TED2011
Dennis Hong: Making a car for blind drivers
Dennis Hong: Construindo un coche para conductores cegos
Filmed:
Readability: 4.3
923,134 views
Mediante o uso de robótica, laser telemétricos, GPS e ferramentas intelixentes de retroalimentación, Dennis Hoing está a construír un coche para invidentes. Isto non é o coche que se conduce só, sinala el coidadosamente, é un coche no que o condutor invidente pode escoller a velocidade, proximidade e ruta e conducir de forma independente.
Dennis Hong - Roboticist
Dennis Hong is the founder and director of RoMeLa -- a Virginia Tech robotics lab that has pioneered several breakthroughs in robot design and engineering. Full bio
Dennis Hong is the founder and director of RoMeLa -- a Virginia Tech robotics lab that has pioneered several breakthroughs in robot design and engineering. Full bio
Double-click the English transcript below to play the video.
00:15
Many believe driving is an activity
0
0
3000
Moita xente pensa que a condución é unha actividade
00:18
solely reserved for those who can see.
1
3000
2000
unicamente reservada para os que poden ver.
00:20
A blind person driving a vehicle safely and independently
2
5000
3000
Que unha persoa cega conducise de forma segura e independente
00:23
was thought to be an impossible task, until now.
3
8000
3000
era unha tarefa considerada imposíbel ate agora.
00:26
Hello, my name is Dennis Hong,
4
11000
2000
Ola, o meu nome é Dennis Hong,
00:28
and we're bringing freedom and independence to the blind
5
13000
2000
e mediante a construción dun vehículo para invidentes
00:30
by building a vehicle for the visually impaired.
6
15000
3000
estámoslles a dar máis liberdade e independencia.
00:33
So before I talk about this car for the blind,
7
18000
3000
Pero antes de falar deste coche para invidentes,
00:36
let me briefly tell you about another project that I worked on
8
21000
2000
permítanme referirme a outro proxecto no que traballei
00:38
called the DARPA Urban Challenge.
9
23000
2000
chamado DARPA Desafío Urbano.
00:40
Now this was about building a robotic car
10
25000
2000
A idea era construír un coche robótico
00:42
that can drive itself.
11
27000
2000
que se conducise el so.
00:44
You press start, nobody touches anything,
12
29000
2000
Púlsase o botón de inicio, e sen tocar nada,
00:46
and it can reach its destination fully autonomously.
13
31000
3000
pódese chegar ao destino de forma completamente autónoma.
00:49
So in 2007, our team won half a million dollars
14
34000
3000
En 2007, o noso equipo gañou medio millón de dólares
00:52
by placing third place in this competition.
15
37000
2000
gracias a conseguir o terceiro premio nesta competición.
00:54
So about that time,
16
39000
2000
Nese momento
00:56
the National Federation of the Blind, or NFB,
17
41000
2000
a Federación Nacional de Cegos, ou en inglés NFB,
00:58
challenged the research committee
18
43000
2000
propuxo ao comité de investigación o reto
01:00
about who can develop a car
19
45000
2000
de desenvolver un coche
01:02
that lets a blind person drive safely and independently.
20
47000
2000
que permitise a unha persoa cega conducir de forma segura e independente.
01:04
We decided to give it a try,
21
49000
2000
Decidimos intentalo,
01:06
because we thought, "Hey, how hard could it be?"
22
51000
2000
porque pensamos: eh, no pode ser tan complicado!
01:08
We have already an autonomous vehicle.
23
53000
2000
Xa temos un vehículo autónomo.
01:10
We just put a blind person in it and we're done, right?
24
55000
2000
Poñemos un persoa cega dentro e xa está, non?
01:12
(Laughter)
25
57000
2000
(Risos)
01:14
We couldn't have been more wrong.
26
59000
2000
Non podíamos estar máis equivocados
01:16
What NFB wanted
27
61000
2000
o que a NFB quería
01:18
was not a vehicle that can drive a blind person around,
28
63000
3000
non era un vehículo que transportase a unha persoa cega.
01:21
but a vehicle where a blind person can make active decisions and drive.
