Self-Assembling Robots and the Potential of Artificial Evolution | Emma Hart | TED

76,908 views ใƒป 2022-04-01

TED


ืื ื ืœื—ืฅ ืคืขืžื™ื™ื ืขืœ ื”ื›ืชื•ื‘ื™ื•ืช ื‘ืื ื’ืœื™ืช ืœืžื˜ื” ื›ื“ื™ ืœื”ืคืขื™ืœ ืืช ื”ืกืจื˜ื•ืŸ.

ืชืจื’ื•ื: zeeva livshitz ืขืจื™ื›ื”: Ido Dekkers
00:04
Imagine a scientist
0
4876
1251
ื“ืžื™ื™ื ื• ืœืขืฆืžื›ื ืžื“ืขื ื™ืช
00:06
who wants to send a robot to explore in a faraway place,
1
6127
3587
ืฉืจื•ืฆื” ืœืฉืœื•ื— ืจื•ื‘ื•ื˜ ืœื—ืงื•ืจ ื‘ืžืงื•ื ืจื—ื•ืง,
00:09
a place whose geography might be completely unknown
2
9756
2628
ืœืžืงื•ื ืฉื”ื’ื™ืื•ื’ืจืคื™ื” ืฉืœื• ืขืฉื•ื™ื” ืœื”ื™ื•ืช ื‘ืœืชื™ ื™ื“ื•ืขื” ืœื—ืœื•ื˜ื™ืŸ
00:12
and perhaps inhospitable.
3
12425
2044
ื•ืื•ืœื™ ืœื ืžืกื‘ื™ืจืช ืคื ื™ื.
00:15
Now imagine that instead of first designing that robot
4
15387
3670
ืขื›ืฉื™ื• ื“ืžื™ื™ื ื• ืฉื‘ืžืงื•ื ื”ืชื›ื ื•ืŸ ื”ืจืืฉื•ืŸ ืฉืœ ื”ืจื•ื‘ื•ื˜ ื”ื–ื”
00:19
and sending it off in the hope that it might be suitable,
5
19099
3295
ื•ืฉืœื™ื—ืชื• ื‘ืชืงื•ื•ื” ืฉื”ื•ื ืขืฉื•ื™ ืœื”ืชืื™ื,
00:22
instead, she sends a robot-producing technology
6
22435
3796
ื‘ืžืงื•ื ื–ื”, ื”ื™ื ืฉื•ืœื—ืช ื˜ื›ื ื•ืœื•ื’ื™ื” ืœื™ื™ืฆื•ืจ ืจื•ื‘ื•ื˜ื™ื
00:26
that figures out what kind of robot is needed once it arrives,
7
26273
3503
ืฉืžื’ืœื” ืื™ื–ื” ืกื•ื’ ืฉืœ ืจื•ื‘ื•ื˜ ื ื—ื•ืฅ ื‘ืจื’ืข ืฉื”ื•ื ืžื’ื™ืข,
00:29
builds it and then enables it to continue to evolve
8
29818
3295
ื‘ื•ื ื” ืื•ืชื• ื•ืื– ืžืืคืฉืจืช ืœื• ืœื”ืžืฉื™ืš ื•ืœื”ืชืคืชื—
00:33
to adapt to its new surroundings.
9
33154
2002
ื›ื“ื™ ืœื”ืกืชื’ืœ ืœืกื‘ื™ื‘ืชื• ื”ื—ื“ืฉื”.
00:36
Itโ€™s exactly what my collaborators and I are working on:
10
36241
3170
ื–ื” ื‘ื“ื™ื•ืง ืžื” ืฉืžืฉืชืคื™ ื”ืคืขื•ืœื” ืฉืœื™ ื•ืื ื™ ืขื•ื‘ื“ื™ื ืขืœื™ื•:
00:39
a radical new technology which enables robots to be created,
11
39452
4296
ื˜ื›ื ื•ืœื•ื’ื™ื” ื—ื“ืฉื” ืจื“ื™ืงืœื™ืช ื”ืžืืคืฉืจืช ืœื™ืฆื•ืจ ืจื•ื‘ื•ื˜ื™ื,
00:43
reproduce and evolve over long periods of time,
12
43748
3337
ืœื”ืชืจื‘ื•ืช ื•ืœื”ืชืคืชื— ืขืœ ืคื ื™ ืคืจืงื™ ื–ืžืŸ ืืจื•ื›ื™ื,
00:47
a technology where robot design and fabrication becomes a task
13
47961
3920
ื˜ื›ื ื•ืœื•ื’ื™ื” ืฉื‘ื” ืขื™ืฆื•ื‘ ื•ื™ื™ืฆื•ืจ ืจื•ื‘ื•ื˜ ื”ื•ืคื›ื™ื ืœืžืฉื™ืžื”
00:51
for machines rather than humans.
14
51923
2461
ืœืžื›ื•ื ื•ืช ื•ืœื ืœื‘ื ื™ ืื“ื.
00:55
Robots are already all around us, in factories, in hospitals, in our home.
15
55885
4588
ืจื•ื‘ื•ื˜ื™ื ื›ื‘ืจ ื ืžืฆืื™ื ืกื‘ื™ื‘ื ื•, ื‘ืžืคืขืœื™ื, ื‘ื‘ืชื™ ื—ื•ืœื™ื, ื‘ื‘ื™ืช ืฉืœื ื•.
01:01
But from an engineer's perspective,
16
61391
1877
ืื‘ืœ ืžื ืงื•ื“ืช ืžื‘ื˜ ืฉืœ ืžื”ื ื“ืก,
01:03
designing a shelf-stacking robot or a Roomba to clean our home
17
63310
3503
ืชื›ื ื•ืŸ ืจื•ื‘ื•ื˜ ืœืขืจื•ื ืžื“ืฃ ืื• ืจื•ืžื‘ื” ืœื ืงื•ืช ืืช ื”ื‘ื™ืช ืฉืœื ื•
01:06
is relatively straightforward.
18
66813
2211
ื”ื•ื ืคืฉื•ื˜ ื™ื—ืกื™ืช.
01:09
We know exactly what they need to do,
19
69065
2253
ืื ื—ื ื• ื™ื•ื“ืขื™ื ื‘ื“ื™ื•ืง ืžื” ื”ื ืฆืจื™ื›ื™ื ืœืขืฉื•ืช,
01:11
and we can imagine the kind of situations they might find themselves in.
20
71318
3461
ื•ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœื“ืžื™ื™ืŸ ืืช ืกื•ื’ ื”ืžืฆื‘ื™ื ืฉื”ื ืขืœื•ืœื™ื ืœืžืฆื•ื ื‘ื”ื ืืช ืขืฆืžื.
