TED2011
Dennis Hong: Making a car for blind drivers
Denis Hong (Dennis Hong): Pravljenje automobila za slepe vozače
Filmed:
Readability: 4.3
923,134 views
Koristeći robotiku, lasersku detekciju, GPS i pametne alate za povratne informacije, Denis Hong konstruiše automobil za vozače koji su slepi. To nije automobil "koji sam vozi", on pažljivo napominje, već automobil u kome slepi vozač može da odredi brzinu, udaljenost i putanju - i da nezavisno vozi.
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
Mnogi veruju da je vožnja aktivnost
00:18
solely reserved for those who can see.
1
3000
2000
rezervisana isključivo za one koji vide.
00:20
A blind person driving a vehicle safely and independently
2
5000
3000
Mogućnost slepe osobe koja bezbedno i nezavisno vozi
00:23
was thought to be an impossible task, until now.
3
8000
3000
se smatralo nemogućim zadatakom, sve do sada.
00:26
Hello, my name is Dennis Hong,
4
11000
2000
Zdravo, moje ime je Denis Hong,
00:28
and we're bringing freedom and independence to the blind
5
13000
2000
i mi uvodimo slobodu i nezavisnost za slepe osobe
00:30
by building a vehicle for the visually impaired.
6
15000
3000
praveći vozilo za osobe sa oštećenim vidom.
00:33
So before I talk about this car for the blind,
7
18000
3000
Pre nego što počnem da govorim o automobilu za slepe osobe,
00:36
let me briefly tell you about another project that I worked on
8
21000
2000
ukratko ću vam reći o još jednom projektu na kome sam radio
00:38
called the DARPA Urban Challenge.
9
23000
2000
koji se naziva DARPA Urbani Izazov.
00:40
Now this was about building a robotic car
10
25000
2000
Ovde se radilo o pravljenju robotskog automobila
00:42
that can drive itself.
11
27000
2000
koji može sam da vozi.
00:44
You press start, nobody touches anything,
12
29000
2000
Pritisnete start, niko ne dira ništa,
00:46
and it can reach its destination fully autonomously.
13
31000
3000
i on može da stigne do svog odredišta potpuno autonomno.
00:49
So in 2007, our team won half a million dollars
14
34000
3000
Naš tim je 2007. godine osvojio pola miliona dolara,
00:52
by placing third place in this competition.
15
37000
2000
osvojivši treće mesto na ovom takmičenju.
00:54
So about that time,
16
39000
2000
U to vreme,
00:56
the National Federation of the Blind, or NFB,
17
41000
2000
Nacionalna federacija slepih, ili NFB,
00:58
challenged the research committee
18
43000
2000
uputila je izazov istraživačkom komitetu
01:00
about who can develop a car
19
45000
2000
vezan za to ko može da razvije automobil
01:02
that lets a blind person drive safely and independently.
20
47000
2000
koji omogućava slepoj osobi da vozi bezbedno i nezavisno.
01:04
We decided to give it a try,
21
49000
2000
Odlučili smo da pokušamo
01:06
because we thought, "Hey, how hard could it be?"
22
51000
2000
i mislili smo “Koliko to teško može da bude?“
01:08
We have already an autonomous vehicle.
23
53000
2000
Mi već imamo autonomno vozilo.
01:10
We just put a blind person in it and we're done, right?
24
55000
2000
Samo stavimo slepu osobu unutra i to je to, je li tako?
01:12
(Laughter)
25
57000
2000
(Smeh)
01:14
We couldn't have been more wrong.
26
59000
2000
Nismo mogli više da pogrešimo.
01:16
What NFB wanted
27
61000
2000
Ono što je NFB želela
01:18
was not a vehicle that can drive a blind person around,
28
63000
3000
nije vozilo koje može da vozi slepu osobu,
01:21
but a vehicle where a blind person can make active decisions and drive.
29
66000
3000
već vozilo gde slepa osoba može da donosi aktivne odluke i da upravlja vozilom.
