TEDGlobal 2013
Raffaello D'Andrea: The astounding athletic power of quadcopters
Raffaello D'Andrea: Osupljiva atletska moč kvadkopterjev
Filmed:
Readability: 4.7
12,409,728 views
V robotskem laboratoriju na TEDGlobal, Raffaelo D'Andrea pokaže svoje leteče kvadkopterje: roboti, ki razmišljajo kot atleti, rešujejo fizikalne probleme, ki jim pomagajo pri učenju. V seriji spretnih predstavitev D'Andrea pokaže drone, ki lovijo žogo, ravnotežje in se skupaj odločajo - bodite pozorni na to-hočem-zdaj predstavitev kvadov, ki jih nadzorujemo s Kinectom.
Raffaello D'Andrea - Autonomous systems pioneer
Raffaello D'Andrea explores the possibilities of autonomous technology by collaborating with artists, engineers and entrepreneurs. Full bio
Raffaello D'Andrea explores the possibilities of autonomous technology by collaborating with artists, engineers and entrepreneurs. Full bio
Double-click the English transcript below to play the video.
00:23
So what does it mean for a machine to be athletic?
0
11307
3184
Kaj pomeni, da je neka naprava atletska?
00:26
We will demonstrate the concept of machine athleticism
1
14491
3417
Pokazali vam bomo koncept
atletskosti naprav
atletskosti naprav
00:29
and the research to achieve it
2
17908
1720
in raziskave, potrebne za to,
00:31
with the help of these flying machines called quadrocopters,
3
19628
2511
s pomočjo teh letečih naprav,
imenovanih kvadkopterji
imenovanih kvadkopterji
00:34
or quads, for short.
4
22139
1887
ali kvadi na kratko.
00:38
Quads have been around for a long time.
5
26034
2529
Kvadi so tu že dolgo časa.
Te dni so tako priljubljeni,
ker so mehansko preprosti.
ker so mehansko preprosti.
00:40
The reason that they're so popular these days
6
28563
1599
00:42
is because they're mechanically simple.
7
30162
1965
00:44
By controlling the speeds of these four propellers,
8
32127
2108
Z nadzorovanjem hitrosti
teh štirih propelerjev,
teh štirih propelerjev,
00:46
these machines can roll, pitch, yaw,
9
34235
3048
se te naprave lahko obračajo,
nagnejo, zavijajo
nagnejo, zavijajo
00:49
and accelerate along their common orientation.
10
37283
2825
in pospešujejo v isti smeri.
00:52
On board are also a battery, a computer,
11
40108
3071
Nameščeni so tudi baterija, računalnik,
00:55
various sensors and wireless radios.
12
43179
3954
različni senzorji in brezžični radii.
00:59
Quads are extremely agile, but this agility comes at a cost.
13
47133
4629
Kvadi so izjemno spretni,
a ta spretnost ima svojo ceno.
a ta spretnost ima svojo ceno.
01:03
They are inherently unstable, and they need some form
14
51762
2992
So neizogibno nestabilni
in potrebujejo neke vrste
avtomatično povratno kontrolo,
avtomatično povratno kontrolo,
01:06
of automatic feedback control in order to be able to fly.
15
54754
3972
da lahko letijo.
01:16
So, how did it just do that?
16
64259
3238
Torej, kako je pravkar naredil to?
01:19
Cameras on the ceiling and a laptop
17
67497
1818
Kamere na stropu in prenosnik
01:21
serve as an indoor global positioning system.
18
69315
2576
služijo kot notranji
globalni sistem določanja položaja.
globalni sistem določanja položaja.
01:23
It's used to locate objects in the space
19
71891
2185
Uporablja se za lociranje
predmetov v prostoru,
predmetov v prostoru,
01:26
that have these reflective markers on them.
20
74076
2527
ki imajo na sebi te odbojne oznake.
Ti podatki so poslani na drugi prenosnik,
01:28
This data is then sent to another laptop
21
76603
2061
ki poganja algoritme za ocene in nadzor,
01:30
that is running estimation and control algorithms,
22
78664
2211
01:32
which in turn sends commands to the quad,
23
80875
1886
ki nato pošilja ukaze kvadu,
01:34
which is also running estimation and control algorithms.
