TED2009
Pattie Maes + Pranav Mistry: Meet the SixthSense interaction
Filmed:
Readability: 4.4
11,289,293 views
This demo -- from Pattie Maes' lab at MIT, spearheaded by Pranav Mistry -- was the buzz of TED. It's a wearable device with a projector that paves the way for profound interaction with our environment. Imagine "Minority Report" and then some.
Pattie Maes - Researcher
As head of the MIT Media Lab's Fluid Interfaces Group, Pattie Maes researches the tools we use to work with information and connect with one another. Full bioPranav Mistry - Director of research, Samsung Research America
As an MIT grad student, Pranav Mistry invented SixthSense, a wearable device that enables new interactions between the real world and the world of data. Full bio
As head of the MIT Media Lab's Fluid Interfaces Group, Pattie Maes researches the tools we use to work with information and connect with one another. Full bioPranav Mistry - Director of research, Samsung Research America
As an MIT grad student, Pranav Mistry invented SixthSense, a wearable device that enables new interactions between the real world and the world of data. Full bio
Double-click the English transcript below to play the video.
00:12
I've been intrigued by this question
0
0
2000
00:14
of whether we could evolve or develop a sixth sense --
1
2000
3000
00:17
a sense that would give us seamless access
2
5000
6000
00:23
and easy access to meta-information
3
11000
3000
00:26
or information that may exist somewhere
4
14000
3000
00:29
that may be relevant to help us make the right decision
5
17000
3000
00:32
about whatever it is that we're coming across.
6
20000
3000
00:35
And some of you may argue,
7
23000
3000
00:38
well, don't today's cell phones do that already?
8
26000
3000
00:41
But I would say no.
9
29000
2000
00:43
When you meet someone here at TED --
10
31000
2000
00:45
and this is the top networking place, of course, of the year --
11
33000
3000
00:48
you don't shake somebody's hand
12
36000
2000
00:50
and then say, "Can you hold on for a moment
13
38000
3000
00:53
while I take out my phone and Google you?"
14
41000
2000
00:55
Or when you go to the supermarket
15
43000
4000
00:59
and you're standing there in that huge aisle
16
47000
2000
01:01
of different types of toilet papers,
17
49000
3000
01:04
you don't take out your cell phone, and open a browser,
18
52000
4000
01:08
and go to a website to try to decide
19
56000
2000
01:10
which of these different toilet papers
20
58000
3000
01:13
is the most ecologically responsible purchase to make.
21
61000
3000
01:16
So we don't really have easy access
22
64000
3000
01:19
to all this relevant information
23
67000
2000
01:21
that can just help us make optimal decisions
24
69000
3000
01:24
about what to do next and what actions to take.
25
72000
3000
01:27
And so my research group at the Media Lab
26
75000
4000
01:31
has been developing a series of inventions
27
79000
4000
01:35
to give us access to this information
28
83000
3000
01:38
in a sort of easy way,
29
86000
2000
01:40
without requiring that the user changes any of their behavior.
30
88000
5000
01:45
And I'm here to unveil
31
93000
2000
01:47
our latest effort,
32
95000
3000
01:50
and most successful effort so far,
33
98000
2000
01:52
which is still very much a work in process.
34
100000
2000
01:54
I'm actually wearing the device right now
35
102000
3000
01:57
and we've sort of cobbled it together
36
105000
3000
02:00
with components that are off the shelf --
37
108000
3000
02:03
and that, by the way, only cost 350 dollars
38
111000
3000
02:06
at this point in time.
39
114000
2000
02:08
I'm wearing a camera, just a simple webcam,
40
116000
4000
02:12
a portable, battery-powered projection system with a little mirror.
41
120000
6000
02:18
These components communicate to my cell phone in my pocket
42
126000
4000
02:22
which acts as the communication and computation device.
43
130000
4000
02:26
And in the video here we see my student Pranav Mistry,
44
134000
4000
02:30
who's really the genius who's been implementing
45
138000
3000
02:33
and designing this whole system.
46
141000
2000
02:35
And we see how this system
47
143000
2000
02:37
lets him walk up to any surface
48
145000
4000
02:41
and start using his hands to interact with the information
49
149000
4000
02:45
that is projected in front of him.
50
153000
2000
02:47
The system tracks the four significant fingers.
51
155000
4000
02:51
In this case, he's wearing simple marker caps
52
159000
4000
02:55
that you may recognize.