29
66000
3000
senón un vehículo no que un persoa cega puidese tomar decisións e conducir.
01:24
So we had to throw everything out the window
30
69000
2000
Así que tivemos que tirar todo pola borda
01:26
and start from scratch.
31
71000
2000
e comezar de cero.
01:28
So to test this crazy idea,
32
73000
2000
Para ensaiar esta disparatada idea,
01:30
we developed a small dune buggy prototype vehicle
33
75000
2000
desenvolvemos un prototipo dun pequeno coche areiro
01:32
to test the feasibility.
34
77000
2000
para comprobar a viabilidade.
01:34
And in the summer of 2009,
35
79000
2000
No verán de 2009,
01:36
we invited dozens of blind youth from all over the country
36
81000
3000
invitamos a ducias de mozos e mozas invidentes de todo o país
01:39
and gave them a chance to take it for a spin.
37
84000
2000
e démoslles a oportunidade de dar unha volta no prototipo.
01:41
It was an absolutely amazing experience.
38
86000
2000
Foi unha experiencia absolutamente incríbel.
01:43
But the problem with this car was
39
88000
2000
Pero o problema do coche era
01:45
it was designed to only be driven in a very controlled environment,
40
90000
3000
que estaba estaba deseñado só para ser conducido nun ambiente controlado:
01:48
in a flat, closed-off parking lot --
41
93000
2000
nun aparcadoiro plano e pechado
01:50
even the lanes defined by red traffic cones.
42
95000
2000
no que incluso os carrís estaban marcados con conos de tráfico.
01:52
So with this success,
43
97000
2000
Con este logro,
01:54
we decided to take the next big step,
44
99000
2000
decidimos dar o seguinte gran paso
01:56
to develop a real car that can be driven on real roads.
45
101000
3000
e desenvolver un coche que puidese ser conducido en carreteiras de verdade.
01:59
So how does it work?
46
104000
2000
E, como funciona?
02:01
Well, it's a rather complex system,
47
106000
2000
Ben, é un sistema bastante complexo
02:03
but let me try to explain it, maybe simplify it.
48
108000
3000
pero permítanme intentar explicarllo, e quizais simplificalo.
02:06
So we have three steps.
49
111000
2000
Temos tres partes:
02:08
We have perception, computation
50
113000
2000
Percepción, cálculo
02:10
and non-visual interfaces.
51
115000
2000
e interfaces non visuais.
02:12
Now obviously the driver cannot see,
52
117000
2000
Obviamente o condutor non pode ver,
02:14
so the system needs to perceive the environment
53
119000
2000
así que o sistema necesita percibir o entorno
02:16
and gather information for the driver.
54
121000
2000
e reunir a información para o condutor.
02:18
For that, we use an initial measurement unit.
55
123000
3000
Para elo, usamos un módulo de medición inicial
02:21
So it measures acceleration, angular acceleration --
56
126000
2000
que calcula a aceleración, a aceleración angular
02:23
like a human ear, inner ear.
57
128000
2000
como se fora un oído humano, o oído interno.
02:25
We fuse that information with a GPS unit
58
130000
2000
Esa información combínase coa do GPS
02:27
to get an estimate of the location of the car.
59
132000
3000
para conseguir unha estimación da localización do coche.
02:30
We also use two cameras to detect the lanes of the road.
60
135000
3000
Tamén se usan dúas cámaras para detectar o movemento das liñas dos carrís.
02:33
And we also use three laser range finders.
61
138000
2000
E tamén tres lasers telemétricos
02:35
The lasers scan the environment to detect obstacles --
62
140000
3000
que examinan o entorno para detectar obstáculos:
02:38
a car approaching from the front, the back
63
143000
2000
un coche acercándose por diante ou por detrás
02:40
and also any obstacles that run into the roads,
64
145000
3000
e calquera obstáculo que pode aparecer na carreteira,
02:43
any obstacles around the vehicle.
65
148000
2000
calquera obstáculo arredor do vehículo.
02:45
So all this vast amount of information is then fed into the computer,
66
150000
3000
Así que toda esta información é enviada ao ordenador,
02:48
and the computer can do two things.