24
82761
3485
ki prav tako poganja
algoritme za ocene in nadzor.
algoritme za ocene in nadzor.
01:41
The bulk of our research is algorithms.
25
89620
2510
Večina našega raziskovanja so algoritmi.
01:44
It's the magic that brings these machines to life.
26
92130
4161
To je čarovnija, ki oživi te naprave.
01:48
So how does one design the algorithms
27
96291
2043
Kako torej narediš algoritme,
ki ustvarijo mehanskega atleta?
ki ustvarijo mehanskega atleta?
01:50
that create a machine athlete?
28
98334
2277
01:52
We use something broadly called model-based design.
29
100611
2880
Uporabimo nekaj, čemur pravimo
na modelih temelječ dizajn.
na modelih temelječ dizajn.
01:55
We first capture the physics with a mathematical model
30
103491
3154
Najprej ujamemo fiziko
z matematičnim modelom,
ki zajame obnašanje naprav.
ki zajame obnašanje naprav.
01:58
of how the machines behave.
31
106645
2134
Uporabimo vejo matematike,
ki ji pravimo teorija nadzora,
ki ji pravimo teorija nadzora,
02:00
We then use a branch of mathematics
32
108779
2297
02:03
called control theory to analyze these models
33
111076
2831
da analiziramo te modele,
02:05
and also to synthesize algorithms for controlling them.
34
113907
3913
in da sintetiziramo algoritme
za njihov nadzor.
za njihov nadzor.
02:09
For example, that's how we can make the quad hover.
35
117820
3048
Naprimer, s tem kvad lebdi.
02:12
We first captured the dynamics
36
120868
1408
Najprej smo zajeli dinamiko
s setom diferencialnih enačb.
s setom diferencialnih enačb.
02:14
with a set of differential equations.
37
122276
1906
02:16
We then manipulate these equations with the help
38
124182
2349
Nato smo manipulirali te enačbe
s pomočjo teorije nadzora,
s pomočjo teorije nadzora,
02:18
of control theory to create algorithms that stabilize the quad.
39
126531
4640
da bi ustvarili algoritme,
ki stabilizirajo kvad.
ki stabilizirajo kvad.
Naj vam prikažem moč tega pristopa.
02:23
Let me demonstrate the strength of this approach.
40
131171
2946
02:29
Suppose that we want this quad to not only hover
41
137198
2549
Recimo, da želimo, da kvad ne samo lebdi,
02:31
but to also balance this pole.
42
139747
2782
ampak tudi uravnoteži to palico.
Z malo vaje
02:34
With a little bit of practice,
43
142529
1844
je precej enostavno za človeka,
02:36
it's pretty straightforward for a human being to do this,
44
144373
2391
a mi imamo prednost
dveh nog na tleh
dveh nog na tleh
02:38
although we do have the advantage of having
45
146764
1755
02:40
two feet on the ground
46
148519
1328
in uporabo naših zelo vsestranskih rok.
02:41
and the use of our very versatile hands.
47
149847
2957
02:44
It becomes a little bit more difficult
48
152804
2469
Postane malo težje,
02:47
when I only have one foot on the ground
49
155273
2296
ko imam na tleh samo en nogo
02:49
and when I don't use my hands.
50
157569
2799
in ko ne uporabljam rok.
02:52
Notice how this pole has a reflective marker on top,
51
160368
2951
Vidite, da ima ta palica na vrhu
svetlečo oznako,
svetlečo oznako,
02:55
which means that it can be located in the space.
52
163319
3894
kar pomeni, da jo lahko
lociramo v prostoru.
lociramo v prostoru.
(občinstvo) Oh!
03:04
(Applause)
53
172971
5976
(aplavz)
(konec aplavza)
03:10
You can notice that this quad is making fine adjustments
54
178947
2826
Lahko vidite,
da kvad dela rahle prilagoditve,
da kvad dela rahle prilagoditve,
03:13
to keep the pole balanced.
55
181773
2195
da bi palico uravnotežil.
03:15
How did we design the algorithms to do this?
56
183968
3059
Kako smo oblikovali algoritme za to?
03:19
We added the mathematical model of the pole
57
187027
2105
Modelu kvada smo dodali
matematični model palice.
matematični model palice.
03:21
to that of the quad.
