
2000
10:43
They would dress the robots.
260
643260
2000
10:45
(Laughter)
261
645260
2000
10:47
And even when we would come up to pick up the robots at the end of the study,
262
647260
3000
10:50
they would come out to the car and say good-bye to the robots.
263
650260
2000
10:52
They didn't do this with a computer.
264
652260
2000
10:54
The last thing I want to talk about today
265
654260
2000
10:56
is the future of children's media.
266
656260
2000
10:58
We know that kids spend a lot of time behind screens today,
267
658260
3000
11:01
whether it's television or computer games or whatnot.
268
661260
3000
11:04
My sons, they love the screen. They love the screen.
269
664260
3000
11:07
But I want them to play; as a mom, I want them to play,
270
667260
3000
11:10
like, real-world play.
271
670260
2000
11:12
And so I have a new project in my group I wanted to present to you today
272
672260
3000
11:15
called Playtime Computing
273
675260
2000
11:17
that's really trying to think about how we can take
274
677260
2000
11:19
what's so engaging about digital media
275
679260
2000
11:21
and literally bring it off the screen
276
681260
2000
11:23
into the real world of the child,
277
683260
2000
11:25
where it can take on many of the properties of real-world play.
278
685260
3000
11:29
So here's the first exploration of this idea,
279
689260
4000
11:33
where characters can be physical or virtual,
280
693260
3000
11:36
and where the digital content
281
696260
2000
11:38
can literally come off the screen
282
698260
2000
11:40
into the world and back.
283
700260
2000
11:42
I like to think of this
284
702260
2000
11:44
as the Atari Pong
285
704260
2000
11:46
of this blended-reality play.
286
706260
2000
11:48
But we can push this idea further.
287
708260
2000
11:50
What if --
288
710260
2000
11:52
(Game) Nathan: Here it comes. Yay!
289
712260
3000
11:55
CB: -- the character itself could come into your world?
290
715260
3000
11:58
It turns out that kids love it
291
718260
2000
12:00
when the character becomes real and enters into their world.
292
720260
3000
12:03
And when it's in their world,
293
723260
2000
12:05
they can relate to it and play with it in a way
294
725260
2000
12:07
that's fundamentally different from how they play with it on the screen.
295
727260
2000
12:09
Another important idea is this notion
296
729260
2000
12:11
of persistence of character across realities.
297
731260
3000
12:14
So changes that children make in the real world
298
734260
2000
12:16
need to translate to the virtual world.
299
736260
2000
12:18
So here, Nathan has changed the letter A to the number 2.
300
738260
3000
12:21
You can imagine maybe these symbols
301
741260
2000
12:23
give the characters special powers when it goes into the virtual world.
302
743260
3000
12:26
So they are now sending the character back into that world.
303
746260
3000
12:29
And now it's got number power.
304
749260
3000
12:32
And then finally, what I've been trying to do here
305
752260
2000
12:34
is create a really immersive experience for kids,
306
754260
3000
12:37
where they really feel like they are part of that story,
307
757260
3000
12:40
a part of that experience.
308
760260
2000
12:42
And I really want to spark their imaginations
309
762260
2000
12:44
the way mine was sparked as a little girl watching "Star Wars."
310
764260
3000
12:47
But I want to do more than that.
311
767260
2000
12:49
I actually want them to create those experiences.
312
769260
3000
12:52
I want them to be able to literally build their imagination
313
772260
2000
12:54
into these experiences and make them their own.
314
774260
2000
12:56
So we've been exploring a lot of ideas
315
776260
2000
12:58
in telepresence and mixed reality
316
778260
2000
13:00
to literally allow kids to project their ideas into this space
317
780260
3000
13:03
where other kids can interact with them
318
783260
2000
13:05
and build upon them.
319
785260
2000
13:07
I really want to come up with new ways of children's media
320
787260
3000
13:10
that foster creativity and learning and innovation.
321
790260
3000
13:13
I think that's very, very important.
322
793260
3000
13:16
So this is a new project.
323
796260
2000
13:18
We've invited a lot of kids into this space,
324
798260
2000
13:20
and they think it's pretty cool.
325
800260
3000
13:23
But I can tell you, the thing that they love the most
326
803260
2000
13:25
is the robot.
327
805260
2000
13:27
What they care about is the robot.
328
807260
3000
13:30
Robots touch something deeply human within us.
329
810260
3000
13:33
And so whether they're helping us
330
813260
2000
13:35
to become creative and innovative,
331
815260
2000
13:37
or whether they're helping us
332
817260
2000
13:39
to feel more deeply connected despite distance,
333
819260
2000
13:41
or whether they are our trusted sidekick
334
821260
2000
13:43
who's helping us attain our personal goals
335
823260
2000
13:45
in becoming our highest and best selves,
336
825260
2000
13:47
for me, robots are all about people.
337
827260
3000
13:50
Thank you.
338
830260
2000
13:52
(Applause)
339
832260
5000
About this website

This site will introduce you to YouTube videos that are useful for learning English. You will see English lessons taught by top-notch teachers from around the world. Double-click on the English subtitles displayed on each video page to play the video from there. The subtitles scroll in sync with the video playback. If you have any comments or requests, please contact us using this contact form.

https://forms.gle/WvT1wiN1qDtmnspy7