David Hanson: Robots that "show emotion"

187,884 views ใƒป 2009-10-14

TED


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

ืžืชืจื’ื: Ido Dekkers ืžื‘ืงืจ: Sigal Tifferet
00:16
I'm Dr. David Hanson, and I build robots with character.
0
16260
3000
ืื ื™ ื“ืจ. ื“ื•ื™ื“ ื”ื ืกื•ืŸ, ื•ืื ื™ ื‘ื•ื ื” ืจื•ื‘ื•ื˜ื™ื ืขื ืื™ืฉื™ื•ืช.
00:19
And by that, I mean
1
19260
2000
ื•ื‘ื–ื” ืื ื™ ืžืชื›ื•ื•ืŸ
00:21
that I develop robots that are characters,
2
21260
2000
ืฉืื ื™ ืžืคืชื— ืจื•ื‘ื•ื˜ื™ื ืฉื”ื ื“ืžื•ื™ื•ืช,
00:23
but also robots that will eventually
3
23260
3000
ืื‘ืœ ื’ื ืจื•ื‘ื•ื˜ื™ื ืฉื‘ืกื•ืคื• ืฉืœ ื“ื‘ืจ
00:26
come to empathize with you.
4
26260
2000
ื™ืœืžื“ื• ืœื”ื–ื“ื”ื•ืช ืืชื›ื.
00:28
So we're starting with a variety of technologies
5
28260
2000
ืื– ื ืชื—ื™ืœ ืขื ืžื’ื•ื•ืŸ ื˜ื›ื ื•ืœื•ื’ื™ื•ืช
00:30
that have converged into these conversational character robots
6
30260
4000
ืฉื”ืชืื—ื“ื• ืœืชื•ืš ื“ืžื•ื™ื•ืช ื”ืจื•ื‘ื•ื˜ื™ื ื”ืžืฉื•ื—ื—ื™ื
00:34
that can see faces, make eye contact with you,
7
34260
2000
ืฉื™ื›ื•ืœื™ื ืœืจืื•ืช ืคืจืฆื•ืคื™ื, ืœื™ืฆื•ืจ ืงืฉืจ ืขื™ืŸ ืืชื›ื,
00:36
make a full range of facial expressions, understand speech
8
36260
3000
ืœื™ืฆื•ืจ ืžื’ื•ื•ืŸ ื”ื‘ืขื•ืช ืคื ื™ื, ืœื”ื‘ื™ืŸ ื“ื™ื‘ื•ืจ,
00:39
and begin to model how you're feeling
9
39260
4000
ื•ืœื”ื‘ื™ืŸ ืื™ืš ืืชื ืžืจื’ื™ืฉื™ื,
00:43
and who you are, and build a relationship with you.
10
43260
3000
ื•ืžื™ ืืชื, ื•ืœื™ืฆื•ืจ ืžืขืจื›ืช ื™ื—ืกื™ื ืืชื›ื.
00:46
I developed a series of technologies
11
46260
2000
ืคื™ืชื—ืชื™ ืกื“ืจืช ื˜ื›ื ื•ืœื•ื’ื™ื•ืช
00:48
that allowed the robots to make more realistic facial expressions
12
48260
3000
ืฉืžืืคืฉืจื•ืช ืœืจื•ื‘ื•ื˜ื™ื ืœื™ืฆื•ืจ ื”ื‘ืขื•ืช ืคื ื™ื ื™ื•ืชืจ ืจืืœื™ืกื˜ื™ื•ืช
00:51
than previously achieved, on lower power,
13
51260
2000
ื™ื•ืชืจ ืžืฉื”ื™ื” ืืคืฉืจ ื‘ืขื‘ืจ, ืขื ืคื—ื•ืช ื›ื•ื—,
00:53
which enabled the walking biped robots, the first androids.
14
53260
4000
ืžื” ืฉื™ืืคืฉืจ ืืช ื”ืจื•ื‘ื•ื˜ื™ื ื”ื•ืœื›ื™ ืขืœ ืฉื ื™ื™ื, ื”ืื ื“ืจื•ืื™ื“ื™ื ื”ืจืืฉื•ื ื™ื.
00:57
So, it's a full range of facial expressions
15
57260
2000
ืื–, ื˜ื•ื•ื— ืฉืœื ืฉืœ ื”ื‘ืขื•ืช ืคื ื™ื
00:59