67
153000
2000
e o ordenador fai dúas cousas:
02:50
One is, first of all, process this information
68
155000
3000
Unha, e primeiro de todo, procesa a información
02:53
to have an understanding of the environment --
69
158000
2000
para comprender o entorno:
02:55
these are the lanes of the road, there's the obstacles --
70
160000
3000
estas son as liñas dos carrís, estes son os obstáculos;
02:58
and convey this information to the driver.
71
163000
2000
e despois comunícalle esta información ao condutor.
03:00
The system is also smart enough
72
165000
2000
O sistema é suficientemente intelixente
03:02
to figure out the safest way to operate the car.
73
167000
2000
para definir a forma máis segura de conducir o coche,
03:04
So we can also generate instructions
74
169000
2000
polo que pode xerar as instrucións
03:06
on how to operate the controls of the vehicle.
75
171000
2000
sobre como conducir o vehículo.
03:08
But the problem is this: How do we convey
76
173000
2000
Pero o problema é: Como comunicar
03:10
this information and instructions
77
175000
2000
esta información e instrucións
03:12
to a person who cannot see
78
177000
2000
a unha persoa que non pode ver
03:14
fast enough and accurate enough so he can drive?
79
179000
3000
e facelo coa suficiente rapidez e precisión para que poida conducir?
03:17
So for this, we developed many different types
80
182000
2000
Para isto deseñamos varios tipos de interfaces de usuario
03:19
of non-visual user interface technology.
81
184000
3000
baseadas en tecnoloxías non visuais.
03:22
So starting from a three-dimensional ping sound system,
82
187000
2000
Comezando por un sistema tridimensional de avisos sonoros,
03:24
a vibrating vest,
83
189000
2000
una chaleco vibrador,
03:26
a click wheel with voice commands, a leg strip,
84
191000
3000
un volante con ordes por voz, unha cinta para as pernas,
03:29
even a shoe that applies pressure to the foot.
85
194000
2000
e incluso un zapato que aplica presión no pé.
03:31
But today we're going to talk about
86
196000
2000
Pero hoxe imos falar sobre
03:33
three of these non-visual user interfaces.
87
198000
2000
tres destas interfaces non visuais.
03:35
Now the first interface is called a DriveGrip.
88
200000
3000
A primeira interface chámase DriveGrip ("Control de condución").
03:38
So these are a pair of gloves,
89
203000
2000
Está composto dun par de guantes
03:40
and it has vibrating elements on the knuckle part
90
205000
2000
con elementos vibratorios nos cotelos
03:42
so you can convey instructions about how to steer --
91
207000
3000
para transmitir a información sobre o control da dirección
03:45
the direction and the intensity.
92
210000
2000
e da súa intensidade
03:47
Another device is called SpeedStrip.
93
212000
2000
Outro dispositivo é o chamado SpeedStrip ("cinta de velocidade").
03:49
So this is a chair -- as a matter of fact, it's actually a massage chair.
94
214000
3000
Está composta dunha cadeira, de feito é unha cadeira de masaxes.
03:52
We gut it out, and we rearrange the vibrating elements in different patterns,
95
217000
4000
Abrímola e reorganizamos os elementos vibratorios seguindo distintos esquemas
03:56
and we actuate them to convey information about the speed,
96
221000
3000
e conseguimos que transmitan a información sobre a velocidade
03:59
and also instructions how to use the gas and the brake pedal.
97
224000
3000
así como instrucións sobre como usar o acelerador e o freo.
04:02
So over here, you can see
98
227000
2000
Aquí poden ver
04:04
how the computer understands the environment,
99
229000
2000
como o ordenador interpreta o entorno.
04:06
and because you cannot see the vibration,
100
231000
2000
E como a vibración non pode ser vista
04:08
we actually put red LED's on the driver so that you can see what's happening.
101
233000
3000
puxemos un díodos LED vermellos no condutor para observar que está a pasar.
04:11
This is the sensory data,
102
236000
2000
Esta é a información sensorial,
04:13
and that data is transferred to the devices through the computer.