58
189132
1519
Ko imamo enkrat model
kombiniranega sistema palica-kvad,
kombiniranega sistema palica-kvad,
03:22
Once we have a model of the combined quad-pole system,
59
190651
2954
03:25
we can use control theory to create algorithms for controlling it.
60
193605
4933
lahko uporabimo teorijo nadzora,
da ustvarimo algoritme za njun nadzor.
da ustvarimo algoritme za njun nadzor.
03:30
Here, you see that it's stable,
61
198538
1588
Vidite, kako je stabilna
03:32
and even if I give it little nudges,
62
200126
2693
in tudi če jo malo potisnem,
03:34
it goes back to the nice, balanced position.
63
202819
5403
gre nazaj -
na lepo, uravnoteženo pozicijo.
Lahko tudi nadgradimo model,
03:40
We can also augment the model to include
64
208222
1663
da vključimo, kje v prostoru želimo kvad.
03:41
where we want the quad to be in space.
65
209885
2441
03:44
Using this pointer, made out of reflective markers,
66
212326
3069
S tem kazalcem, narejenim
iz odsevnih oznak,
iz odsevnih oznak,
03:47
I can point to where I want the quad to be in space
67
215395
2224
lahko pokažem, kje v prostoru želim kvad,
03:49
a fixed distance away from me.
68
217619
3367
na določeni distanci od mene.
(Smeh)
04:07
The key to these acrobatic maneuvers is algorithms,
69
235763
2902
Ključ do teh akrobatskih
manevrov so algoritmi,
manevrov so algoritmi,
04:10
designed with the help of mathematical models
70
238665
2426
oblikovani s pomočjo matematičnih modelov
04:13
and control theory.
71
241091
1950
in teorije nadzora.
04:15
Let's tell the quad to come back here
72
243041
2214
Povejmo kvadu, naj pride nazaj sem
04:17
and let the pole drop,
73
245255
1819
in naj pusti palico, da pade,
in pokazal vam bom, kako pomembno
04:19
and I will next demonstrate the importance
74
247074
1918
04:20
of understanding physical models
75
248992
2119
je razumeti fizikalne modele
04:23
and the workings of the physical world.
76
251111
4120
in delovanje fizičnega sveta.
04:37
Notice how the quad lost altitude
77
265462
1770
Opazite, kako je kvad izgubil višino,
ko sem nanj postavil kozarec vode.
ko sem nanj postavil kozarec vode.
04:39
when I put this glass of water on it.
78
267232
2082
04:41
Unlike the balancing pole, I did not include
79
269314
2801
Za razliko od palice,
nisem vključil
matematičnega modela kozarca
matematičnega modela kozarca
04:44
the mathematical model of the glass in the system.
80
272115
2584
v sistem.
04:46
In fact, the system doesn't even know that the glass of water is there.
81
274699
2919
Pravzaprav, sistem sploh ne ve,
da je kozarec tam.
da je kozarec tam.
04:49
Like before, I could use the pointer to tell the quad
82
277618
3292
Kot prej, lahko uporabim kazalec,
da povem kvadu,
da povem kvadu,
04:52
where I want it to be in space.
83
280910
2589
kje v prostoru želim, da je.
04:55
(Applause)
84
283499
9597
(Aplavz)
(konec aplavza)
05:05
Okay, you should be asking yourself,
85
293096
2110
Ok, sedaj bi se morali vprašati,
05:07
why doesn't the water fall out of the glass?
86
295206
2509
zakaj voda ne steče iz kozarca?
05:09
Two facts: The first is that gravity acts
87
297715
3211
Dve dejstvi.
Prvo je, da gravitacija vpliva
na vse objekte enako.
na vse objekte enako.
05:12
on all objects in the same way.
88
300926
2125
05:15
The second is that the propellers are all pointing
89
303051
2464
Drugo je, da so propelerji
vsi obrnjeni v isto smer kozarca, gor.
05:17
in the same direction of the glass, pointing up.
90
305515
3127
05:20
You put these two things together, the net result
91
308642
2377
Ko združiš ti dve stvari,
je skupni rezultat, da so vse
stranske sile na kozarec majhne
stranske sile na kozarec majhne
05:23
is that all side forces on the glass are small
92
311019
2287
05:25
and are mainly dominated by aerodynamic effects,
93
313306
2785
in jim dominirajo aerodinamični učinki,
05:28
which as these speeds are negligible.