01:24
So we had to throw everything out the window
30
69000
2000
Morali smo da se odreknemo svega
01:26
and start from scratch.
31
71000
2000
i da počnemo ispočetka.
01:28
So to test this crazy idea,
32
73000
2000
Da bi testirali ovu ludu ideju,
01:30
we developed a small dune buggy prototype vehicle
33
75000
2000
razvili smo malo prototip vozilo za vožnju po pesku
01:32
to test the feasibility.
34
77000
2000
da testiramo izvodljivost toga.
01:34
And in the summer of 2009,
35
79000
2000
U leto 2009.,
01:36
we invited dozens of blind youth from all over the country
36
81000
3000
pozvali smo desetine slepih mladih ljudi iz cele zemlje
01:39
and gave them a chance to take it for a spin.
37
84000
2000
i dali smo im šansu da isprobaju vozilo.
01:41
It was an absolutely amazing experience.
38
86000
2000
To je bilo apsolutno neverovatno iskustvo.
01:43
But the problem with this car was
39
88000
2000
Problem sa ovim automobilom je bio taj
01:45
it was designed to only be driven in a very controlled environment,
40
90000
3000
da je bio projektovan samo za vožnju u veoma kontrolisanom okruženju,
01:48
in a flat, closed-off parking lot --
41
93000
2000
na ravnom, zatvorenom parkingu –
01:50
even the lanes defined by red traffic cones.
42
95000
2000
čak su i saobraćajne trake bile definisane crvenim saobraćajnim kupama.
01:52
So with this success,
43
97000
2000
Sa ovim uspehom,
01:54
we decided to take the next big step,
44
99000
2000
odlučili smo da napravimo sledeći veliki korak,
01:56
to develop a real car that can be driven on real roads.
45
101000
3000
da razvijemo stvarni automobil, koji se može voziti na pravim putevima.
01:59
So how does it work?
46
104000
2000
Kako to funkcioniše?
02:01
Well, it's a rather complex system,
47
106000
2000
Dakle, to je veoma složen sistem,
02:03
but let me try to explain it, maybe simplify it.
48
108000
3000
ali dozvolite mi da pokušam da objasnim, ili da ga pojednostavim.
02:06
So we have three steps.
49
111000
2000
Postoje tri koraka.
02:08
We have perception, computation
50
113000
2000
Postoje percepcija, obrada
02:10
and non-visual interfaces.
51
115000
2000
i ne-vizuelni interfejsi.
02:12
Now obviously the driver cannot see,
52
117000
2000
Očigleno je da vozač ne može da vidi,
02:14
so the system needs to perceive the environment
53
119000
2000
tako da sistem mora da opaža okruženje
02:16
and gather information for the driver.
54
121000
2000
i prikuplja informacije za vozača.
02:18
For that, we use an initial measurement unit.
55
123000
3000
Za ovu svrhu, koristi se početna merna jedinica.
02:21
So it measures acceleration, angular acceleration --
56
126000
2000
Ona meri ubrzanje, ugaono ubrzanje –
02:23
like a human ear, inner ear.
57
128000
2000
kao ljudsko uho, unutrašnje uho.
02:25
We fuse that information with a GPS unit
58
130000
2000
Te informacije se spajaju sa GPS jedinicom
02:27
to get an estimate of the location of the car.
59
132000
3000
da bi se dobila procena lokacije automobila.
02:30
We also use two cameras to detect the lanes of the road.
60
135000
3000
Takođe se koriste dve kamere za detektovanje saobraćajnih traka na putu.
02:33
And we also use three laser range finders.
61
138000
2000
Koriste se i tri laserska detektora.
02:35
The lasers scan the environment to detect obstacles --
62
140000
3000
Laseri skeniraju okruženje da bi detektovali prepreke –
02:38
a car approaching from the front, the back
63
143000
2000
vozilo koje se približava sa prednje strane, sa zadnje strane
02:40
and also any obstacles that run into the roads,
64
145000
3000
i bilo koje prepreke koje se nalaze na putu,
02:43
any obstacles around the vehicle.