53
163000
2000
02:57
But if you want a more stylish version
54
165000
2000
02:59
you could also paint your nails in different colors.
55
167000
4000
03:03
And the camera basically tracks these four fingers
56
171000
4000
03:07
and recognizes any gestures that he's making
57
175000
3000
03:10
so he can just go to, for example, a map of Long Beach,
58
178000
5000
03:15
zoom in and out, etc.
59
183000
2000
03:17
The system also recognizes iconic gestures
60
185000
3000
03:20
such as the "take a picture" gesture,
61
188000
3000
03:23
and then takes a picture of whatever is in front of you.
62
191000
3000
03:26
And when he then walks back to the Media Lab,
63
194000
4000
03:30
he can just go up to any wall
64
198000
2000
03:32
and project all the pictures that he's taken,
65
200000
3000
03:35
sort through them and organize them,
66
203000
2000
03:37
and re-size them, etc.,
67
205000
2000
03:39
again using all natural gestures.
68
207000
3000
03:42
So, some of you most likely were here two years ago
69
210000
4000
03:46
and saw the demo by Jeff Han
70
214000
5000
03:51
or some of you may think, "Well, doesn't this look like the Microsoft Surface Table?"
71
219000
3000
03:54
And yes, you also interact using natural gestures,
72
222000
5000
03:59
both hands, etc.
73
227000
2000
04:01
But the difference here is that you can use any surface,
74
229000
3000
04:04
you can walk to up to any surface,
75
232000
3000
04:07
including your hand if nothing else is available
76
235000
3000
04:10
and interact with this projected data.
77
238000
3000
04:13
The device is completely portable,
78
241000
3000
04:16
and can be ...
79
244000
2000
04:18
(Applause)
80
246000
7000
04:25
So one important difference is that it's totally mobile.
81
253000
4000
04:29
Another even more important difference is that in mass production
82
257000
4000
04:33
this would not cost more tomorrow than today's cell phones
83
261000
4000
04:37
and would actually not sort of be a bigger packaging --
84
265000
4000
04:41
could look a lot more stylish
85
269000
2000
04:43
than this version that I'm wearing around my neck.
86
271000
3000
04:46
But other than letting some of you live out your fantasy
87
274000
6000
04:52
of looking as cool as Tom Cruise in "Minority Report,"
88
280000
4000
04:56
the reason why we're really excited about this device
89
284000
4000
05:00
is that it really can act as one of these sixth-sense devices
90
288000
6000
05:06
that gives you relevant information
91
294000
3000
05:09
about whatever is in front of you.
92
297000
2000
05:11
So we see Pranav here going into the supermarket
93
299000
5000
05:16
and he's shopping for some paper towels.
94
304000
3000
05:19
And, as he picks up a product the system can recognize
95
307000
3000
05:22
the product that he's picking up,
96
310000
2000
05:24
using either image recognition or marker technology,
97
312000
4000
05:28
and give him the green light or an orange light.
98
316000
3000
05:31
He can ask for additional information.
99
319000
3000
05:34
So this particular choice here
100
322000
4000
05:38
is a particularly good choice, given his personal criteria.
101
326000
4000
05:42
Some of you may want the toilet paper with the most bleach in it
102
330000
4000
05:46
rather than the most ecologically-responsible choice.
103
334000
3000
05:49
(Laughter)
104
337000
3000
05:52
If he picks up a book in the bookstore,
105
340000
3000
05:55
he can get an Amazon rating --
106
343000
2000
05:57
it gets projected right on the cover of the book.
107
345000
2000
05:59
This is Juan's book, our previous speaker,
108
347000
5000
06:04
which gets a great rating, by the way, at Amazon.
109
352000
2000
06:06
And so, Pranav turns the page of the book
110
354000
3000
06:09
and can then see additional information about the book --
111
357000
3000
06:12
reader comments, maybe sort of information by his favorite critic, etc.
112
360000
7000
06:19
If he turns to a particular page
113
367000
2000
06:21
he finds an annotation by maybe an expert of a friend of ours
114
369000
4000
06:25
that gives him a little bit of additional information
115
373000
2000
06:27
about whatever is on that particular page.
116
375000
3000
06:30
Reading the newspaper --
117
378000
2000
06:32
it never has to be outdated.