103
238000
3000
e esta é a información transferida aos dispositivos a través do ordenador.
04:16
So these two devices, DriveGrip and SpeedStrip,
104
241000
2000
Estes dous dispositivos, DriveGrip e SpeedStrip,
04:18
are very effective.
105
243000
2000
son moi efectivos.
04:20
But the problem is
106
245000
2000
Pero o problema é
04:22
these are instructional cue devices.
107
247000
2000
que son dispositivos que proporcionan ordes.
04:24
So this is not really freedom, right?
108
249000
2000
Así isto non é unha liberdade real, non si?
04:26
The computer tells you how to drive --
109
251000
2000
O ordenador indica como conducir:
04:28
turn left, turn right, speed up, stop.
110
253000
2000
xire á esquerda, á dereita, acelere, pare.
04:30
We call this the "backseat-driver problem."
111
255000
2000
Chamamos a isto o problema do condutor no asento de atrás.
04:32
So we're moving away from the instructional cue devices,
112
257000
3000
Así que nos alonxamos destes dispositivos que proporcionan ordes
04:35
and we're now focusing more
113
260000
2000
e estámonos a centrar
04:37
on the informational devices.
114
262000
2000
en dispositivos máis ben informativos.
04:39
A good example for this informational non-visual user interface
115
264000
2000
Un bo exemplo deste tipo de interfaces de usuario non-visuais
04:41
is called AirPix.
116
266000
2000
é a chamada AirPix.
04:43
So think of it as a monitor for the blind.
117
268000
2000
Pensade nela como nun monitor para invidentes.
04:45
So it's a small tablet, has many holes in it,
118
270000
2000
É unha pequena táboa con moitos orificios
04:47
and compressed air comes out,
119
272000
2000
dos que sae aire comprimido
04:49
so it can actually draw images.
120
274000
2000
e dese forma pode debuxar imaxes.
04:51
So even though you are blind, you can put your hand over it,
121
276000
2000
Así aínda que sexas cego, podes colocar a túa man enriba del
04:53
you can see the lanes of the road and obstacles.
122
278000
2000
e imaxinar como son os carrís da carreteira e os obstáculos.
04:55
Actually, you can also change the frequency of the air coming out
123
280000
3000
De feito, podes cambiar a frecuencia coa que sae o ar
04:58
and possibly the temperature.
124
283000
2000
así como a temperatura.
05:00
So it's actually a multi-dimensional user interface.
125
285000
3000
Así que en realidade é unha interface de usuario multidimensional.
05:03
So here you can see the left camera, the right camera from the vehicle
126
288000
3000
Aquí poden ver a cámara esquerda e dereita do vehículo
05:06
and how the computer interprets that and sends that information to the AirPix.
127
291000
3000
e como ordenador interpreta e transmite a información a AirPix.
05:09
For this, we're showing a simulator,
128
294000
2000
Usamos un simulador
05:11
a blind person driving using the AirPix.
129
296000
3000
para que a persoa cega poida conducir usando AirPix.
05:14
This simulator was also very useful for training the blind drivers
130
299000
3000
O simulador resultou tamén moi útil para adestrar condutores cegos
05:17
and also quickly testing different types of ideas
131
302000
2000
e probar de forma rápida distintos tipos de ideas
05:19
for different types of non-visual user interfaces.
132
304000
2000
para distintos tipos de interfaces non visuais.
05:21
So basically that's how it works.
133
306000
2000
Así que, en esencia, é así como funciona.
05:23
So just a month ago,
134
308000
2000
Hai tan só un mes,
05:25
on January 29th,
135
310000
2000
o 29 de xaneiro,
05:27
we unveiled this vehicle for the very first time to the public
136
312000
2000
exhibimos o vehículo por primeira vez ao público
05:29
at the world-famous Daytona International Speedway
137
314000
3000
no famoso circuíto internacional de Daytona,
05:32
during the Rolex 24 racing event.
138
317000
2000
coincidindo coa carreira Rolex 24.
05:34
We also had some surprises. Let's take a look.
139
319000
3000
Tamén nos levamos algunhas sorpresas. Botemos unha ollada.