65
148000
2000
kao i prepreke koje se nalaze oko vozila.
02:45
So all this vast amount of information is then fed into the computer,
66
150000
3000
Ova ogromna količina informacija se zatim šalje u kompjuter,
02:48
and the computer can do two things.
67
153000
2000
i kompjuter može da radi dve stvari.
02:50
One is, first of all, process this information
68
155000
3000
Jedna je, pre svega, obrada ovih informacija
02:53
to have an understanding of the environment --
69
158000
2000
zbog razumevanja okruženja –
02:55
these are the lanes of the road, there's the obstacles --
70
160000
3000
to su trake na putu, prepreke –
02:58
and convey this information to the driver.
71
163000
2000
i da prenese ove informacije vozaču.
03:00
The system is also smart enough
72
165000
2000
Sistem je dovoljno pametan
03:02
to figure out the safest way to operate the car.
73
167000
2000
da odredi najbezbedniji put za kretanje vozila.
03:04
So we can also generate instructions
74
169000
2000
Takođe mogu da se naprave instrukcije
03:06
on how to operate the controls of the vehicle.
75
171000
2000
kako upravljati komandama u vozilu.
03:08
But the problem is this: How do we convey
76
173000
2000
Ali problem je sledeći: Kako da prenesemo
03:10
this information and instructions
77
175000
2000
ove informacije i instrukcije
03:12
to a person who cannot see
78
177000
2000
osobi koja ne može da vidi
03:14
fast enough and accurate enough so he can drive?
79
179000
3000
dovoljno brzo i precizno da vidi da bi mogla da vozi?
03:17
So for this, we developed many different types
80
182000
2000
Za ovu svrhu, razvili smo mnogo različitih tipova
03:19
of non-visual user interface technology.
81
184000
3000
tehnologija ne-vizuelnih, korisničkih interfejsa.
03:22
So starting from a three-dimensional ping sound system,
82
187000
2000
Počevši sa trodimenzionalnim ping zvučnim sistemom,
03:24
a vibrating vest,
83
189000
2000
vibrirajućim prslukom,
03:26
a click wheel with voice commands, a leg strip,
84
191000
3000
volanom sa dugmićima i zvučnim komandama, nožnom trakom,
03:29
even a shoe that applies pressure to the foot.
85
194000
2000
čak i cipelom koja prenosi pritisak na stopalo.
03:31
But today we're going to talk about
86
196000
2000
Danas ćemo govoriti
03:33
three of these non-visual user interfaces.
87
198000
2000
o tri od ovih ne-vizuelnih interfejsa.
03:35
Now the first interface is called a DriveGrip.
88
200000
3000
Prvi interfejs se zove Upravljačko rukovanje.
03:38
So these are a pair of gloves,
89
203000
2000
To je par rukavica
03:40
and it has vibrating elements on the knuckle part
90
205000
2000
koje poseduju vibrirajuće elemente u predelu šake
03:42
so you can convey instructions about how to steer --
91
207000
3000
i omogućavaju prenošenje instrukcije koje se tiču upravljanja –
03:45
the direction and the intensity.
92
210000
2000
smer i intenzitet.
03:47
Another device is called SpeedStrip.
93
212000
2000
Drugi uređaj se zove Brzinska oprema.
03:49
So this is a chair -- as a matter of fact, it's actually a massage chair.
94
214000
3000
To je stolica – u stvari, to je stolica koja masira.
03:52
We gut it out, and we rearrange the vibrating elements in different patterns,
95
217000
4000
Rekonstruisali smo je, preuredili smo vibrirajuće elemente na različite načine
03:56
and we actuate them to convey information about the speed,
96
221000
3000
i aktivirali smo ih da prenose informacije o brzini,
03:59
and also instructions how to use the gas and the brake pedal.
97
224000
3000
takođe i instrukcije kako se koriste pedale gasa i kočnice.
04:02
So over here, you can see
98
227000
2000
Ovde možete videti
04:04
how the computer understands the environment,
99
229000
2000
kako kompjuter razume okruženje,
04:06
and because you cannot see the vibration,
100
231000
2000
i zato što vi ne možete da vidite vibraciju,
04:08
we actually put red LED's on the driver so that you can see what's happening.
