ABOUT THE SPEAKER
Hod Lipson - Roboticist
Hod Lipson works at the intersection of engineering and biology, studying robots and the way they "behave" and evolve. His work has exciting implications for design and manufacturing -- and serves as a window to understand our own behavior and evolution.

Why you should listen

To say that Hod Lipson and his team at Cornell build robots is not completely accurate: They may simply set out a pile of virtual robot parts, devise some rules for assembly, and see what the parts build themselves into. They've created robots that decide for themselves how they want to walk; robots that develop a sense of what they look like; even robots that can, through trial and error, construct other robots just like themselves.

Working across disciplines -- physics, computer science, math, biology and several flavors of engineer -- the team studies techniques for self-assembly and evolution that have great implications for fields such as micro-manufacturing -- allowing tiny pieces to assemble themselves at scales heretofore impossible -- and extreme custom manufacturing (in other words, 3-D printers for the home).

His lab's Outreach page is a funhouse of tools and instructions, including the amazing Golem@Home -- a self-assembling virtual robot who lives in your screensaver.

More profile about the speaker
Hod Lipson | Speaker | TED.com
TED2007

Hod Lipson: Building "self-aware" robots

Hod Lipson izrađuje samosvjesne robote

Filmed:
1,460,460 views

Hod Lipson demostrira nekoliko svojih cool malih robota, koji imaju sposobnost učiti, razumjeti sami sebe i čak replicirati sami sebe.
- Roboticist
Hod Lipson works at the intersection of engineering and biology, studying robots and the way they "behave" and evolve. His work has exciting implications for design and manufacturing -- and serves as a window to understand our own behavior and evolution. Full bio

Double-click the English transcript below to play the video.