05:37
(Music)
140
322000
10000
(Música)
05:47
(Video) Announcer: This is an historic day in January.
141
332000
4000
(Vídeo) Locutor: Este é un día histórico [inintelixíbel]
05:51
He's coming up to the grandstand, fellow Federationists.
142
336000
4000
Estase a aproximar á tribuna, queridos espectadores.
05:55
(Cheering)
143
340000
6000
(Aclamacións)
06:01
(Honking)
144
346000
3000
(Bucinazos)
06:04
There's the grandstand now.
145
349000
2000
Agora está ao lado da tribuna.
06:06
And he's [unclear] following that van that's out in front of him.
146
351000
4000
Está a seguir [inintelixíbel] a furgoneta que vai diante.
06:10
Well there comes the first box.
147
355000
2000
Aquí chega a primeira caixa.
06:12
Now let's see if Mark avoids it.
148
357000
3000
Veremos se Mark a evita.
06:15
He does. He passes it on the right.
149
360000
3000
Faino. Evítaa pola dereita.
06:20
Third box is out. The fourth box is out.
150
365000
3000
A terceira caixa está fora, e a cuarta.
06:23
And he's perfectly making his way between the two.
151
368000
3000
E consegue pasar sen problemas entre as dúas.
06:26
He's closing in on the van
152
371000
2000
Está acercándose á furgoneta
06:28
to make the moving pass.
153
373000
3000
para adiantala.
06:32
Well this is what it's all about,
154
377000
2000
Ben, isto foi o máis importante
06:34
this kind of dynamic display of audacity and ingenuity.
155
379000
4000
desta exhibición de audacia e enxeño.
06:39
He's approaching the end of the run,
156
384000
3000
Acércase o final do percorrido,
06:42
makes his way between the barrels that are set up there.
157
387000
5000
pasa entre os barrís colocados nel.
06:47
(Honking)
158
392000
3000
(Bucinazos)
06:50
(Applause)
159
395000
3000
(Aplausos)
06:56
Dennis Hong: I'm so happy for you.
160
401000
2000
Dennis Hong: Estou tan contento por vós.
06:58
Mark's going to give me a ride back to the hotel.
161
403000
2000
Mark vaime levar en coche de volta ao hotel.
07:00
Mark Riccobono: Yes.
162
405000
2000
Mark Riccobono: Si.
07:05
(Applause)
163
410000
9000
(Aplausos)
07:14
DH: So since we started this project,
164
419000
2000
DH: Dende que comenzamos este proxecto,
07:16
we've been getting hundreds of letters, emails, phone calls
165
421000
3000
temos recibido centos de cartas, correos electrónicos, chamadas
07:19
from people from all around the world.
166
424000
2000
de xente de todo o mundo.
07:21
Letters thanking us, but sometimes you also get funny letters like this one:
167
426000
3000
Cartas de agradecemento, pero ás veces tamén algunhas simpáticas como esta:
07:24
"Now I understand why there is Braille on a drive-up ATM machine."
168
429000
4000
"Agora entendo por que hai indicacións en Braille nos caixeiros para condutores."
07:28
(Laughter)
169
433000
2000
(Risos)
07:30
But sometimes --
170
435000
2000
Pero ás veces
07:32
(Laughter)
171
437000
2000
(Risos)
07:34
But sometimes I also do get --
172
439000
2000
Pero ás veces tamén recibimos,
07:36
I wouldn't call it hate mail --
173
441000
2000
non as chamaría cartas de odio,
07:38
but letters of really strong concern:
174
443000
2000
pero son realmente preocupantes.
07:40
"Dr. Hong, are you insane,
175
445000
2000
"Dr. Hong, está mal da cabeza?,
07:42
trying to put blind people on the road?
176
447000
2000
quere poñer cegos ao volante?
07:44
You must be out of your mind."
177
449000
2000
Tes que ser tolo."
07:46
But this vehicle is a prototype vehicle,
178
451000
2000
Pero este vehículo é un prototipo,
07:48
and it's not going to be on the road
179
453000
2000
e non estará nas carreteiras
07:50
until it's proven as safe as, or safer than, today's vehicle.