101
233000
3000
stavili smo crvene LED svetiljke na vozača tako da možete da vidite šta se dešava.
04:11
This is the sensory data,
102
236000
2000
Ovo su podaci sa senzora,
04:13
and that data is transferred to the devices through the computer.
103
238000
3000
i ti podaci se prenose u uređaje pomoću kompjutera.
04:16
So these two devices, DriveGrip and SpeedStrip,
104
241000
2000
Ova dva uređaja, Upravljačko rukovanje i Brzinska oprema,
04:18
are very effective.
105
243000
2000
su veoma efektivni.
04:20
But the problem is
106
245000
2000
Problem je
04:22
these are instructional cue devices.
107
247000
2000
što su to uređaji koji daju instrukcije.
04:24
So this is not really freedom, right?
108
249000
2000
Ovo nije u stvari sloboda, zar ne?
04:26
The computer tells you how to drive --
109
251000
2000
Kompjuter vam govori kako da vozite –
04:28
turn left, turn right, speed up, stop.
110
253000
2000
skreni levo, skreni desno, ubrzaj, zaustavi se.
04:30
We call this the "backseat-driver problem."
111
255000
2000
Mi ovo nazivamo "problem da vam stalno neko suflira".
04:32
So we're moving away from the instructional cue devices,
112
257000
3000
Mi se udaljavamo od uređaja koji daju instrukcije,
04:35
and we're now focusing more
113
260000
2000
i sada se više fokusiramo
04:37
on the informational devices.
114
262000
2000
na informativne uređaje.
04:39
A good example for this informational non-visual user interface
115
264000
2000
Dobar primer ovih informativnih ne-vizuelnih korisničkih interfejsa
04:41
is called AirPix.
116
266000
2000
se naziva Vazdušna fotografija.
04:43
So think of it as a monitor for the blind.
117
268000
2000
To zamislite kao monitor za slepe ljude.
04:45
So it's a small tablet, has many holes in it,
118
270000
2000
To je mala ploča, ima mnogo otvora u sebi,
04:47
and compressed air comes out,
119
272000
2000
kompresovani vazduh izlazi napolje,
04:49
so it can actually draw images.
120
274000
2000
tako da on u stvari može da pravi slike.
04:51
So even though you are blind, you can put your hand over it,
121
276000
2000
Čak iako ste slepi, možete da stavite ruku preko njega
04:53
you can see the lanes of the road and obstacles.
122
278000
2000
i da vidite saobraćajne trake na putu i prepreke.
04:55
Actually, you can also change the frequency of the air coming out
123
280000
3000
Takođe možete da promenite učestalost vazduha koji izlazi
04:58
and possibly the temperature.
124
283000
2000
kao i temperaturu.
05:00
So it's actually a multi-dimensional user interface.
125
285000
3000
To je u stvari multidimenzionalni korisnički interfejs.
05:03
So here you can see the left camera, the right camera from the vehicle
126
288000
3000
Ovde možete da vidite levu kameru, desnu kameru vozila
05:06
and how the computer interprets that and sends that information to the AirPix.
127
291000
3000
i kako kompjuter to interpretira i šalje te informacije Vazdušnoj fotografiji.
05:09
For this, we're showing a simulator,
128
294000
2000
Za ovu svrhu, pokazujemo simulator,
05:11
a blind person driving using the AirPix.
129
296000
3000
slepa osoba koja vozi koristeći Vazdušnu fotografiju.
05:14
This simulator was also very useful for training the blind drivers
130
299000
3000
Ovaj simulator je takođe veoma bio koristan za obuku slepih vozača
05:17
and also quickly testing different types of ideas
131
302000
2000
kao i za brzo testiranje različitih tipova ideja
05:19
for different types of non-visual user interfaces.
132
304000
2000
za različite tipove ne-vizuelnih, korisničkih interfejsa.
