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 contruieste roboti "constienti de sine"

Filmed:
1,460,460 views

Hod Lipson face o demonstratie cu roboteii lui, care sunt capabili sa invete, sa se intelega unul pe celalalt si chiar sa se autoreproduca.
- 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 robotsroboți?
0
0
2000
Deci, unde sunt robotii?
00:27
We'veNe-am been told for 40 yearsani alreadydeja that they're comingvenire sooncurând.
1
2000
3000
De 40 de ani ni se spune ca vor veni in curand.
00:30
Very sooncurând they'llei vor be doing everything for us.
2
5000
3000
In curand o sa faca totul in locul nostru:
00:33
They'llEle vor be cookinggătire, cleaningcurățenie, buyingcumpărare things, shoppingcumpărături, buildingclădire. But they aren'tnu sunt here.
3
8000
5000
o sa gateasca,o sa faca curat,o sa faca cumparaturi, o sa construiasca.Dar nu sunt aici.
00:38
MeanwhileÎntre timp, we have illegalilegal immigrantsimigranţi doing all the work,
4
13000
4000
Intre timp ,avem imigranti ilegali care fac toata treaba,
00:42
but we don't have any robotsroboți.
5
17000
2000
dar nu avem nici un robot.
00:44
So what can we do about that? What can we say?
6
19000
4000
Asa ca ce putem sa facem? Ce putem sa spunem?
00:48
So I want to give a little bitpic of a differentdiferit perspectiveperspectivă
7
23000
4000
As vrea sa va arat o modalitate alternativa
00:52
of how we can perhapspoate look at these things in a little bitpic of a differentdiferit way.
8
27000
6000
despre cum ne putem uita la lucruri intr-un mod putin diferit.
00:58
And this is an x-rayraze X pictureimagine
9
33000
2000
Aceasta este o radiografie
01:00
of a realreal beetlegândac, and a SwissElveţian watch, back from '88. You look at that --
10
35000
5000
a unui gandac adevarat, si a unui ceas elvetian, din '88.Te uiti la --
01:05
what was trueAdevărat then is certainlycu siguranță trueAdevărat todayastăzi.
11
40000
2000
ce era adevarat atunci cu siguranta este adevarat si astazi.
01:07
We can still make the piecesbucăți. We can make the right piecesbucăți.
12
42000
3000
Inca mai putem sa fabricam piesele, putem face piesele corecte.
01:10
We can make the circuitrycircuite of the right computationalcomputațională powerputere,
13
45000
3000
putem sa facem o placuta cu circuite de calcul,
01:13
but we can't actuallyde fapt put them togetherîmpreună to make something
14
48000
3000
dar nu putem sa le punem la un loc sa facem ceva anume
01:16
that will actuallyde fapt work and be as adaptiveadaptivă as these systemssisteme.
15
51000
5000
care sa functioneze cu adevarat si sa fie capabil sa se adapteze la fel ca aceste sisteme.
01:21
So let's try to look at it from a differentdiferit perspectiveperspectivă.
16
56000
2000
Asa ca sa incercam sa privim lucrurile dintr-o alta perspectiva.
01:23
Let's summonconvoca the bestCel mai bun designerproiectant, the mothermamă of all designersdesigneri.
17
58000
4000
Sa-l luam pe cel mai bun designer, cel mai bun designer dintre toti:
01:27
Let's see what evolutionevoluţie can do for us.
18
62000
3000
sa vedem ce poate face evolutia pentru noi.
01:30
So we threwaruncat in -- we createdcreată a primordialprimordial soupsupă
19
65000
4000
Asa ca am amestecat-- am creat supa primordiala
01:34
with lots of piecesbucăți of robotsroboți -- with barsbaruri, with motorsmotoare, with neuronsneuroni.
20
69000
4000
cu multe bucati de roboti : cu fiare, cu motoare , cu neuroni.
01:38
Put them all togetherîmpreună, and put all this undersub kinddrăguț of naturalnatural selectionselecţie,
21
73000
4000
Le adunam pe toate la un loc, si le supunem unui fel de proces natural de selectie,
01:42
undersub mutationmutaţie, and rewardedrecompensat things for how well they can movemișcare forwardredirecţiona.
22
77000
4000
unui proces de transformare, si vedem cat de bine au sa evolueze.
01:46
A very simplesimplu tasksarcină, and it's interestinginteresant to see what kinddrăguț of things camea venit out of that.
23
81000
6000
O sarcina foarte simpla, si e interesant de vazut ce fel de chestii rezulta.
01:52
So if you look, you can see a lot of differentdiferit machinesmaşini
24
87000
3000
Asa ca daca va uitati, o sa vedeti o gramada de masinarii diferite
01:55
come out of this. They all movemișcare around.