180
455000
2000
ate que se comprobe que é igual ou máis seguro que calquera vehículo actual.
07:52
And I truly believe that this can happen.
181
457000
3000
E creo sinceramente que isto pasará.
07:55
But still, will the society,
182
460000
2000
Aínda así, o pensa a sociedade?
07:57
would they accept such a radical idea?
183
462000
2000
Está preparada para aceptar unha idea tan radical?
07:59
How are we going to handle insurance?
184
464000
2000
Como o tratarán as aseguradoras?
08:01
How are we going to issue driver's licenses?
185
466000
2000
Que pasarán cos carnés de conducir?
08:03
There's many of these different kinds of hurdles besides technology challenges
186
468000
3000
Existen numerosos obstáculos similares, alén dos problemas técnicos,
08:06
that we need to address before this becomes a reality.
187
471000
3000
que aínda están por afrontar antes de que isto se converta en realidade.
08:09
Of course, the main goal of this project
188
474000
2000
Por suposto, a principal meta do proxecto
08:11
is to develop a car for the blind.
189
476000
2000
é desenvolver un coche para os cegos.
08:13
But potentially more important than this
190
478000
2000
Pero quizais máis importe que iso
08:15
is the tremendous value of the spin-off technology
191
480000
3000
é o inmenso valor dos subprodutos tecnolóxicos
08:18
that can come from this project.
192
483000
2000
que poder xurdir de este proxecto.
08:20
The sensors that are used can see through the dark,
193
485000
2000
Os sensores que usamos poden ser utilizados para ver na escuridade,
08:22
the fog and rain.
194
487000
2000
na néboa e baixo a chuvia.
08:24
And together with this new type of interfaces,
195
489000
2000
E xunto con este novo tipo de interfaces,
08:26
we can use these technologies
196
491000
2000
podemos utilizar estas tecnoloxías
08:28
and apply them to safer cars for sighted people.
197
493000
2000
e aplicalas para construír coches para videntes máis seguros.
08:30
Or for the blind, everyday home appliances --
198
495000
3000
Ou tamén electrodomésticos para invidentes
08:33
in the educational setting, in the office setting.
199
498000
2000
no entorno educativo e nas oficinas.
08:35
Just imagine, in a classroom a teacher writes on the blackboard
200
500000
3000
Tan son imaxinen, unha clase na que o profesor escrebe no encerado
08:38
and a blind student can see what's written and read
201
503000
3000
e un estudante cego pode ver o está escrito e lelo
08:41
using these non-visual interfaces.
202
506000
2000
usando estas interfaces non visuais.
08:43
This is priceless.
203
508000
3000
Isto non ten prezo.
08:46
So today, the things I've showed you today, is just the beginning.
204
511000
3000
Por agora, o que lles mostrei hoxe, é só o comezo.
08:49
Thank you very much.
205
514000
2000
Moitas gracias.
08:51
(Applause)
206
516000
11000
(Aplausos)
ABOUT THE SPEAKER
Dennis Hong - RoboticistDennis Hong is the founder and director of RoMeLa -- a Virginia Tech robotics lab that has pioneered several breakthroughs in robot design and engineering.
Why you should listen
As director of a groundbreaking robotics lab, Dennis Hong guides his team of students through projects on robot locomotion and mechanism design, creating award-winning humanoid robots like DARwIn (Dynamic Anthropomorphic Robot with Intelligence). His team is known as RoMeLa (Robotics & Mechanisms Laboratory) and operates at Virginia Tech.
Hong has also pioneered various innovations in soft-body robots, using a “whole-skin locomotion” as inspired by amoebae. Marrying robotics with biochemistry, he has been able to generate new types of motion with these ingenious forms. For his contributions to the field, Hong was selected as a NASA Summer Faculty Fellow in 2005, given the CAREER award by the National Science Foundation in 2007 and in 2009, named as one of Popular Science's Brilliant 10. He is also a gourmet chef and a magician, performing shows for charity and lecturing on the science of magic.
Dennis Hong | Speaker | TED.com