00:25
So, where are the robotsroboti?
0
0
2000
Dakle, što su roboti?
00:27
We'veMoramo been told for 40 yearsgodina alreadyveć that they're comingdolazak soonuskoro.
1
2000
3000
Već nam se 40 godina priča kako će se uskoro pojaviti.
00:30
Very soonuskoro they'lloni će be doing everything for us.
2
5000
3000
Ubrzo oni će raditi sve za nas:
00:33
They'llOni će be cookingkuhanje, cleaningčišćenje, buyingkupovina things, shoppingkupovina, buildingzgrada. But they aren'tnisu here.
3
8000
5000
oni će kuhati, čistiti, kupovati stvari, ići u kupovinu, graditi. Ali oni nisu ovdje.
00:38
MeanwhileU međuvremenu, we have illegalnezakonit immigrantsimigranata doing all the work,
4
13000
4000
U međuvremenu, imamo ilegalne imigrante koji rade sav taj posao,
00:42
but we don't have any robotsroboti.
5
17000
2000
ali nemamo robote.
00:44
So what can we do about that? What can we say?
6
19000
4000
Dakle, što možemo učiniti oko toga? Što možemo reći?
00:48
So I want to give a little bitbit of a differentdrugačiji perspectiveperspektiva
7
23000
4000
Dakle, želim dati malo drugačiju perspektivu
00:52
of how we can perhapsmožda look at these things in a little bitbit of a differentdrugačiji way.
8
27000
6000
o tome kako možda možemo gledati na te stvari na pomalo drugačiji način.
00:58
And this is an x-rayrendgenski pictureslika
9
33000
2000
A ovo je rendgenska snimka
01:00
of a realstvaran beetlebuba, and a SwissŠvicarski watch, back from '88. You look at that --
10
35000
5000
prave bube i švicarskog sata, iz 1988.godine. Gledate u to --
01:05
what was truepravi then is certainlysigurno truepravi todaydanas.
11
40000
2000
ono što je bilo istinito tada je definitivno istinito danas.
01:07
We can still make the pieceskomada. We can make the right pieceskomada.
12
42000
3000
Mi još uvijek možemo izraditi dijelove, mi možemo izraditi prave dijelove,
01:10
We can make the circuitrystrujni krugovi of the right computationalračunalna powervlast,
13
45000
3000
mi možemo izraditi strujne krugove prave računalne moći,
01:13
but we can't actuallyzapravo put them togetherzajedno to make something
14
48000
3000
ali mi ih zapravo ne možemo staviti zajedno kako bi napravili nešto
01:16
that will actuallyzapravo work and be as adaptiveprilagodljiv as these systemssustavi.
15
51000
5000
što će zapravo raditi i biti prilagodljivo poput ovih sustava.
01:21
So let's try to look at it from a differentdrugačiji perspectiveperspektiva.
16
56000
2000
Dakle, pokušajmo ih gledati iz druge perspektive.
01:23
Let's summonzvati the bestnajbolje designerdizajner, the mothermajka of all designersdizajneri.
17
58000
4000
Pozovimo najboljeg dizajnera, majku svih dizajnera:
01:27
Let's see what evolutionevolucija can do for us.
18
62000
3000
da vidimo što evolucija može učiniti za nas.
01:30
So we threwbacio in -- we createdstvorio a primordialpraiskonski soupjuha
19
65000
4000
Dakle, ubacili smo -- stvorili smo praiskonsku juhu
01:34
with lots of pieceskomada of robotsroboti -- with barsbarovi, with motorsmotori, with neuronsneuroni.
20
69000
4000
s mnogim dijelovima robota: sa šipkama, s motorima, s neuronima.
01:38
Put them all togetherzajedno, and put all this underpod kindljubazan of naturalprirodni selectionizbor,
21
73000
4000
Stavite ih sve zajedno, i stavite sve to pod jednu vrstu prirodne selekcije,
01:42
underpod mutationmutacija, and rewardednagrađeni things for how well they can movepotez forwardnaprijed.
22
77000
4000
pod mutaciju, i nagrađene stvari ovisno o tome kako dobro se mogu kretati naprijed.
01:46
A very simplejednostavan taskzadatak, and it's interestingzanimljiv to see what kindljubazan of things camedošao out of that.
23
81000
6000
Jako jednostavan zadatak, i zanimljivo je vidjeti kakve vrste stvari su proizašle iz toga.
01:52
So if you look, you can see a lot of differentdrugačiji machinesstrojevi
24
87000
3000
Ako pogledate, možete vidjeti kako je mnogo različitih strojeva
01:55
come out of this. They all movepotez around.
25
90000
2000
proizašlo iz toga. Svi se oni kreću okolo,
01:57
They all crawlpuzati in differentdrugačiji waysnačine, and you can see on the right,
26
92000
4000
svi oni pužu u različitim smjerovima, i možete vidjeti ovdje na desnoj strani,
02:01
that we actuallyzapravo madenapravljen a couplepar of these things,
27
96000
2000
da smo zapravo napravili par tih stvari,
02:03
and they work in realitystvarnost. These are not very fantasticfantastičan robotsroboti,
28
98000