01:14
So we design with this in mind.
21
74821
1794
ืื– ืื ื—ื ื• ืžืขืฆื‘ื™ื ืขื ืœืงื™ื—ืช ื”ื“ื‘ืจ ื‘ื—ืฉื‘ื•ืŸ.
01:18
But what if we want to send that robot to operate
22
78033
2794
ืื‘ืœ ืžื” ืื ื ืจืฆื” ืœืฉืœื•ื— ืืช ื”ืจื•ื‘ื•ื˜ ื”ื–ื” ืœืคืขื•ืœ
01:20
in a place that we have little or even no knowledge about?
23
80827
3003
ื‘ืžืงื•ื ืฉื™ืฉ ืœื ื• ืžืขื˜ ืื• ืืคื™ืœื• ืื™ืŸ ื‘ื›ืœืœ ื™ื“ืข ืœื’ื‘ื™ื•?
01:24
For example, cleaning up legacy waste inside a nuclear reactor
24
84456
3295
ืœื“ื•ื’ืžื” ื ื™ืงื•ื™ ืคืกื•ืœืช ื™ืฉื ื” ื‘ืชื•ืš ื›ื•ืจ ื’ืจืขื™ื ื™
01:27
where it's unsafe to send humans,
25
87751
3003
ื‘ืžืงื•ื ืฉืœื ื‘ื˜ื•ื— ืœืฉืœื•ื— ื‘ื ื™ ืื“ื,
01:30
mining for minerals deep in a trench at the bottom of the ocean,
26
90754
3879
ื›ืจื™ื™ื” ืฉืœ ืžื™ื ืจืœื™ื ืขืžื•ืง ื‘ืชืขืœื” ื‘ืงืจืงืขื™ืช ื”ืื•ืงื™ื™ื ื•ืก,
01:34
or exploring a faraway asteroid.
27
94674
2169
ืื• ืœื—ืงื•ืจ ืืกื˜ืจื•ืื™ื“ ืจื—ื•ืง.
01:38
How frustrating would it be if the human-designed robot,
28
98345
3670
ื›ืžื” ืžืชืกื›ืœ ื–ื” ื™ื”ื™ื” ืื ื”ืจื•ื‘ื•ื˜ ืฉืชื•ื›ื ืŸ ืขืœ ื™ื“ื™ ืื“ื,
01:42
that had taken years to get to the asteroid
29
102057
2794
ื•ืฉืœืงื— ืฉื ื™ื ืœื”ื’ื™ืข ืœืืกื˜ืจื•ืื™ื“
01:44
suddenly found it needed to drill a hole
30
104851
2336
ืคืชืื•ื ืžืฆื ืฉืฆืจื™ืš ืœืงื“ื•ื— ื—ื•ืจ
01:47
to collect a sample or clamber up a cliff
31
107187
3044
ื›ื“ื™ ืœืืกื•ืฃ ื“ื’ื™ืžื” ืื• ืœื˜ืคืก ื‘ืžืขืœื” ืฆื•ืง
01:50
but it didn't have the right tools
32
110273
1627
ืื‘ืœ ืœื ื”ื™ื• ืœื• ืืช ื”ื›ืœื™ื ื”ื ื›ื•ื ื™ื
01:51
or the right means of locomotion to do so?
33
111941
2169
ืื• ืืช ืืžืฆืขื™ ื”ืชื ื•ืขื” ื”ื ื›ื•ื ื™ื ืœืขืฉื•ืช ื–ืืช?
01:55
If instead we had a technology
34
115236
2586
ืื ื‘ืžืงื•ื ื–ื” ื”ื™ื™ืชื” ืœื ื• ื˜ื›ื ื•ืœื•ื’ื™ื”
01:57
that enabled the robots to be designed and optimized in situ,
35
117864
4254
ืฉืื™ืคืฉืจื” ืœืขืฆื‘ ืืช ื”ืจื•ื‘ื•ื˜ื™ื ื•ืœืžื˜ื‘ ืื•ืชื ื‘ืืชืจ,
02:02
in the environment in which they need to live and work,
36
122160
3253
ื‘ืกื‘ื™ื‘ื” ืฉื‘ื” ื”ื ืฆืจื™ื›ื™ื ืœื—ื™ื•ืช ื•ืœืขื‘ื•ื“,
02:05
then we could potentially save years of wasted effort
37
125455
2878
ืื– ื”ื™ื™ื ื• ื™ื›ื•ืœื™ื ื‘ืคื•ื˜ื ืฆื™ื” ืœื—ืกื•ืš ืฉื ื™ื ืฉืœ ืžืืžืฅ ืžื‘ื•ื–ื‘ื–
02:08
and produce robots that are uniquely adapted
38
128375
2252
ื•ืœื™ื™ืฆืจ ืจื•ื‘ื•ื˜ื™ื ื”ืžื•ืชืืžื™ื ื‘ืื•ืคืŸ ื™ื™ื—ื•ื“ื™
02:10
to the environments that they find themselves in.
39
130669
2335
ืœืกื‘ื™ื‘ื•ืช ืฉื‘ื”ืŸ ื”ื ืžื•ืฆืื™ื ืืช ืขืฆืžื ื‘ื”ืŸ.
02:15
So to realize this technology, we've been turning to nature for help.
40
135173
4046
ืื– ื›ื“ื™ ืœืžืžืฉ ืืช ื”ื˜ื›ื ื•ืœื•ื’ื™ื” ื”ื–ื•, ืคื ื™ื ื• ืœื˜ื‘ืข ืœืขื–ืจื”.
02:20
All around us,
41
140345
1209
ื‘ื›ืœ ืžืงื•ื ืžืกื‘ื™ื‘ื ื•,
02:21
we see examples of biological species
42
141596
3003
ืื ื• ืจื•ืื™ื ื“ื•ื’ืžืื•ืช ืฉืœ ืžื™ื ื™ื ื‘ื™ื•ืœื•ื’ื™ื™ื
02:24
that have evolved smart adaptations
43
144599
2211
ืฉืคื™ืชื—ื• ื”ืชืืžื•ืช ื—ื›ืžื•ืช
02:26
that enable them to thrive in a given environment.
44
146810
2752
ืฉืžืืคืฉืจื•ืช ืœื”ื ืœืฉื’ืฉื’ ื‘ืกื‘ื™ื‘ื” ื ืชื•ื ื”.