118
380000
3000
06:35
(Laughter)
119
383000
2000
06:37
You can get video annotations of the event that you're reading about
120
385000
4000
06:41
You can get the latest sports scores etc.
121
389000
4000
06:45
This is a more controversial one.
122
393000
3000
06:48
(Laughter)
123
396000
1000
06:49
As you interact with someone at TED,
124
397000
3000
06:52
maybe you can see a word cloud of the tags,
125
400000
4000
06:56
the words that are associated with that person
126
404000
2000
06:58
in their blog and personal web pages.
127
406000
3000
07:01
In this case, the student is interested in cameras, etc.
128
409000
5000
07:06
On your way to the airport,
129
414000
2000
07:08
if you pick up your boarding pass, it can tell you that your flight is delayed,
130
416000
4000
07:12
that the gate has changed, etc.
131
420000
3000
07:15
And, if you need to know what the current time is
132
423000
3000
07:18
it's as simple as drawing a watch --
133
426000
4000
07:22
(Laughter)
134
430000
1000
07:23
(Applause)
135
431000
1000
07:24
on your arm.
136
432000
2000
07:26
So that's where we're at so far
137
434000
4000
07:30
in developing this sixth sense
138
438000
4000
07:34
that would give us seamless access to all this relevant information
139
442000
4000
07:38
about the things that we may come across.
140
446000
3000
07:41
My student Pranav, who's really, like I said, the genius behind this.
141
449000
4000
07:45
(Applause) (Standing ovation)
142
453000
23000
08:08
He does deserve a lot of applause
143
476000
3000
08:11
because I don't think he's slept much in the last three months, actually.
144
479000
4000
08:15
And his girlfriend is probably not very happy about him either.
145
483000
3000
08:18
But it's not perfect yet, it's very much a work in progress.
146
486000
5000
08:23
And who knows, maybe in another 10 years
147
491000
3000
08:26
we'll be here with the ultimate sixth sense brain implant.
148
494000
5000
08:31
Thank you.
149
499000
1000
08:32
(Applause)
150
500000
4000
ABOUT THE SPEAKERS
Pattie Maes - ResearcherAs head of the MIT Media Lab's Fluid Interfaces Group, Pattie Maes researches the tools we use to work with information and connect with one another.
Why you should listen
Pattie Maes was the key architect behind what was once called "collaborative filtering" and has become a key to Web 2.0: the immense engine of recommendations -- or "things like this" -- fueled by other users. In the 1990s, Maes' Software Agents program at MIT created Firefly, a technology (and then a startup sold to Microsoft) that let users choose songs they liked, and find similar songs they'd never heard of, by taking cues from others with similar taste. This brought a sea change in the way we interact with software, with culture and with one another.
Now Maes is working on a similarly boundary-breaking initiative. She founded Fluid Interfaces Group, also part of the MIT Media Lab, to rethink the ways in which humans and computers interact, partially by redefining both human and computer. In Maes' world (and really, in all of ours), the computer is no longer a distinct object, but a source of intelligence that's embedded in our environment. By outfitting ourselves with digital accessories, we can continually learn from (and teach) our surroundings. The uses of this tech -- from healthcare to home furnishings, warfare to supermarkets -- are powerful and increasingly real.
Pattie Maes | Speaker | TED.com
Pranav Mistry - Director of research, Samsung Research America
As an MIT grad student, Pranav Mistry invented SixthSense, a wearable device that enables new interactions between the real world and the world of data.
Why you should listen
When Pranav Mistry was a PhD student in the Fluid Interfaces Group at MIT's Media Lab, he worked with lab director Pattie Maes to create some of the most entertaining and thought-provoking interfaces the world had ever seen. And not just computer interfaces, mind you -- these are ways to help the digital and the actual worlds interface. Imagine: intelligent sticky notes, Quickies, that can be searched and can send reminders; a pen that draws in 3D; and TaPuMa, a tangible public map that can act as Google of physical world. And of course the legendary SixthSense, which is now open sourced
Before his studies at MIT, he worked with Microsoft as a UX researcher; he's a graduate of IIT. Now, as director of research at Samsung Research America, Mistry heads the Think Tank Team, an interdisciplinary group of researchers that hunts for new ways to mix digital informational with real-world interactions. As an example, Mistry launched the company's smartwatch, the Galaxy Gear, in 2013.
Pranav Mistry | Speaker | TED.com