3000
i one rade u stvarnosti. Ovo nisu jako fantastični roboti,
02:06
but they evolvedrazvio to do exactlytočno what we rewardnagrada them for:
29
101000
4000
ali su evoluirali do toga da rade točno ono za što ih nagrađujemo:
02:10
for movingkreće forwardnaprijed. So that was all doneučinio in simulationsimuliranje,
30
105000
3000
za kretanje unaprijed. Dakle, to je sve napravljeno pomoću simulacije,
02:13
but we can alsotakođer do that on a realstvaran machinemašina.
31
108000
2000
ali možemo to učiniti i na pravom stroju.
02:15
Here'sOvdje je a physicalfizička robotrobot that we actuallyzapravo
32
110000
5000
Ovdje je fizički robot kojem smo zapravo
02:20
have a populationpopulacija of brainsmozak,
33
115000
3000
usadili mozak,
02:23
competingnatječu, or evolvingrazvojni on the machinemašina.
34
118000
2000
koji se takmiči, ili evoluira, na stroju.
02:25
It's like a rodeorodeo showpokazati. They all get a ridevožnja on the machinemašina,
35
120000
3000
To je poput rodea: svi oni dobiju vožnju na stroju,
02:28
and they get rewardednagrađeni for how fastbrzo or how fardaleko
36
123000
3000
i svi oni budu nagrađeni ovisno kako brzo ili kako daleko
02:31
they can make the machinemašina movepotez forwardnaprijed.
37
126000
2000
mogu natjerati stroj da se kreće naprijed.
02:33
And you can see these robotsroboti are not readyspreman
38
128000
2000
I možete vidjeti da ti roboti nisu spremni
02:35
to take over the worldsvijet yetjoš, but
39
130000
3000
da preuzmu svijet još, ali
02:38
they graduallypostepeno learnnaučiti how to movepotez forwardnaprijed,
40
133000
2000
oni postepeno uče kako se kretati naprijed,
02:40
and they do this autonomouslysamostalno.
41
135000
3000
i to rade samostalno.
02:43
So in these two examplesprimjeri, we had basicallyu osnovi
42
138000
4000
Dakle, u ova dva primjera, mi smo u osnovi imali
02:47
machinesstrojevi that learnednaučeno how to walkhodati in simulationsimuliranje,
43
142000
3000
strojeve koji su učili kako hodati u simulaciji,
02:50
and alsotakođer machinesstrojevi that learnednaučeno how to walkhodati in realitystvarnost.
44
145000
2000
i isto tako strojeve koji su učili kako hodati u stvarnosti.
02:52
But I want to showpokazati you a differentdrugačiji approachpristup,
45
147000
2000
Ali želim vam pokazati drugačiji pristup,
02:54
and this is this robotrobot over here, whichkoji has fourčetiri legsnoge.
46
149000
6000
a to je ovaj robot, ovdje, koji ima četiri noge,
03:00
It has eightosam motorsmotori, fourčetiri on the kneeskoljena and fourčetiri on the hipkuk.
47
155000
2000
ima osam motora, četiri na koljenima i četiri na boku.
03:02
It has alsotakođer two tiltnagib sensorssenzori that tell the machinemašina
48
157000
3000
Ujedno ima i dva nagibna senzora koji govore stroju
03:05
whichkoji way it's tiltingNagibni.
49
160000
3000
u kojem smjeru je nagib.
03:08
But this machinemašina doesn't know what it looksizgled like.
50
163000
2000
Ali ovaj stroj ne zna kako izgleda.
03:10
You look at it and you see it has fourčetiri legsnoge,
51
165000
2000
Gledate u njega i vidite da ima četiri noge,
03:12
the machinemašina doesn't know if it's a snakezmija, if it's a treedrvo,
52
167000
2000
stroj ne zna je li to zmija, ili drvo,
03:14
it doesn't have any ideaideja what it looksizgled like,
53
169000
3000
nema nikakvu ideju o tome kako izgleda,
03:17
but it's going to try to find that out.
54
172000
2000
ali pokušat će to doznati.
03:19
InitiallyU početku, it does some randomslučajan motionpokret,
55
174000
2000
Inicijalno, radi neke nasumične pokrete,
03:21
and then it triespokušava to figurelik out what it mightmoć look like.
56
176000
3000
i zatim pokušava dokučiti na što bi mogao ličiti --
03:24
And you're seeingvidim a lot of things passingpretjecanje throughkroz its mindsmisli,
57
179000
2000
i vidite mnogo stvari koje prolaze kroz njegove misli,
03:26
a lot of self-modelsSelf-modeli that try to explainobjasniti the relationshipodnos
58
181000
4000
mnogo samo-modela koji pokušavaju objasniti vezu
03:30
betweenizmeđu actuationpotisku spreja and sensingočitavanje. It then triespokušava to do
59
185000
3000
između stavljanja u pokret i osjećanja -- i zatim pokušava uraditi
03:33
a seconddrugi actionakcijski that createsstvara the mostnajviše disagreementneslaganje
60
188000
4000
drugu radnju koja stvara najviše neslaganja
03:37
amongmeđu predictionspredviđanja of these alternativealternativa modelsmodeli,
61
192000
2000