94
316091
3841
ki so ob teh hitrostih zanemarljivi.
05:35
And that's why you don't need to model the glass.
95
323336
2071
In zato vam ni treba
narediti modela za kozarec.
narediti modela za kozarec.
05:37
It naturally doesn't spill no matter what the quad does.
96
325407
3848
Naravno se ne polije,
ne glede na to, kaj naredi kvad.
ne glede na to, kaj naredi kvad.
(občinstvo) Oh!
(aplavz)
05:50
(Applause)
97
338651
7051
(konec aplavza)
05:57
The lesson here is that some high-performance tasks
98
345702
4016
Lekcija tu je,
da so nekatere visoko zmogljivostne
naloge lažje od drugih
naloge lažje od drugih
06:01
are easier than others,
99
349718
1397
06:03
and that understanding the physics of the problem
100
351115
2296
in da ti razumevanje fizikalnosti problema
06:05
tells you which ones are easy and which ones are hard.
101
353411
2616
pove, katere so lahke in katere težke.
06:08
In this instance, carrying a glass of water is easy.
102
356027
2359
V tem primeru je nošenje kozarca lahko.
06:10
Balancing a pole is hard.
103
358386
3785
Uravnotežiti palico je težko.
06:14
We've all heard stories of athletes
104
362171
1802
Vsi smo slišali zgodbe o atletih, ki so
izvajali podvige med fizično poškodbo.
izvajali podvige med fizično poškodbo.
06:15
performing feats while physically injured.
105
363973
2493
06:18
Can a machine also perform
106
366466
1519
Lahko naprava še vedno deluje,
kljub hudi poškodbi?
kljub hudi poškodbi?
06:19
with extreme physical damage?
107
367985
2651
06:22
Conventional wisdom says that you need
108
370636
1726
Konvencionalna modrost pravi,
da potrebuješ vsaj štiri fiksne motorne
propelerske pare, da lahko leti,
propelerske pare, da lahko leti,
06:24
at least four fixed motor propeller pairs in order to fly,
109
372362
3690
06:28
because there are four degrees of freedom to control:
110
376052
2112
ker nadzorujemo štiri stopnje prostosti:
06:30
roll, pitch, yaw and acceleration.
111
378164
3028
obračanje, nagibanje,
zavijanje in pospeševanje.
zavijanje in pospeševanje.
06:33
Hexacopters and octocopters, with six and eight propellers,
112
381192
3245
Heksakopterji in oktokopterji,
s šestimi in osmimi propelerji,
s šestimi in osmimi propelerji,
06:36
can provide redundancy,
113
384437
1483
lahko nudijo več moči, kot je potrebujejo,
ampak kvadkopterji so bolj popularni,
ampak kvadkopterji so bolj popularni,
06:37
but quadrocopters are much more popular
114
385920
1989
06:39
because they have the minimum number
115
387909
1815
ker imajo minimalno število fiksnih
motornih propelerskih parov: štiri.
motornih propelerskih parov: štiri.
06:41
of fixed motor propeller pairs: four.
116
389724
2476
Ali pač?
06:44
Or do they?
117
392200
1965
(občinstvo) Oh!
(smeh)
Če analiziramo
matematični model te naprave
matematični model te naprave
07:01
If we analyze the mathematical model of this machine
118
409476
2600
07:04
with only two working propellers,
119
412076
2176
s samo dvema delujočima propelerjema,
07:06
we discover that there's an unconventional way to fly it.
120
414252
6756
odkrijemo, da obstaja
neobičajen način letenja.
neobičajen način letenja.
07:19
We relinquish control of yaw,
121
427980
1706
Izgubimo zavijanje,
07:21
but roll, pitch and acceleration can still be controlled
122
429686
3070
ampak obračanje, nagibanje
in pospeševanje lahko še vedno nadzorujemo
in pospeševanje lahko še vedno nadzorujemo
07:24
with algorithms that exploit this new configuration.
123
432756
5452
z algoritmi, ki uporabijo
to novo konfiguracijo.
to novo konfiguracijo.
07:33
Mathematical models tell us exactly when
124
441668
2432
Matematični modeli nam povedo,
točno zakaj in kdaj je to možno.
točno zakaj in kdaj je to možno.