25
90000
2000
care au iesit din asta.Toate se misca,
01:57
They all crawlcrawl in differentdiferit waysmoduri, and you can see on the right,
26
92000
4000
intr-un fel sau altul,puteti vedea in dreapta,
02:01
that we actuallyde fapt madefăcut a couplecuplu of these things,
27
96000
2000
chiar am creat niste chestii de astea,
02:03
and they work in realityrealitate. These are not very fantasticfantastic robotsroboți,
28
98000
3000
si chiar functioneaza. Nu sunt cine stie ce roboti,
02:06
but they evolvedevoluat to do exactlyexact what we rewardrecompensă them for:
29
101000
4000
dar au evoluat si au ajuns sa facea ce le-am cerut:
02:10
for movingin miscare forwardredirecţiona. So that was all doneTerminat in simulationsimulare,
30
105000
3000
se mearga inainte.Toate aceastea au fost facute intr-o simulare,
02:13
but we can alsode asemenea do that on a realreal machinemaşină.
31
108000
2000
dar putem face asta si cu o masinarie reala.
02:15
Here'sAici este a physicalfizic robotrobot that we actuallyde fapt
32
110000
5000
Acesta este un robot pe care avem
02:20
have a populationpopulație of brainscreier,
33
115000
3000
o populatie de creiere,
02:23
competingconcurent, or evolvingevoluție on the machinemaşină.
34
118000
2000
care concureaza unele cu celelalte, sau evoluaza, pe robot.
02:25
It's like a rodeoțarc showspectacol. They all get a ridecălătorie on the machinemaşină,
35
120000
3000
E ca la un rodeo show: toti apuca sa controleze masinaria,
02:28
and they get rewardedrecompensat for how fastrapid or how fardeparte
36
123000
3000
si sunt recompensati pentru cat de repede sau cat de departe
02:31
they can make the machinemaşină movemișcare forwardredirecţiona.
37
126000
2000
au facut masinaria sa mearga.
02:33
And you can see these robotsroboți are not readygata
38
128000
2000
Dupa cum vedeti acesti roboti nu sunt gata inca
02:35
to take over the worldlume yetinca, but
39
130000
3000
sa preia controlul asupra lumii,dar
02:38
they graduallytreptat learnînvăța how to movemișcare forwardredirecţiona,
40
133000
2000
invata treptat cum sa se miste inainte,
02:40
and they do this autonomouslyautonom.
41
135000
3000
si fac aceste lucru in mod autonom.
02:43
So in these two examplesexemple, we had basicallype scurt
42
138000
4000
Deci in aceste doua exemple, am avut de fapt
02:47
machinesmaşini that learnedînvățat how to walkmers pe jos in simulationsimulare,
43
142000
3000
masinarii care au invatat cum sa mearga intr-o simulare,
02:50
and alsode asemenea machinesmaşini that learnedînvățat how to walkmers pe jos in realityrealitate.
44
145000
2000
si masinarii care au invatat sa mearga in realitate.
02:52
But I want to showspectacol you a differentdiferit approachabordare,
45
147000
2000
Dar vreau sa va arat o abordare diferita,
02:54
and this is this robotrobot over here, whichcare has fourpatru legspicioare.
46
149000
6000
si acesta este robotul, aici, care are patru picioare,
03:00
It has eightopt motorsmotoare, fourpatru on the kneesgenunchi and fourpatru on the hipşold.
47
155000
2000
are opt motoare , patru la genunchi si patru la solduri.
03:02
It has alsode asemenea two tiltînclinare sensorssenzori that tell the machinemaşină
48
157000
3000
Mai are si doi senzori care ii spun masinariei
03:05
whichcare way it's tiltingÎnclinarea.
49
160000
3000
in ce parte sa se incline.
03:08
But this machinemaşină doesn't know what it looksarată like.
50
163000
2000
Dar aceasta masinarie nu stie cum arata.
03:10
You look at it and you see it has fourpatru legspicioare,
51
165000
2000
Tu te uiti la ea si vezi ca are patru picioare,
03:12
the machinemaşină doesn't know if it's a snakesarpe, if it's a treecopac,
52
167000
2000
masinaria nu stie daca e un sarpe, daca e un copac,
03:14
it doesn't have any ideaidee what it looksarată like,
53
169000
3000
nu are nici o idee despre cum arata,
03:17
but it's going to try to find that out.
54
172000
2000
dar o sa incerce sa afle.
03:19
InitiallyIniţial, it does some randomîntâmplător motionmişcare,
55
174000
2000
Initial, o sa incerce niste miscari aleatorii,
03:21
and then it triesîncercări to figurefigura out what it mightar putea look like.