05:21
So basically that's how it works.
133
306000
2000
U osnovi to radi ovako.
05:23
So just a month ago,
134
308000
2000
Pre samo mesec dana,
05:25
on January 29th,
135
310000
2000
29. januara,
05:27
we unveiled this vehicle for the very first time to the public
136
312000
2000
po prvi put smo prikazali ovo vozilo javnosti
05:29
at the world-famous Daytona International Speedway
137
314000
3000
na svetski poznatoj Dejtona međunarodnoj stazi
05:32
during the Rolex 24 racing event.
138
317000
2000
tokom Roleks 24 trkačkog događaja.
05:34
We also had some surprises. Let's take a look.
139
319000
3000
Imali smo i nekoliko iznenađenja. Hajde da pogledamo.
05:37
(Music)
140
322000
10000
(Muzika)
05:47
(Video) Announcer: This is an historic day in January.
141
332000
4000
(Video) Spiker: Ovo je istorijski dan u januaru.
05:51
He's coming up to the grandstand, fellow Federationists.
142
336000
4000
On izlazi na pozornicu, drugovi naši.
05:55
(Cheering)
143
340000
6000
(Ovacije)
06:01
(Honking)
144
346000
3000
(Trubljenje)
06:04
There's the grandstand now.
145
349000
2000
Tamo je sada pozornica.
06:06
And he's [unclear] following that van that's out in front of him.
146
351000
4000
I on [nejasno] prati taj kombi koji je ispred njega.
06:10
Well there comes the first box.
147
355000
2000
Dolazi prva kutija.
06:12
Now let's see if Mark avoids it.
148
357000
3000
Da vidimo da li će je Mark izbeći.
06:15
He does. He passes it on the right.
149
360000
3000
Izbegava je. On je prolazi sa desne strane.
06:20
Third box is out. The fourth box is out.
150
365000
3000
Treća kutija je izbačena. Četvrta kutija je izbačena.
06:23
And he's perfectly making his way between the two.
151
368000
3000
On savršeno pronalazi put između dve kutije.
06:26
He's closing in on the van
152
371000
2000
Približava se kombiju
06:28
to make the moving pass.
153
373000
3000
da bi ga pretekao.
06:32
Well this is what it's all about,
154
377000
2000
U ovome je suština,
06:34
this kind of dynamic display of audacity and ingenuity.
155
379000
4000
vrsta dinamičnog monitora sa zvukovima i genijalnošću.
06:39
He's approaching the end of the run,
156
384000
3000
On se približava kraju staze
06:42
makes his way between the barrels that are set up there.
157
387000
5000
i pronalazi put između buradi koja je tamo postavljena.
06:47
(Honking)
158
392000
3000
(Trubljenje)
06:50
(Applause)
159
395000
3000
(Aplauz)
06:56
Dennis Hong: I'm so happy for you.
160
401000
2000
Denis Hong: Veoma sam srećan zbog tebe.
06:58
Mark's going to give me a ride back to the hotel.
161
403000
2000
Mark će me odvesti nazad do hotela.
07:00
Mark Riccobono: Yes.
162
405000
2000
Mark Rikobono: Da.
07:05
(Applause)
163
410000
9000
(Aplauz)
07:14
DH: So since we started this project,
164
419000
2000
DH: Od kada smo započeli ovaj projekat,
07:16
we've been getting hundreds of letters, emails, phone calls
165
421000
3000
dobijamo stotine pisama, mejlova, telefonskih poziva
07:19
from people from all around the world.
166
424000
2000
od ljudi iz čitavog sveta.
07:21
Letters thanking us, but sometimes you also get funny letters like this one:
167
426000
3000
Pisma u kojima nam se zahvaljuju, a ponekad dobijemo i neko zabavno pismo kao što je ovo:
07:24
"Now I understand why there is Braille on a drive-up ATM machine."
168
429000
4000
“Sad razumem zašto se Brajevo pismo nalazi na bankomatu kome se može prići kolima.”