07:36
and why this is possible.
125
444100
2072
V tem primeru nam to znanje
omogoča, da oblikujemo
omogoča, da oblikujemo
07:38
In this instance, this knowledge allows us to design
126
446172
2368
07:40
novel machine architectures
127
448540
2256
izvirne načrte naprav
07:42
or to design clever algorithms that gracefully handle damage,
128
450796
4176
ali oblikovanje pametnih algoritmov,
ki elegantno obvladajo poškodbe,
ki elegantno obvladajo poškodbe,
07:46
just like human athletes do,
129
454972
1724
tako kot človeški atleti,
07:48
instead of building machines with redundancy.
130
456696
3823
namesto da bi gradili naprave
z več moči, kot je potrebujejo.
z več moči, kot je potrebujejo.
07:52
We can't help but hold our breath when we watch
131
460519
2112
Ne moremo, da ne bi zajeli sape,
ko gledamo potapljača,
kako se požene v vodo,
kako se požene v vodo,
07:54
a diver somersaulting into the water,
132
462631
2437
07:57
or when a vaulter is twisting in the air,
133
465068
1790
ali ko se skakalec vrti v zraku,
07:58
the ground fast approaching.
134
466858
1718
tla pa se mu hitro približujejo.
08:00
Will the diver be able to pull off a rip entry?
135
468576
2568
Bo potapljaču uspel skok?
08:03
Will the vaulter stick the landing?
136
471144
2000
Bo skakalcu uspel pristanek?
08:05
Suppose we want this quad here
137
473144
1668
Recimo da želimo,
da se ta kvad trikrat obrne
da se ta kvad trikrat obrne
08:06
to perform a triple flip and finish off
138
474812
2451
in konča na istem mestu, kot je začel.
08:09
at the exact same spot that it started.
139
477263
2269
08:11
This maneuver is going to happen so quickly
140
479532
2347
Ta manever se bo zgodil tako hitro,
08:13
that we can't use position feedback to correct the motion during execution.
141
481879
3629
da ne moremo uporabiti pozicijske
povratne informacije.
povratne informacije.
08:17
There simply isn't enough time.
142
485508
2274
Preprosto ni dovolj časa.
08:19
Instead, what the quad can do is perform the maneuver blindly,
143
487782
3694
Namesto tega lahko kvad
slepo izvede manever,
slepo izvede manever,
08:23
observe how it finishes the maneuver,
144
491476
2232
opazuje, kako konča manever,
08:25
and then use that information to modify its behavior
145
493708
2424
in potem uporabi te informacije,
da popravi to gibanje,
da popravi to gibanje,
08:28
so that the next flip is better.
146
496132
2289
tako, da je naslednjič boljše.
08:30
Similar to the diver and the vaulter,
147
498421
1812
Podobno kot potapljač ali skakalec,
08:32
it is only through repeated practice
148
500233
1919
samo skozi vajo
08:34
that the maneuver can be learned and executed
149
502152
1925
se lahko ta manever nauči in izvede
08:36
to the highest standard.
150
504077
2133
po najvišjih standardih.
(smeh)
(aplavz)
08:46
(Applause)
151
514412
4752
08:51
Striking a moving ball is a necessary skill in many sports.
152
519164
3472
Zadeti premikajočo se žogo,
je nujna sposobnost v mnogih športih.
je nujna sposobnost v mnogih športih.
08:54
How do we make a machine do
153
522636
1795
Kako naprava naredi nekaj,
08:56
what an athlete does seemingly without effort?
154
524431
3753
kot naredi atlet navidez brez truda?
(smeh)
09:15
(Applause)
155
543943
6599
(aplavz)
(konec aplavza)
09:22
This quad has a racket strapped onto its head
156
550542
2650
Ta kvad ima lopar na glavi
09:25
with a sweet spot roughly the size of an apple, so not too large.
157
553192
3487
z optimalno točko v velikosti jabolka,
torej ne preveliko.
torej ne preveliko.
09:28
The following calculations are made every 20 milliseconds,
158
556679
3167
Naslednji izračuni
so narejeni vsakih 20 milisekund
so narejeni vsakih 20 milisekund
09:31
or 50 times per second.
159
559846
1756
ali 50-krat na sekundo.
09:33
We first figure out where the ball is going.