56
176000
3000
si apoi incearca sa afle cum arata --
03:24
And you're seeingvedere a lot of things passingtrecere throughprin its mindsminți,
57
179000
2000
si vedeti cum o gramada de lucruri ii trec prin minte,
03:26
a lot of self-modelsauto-modele that try to explainexplica the relationshiprelaţie
58
181000
4000
o gramada de auto-modele care incearca sa explice relatia
03:30
betweenîntre actuationAcționarea comutatorului and sensingdetectare. It then triesîncercări to do
59
185000
3000
dintre actiune si raspuns-- si apoi incearca
03:33
a secondal doilea actionacțiune that createscreează the mostcel mai disagreementdezacord
60
188000
4000
o a doua actiune care creaza dezacord
03:37
amongprintre predictionsPredictii of these alternativealternativă modelsmodele,
61
192000
2000
printre predictiile modelelor alternative,
03:39
like a scientistom de stiinta in a lablaborator. Then it does that
62
194000
2000
ca un om de stiinta intr-un laborator. Apoi face asta
03:41
and triesîncercări to explainexplica that, and pruneprune out its self-modelsauto-modele.
63
196000
4000
si incearca sa explice, si sa isi intreaca concurentii.
03:45
This is the last cycleciclu, and you can see it's prettyfrumos much
64
200000
3000
Acesta e ultimul ciclu, si dupa cum puteti vedea
03:48
figuredimaginat out what its selfde sine looksarată like. And onceo singura data it has a self-modelauto-model,
65
203000
4000
si-a dat seama cum arata,odata ce a avut un model dupa care sa se ia,
03:52
it can use that to derivederiva a patternmodel of locomotionlocomoţie.
66
207000
4000
se poate lua dupa asta ca sa isi creeze un tipar de locomotie.
03:56
So what you're seeingvedere here are a couplecuplu of machinesmaşini --
67
211000
2000
Deci ce vedeti aici este o adunatura de masinarii--
03:58
a patternmodel of locomotionlocomoţie.
68
213000
2000
un tipar de locomotie.
04:00
We were hopingîn speranța that it wassLaura going to have a kinddrăguț of evilrău, spiderypăianjen walkmers pe jos,
69
215000
4000
Speram ca o sa aiba un mers "smecher" ,ca al unui paianjen,
04:04
but insteadin schimb it createdcreată this prettyfrumos lameșchiop way of movingin miscare forwardredirecţiona.
70
219000
4000
dar in schimb,si-a creat acest mod nasol de a se misca inspre inainte.
04:08
But when you look at that, you have to remembertine minte
71
223000
3000
Dar cand te uiti la asta , trebuie sa tii cont
04:11
that this machinemaşină did not do any physicalfizic trialsîncercări on how to movemișcare forwardredirecţiona,
72
226000
6000
ca aceasta masinarie nu stia cum sa se miste inainte,
04:17
nornici did it have a modelmodel of itselfîn sine.
73
232000
2000
nici nu stia cum arata.
04:19
It kinddrăguț of figuredimaginat out what it looksarată like, and how to movemișcare forwardredirecţiona,
74
234000
3000
Si-a dat seama cum arata , si cum sa se miste,
04:22
and then actuallyde fapt triedîncercat that out.
75
237000
4000
si apoi a facut o incercare.
04:26
(ApplauseAplauze)
76
241000
5000
(Aplauze)
04:31
So, we'llbine movemișcare forwardredirecţiona to a differentdiferit ideaidee.
77
246000
4000
Asa, se ne indreptam atentia spre o idee diferita.
04:35
So that was what happeneds-a întâmplat when we had a couplecuplu of --
78
250000
5000
Deci asta sa intamplat cand am avut o gramada de --
04:40
that's what happeneds-a întâmplat when you had a couplecuplu of -- OK, OK, OK --
79
255000
4000
asta sa intamplat cand am avut o gramada de -- Ok ,Ok ,Ok--
04:44
(LaughterRâs)
80
259000
2000
(Rasete)
04:46
-- they don't like eachfiecare other. So
81
261000
2000
-- nu se plac.Deci
04:48
there's a differentdiferit robotrobot.
82
263000
3000
e un robot diferit.
04:51
That's what happeneds-a întâmplat when the robotsroboți actuallyde fapt
83
266000
2000
Asta sa intamplat cand robotii
04:53
are rewardedrecompensat for doing something.
84
268000
2000
au fost recompensati pentru ca fac ceva.
04:55
What happensse întâmplă if you don't rewardrecompensă them for anything, you just throwarunca them in?
85
270000
3000
Dar ce se intampla cand nu ii recompensezi, doar ii arunci acolo?
04:58
So we have these cubescuburi, like the diagramdiagramă showeda arătat here.
86
273000
3000
Deci avem cuburile astea,dupa cum arata diagrama asta.