02:31
For example, in the Cuban rainforest,
45
151064
2669
ืœื“ื•ื’ืžื”, ื‘ื™ืขืจ ื”ื’ืฉื ื”ืงื•ื‘ื ื™,
02:33
we find vines that have evolved leaves
46
153775
2669
ืื ื• ืžื•ืฆืื™ื ื’ืคื ื™ื ืฉืคื™ืชื—ื• ืขืœื™ื
02:36
that are shaped like human-designed satellite dishes.
47
156486
3086
ื”ืžืขื•ืฆื‘ื™ื ื›ืžื• ืฆืœื—ื•ืช ืœื•ื•ื™ืŸ ื‘ืขื™ืฆื•ื‘ ืื ื•ืฉื™.
02:39
These leaves direct bats to their flowers
48
159614
2544
ืขืœื™ื ืืœื• ืžื›ื•ื•ื ื™ื ืขื˜ืœืคื™ื ืืœ ื”ืคืจื—ื™ื ืฉืœื”ื
02:42
by amplifying the signals that the bats send out,
49
162158
2795
ืขืœ ื™ื“ื™ ื”ื’ื‘ืจืช ื”ืื•ืชื•ืช ืฉื”ืขื˜ืœืคื™ื ืฉื•ืœื—ื™ื ื”ื—ื•ืฆื”,
02:44
therefore, improving pollination.
50
164953
1960
ื•ื›ืš, ืžืฉืคืจื™ื ืืช ื”ื”ืื‘ืงื”.
02:48
What if we could create an artificial version of evolution
51
168665
4046
ืžื” ืื ื”ื™ื™ื ื• ื™ื›ื•ืœื™ื ืœื™ืฆื•ืจ ื’ืจืกื” ืžืœืื›ื•ืชื™ืช ืฉืœ ืื‘ื•ืœื•ืฆื™ื”
02:52
that would enable robots to evolve in a similar manner
52
172752
3253
ืฉืชืืคืฉืจ ืœืจื•ื‘ื•ื˜ื™ื ืœื”ืชืคืชื— ื‘ืฆื•ืจื” ื“ื•ืžื”
02:56
as biological organisms?
53
176047
2211
ื›ืื•ืจื’ื ื™ื–ืžื™ื ื‘ื™ื•ืœื•ื’ื™ื™ื?
03:00
I'm not talking about biomimicry,
54
180051
2169
ืื ื™ ืœื ืžื“ื‘ืจืช ืขืœ ื‘ื™ื•ืžื™ืžื™ืงืจื™ (ื—ื™ืงื•ื™ ืœื˜ื‘ืข),
03:02
a technology which simply copies what's observed in nature.
55
182262
3545
ื˜ื›ื ื•ืœื•ื’ื™ื” ืฉืคืฉื•ื˜ ืžืขืชื™ืงื” ืืช ืžื” ืฉื ืฆืคื” ื‘ื˜ื‘ืข.
03:06
What we're hoping to harness is the creativity of evolution,
56
186808
4212
ืžื” ืฉืื ื—ื ื• ืžืงื•ื•ื™ื ื–ื” ืœืจืชื•ื ืืช ื”ื™ืฆื™ืจืชื™ื•ืช ืฉืœ ื”ืื‘ื•ืœื•ืฆื™ื”,
03:11
to discover designs that are not observed here on Earth,
57
191020
3587
ืœื’ืœื•ืช ืขื™ืฆื•ื‘ื™ื ืฉืœื ื ืฆืคื™ื ื›ืืŸ ืขืœ ื›ื“ื•ืจ ื”ืืจืฅ,
03:14
the human engineer might not have thought of
58
194649
2419
ืฉื”ืžื”ื ื“ืก ื”ืื ื•ืฉื™ ืื•ืœื™ ืœื ื—ืฉื‘ ืขืœื™ื”ื
03:17
or even be capable of conceiving.
59
197068
2211
ืื• ืืคื™ืœื• ืœื ื™ื›ืœ ืœื”ื™ื•ืช ืžืกื•ื’ืœ ืœื”ืจื•ืช ืื•ืชื.
03:20
In theory,
60
200947
1168
ื‘ืชื™ืื•ืจื™ื”,
03:22
this evolutionary design technology could operate completely autonomously
61
202157
3920
ื˜ื›ื ื•ืœื•ื’ื™ื™ืช ืขื™ืฆื•ื‘ ืื‘ื•ืœื•ืฆื™ื•ื ื™ืช ื–ื• ื™ื›ื•ืœื” ืœืคืขื•ืœ ื‘ืื•ืคืŸ ืื•ื˜ื•ื ื•ืžื™ ืœื—ืœื•ื˜ื™ืŸ
03:26
in a faraway place.
62
206119
2127
ื‘ืžืงื•ื ืจื—ื•ืง. ืื‘ืœ ื‘ืื•ืชื” ืžื™ื“ื”
03:28
But equally it could be guided by humans.
63
208288
2377
ื–ื” ื™ื›ื•ืœ ืœื”ื™ื•ืช ืžื•ื ื—ื” ืขืœ ื™ื“ื™ ื‘ื ื™ ืื“ื.
03:31
Just as we breed plants for qualities such as drought resistance or taste,
64
211291
4588
ื‘ื“ื™ื•ืง ื›ืคื™ ืฉืื ื• ืžื’ื“ืœื™ื ืฆืžื—ื™ื ืขื‘ื•ืจ ืื™ื›ื•ื™ื•ืช ื›ื’ื•ืŸ ืขืžื™ื“ื•ืช ืœื‘ืฆื•ืจืช ืื• ืœื˜ืขื,
03:35
the human robot breeder could guide artificial evolution to producing robots
65
215879
5171
ืžื’ื“ืœ ื”ืจื•ื‘ื•ื˜ื™ื ื”ืื ื•ืฉื™ ื™ื›ื•ืœ ืœื”ื“ืจื™ืš ืื‘ื•ืœื•ืฆื™ื” ืžืœืื›ื•ืชื™ืช ืœื™ื™ืฆื•ืจ ืจื•ื‘ื•ื˜ื™ื
03:41
with specific qualities.
66
221050
1711
ืขื ืื™ื›ื•ื™ื•ืช ืกืคืฆื™ืคื™ื•ืช.
03:42
For example,
67
222802
1126
ืœื“ื•ื’ืžื”,
03:43
the ability to squeeze through a narrow gap
68
223970
2377
ื”ื™ื›ื•ืœืช ืœื”ื™ื“ื—ืง ื“ืจืš ืคื™ืจืฆื” ืฆืจื”
03:46
or perhaps operate at low energy.