160
561602
2812
Najprej ugotovimo, kam gre žoga.
09:36
We then next calculate how the quad should hit the ball
161
564414
2437
Nato izračunamo, kako naj kvad udari žogo,
09:38
so that it flies to where it was thrown from.
162
566851
3099
da leti tja, od koder je bila vržena.
09:41
Third, a trajectory is planned that carries the quad
163
569950
4456
tretjič načrtujemo tirnico, ki ponese kvad
09:46
from its current state to the impact point with the ball.
164
574406
3024
od trenutnega mesta
na točko udarca z žogo.
na točko udarca z žogo.
09:49
Fourth, we only execute 20 milliseconds' worth of that strategy.
165
577430
3809
Četrtič, izvedemo samo 20 milisekund
te strategije.
te strategije.
09:53
Twenty milliseconds later, the whole process is repeated
166
581239
2807
Dvajset milisekund kasneje
se celoten proces ponovi,
se celoten proces ponovi,
09:56
until the quad strikes the ball.
167
584046
2243
dokler kvad ne udari žoge.
(aplavz)
10:07
(Applause)
168
595560
2646
Naprave ne samo da same
izvedejo dinamične manevre,
izvedejo dinamične manevre,
10:10
Machines can not only perform dynamic maneuvers on their own,
169
598206
3372
10:13
they can do it collectively.
170
601578
1863
to lahko počnejo v skupinah.
10:15
These three quads are cooperatively carrying a sky net.
171
603441
3587
Ti trije kvadi skupaj nosijo mrežo.
(aplavz)
10:28
(Applause)
172
616574
5411
(konec aplavza)
10:33
They perform an extremely dynamic
173
621985
2197
Izvajajo neverjetno
dinamičen in kolektiven manever,
dinamičen in kolektiven manever,
10:36
and collective maneuver
174
624182
2168
10:38
to launch the ball back to me.
175
626350
1692
da bi mi prinesli žogo nazaj.
10:40
Notice that, at full extension, these quads are vertical.
176
628042
3511
Vidite, ob popolni raztegnitvi
so ti kvadi vertikalno.
so ti kvadi vertikalno.
10:48
(Applause)
177
636486
1772
(aplavz)
10:50
In fact, when fully extended,
178
638258
2287
Ob popolni iztegnitvi
je to petkrat več kot to,
kar čuti bungee skakalec
kar čuti bungee skakalec
10:52
this is roughly five times greater than what a bungee jumper feels
179
640545
2685
10:55
at the end of their launch.
180
643230
4588
na koncu skoka.
11:03
The algorithms to do this are very similar
181
651009
2677
Algoritmi za to so zelo podobni
11:05
to what the single quad used to hit the ball back to me.
182
653686
3384
tistim, ki jih je uporabil en kvad,
da mi je odbil žogo nazaj.
da mi je odbil žogo nazaj.
11:09
Mathematical models are used to continuously re-plan
183
657070
2864
Matematično modeli so uporabljeni
za neprestano re-planiranje
za neprestano re-planiranje
11:11
a cooperative strategy 50 times per second.
184
659934
4515
kooperativne strategije
50-krat na sekundo.
50-krat na sekundo.
11:16
Everything we have seen so far has been
185
664449
1877
Vse, kar smo videli do zdaj,
so bile naprave in njihove sposobnosti.
so bile naprave in njihove sposobnosti.
11:18
about the machines and their capabilities.
186
666326
2463
11:20
What happens when we couple this machine athleticism
187
668789
3015
Kaj se zgodi, ko združimo
atletskost teh naprav
atletskost teh naprav
11:23
with that of a human being?
188
671804
1776
s človeško?
11:25
What I have in front of me is a commercial gesture sensor
189
673580
3805
Pred seboj imam komercialni
senzor gibanja,
senzor gibanja,
11:29
mainly used in gaming.
190
677385
1309
ki se uporablja pri igrah.
11:30
It can recognize what my various body parts
191
678694
1804
Lahko prepozna, kaj počnejo
deli mojega telesa v realnem času.
deli mojega telesa v realnem času.
11:32
are doing in real time.
192
680498
2048
11:34
Similar to the pointer that I used earlier,
193
682546
2116
Podobno kot kazalec,
ki sem ga uporabil prej.
ki sem ga uporabil prej.