05:01
The cubecub can swivelpivotant, or flipflip- on its sidelatură,
87
276000
2000
Cubul poate sa pivoteze ,sau sa sara pe o parte,
05:04
and we just throwarunca 1,000 of these cubescuburi into a soupsupă --
88
279000
4000
si aruncam 1,000 de cuburi de astea intr-o supa--
05:08
this is in simulationsimulare --and--şi don't rewardrecompensă them for anything,
89
283000
2000
asta intr-o simulare-- si nu ii recompensam pentru nimic.
05:10
we just let them flipflip-. We pumppompa energyenergie into this
90
285000
3000
ii lasam acolo sa sara. Le dam energie
05:13
and see what happensse întâmplă in a couplecuplu of mutationsmutații.
91
288000
3000
si vedem ce se intampla in cateva mutatii.
05:16
So, initiallyinițial nothing happensse întâmplă, they're just flippingflipping around there.
92
291000
3000
Initial, nimic nu se intampla, doar sar de colo colo.
05:19
But after a very shortmic de statura while, you can see these bluealbastru things
93
294000
4000
Dar dupa o scurta perioada de timp,puteti vedea aceste chestii albastre
05:23
on the right there beginÎNCEPE to take over.
94
298000
2000
din dreapta incep sa preia controlul.
05:25
They beginÎNCEPE to self-replicateauto-reproduc. So in absenceabsență of any rewardrecompensă,
95
300000
4000
Incep sa se auto-reproduca.Asa ca in absenta vreunei recompense,
05:29
the intrinsicintrinsecă rewardrecompensă is self-replicationautoreplicare.
96
304000
3000
propria recompensa este auto-reproducerea.
05:32
And we'vene-am actuallyde fapt builtconstruit a couplecuplu of these,
97
307000
1000
Si chiar am construit cativa din astia ,
05:33
and this is partparte of a largermai mare robotrobot madefăcut out of these cubescuburi.
98
308000
4000
si asta e o parte dintr-un robot mai mare facut din aceste cuburi,
05:37
It's an acceleratedaccelerat viewvedere, where you can see the robotrobot actuallyde fapt
99
312000
3000
e o filmare accelerata, in care puteti vedea cum robotul
05:40
carryingpurtător out some of its replicationreplică processproces.
100
315000
2000
urmeaza pasii spre procesul de replicare.
05:42
So you're feedinghrănire it with more materialmaterial -- cubescuburi in this casecaz --
101
317000
4000
Deci o hranim cu mai mult material-- cuburi in cazul de fata--
05:46
and more energyenergie, and it can make anothero alta robotrobot.
102
321000
3000
si mai multa energie, si poate face un alt robot.
05:49
So of coursecurs, this is a very crudebrut machinemaşină,
103
324000
3000
Dar desigur , aceasta este o masinarie foarte primitiva,
05:52
but we're workinglucru on a micro-scalemicro-scară versionversiune of these,
104
327000
2000
dar lucram la versiuni microscopice ale acestor masinarii,
05:54
and hopefullyin speranta the cubescuburi will be like a powderpudra that you pourturna in.
105
329000
3000
si speram ca ,cuburile o sa fie ca o pudra pe care o adaugi.
05:57
OK, so what can we learnînvăța? These robotsroboți are of coursecurs
106
332000
5000
OK, deci ce putem invatat? Acesti roboti nu sunt desigur
06:02
not very usefulutil in themselvesînșiși, but they mightar putea teacha preda us something
107
337000
3000
foarte folositori, dar ne pot invata cate ceva
06:05
about how we can buildconstrui better robotsroboți,
108
340000
3000
despre cum putem sa contruim roboti mai buni,
06:08
and perhapspoate how humansoameni, animalsanimale, createcrea self-modelsauto-modele and learnînvăța.
109
343000
5000
si poate cum oameni , animalele, pot crea auto-modele si invata.
06:13
And one of the things that I think is importantimportant
110
348000
2000
Si unul din lucrurile pe care il consider important
06:15
is that we have to get away from this ideaidee
111
350000
2000
este acela ca trebuie sa ne indepartam de idea
06:17
of designingproiect the machinesmaşini manuallymanual,
112
352000
2000
de a proiecta manual masinariile,
06:19
but actuallyde fapt let them evolveevolua and learnînvăța, like childrencopii,
113
354000
3000
si in schimb sa le lasam sa evolueze si sa invete,precum copiii,
06:22
and perhapspoate that's the way we'llbine get there. Thank you.
114
357000
2000
si poate in felul acesta o sa reusim . Multumesc.
06:24
(ApplauseAplauze)
115
359000
2000
(Aplauze)
Translated by Tita Mihai
Reviewed by Mîrzac Iulian

▲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