69
226389
2711
ืื• ืื•ืœื™ ืœืคืขื•ืœ ื‘ืื ืจื’ื™ื” ื ืžื•ื›ื”.
03:51
This idea of artificial evolution imitating biological evolution
70
231686
3962
ื”ืจืขื™ื•ืŸ ื”ื–ื” ืฉืœ ืื‘ื•ืœื•ืฆื™ื” ืžืœืื›ื•ืชื™ืช, ื—ื™ืงื•ื™ ืื‘ื•ืœื•ืฆื™ื” ื‘ื™ื•ืœื•ื’ื™ืช
03:55
using a computer program
71
235648
1669
ื‘ืืžืฆืขื•ืช ืชื•ื›ื ืช ืžื—ืฉื‘
03:57
to breed better and better solutions to problems over time
72
237317
3587
ืœื”ืฆืžื™ื— ืขื ื”ื–ืžืŸ ืคืชืจื•ื ื•ืช ื˜ื•ื‘ื™ื ื™ื•ืชืจ ื•ื™ื•ืชืจ ืœื‘ืขื™ื•ืช
04:00
isn't actually new.
73
240904
1543
ืื™ื ื• ื—ื“ืฉ ืœืžืขืฉื”.
04:03
In fact, artificial evolution,
74
243323
2544
ืœืžืขืฉื”, ืื‘ื•ืœื•ืฆื™ื” ืžืœืื›ื•ืชื™ืช,
04:05
algorithms operating inside a computer,
75
245909
2711
ืืœื’ื•ืจื™ืชืžื™ื ื”ืคื•ืขืœื™ื ื‘ืชื•ืš ืžื—ืฉื‘,
04:08
have been used to design everything from tables to turbine blades.
76
248620
4254
ืฉื™ืžืฉื• ืœืขื™ืฆื•ื‘ ื”ื›ืœ ืžืฉื•ืœื—ื ื•ืช ื•ืขื“ ืœื”ื‘ื™ ื˜ื•ืจื‘ื™ื ื”.
04:13
Back in 2006,
77
253291
1668
ืขื•ื“ ื‘ืฉื ืช 2006,
04:15
NASA even sent a satellite into space with a communication antenna
78
255001
4004
ื ืืกโ€œื ืืคื™ืœื• ืฉืœื—ื” ืœื•ื•ื™ื™ืŸ ืœื—ืœืœ ืขื ืื ื˜ื ืช ืชืงืฉื•ืจืช
04:19
that had been designed by artificial evolution.
79
259047
2711
ืฉืขื•ืฆื‘ื” ืขืœ ื™ื“ื™ ืื‘ื•ืœื•ืฆื™ื” ืžืœืื›ื•ืชื™ืช.
04:23
But evolving robots is actually much harder
80
263843
2544
ืื‘ืœ ืจื•ื‘ื•ื˜ื™ื ืžืชืคืชื—ื™ื ื–ื” ืœืžืขืฉื” ื”ืจื‘ื” ื™ื•ืชืจ ืงืฉื”
04:26
than evolving passive objects such as tables,
81
266429
2878
ืžืืฉืจ ืื•ื‘ื™ื™ืงื˜ื™ื ืคืกื™ื‘ื™ื™ื ืžืชืคืชื—ื™ื ื›ืžื• ืฉื•ืœื—ื ื•ืช,
04:29
because robots need brains as well as bodies
82
269307
3420
ื›ื™ ืจื•ื‘ื•ื˜ื™ื ืฆืจื™ื›ื™ื ืžื•ื— ื›ืžื• ื’ื ื’ื•ืฃ
04:32
in order to make sense of the information in the world around them
83
272769
5047
ื›ื“ื™ ืœื”ื‘ื™ืŸ ืืช ื”ืžื™ื“ืข ื‘ืขื•ืœื ื”ืกื•ื‘ื‘ ืื•ืชื
04:37
and translate that into appropriate behaviors.
84
277816
2836
ื•ืœืชืจื’ื ืืช ื–ื” ืœื”ืชื ื”ื’ื•ื™ื•ืช ืžืชืื™ืžื•ืช.
04:41
So how do we do it?
85
281903
1543
ืื– ืื™ืš ืขื•ืฉื™ื ืืช ื–ื”?
04:44
Surprisingly, evolution only needs three ingredients:
86
284489
4046
ื‘ืื•ืคืŸ ืžืคืชื™ืข, ื”ืื‘ื•ืœื•ืฆื™ื” ืฆืจื™ื›ื” ืจืง ืฉืœื•ืฉื” ืžืจื›ื™ื‘ื™ื:
04:49
a population of individuals which exhibit some physical variations;
87
289369
5589
ืื•ื›ืœื•ืกื™ื™ืช ื™ื—ื™ื“ื™ื ืืฉืจ ืžืฆื™ื’ื” ื›ืžื” ื•ืจื™ืืฆื™ื•ืช ืคื™ื–ื™ื•ืช;
04:54
a method of reproduction
88
294999
1877
ืฉื™ื˜ืช ืจื‘ื™ื™ื”
04:56
in which offspring inherit some traits from their parents
89
296876
3045
ืฉื‘ื” ืฆืืฆืื™ื ื™ื•ืจืฉื™ื ื›ืžื” ืชื›ื•ื ื•ืช ืžื”ื•ืจื™ื”ื
04:59
and occasionally acquire new ones via mutation;
90
299963
3545
ื•ืžื“ื™ ืคืขื ืจื•ื›ืฉื™ื ื—ื“ืฉื•ืช ื‘ืืžืฆืขื•ืช ืžื•ื˜ืฆื™ื”;
05:03
and finally, a means of natural selection.
91
303550
2460
ื•ืœื‘ืกื•ืฃ, ืืžืฆืขื™ื ืœื‘ืจื™ืจื” ื˜ื‘ืขื™ืช.
05:07
So we can replicate these three ingredients to evolve robots
92
307178
3295
ื›ืš ืฉืื ื—ื ื• ื™ื›ื•ืœื™ื ืœืฉื—ื–ืจ ืืช ืฉืœื•ืฉืช ื”ืžืจื›ื™ื‘ื™ื ืœืคื™ืชื•ื— ืจื•ื‘ื•ื˜ื™ื
05:10
using a mixture of hardware and software.
93
310473
2836
ื‘ืืžืฆืขื•ืช ืฉื™ืœื•ื‘ ืฉืœ ื—ื•ืžืจื” ื•ืชื•ื›ื ื”.
05:14
The first task is to design a digital version of DNA.