11:36
we can use this as inputs to the system.
194
684662
2792
lahko vstavimo te vhodne podatke v sistem.
11:39
We now have a natural way of interacting
195
687454
2396
Sedaj imamo naraven način sodelovanja
11:41
with the raw athleticism of these quads with my gestures.
196
689850
4944
surove atletskosti tega kvada
z mojimi kretnjami.
z mojimi kretnjami.
12:22
(Applause)
197
730453
4400
(aplavz)
12:35
Interaction doesn't have to be virtual. It can be physical.
198
743982
4007
Interakcija ni nujno virtualna.
Lahko je fizična.
12:39
Take this quad, for example.
199
747989
1725
Poglejmo naprimer tale kvad.
12:41
It's trying to stay at a fixed point in space.
200
749714
2628
Poskuša obstati
na določeni točki v prostoru.
na določeni točki v prostoru.
12:44
If I try to move it out of the way, it fights me,
201
752342
3837
Če ga poskušam premakniti, se upira
12:48
and moves back to where it wants to be.
202
756179
4155
in se premakne tja, kjer želi biti.
A to obnašanje lahko spremenimo.
12:52
We can change this behavior, however.
203
760334
3039
12:55
We can use mathematical models
204
763373
1699
Lahko uporabimo matematične modele,
12:57
to estimate the force that I'm applying to the quad.
205
765072
3133
ki ocenijo silo, ki jo uporabim na kvadu.
13:00
Once we know this force, we can also change the laws of physics,
206
768205
3238
Ko poznamo to silo,
lahko spremenimo zakone fizike,
lahko spremenimo zakone fizike,
13:03
as far as the quad is concerned, of course.
207
771443
4499
vsaj kar se tiče kvada.
13:07
Here the quad is behaving as if it were
208
775942
2263
Tu se kvad obnaša,
kot da bi bil v viskozni tekočini.
kot da bi bil v viskozni tekočini.
13:10
in a viscous fluid.
209
778205
4365
13:14
We now have an intimate way
210
782570
2174
Sedaj imamo intimen način
sodelovanja z napravo.
sodelovanja z napravo.
13:16
of interacting with a machine.
211
784744
1849
13:18
I will use this new capability to position
212
786593
2506
To novo sposobnost bom uporabil,
da namestim
da namestim
13:21
this camera-carrying quad to the appropriate location
213
789099
2577
ta kvad s kamero na primerno lokacijo
13:23
for filming the remainder of this demonstration.
214
791676
3186
za snemanje preostanka te predstavitve.
13:36
So we can physically interact with these quads
215
804222
2768
Tako lahko fizično komuniciramo
s temi kvadi
s temi kvadi
13:38
and we can change the laws of physics.
216
806990
2403
in lahko spremenimo zakone fizike.
13:41
Let's have a little bit of fun with this.
217
809393
2313
Pozabavajmo se.
Zdaj boste videli
13:43
For what you will see next, these quads
218
811706
1704
kvade, ki se bodo obnašali,
kot bi bili na Plutonu.
kot bi bili na Plutonu.
13:45
will initially behave as if they were on Pluto.
219
813410
3496
13:48
As time goes on, gravity will be increased
220
816906
2312
Čez čas se bo gravitacija povečevala,
13:51
until we're all back on planet Earth,
221
819218
2120
dokler ne bomo nazaj na Zemlji,
a zagotavljam, da ne bomo prišli tja.
13:53
but I assure you we won't get there.
222
821338
1719
13:55
Okay, here goes.
223
823057
3501
No, gremo.
(smeh)
14:05
(Laughter)
224
833667
3412
14:34
(Laughter)
225
862778
3208
(smeh)
(aplavz)
14:37
(Applause)
226
865986
3386
14:41
Whew!
227
869372
1207
Uf!
14:46
You're all thinking now,
228
874779
1517
Sedaj si mislite,
14:48
these guys are having way too much fun,
229
876296
1975
tile se preveč zabavajo
14:50
and you're probably also asking yourself,
230
878271
2079
in najbrž se sprašujete,
14:52
why exactly are they building machine athletes?
231
880350
3936
zakaj sploh gradijo mehanične atlete?