između predviđanja tih opcijskih modela,
03:39
like a scientistnaučnik in a lablaboratorija. Then it does that
62
194000
2000
poput znanstvenika u laboratoriju. Zatim radi to
03:41
and triespokušava to explainobjasniti that, and prunešljiva out its self-modelsSelf-modeli.
63
196000
4000
i pokušava to objasniti, i izrezati vlastite samo-modele.
03:45
This is the last cycleciklus, and you can see it's prettyprilično much
64
200000
3000
Ovo je posljednji ciklus, i možete vidjeti da je više-manje
03:48
figuredshvaćen out what its selfsam looksizgled like. And oncejednom it has a self-modelSelf-model,
65
203000
4000
dokučio kako njegovo biće izgleda, i jednom kada ima samo-model,
03:52
it can use that to deriveizvući a patternuzorak of locomotionmotorički.
66
207000
4000
može to iskoristiti da izvuće uzorak kretanja.
03:56
So what you're seeingvidim here are a couplepar of machinesstrojevi --
67
211000
2000
Dakle, ono što vidite ovdje je par strojeva --
03:58
a patternuzorak of locomotionmotorički.
68
213000
2000
uzorak kretanja.
04:00
We were hopingnadajući that it wassmogao uoËiti going to have a kindljubazan of evilzlo, spideryprofinjenije walkhodati,
69
215000
4000
Nadali smo se kako će imati tu neku vrstu zlobnog, paukovskog hoda,
04:04
but insteadumjesto it createdstvorio this prettyprilično lamejadan way of movingkreće forwardnaprijed.
70
219000
4000
ali umjesto toga, stvorio je prilično jadan način kretanja naprijed.
04:08
But when you look at that, you have to rememberzapamtiti
71
223000
3000
Ali kada to gledate, morate upamtiti
04:11
that this machinemašina did not do any physicalfizička trialsispitivanja on how to movepotez forwardnaprijed,
72
226000
6000
kako taj stroj nije radio nikakve fizičke pokuse kako se kretati unaprijed,
04:17
norni did it have a modelmodel of itselfsebe.
73
232000
2000
niti je imao model samog sebe.
04:19
It kindljubazan of figuredshvaćen out what it looksizgled like, and how to movepotez forwardnaprijed,
74
234000
3000
Nekako je sam dokučio kako izgleda, i kako se treba kretati naprijed,
04:22
and then actuallyzapravo triedpokušala that out.
75
237000
4000
i zatim je zapravo to pokušao.
04:26
(ApplausePljesak)
76
241000
5000
(Pljesak)
04:31
So, we'lldobro movepotez forwardnaprijed to a differentdrugačiji ideaideja.
77
246000
4000
Dakle, mi ćemo krenuti na drugačiju ideju.
04:35
So that was what happeneddogodilo when we had a couplepar of --
78
250000
5000
Dakle, to se dogodilo kada smo imali par --
04:40
that's what happeneddogodilo when you had a couplepar of -- OK, OK, OK --
79
255000
4000
to se dogodilo kada si imao par -- OK, OK, OK --
04:44
(LaughterSmijeh)
80
259000
2000
(Smijeh)
04:46
-- they don't like eachsvaki other. So
81
261000
2000
-- ne vole jedan drugoga. Dakle,
04:48
there's a differentdrugačiji robotrobot.
82
263000
3000
ovdje je različit robot.
04:51
That's what happeneddogodilo when the robotsroboti actuallyzapravo
83
266000
2000
To je ono što se dogodilo kada roboti zapravo
04:53
are rewardednagrađeni for doing something.
84
268000
2000
budu nagrađeni za nešto što su napravili.
04:55
What happensdogađa se if you don't rewardnagrada them for anything, you just throwbacanje them in?
85
270000
3000
Što se događa ako ih ne nagradite za bilošto, već ih samo ubacite unutra?
04:58
So we have these cubeskocke, like the diagramdijagram showedpokazala here.
86
273000
3000
Dakle, imamo te kocke, kako je to ovdje prikazano na dijagramu.
05:01
The cubekocka can swivelOkretni, or flipdrzak on its sidestrana,
87
276000
2000
Kocka se može okretati, ili se preokrenuti na stranu,
05:04
and we just throwbacanje 1,000 of these cubeskocke into a soupjuha --
88
279000
4000
i mi samo ubacimo 1.000 takvih kocki u juhu --
05:08
this is in simulationsimuliranje --and--i don't rewardnagrada them for anything,
89
283000
2000
ovo je u simulaciji -- i ne nagradimo ih za išta,
05:10
we just let them flipdrzak. We pumppumpa energyenergija into this
90
285000
3000
jednostavno im damo da polude. Upumpavamo energiju u to
05:13
and see what happensdogađa se in a couplepar of mutationsmutacije.
91
288000
3000
i vidimo što se događa u par mutacija.
05:16
So, initiallyu početku nothing happensdogađa se, they're just flippingpreklapanje around there.
92
291000
3000
Dakle, inicijalno, ništa se ne događa, samo lude tamo.
05:19
But after a very shortkratak while, you can see these blueplava things
93
294000
4000
Ali nedugo nakon toga, možete vidjeti ove plave stvari