94
314769
4296
ื”ืžืฉื™ืžื” ื”ืจืืฉื•ื ื” ื”ื™ื ืœืขืฆื‘ ื’ืจืกื” ื“ื™ื’ื™ื˜ืœื™ืช ืฉืœ DNA.
05:19
That is a digital blueprint that describes the robot's brain, its body,
95
319107
5464
ืฉื–ื• ืชื•ื›ื ื™ืช ื“ื™ื’ื™ื˜ืœื™ืช ืฉืžืชืืจืช ืืช ื”ืžื•ื— ืฉืœ ื”ืจื•ื‘ื•ื˜, ื”ื’ื•ืฃ ืฉืœื•,
05:24
its sensory mechanisms and its means of locomotion.
96
324612
3212
ืžื ื’ื ื•ื ื™ ื”ื—ื™ืฉื” ืฉืœื• ื•ืืžืฆืขื™ ื”ืชื ื•ืขื” ืฉืœื•.
05:29
Using a randomly generated set of these blueprints,
97
329492
2795
ืชื•ืš ืฉื™ืžื•ืฉ ื‘ืกื˜ ืฉืœ ืฉืจื˜ื•ื˜ื™ื ืืœื” ืฉื ื•ืฆืจื™ื ื‘ืืงืจืื™,
05:32
we can create an initial population of 10 or more robots
98
332328
3420
ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœื™ืฆื•ืจ ืื•ื›ืœื•ืกื™ื™ื” ืจืืฉื•ื ื™ืช ืฉืœ 10 ืจื•ื‘ื•ื˜ื™ื ืื• ื™ื•ืชืจ
05:35
to kick-start this evolutionary process.
99
335790
3212
ื›ื“ื™ ืœื”ื ื™ืข ืืช ื”ืชื”ืœื™ืš ื”ืื‘ื•ืœื•ืฆื™ื•ื ื™ ื”ื–ื”.
05:40
We've designed a technology that can take the digital blueprint
100
340587
3586
ืชื›ื ื ื• ื˜ื›ื ื•ืœื•ื’ื™ื” ืฉื™ื›ื•ืœื” ืœืงื—ืช ืืช ื”ืชื•ื›ื ื™ืช ื”ื“ื™ื’ื™ื˜ืœื™ืช
05:44
and turn it into a physical robot without any need for human assistance.
101
344215
4088
ื•ืœื”ืคื•ืš ืื•ืชื” ืœืจื•ื‘ื•ื˜ ืคื™ื–ื™ ืœืœื ื›ืœ ืฆื•ืจืš ื‘ืกื™ื•ืข ืื ื•ืฉื™.
05:49
For example, it uses a 3D printer to print the skeleton of the robot
102
349220
4463
ืœื“ื•ื’ืžื”, ืฉื™ืžื•ืฉ ื‘ืžื“ืคืกืช ืชืœืช ืžื™ืžื“ ื›ื“ื™ ืœื”ื“ืคื™ืก ืืช ื”ืฉืœื“ ืฉืœ ื”ืจื•ื‘ื•ื˜
05:53
and then an automated assembly arm like you might find in a factory
103
353725
3962
ื•ืœืื—ืจ ืžื›ืŸ ื–ืจื•ืข ื”ืจื›ื‘ื” ืื•ื˜ื•ืžื˜ื™ืช ื›ืžื• ืฉืืชื ืขืฉื•ื™ื™ื ืœืžืฆื•ื ื‘ืžืคืขืœ
05:57
to add any electronics and moving parts,
104
357687
2878
ื›ื“ื™ ืœื”ื•ืกื™ืฃ ืืœืงื˜ืจื•ื ื™ืงื” ื›ืœืฉื”ื™ ื•ื—ืœืงื™ื ื ืขื™ื,
06:00
including a small computer that acts as a brain.
105
360607
2794
ื›ื•ืœืœ ืžื—ืฉื‘ ืงื˜ืŸ ืฉืคื•ืขืœ ื›ืžื• ืžื•ื—.
06:04
And to enable this brain to adapt to the new body of the robot,
106
364611
3795
ื•ื›ื“ื™ ืœืืคืฉืจ ืœืžื•ื— ื”ื–ื” ืœื”ืกืชื’ืœ ืœื’ื•ืฃ ื”ื—ื“ืฉ ืฉืœ ื”ืจื•ื‘ื•ื˜,
06:08
we send every robot produced to an equivalent of a kindergarten,
107
368448
5255
ืื ื—ื ื• ืฉื•ืœื—ื™ื ื›ืœ ืจื•ื‘ื•ื˜ ืฉื™ื•ืฆืจ ืœืžืขื™ืŸ ื’ืŸ ื™ืœื“ื™ื,
06:13
a place where the newborn robot can refine its motor skills
108
373745
3753
ืžืงื•ื ืฉื‘ื• ื”ืจื•ื‘ื•ื˜ ื”ื ื•ืœื“ ื™ื›ื•ืœ ืœื—ื“ื“ ืืช ื”ื›ื™ืฉื•ืจื™ื ื”ืžื•ื˜ื•ืจื™ื™ื ืฉืœื•
06:17
almost like a small child would.
109
377540
1877
ื›ืžืขื˜ ื›ืžื• ืฉื™ืœื“ ืงื˜ืŸ ื”ื™ื” ืขื•ืฉื”.
06:21
To mimic natural selection,
110
381961
1835
ื›ื“ื™ ืœื—ืงื•ืช ืืช ื”ื‘ืจื™ืจื” ื”ื˜ื‘ืขื™ืช,
06:23
we score these robots on the ability to conduct a task.
111
383796
3254
ืื ื—ื ื• ืžื“ืจื’ื™ื ืืช ื”ืจื•ื‘ื•ื˜ื™ื ื”ืืœื” ืขืœ ืคื™ ื”ื™ื›ื•ืœืช ืœื‘ืฆืข ืžืฉื™ืžื”.
06:27
And then we use these scores
112
387926
1710
ื•ืื– ืื ื—ื ื• ืžืฉืชืžืฉื™ื ื‘ืฆื™ื•ื ื™ื ื”ืืœื”
06:29
to selectively decide which robots get to reproduce.
113
389677
3879
ื›ื“ื™ ืœื”ื—ืœื™ื˜ ื‘ืื•ืคืŸ ืกืœืงื˜ื™ื‘ื™ ืื™ืœื• ืจื•ื‘ื•ื˜ื™ื ื–ื•ื›ื™ื ืœื”ืชืจื‘ื•ืช.