14:56
Some conjecture that the role of play in the animal kingdom
232
884286
2652
Nekateri domnevajo,
da je vloga igre v živalskem kraljestvu,
da je vloga igre v živalskem kraljestvu,
14:58
is to hone skills and develop capabilities.
233
886938
2752
izboljšane spretnosti
in razvijanje sposobnosti.
in razvijanje sposobnosti.
15:01
Others think that it has more of a social role,
234
889690
2066
Drugi mislijo, da ima socialno vlogo,
15:03
that it's used to bind the group.
235
891756
1674
da poveže skupino.
15:05
Similarly, we use the analogy of sports and athleticism
236
893430
3533
Podobno uporabljamo
analogijo športa in atletskosti,
analogijo športa in atletskosti,
15:08
to create new algorithms for machines
237
896963
2079
da ustvarimo nove algoritme za naprave,
15:11
to push them to their limits.
238
899042
2147
da jih potisnemo do meja.
15:13
What impact will the speed of machines have on our way of life?
239
901189
3677
Kakšen vpliv bo imela hitrost
teh naprav na naša življenja?
teh naprav na naša življenja?
15:16
Like all our past creations and innovations,
240
904866
2389
Kot vsi naši pretekli izumi in inovacije,
15:19
they may be used to improve the human condition
241
907255
2827
jih lahko uporabimo
za izboljšanje kvalitete življenja
za izboljšanje kvalitete življenja
15:22
or they may be misused and abused.
242
910082
2501
ali pa bodo zlorabljeni.
15:24
This is not a technical choice we are faced with;
243
912583
1923
To ni tehnična izbira,
15:26
it's a social one.
244
914506
1755
socialna je.
15:28
Let's make the right choice,
245
916261
1390
Odločimo se prav,
15:29
the choice that brings out the best in the future of machines,
246
917651
2405
za odločitev, ki potegne najboljše
iz prihodnosti naprav,
iz prihodnosti naprav,
15:32
just like athleticism in sports
247
920056
1812
tako kot atletskost v športu
potegne najboljše iz nas.
potegne najboljše iz nas.
15:33
can bring out the best in us.
248
921868
2161
15:36
Let me introduce you to the wizards behind the green curtain.
249
924029
3450
Naj vam predstavim čarovnike
za zeleno zaveso.
za zeleno zaveso.
15:39
They're the current members of the Flying Machine Arena research team.
250
927479
2900
To so trenutni člani raziskovalne ekipe
Flying Machine Arena.
Flying Machine Arena.
15:42
(Applause)
251
930379
4769
(aplavz)
15:47
Federico Augugliaro, Dario Brescianini, Markus Hehn,
252
935148
3046
Federico Augugliaro, Dario Brescianini,
Markus Hehn, Sergei Lupashin,
Mark Muller in Robin Ritz.
Mark Muller in Robin Ritz.
15:50
Sergei Lupashin, Mark Muller and Robin Ritz.
253
938194
2824
15:53
Look out for them. They're destined for great things.
254
941018
1932
Bodite pozorni nanje.
Dosegli bodo velike stvari.
Dosegli bodo velike stvari.
15:54
Thank you.
255
942950
1178
Hvala.
15:56
(Applause)
256
944128
6354
(aplavz)
ABOUT THE SPEAKER
Raffaello D'Andrea - Autonomous systems pioneerRaffaello D'Andrea explores the possibilities of autonomous technology by collaborating with artists, engineers and entrepreneurs.
Why you should listen
Raffaello D'Andrea combines academics, business, and the arts to explore the capabilities of autonomous systems. As part of his research as professor of dynamic systems and control at the Swiss Federal Institute of Technology (ETH Zürich), he and his collaborators enchant viewers with works like the self-destructing, self-assembling Robotic Chair, or the Balancing Cube that can perch itself on its corners.
D’Andrea and his team created the Flying Machine Arena to test the gravity-defying abilities of their athletic flying robots. Building on research in the Flying Machine Arena, ETH Zürich partnered with its spin-off company Verity Studios and with Cirque du Soleil to create “Sparked,” a short film showcasing the unexpected airborne dexterity of quadcopters. D’Andrea is the co-founder of Kiva Systems, a robotics company that develops intelligent automated warehouse systems and that was acquired by Amazon in 2012.
Raffaello D'Andrea | Speaker | TED.com