05:23
on the right there beginpočeti to take over.
94
298000
2000
na desnoj strani koje počinju preuzimati.
05:25
They beginpočeti to self-replicateSelf-odgovor. So in absenceodsutnost of any rewardnagrada,
95
300000
4000
Počinju se samo-razmnožavati. Dakle, u odsustvu ikakve nagrade,
05:29
the intrinsicintrinzična rewardnagrada is self-replicationsamo-odgovor.
96
304000
3000
intrinzična nagrada je samo-razmnožavanje.
05:32
And we'veimamo actuallyzapravo builtizgrađen a couplepar of these,
97
307000
1000
I mi smo zapravo izradili par tih,
05:33
and this is partdio of a largerveći robotrobot madenapravljen out of these cubeskocke.
98
308000
4000
i to je dio većeg robota koji je napravljen od tih kocki,
05:37
It's an acceleratedubrzan viewpogled, where you can see the robotrobot actuallyzapravo
99
312000
3000
to je ubrzan prikaz, gdje možete vidjeti kako robot zapravo
05:40
carryingnošenje out some of its replicationodgovor processpostupak.
100
315000
2000
prolazi kroz neki od procesa razmnožavanja.
05:42
So you're feedinghranjenje it with more materialmaterijal -- cubeskocke in this casespis --
101
317000
4000
Dakle, hranite ga s više materijala -- kocki u ovom slučaju --
05:46
and more energyenergija, and it can make anotherjoš robotrobot.
102
321000
3000
i više energije, i može stvoriti još jedan robot.
05:49
So of coursenaravno, this is a very crudeSirovi machinemašina,
103
324000
3000
Dakle, naravno, ovo je vrlo sirov stroj,
05:52
but we're workingrad on a micro-scalemikro-skali versionverzija of these,
104
327000
2000
ali radimo na mikro-verziji njih,
05:54
and hopefullynadajmo se the cubeskocke will be like a powderpuder that you poursipati in.
105
329000
3000
i nadamo se kako će te kocke biti poput praha koji ulijete.
05:57
OK, so what can we learnnaučiti? These robotsroboti are of coursenaravno
106
332000
5000
U redu, dakle, što možemo naučiti? Ti roboti naravno
06:02
not very usefulkoristan in themselvesse, but they mightmoć teachučiti us something
107
337000
3000
nisu sami po sebi korisni, ali bi nas mogli naučiti nešto
06:05
about how we can buildizgraditi better robotsroboti,
108
340000
3000
o tome kako možemo izraditi bolje robote,
06:08
and perhapsmožda how humansljudi, animalsživotinje, createstvoriti self-modelsSelf-modeli and learnnaučiti.
109
343000
5000
i možda kako ljudi, životinje, stvaraju samo-modele i uče.
06:13
And one of the things that I think is importantvažno
110
348000
2000
I jedna od stvari za koju smatram da je važna
06:15
is that we have to get away from this ideaideja
111
350000
2000
da se moramo odmaknuti od te ideje
06:17
of designingprojektiranje the machinesstrojevi manuallyručno,
112
352000
2000
ručnog dizajniranja strojeva,
06:19
but actuallyzapravo let them evolverazviti and learnnaučiti, like childrendjeca,
113
354000
3000
već im dopustiti da evoluiraju i uče, poput djece,
06:22
and perhapsmožda that's the way we'lldobro get there. Thank you.
114
357000
2000
i možda je to način da stignemo tamo. Hvala vam.
06:24
(ApplausePljesak)
115
359000
2000
(Pljesak)

▲Back to top

ABOUT THE SPEAKER
Hod Lipson - Roboticist
Hod Lipson works at the intersection of engineering and biology, studying robots and the way they "behave" and evolve. His work has exciting implications for design and manufacturing -- and serves as a window to understand our own behavior and evolution.

Why you should listen

To say that Hod Lipson and his team at Cornell build robots is not completely accurate: They may simply set out a pile of virtual robot parts, devise some rules for assembly, and see what the parts build themselves into. They've created robots that decide for themselves how they want to walk; robots that develop a sense of what they look like; even robots that can, through trial and error, construct other robots just like themselves.

Working across disciplines -- physics, computer science, math, biology and several flavors of engineer -- the team studies techniques for self-assembly and evolution that have great implications for fields such as micro-manufacturing -- allowing tiny pieces to assemble themselves at scales heretofore impossible -- and extreme custom manufacturing (in other words, 3-D printers for the home).

His lab's Outreach page is a funhouse of tools and instructions, including the amazing Golem@Home -- a self-assembling virtual robot who lives in your screensaver.

More profile about the speaker
Hod Lipson | Speaker | TED.com