06:34
The reproduction mechanism
114
394891
1585
ืžื ื’ื ื•ืŸ ื”ืจื‘ื™ื™ื”
06:36
mixes the digital DNA of the chosen parent robots
115
396476
4004
ืžืขืจื‘ื‘ ืืช ื”-DNA ื”ื“ื™ื’ื™ื˜ืœื™ ืฉืœ ื”ืจื•ื‘ื•ื˜ ื”ื”ื•ืจื” ืฉื ื‘ื—ืจ
06:40
to create a new blueprint for a child robot
116
400521
3462
ื›ื“ื™ ืœื™ืฆื•ืจ ืชื•ื›ื ื™ืช ื—ื“ืฉื” ืขื‘ื•ืจ ืจื•ื‘ื•ื˜ ื™ืœื“
06:44
that inherits some of the characteristics from its parents
117
404025
3378
ืฉื™ื•ืจืฉ ื—ืœืง ืžื”ืžืืคื™ื™ื ื™ื ืžื”ื•ืจื™ื•
06:47
but occasionally also exhibits some new ones.
118
407445
2920
ืื‘ืœ ืžื“ื™ ืคืขื ื’ื ืžืฆื™ื’ ื›ืžื” ื—ื“ืฉื™ื.
06:51
And by repeating the cycle of selection and reproduction over and over again,
119
411366
5297
ื•ืขืœ ื™ื“ื™ ื—ื–ืจื” ืขืœ ืžื—ื–ื•ืจ ื”ืกืœืงืฆื™ื” ื•ื”ืจื‘ื™ื™ื” ืฉื•ื‘ ื•ืฉื•ื‘,
06:56
we hope that we can breed successive generations of robots
120
416704
3128
ืื ื• ืžืงื•ื•ื™ื ืฉื ื•ื›ืœ ืœื”ืจื‘ื•ืช ื“ื•ืจื•ืช ืจืฆื•ืคื™ื ืฉืœ ืจื•ื‘ื•ื˜ื™ื
06:59
where, just like is often observed in biological evolution,
121
419874
3921
ื”ื™ื›ืŸ, ื‘ื“ื™ื•ืง ื›ืžื• ืฉื ืฆืคื” ืœืขืชื™ื ืงืจื•ื‘ื•ืช ื‘ืื‘ื•ืœื•ืฆื™ื” ื‘ื™ื•ืœื•ื’ื™ืช,
07:03
each generation gets better than the last,
122
423836
2586
ื›ืœ ื“ื•ืจ ืžืฉืชืคืจ ืžืงื•ื“ืžื•.
07:06
with the robots gradually optimizing their form and their behavior
123
426422
3712
ื›ืฉื”ืจื•ื‘ื•ื˜ื™ื ืขื•ืฉื™ื ืื•ืคื˜ื™ืžื™ื–ืฆื™ื” ื”ื“ืจื’ืชื™ืช ืฉืœ ืฆื•ืจืชื ื•ื”ืชื ื”ื’ื•ืชื
07:10
to the task and the environment that they find themselves in.
124
430176
3337
ืœืžืฉื™ืžื” ื•ืœืกื‘ื™ื‘ื” ืฉื‘ื”ืŸ ื”ื ืžื•ืฆืื™ื ืืช ืขืฆืžื.
07:15
Now, although this can all take place
125
435139
2211
ืขื›ืฉื™ื•, ืœืžืจื•ืช ืฉื›ืœ ื–ื” ื™ื›ื•ืœ ืœื”ืชืจื—ืฉ
07:17
in a time frame that's much faster than biological evolution,
126
437392
3253
ื‘ื˜ื•ื•ื— ื–ืžืŸ ืฉื”ื•ื ื”ืจื‘ื” ื™ื•ืชืจ ืžื”ื™ืจ ืžืืฉืจ ืื‘ื•ืœื•ืฆื™ื” ื‘ื™ื•ืœื•ื’ื™ืช,
07:20
which sometimes takes thousands of years,
127
440687
2544
ืฉืœืคืขืžื™ื ืœื•ืงื—ืช ืืœืคื™ ืฉื ื™ื,
07:23
it's still relatively slow in terms of the time frames we might expect
128
443272
3546
ื–ื” ืขื“ื™ื™ืŸ ืื™ื˜ื™ ื™ื—ืกื™ืช ื‘ืžื•ื ื—ื™ื ืฉืœ ืžืกื’ืจื•ืช ื”ื–ืžืŸ ืฉืื ื• ืขืฉื•ื™ื™ื ืœืฆืคื•ืช ืœื”ืŸ
07:26
in our modern world
129
446818
1251
ื‘ืขื•ืœื ื”ืžื•ื“ืจื ื™ ืฉืœื ื•
07:28
to design and produce an artifact.
130
448111
2502
ืœืขืฆื‘ ื•ืœื™ื™ืฆืจ ื—ืคืฅ.
07:30
It's mainly due to the 3D printing process,
131
450947
2252
ื–ื” ื‘ืขื™ืงืจ ืขืงื‘ ืชื”ืœื™ืš ื”ื“ืคืกืช ืชืœืช ืžื™ืžื“,
07:33
which can take more than four hours per robot,
132
453241
2502
ืฉื™ื›ื•ืœ ืœืงื—ืช ื™ื•ืชืจ ืžืืจื‘ืข ืฉืขื•ืช ืœื›ืœ ืจื•ื‘ื•ื˜,
07:35
depending on the complexity and the shape of the robot.
133
455785
2961
ื‘ื”ืชืื ืœืžื•ืจื›ื‘ื•ืช ื•ืœืฆื•ืจืช ื”ืจื•ื‘ื•ื˜.
07:40
But we can give our artificial evolutionary process a helping hand
134
460456
3504
ืื‘ืœ ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœืชืช ืœืชื”ืœื™ืš ื”ืื‘ื•ืœื•ืฆื™ื•ื ื™ ื”ืžืœืื›ื•ืชื™ ืฉืœื ื• ื™ื“ ืžืกื™ื™ืขืช
07:44
to reduce the number of physical robots that we actually need to make.
135
464002
3586
ื›ื“ื™ ืœืฆืžืฆื ืืช ืžืกืคืจ ื”ืจื•ื‘ื•ื˜ื™ื ื”ืคื™ื–ื™ื™ื ืฉืื ื—ื ื• ื‘ืขืฆื ืฆืจื™ื›ื™ื ืœื™ื™ืฆืจ.