07:28
(Laughter)
169
433000
2000
(Smeh)
07:30
But sometimes --
170
435000
2000
Ponekad –
07:32
(Laughter)
171
437000
2000
(Smeh)
07:34
But sometimes I also do get --
172
439000
2000
Ponekad stvarno dobijem –
07:36
I wouldn't call it hate mail --
173
441000
2000
ne bih to nazvao mejlom mržnje –
07:38
but letters of really strong concern:
174
443000
2000
već pisma veoma velike zabrinutosti:
07:40
"Dr. Hong, are you insane,
175
445000
2000
“Dr Hong, da li ste vi normalni,
07:42
trying to put blind people on the road?
176
447000
2000
pokušavate da stavite slepe ljude da voze?
07:44
You must be out of your mind."
177
449000
2000
Mora da ste van pameti.”
07:46
But this vehicle is a prototype vehicle,
178
451000
2000
Ovo vozilo je prototip vozilo
07:48
and it's not going to be on the road
179
453000
2000
i neće se naći na ulicama dok se ne dokaže
07:50
until it's proven as safe as, or safer than, today's vehicle.
180
455000
2000
kao podjednako bezbedno ili bezbednije od današnjeg vozila.
07:52
And I truly believe that this can happen.
181
457000
3000
Ja zaista verujem da se ovo može dogoditi.
07:55
But still, will the society,
182
460000
2000
Ali da li će društvo
07:57
would they accept such a radical idea?
183
462000
2000
prihvatiti ovako radikalnu ideju?
07:59
How are we going to handle insurance?
184
464000
2000
Kako će se rešiti osiguranje?
08:01
How are we going to issue driver's licenses?
185
466000
2000
Kako će se izdavati vozačke dozvole?
08:03
There's many of these different kinds of hurdles besides technology challenges
186
468000
3000
Postoji mnogo različitih poteškoća pored tehničkih izazova
08:06
that we need to address before this becomes a reality.
187
471000
3000
koje moramo da rešimo pre nego što ovo postane realnost.
08:09
Of course, the main goal of this project
188
474000
2000
Naravno, glavni cilj ovog projekta
08:11
is to develop a car for the blind.
189
476000
2000
je da se razvije automobil za slepe ljude.
08:13
But potentially more important than this
190
478000
2000
Još važnije od ovoga potencijalno
08:15
is the tremendous value of the spin-off technology
191
480000
3000
može biti ogromna vrednost nove tehnologije
08:18
that can come from this project.
192
483000
2000
koja može da se izrodi iz ovog projekta.
08:20
The sensors that are used can see through the dark,
193
485000
2000
Senzori koji se koriste mogu da vide
08:22
the fog and rain.
194
487000
2000
po mraku, magli i kiši.
08:24
And together with this new type of interfaces,
195
489000
2000
Zajedno sa ovim novim tipom interfejsa,
08:26
we can use these technologies
196
491000
2000
možemo da koristimo ove tehnologije
08:28
and apply them to safer cars for sighted people.
197
493000
2000
i primenimo ih na bezbednije automobile za osobe sa dobrim vidom.
08:30
Or for the blind, everyday home appliances --
198
495000
3000
I za slepe ljude, svakodnevne kućne uređaje –
08:33
in the educational setting, in the office setting.
199
498000
2000
u obrazovnom okruženju, u kancelarijskom okruženju.
08:35
Just imagine, in a classroom a teacher writes on the blackboard
200
500000
3000
Samo zamislite, u učionici nastavnik piče na tabli
08:38
and a blind student can see what's written and read
201
503000
3000
a slepi student može da vidi šta je napisano i čita
08:41
using these non-visual interfaces.
202
506000
2000
pomoću ovih ne-vizuelnih interfejsa.
08:43
This is priceless.
203
508000
3000
To je neprocenjivo.
08:46
So today, the things I've showed you today, is just the beginning.
204
511000
3000
Stvari koje sam vam pokazao danas, su samo početak.
08:49
Thank you very much.
205
514000
2000
Hvala vam puno.
08:51
(Applause)
206
516000
11000
(Aplauz)
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