07:49
We create a digital copy of every robot produced
136
469298
2837
ืื ื• ื™ื•ืฆืจื™ื ืขื•ืชืง ื“ื™ื’ื™ื˜ืœื™ ืžื›ืœ ืจื•ื‘ื•ื˜ ืฉื™ื•ืฆืจ
07:52
inside a simulation in a computer,
137
472176
2837
ื‘ืชื•ืš ืกื™ืžื•ืœืฆื™ื” ื‘ืžื—ืฉื‘,
ื•ืžืืคืฉืจื™ื ืœืื•ื›ืœื•ืกื™ื™ืช ื”ืจื•ื‘ื•ื˜ื™ื ื”ื•ื•ื™ืจื˜ื•ืืœื™ืช ื”ื–ื• ืœื”ืชืคืชื—.
07:55
and we allow this virtual population of robots to evolve.
138
475013
4170
07:59
Now it's quite likely that the simulation isn't a very accurate representation
139
479642
5047
ื–ื” ื“ื™ ืกื‘ื™ืจ ืฉื”ืกื™ืžื•ืœืฆื™ื” ืื™ื ื” ื™ื™ืฆื•ื’ ืžื“ื•ื™ืง ื‘ืžื™ื•ื—ื“
08:04
of the real world.
140
484689
1668
ืฉืœ ื”ืขื•ืœื ื”ืืžื™ืชื™.
08:06
But it has an advantage that it enables models of robots to be created
141
486983
4004
ืื‘ืœ ื™ืฉ ืœื–ื” ื™ืชืจื•ืŸ ืฉื”ื™ื ืžืืคืฉืจืช ืœืžื•ื“ืœื™ื ืฉืœ ืจื•ื‘ื•ื˜ื™ื ืœื”ื™ื•ื•ืฆืจ
08:11
and tested in seconds rather than hours.
142
491029
2377
ื•ืœื”ื™ื‘ื“ืง ื‘ืฉื ื™ื•ืช ื•ืœื ื‘ืฉืขื•ืช.
08:14
So using the simulator technology,
143
494032
2460
ืื– ื‘ืืžืฆืขื•ืช ื˜ื›ื ื•ืœื•ื’ื™ื™ืช ื”ืกื™ืžื•ืœื˜ื•ืจ,
08:16
we can quickly explore the potential of a wide range of robot types
144
496534
3795
ื ื•ื›ืœ ืœื—ืงื•ืจ ื‘ืžื”ื™ืจื•ืช ืืช ื”ืคื•ื˜ื ืฆื™ืืœ ืฉืœ ืžื’ื•ื•ืŸ ืจื—ื‘ ืฉืœ ืกื•ื’ื™ ืจื•ื‘ื•ื˜ื™ื
08:20
of different shapes and sizes, of different sensory configurations,
145
500371
3921
ื‘ืฆื•ืจื•ืช ื•ื’ื“ืœื™ื ืฉื•ื ื™ื, ืฉืœ ืชืฆื•ืจื•ืช ื—ื•ืฉื™ื•ืช ืฉื•ื ื•ืช,
08:24
and quickly get a rough estimate of how useful each robot may be
146
504292
3837
ื•ืœืงื‘ืœ ื‘ืžื”ื™ืจื•ืช ื”ืขืจื›ื” ื’ืกื” ืขื“ ื›ืžื” ื›ืœ ืจื•ื‘ื•ื˜ ื™ื›ื•ืœ ืœื”ื™ื•ืช ืฉื™ืžื•ืฉื™
08:28
before we physically make it.
147
508171
2127
ืœืคื ื™ ืฉืžื™ื™ืฆืจื™ื ืื•ืชื• ืคื™ื–ื™ืช.
08:32
And we predict that by allowing a novel form of breeding
148
512258
3545
ื•ืื ื—ื ื• ื—ื•ื–ื™ื ืฉืขืœ ื™ื“ื™ ื”ืชืจืช ืฆื•ืจื” ื—ื“ืฉื” ืฉืœ ืจื‘ื™ื™ื”
08:35
in which a physical robot can breed with one of its virtual cousins,
149
515803
5172
ืฉื‘ื” ืจื•ื‘ื•ื˜ ืคื™ื–ื™ ื™ื›ื•ืœ ืœื”ืชืจื‘ื•ืช ืขื ืื—ื“ ืžื‘ื ื™ ื”ื“ื•ื“ื™ื ื”ื•ื•ื™ืจื˜ื•ืืœื™ื™ื ืฉืœื•,
08:41
then the useful traits that have been discovered in simulation
150
521017
3211
ื•ืื– ื”ืชื›ื•ื ื•ืช ื”ืฉื™ืžื•ืฉื™ื•ืช ืฉื”ืชื’ืœื• ื‘ืกื™ืžื•ืœืฆื™ื”
08:44
will quickly spread into the physical robot population,
151
524270
2961
ื™ืชืคืฉื˜ื• ื‘ืžื”ื™ืจื•ืช ืœืชื•ืš ืื•ื›ืœื•ืกื™ื™ืช ื”ืจื•ื‘ื•ื˜ื™ื ื”ืคื™ื–ื™ื™ื,
08:47
where they can be further refined in situ.
152
527273
2836
ืฉืฉื ื ื™ืชืŸ ืœืขื“ืŸ ืื•ืชื ืขื•ื“ ื™ื•ืชืจ ื‘ืžืงื•ืžื ื”ืžืชืื™ื.
08:52
It might sound like science fiction,
153
532487
2127
ื–ื” ืื•ืœื™ ื ืฉืžืข ื›ืžื• ืžื“ืข ื‘ื“ื™ื•ื ื™,
08:54
but actually there's a serious point.
154
534655
2253
ืื‘ืœ ื‘ืขืฆื ื™ืฉ ื ืงื•ื“ื” ืจืฆื™ื ื™ืช.
09:00
While we expect the technology that I've just described
155
540286
3504
ื‘ืขื•ื“ ืื ื• ืžืฆืคื™ื ืฉื”ื˜ื›ื ื•ืœื•ื’ื™ื” ืฉื–ื” ืขืชื” ืชื™ืืจืชื™
09:03
to be useful in designing robots,
156
543831
2336
ืชื”ื™ื” ืฉื™ืžื•ืฉื™ืช ื‘ืขื™ืฆื•ื‘ ืจื•ื‘ื•ื˜ื™ื,
09:06
for example, to work in situations where it's unsafe to send humans
157
546167
4087
ืœืžืฉืœ, ืœืขื‘ื•ื“ ื‘ืžืฆื‘ื™ื ืฉืœืฉื ืœื ื‘ื˜ื•ื— ืœืฉืœื•ื— ื‘ื ื™ ืื“ื
09:10
or to help us pursue our scientific quest for exoplanetary exploration,
158
550296
5589
ืื• ืœืขื–ื•ืจ ืœื ื• ืœื”ืžืฉื™ืš ื‘ืžืกืข ื”ืžื“ืขื™ ืฉืœื ื• ืœื—ืงืจ ืืงืกื•ืคืœื ื˜ืจื™,
09:15
there are some more pragmatic reasons
159
555927
1793
ื™ืฉ ื›ืžื” ืกื™ื‘ื•ืช ืคืจื’ืžื˜ื™ื•ืช ื™ื•ืชืจ
09:17
why we should consider artificial evolution.
160
557720
2795
ืžื“ื•ืข ืขืœื™ื ื• ืœืฉืงื•ืœ ืื‘ื•ืœื•ืฆื™ื” ืžืœืื›ื•ืชื™ืช.
09:22
As climate change gathers pace,
161
562475
2002
ื›ื›ืœ ืฉืฉื™ื ื•ื™ื™ ื”ืืงืœื™ื ืžืชื’ื‘ืจื™ื,
09:24
it is clear that we need a radical rethink
162
564477
2169
ื‘ืจื•ืจ ืฉืื ื—ื ื• ืฆืจื™ื›ื™ื ื—ืฉื™ื‘ื” ืžื—ื“ืฉ ืจื“ื™ืงืœื™ืช
09:26
to our approach to robotic design here on Earth
163
566687
2420
ืœื’ื™ืฉื” ืฉืœื ื• ืœืขื™ืฆื•ื‘ ืจื•ื‘ื•ื˜ื™ ื›ืืŸ ืขืœ ื›ื“ื•ืจ ื”ืืจืฅ
09:29
in order to reduce that ecological footprint.
164
569148
2670
ื‘ืžื˜ืจื” ืœื”ืคื—ื™ืช ืืช ื˜ื‘ื™ืขืช ื”ืจื’ืœ ื”ืืงื•ืœื•ื’ื™ืช ื”ื–ื•.
09:32
For example,
165
572485
1168
ืœื“ื•ื’ืžื”
09:33
creating new designs of robot built from sustainable materials
166
573653
4337
ื™ืฆื™ืจืช ืขื™ืฆื•ื‘ื™ื ื—ื“ืฉื™ื ืฉืœ ืจื•ื‘ื•ื˜ื™ื ื‘ื ื•ื™ื™ื ืžื—ื•ืžืจื™ื ื‘ื ื™ ืงื™ื™ืžื
09:38
that operate at low energy,
167
578032
1919
ืฉืคื•ืขืœื™ื ื‘ืื ืจื’ื™ื” ื ืžื•ื›ื”,
09:39
that are repairable and recyclable.
168
579992
2837
ื”ื ื™ืชื ื™ื ืœืชื™ืงื•ืŸ ื•ืœืžื™ื—ื–ื•ืจ.
09:44
It's quite likely that this new generation of robots
169
584330
2544
ื“ื™ ืกื‘ื™ืจ ืฉื“ื•ืจ ื—ื“ืฉ ื–ื” ืฉืœ ืจื•ื‘ื•ื˜ื™ื
09:46
won't look anything like the robots that we see around us today,
170
586874
3629
ืœื ื™ื™ืจืื” ื›ืžื• ื”ืจื•ื‘ื•ื˜ื™ื ืฉืื ื• ืจื•ืื™ื ืกื‘ื™ื‘ื ื• ื”ื™ื•ื,
09:50
but that's exactly why artificial evolution might help.
171
590503
3670
ืื‘ืœ ื–ื• ื‘ื“ื™ื•ืง ื”ืกื™ื‘ื” ืฉืื‘ื•ืœื•ืฆื™ื” ืžืœืื›ื•ืชื™ืช ืขืฉื•ื™ื” ืœืขื–ื•ืจ.
09:55
Discovering novel designs by processes that are unfettered by the constraints
172
595007
4713
ื’ื™ืœื•ื™ ืขื™ืฆื•ื‘ื™ื ื—ื“ืฉื™ื ืœืคื™ ืชื”ืœื™ื›ื™ื ืฉืื™ื ื ืžื•ื’ื‘ืœื™ื ืขืœ ื™ื“ื™ ื”ืื™ืœื•ืฆื™ื
09:59
that our own understanding of engineering science
173
599762
2753
ืฉื”ื”ื‘ื ื” ืฉืœื ื• ืฉืœ ืžื“ืข ื”ื”ื ื“ืกื”
10:02
imposes on the design process.
174
602557
2043
ื›ื•ืคื” ืขืœ ืชื”ืœื™ืš ื”ืขื™ืฆื•ื‘.
10:05
Thank you.
175
605560
1167
ืชื•ื“ื”.
10:06
(Applause)
176
606769
3337
ืžื—ื™ืื•ืช ื›ืคื™ื™ื
ืขืœ ืืชืจ ื–ื”

ืืชืจ ื–ื” ื™ืฆื™ื’ ื‘ืคื ื™ื›ื ืกืจื˜ื•ื ื™ YouTube ื”ืžื•ืขื™ืœื™ื ืœืœื™ืžื•ื“ ืื ื’ืœื™ืช. ืชื•ื›ืœื• ืœืจืื•ืช ืฉื™ืขื•ืจื™ ืื ื’ืœื™ืช ื”ืžื•ืขื‘ืจื™ื ืขืœ ื™ื“ื™ ืžื•ืจื™ื ืžื”ืฉื•ืจื” ื”ืจืืฉื•ื ื” ืžืจื—ื‘ื™ ื”ืขื•ืœื. ืœื—ืฅ ืคืขืžื™ื™ื ืขืœ ื”ื›ืชื•ื‘ื™ื•ืช ื‘ืื ื’ืœื™ืช ื”ืžื•ืฆื’ื•ืช ื‘ื›ืœ ื“ืฃ ื•ื™ื“ืื• ื›ื“ื™ ืœื”ืคืขื™ืœ ืืช ื”ืกืจื˜ื•ืŸ ืžืฉื. ื”ื›ืชื•ื‘ื™ื•ืช ื’ื•ืœืœื•ืช ื‘ืกื ื›ืจื•ืŸ ืขื ื”ืคืขืœืช ื”ื•ื•ื™ื“ืื•. ืื ื™ืฉ ืœืš ื”ืขืจื•ืช ืื• ื‘ืงืฉื•ืช, ืื ื ืฆื•ืจ ืื™ืชื ื• ืงืฉืจ ื‘ืืžืฆืขื•ืช ื˜ื•ืคืก ื™ืฆื™ืจืช ืงืฉืจ ื–ื”.

https://forms.gle/WvT1wiN1qDtmnspy7