simulating all the major muscles in the human face,
16
59260
2000
ืฉืžื“ืžื™ื ืืช ื›ืœ ื”ืฉืจื™ืจื™ื ื”ืขื™ืงืจื™ื™ื ื‘ืคื ื™ื ื”ืื ื•ืฉื™ื•ืช,
01:01
running on very small batteries,
17
61260
2000
ืขื•ื‘ื“ื™ื ืขืœ ืกื•ืœืœื•ืช ืงื˜ื ื•ืช ืžืื•ื“,
01:03
extremely lightweight.
18
63260
2000
ืงืœื™ื ืžืื•ื“.
01:05
The materials that allowed the battery-operated facial expressions
19
65260
3000
ื”ื—ื•ืžืจื™ื ืฉืื™ืคืฉืจื• ืืช ื”ื‘ืขื•ืช ื”ืคื ื™ื ืžื•ืคืขืœื•ืช ื”ืกื•ืœืœื•ืช
01:08
is a material that we call Frubber,
20
68260
2000
ื”ื•ื ื—ื•ืžืจ ืฉืื ื• ืงื•ืจืื™ื ืœื• ืคืจืื‘ืจ,
01:10
and it actually has three major innovations
21
70260
2000
ื•ื™ืฉ ืœืžืขืฉื” ืฉืœื•ืฉื” ื—ื™ื“ื•ืฉื™ื
01:12
in the material that allow this to happen.
22
72260
2000
ื‘ื—ื•ืžืจ ืฉื’ื•ืจื ืœื–ื” ืœืงืจื•ืช.
01:14
One is hierarchical pores,
23
74260
2000
ืื—ื“ ื”ื•ื ื ืงื‘ื•ื‘ื™ื•ืช ื”ื™ืจืจื›ื™ื•ืช.
01:16
and the other is a macro-molecular nanoscale porosity in the material.
24
76260
4000
ื•ื”ืฉื ื™ ื”ื•ื ื ื ื•-ื ืงื‘ื•ื‘ื™ื•ืช ื‘ืจืžื” ื”ืžืงืจื• ืžื•ืœืงื•ืœืจื™ืช ื‘ื—ื•ืžืจ.
01:20
There he's starting to walk.
25
80260
3000
ืคื” ื”ื•ื ืžืชื—ื™ืœ ืœืœื›ืช.
01:23
This is at the Korean Advanced Institute of Science and Technology.
26
83260
3000
ื–ื” ื‘ืžื›ื•ืŸ ื”ืงื•ืจื™ืื ื™ ื”ืžืชืงื“ื ืœืžื“ืข ื•ื˜ื›ื ื•ืœื•ื’ื™ื”.
01:26
I built the head. They built the body.
27
86260
4000
ืื ื™ ื‘ื ื™ืชื™ ืืช ื”ืจืืฉ. ื”ื ื‘ื ื• ืืช ื”ื’ื•ืฃ.
01:30
So the goal here is to achieve sentience in machines,
28
90260
3000
ืื– ื”ืžื˜ืจื” ื”ื™ื ืœื”ืฉื™ื’ ื™ื›ื•ืœืช ื—ื™ืฉื” ื‘ืžื›ื•ื ื•ืช,
01:33
and not just sentience, but empathy.
29
93260
4000
ื•ืœื ืจืง ื™ื›ื•ืœืช ื—ื™ืฉื”, ื’ื ืืžืคื˜ื™ื”.
01:37
We're working with the Machine Perception Laboratory
30
97260
2000
ืื ื—ื ื• ืขื•ื‘ื“ื™ื ืขื ืžืขื‘ื“ืช ื”ืชืคื™ืกื” ื”ืžื›ืื ื™ืช
01:39
at the U.C. San Diego.
31
99260
2000
ื‘ืื•ื ื™ื‘ืจืกื™ื˜ืช ืกืŸ ื“ื™ื™ื’ื•.
01:41
They have this really remarkable facial expression technology
32
101260
3000
ื™ืฉ ืœื”ื ืืช ื˜ื›ื ื•ืœื•ื’ื™ืช ื”ื‘ืขื•ืช ื”ืคื ื™ื ื”ืžื“ื”ื™ืžื”
01:44
that recognizes facial expressions,
33
104260
2000
ืฉืžื–ื”ื” ื”ื‘ืขื•ืช ืคื ื™ื,
01:46
what facial expressions you're making.
34
106260
2000
ืื™ื–ื• ื”ื‘ืขื” ืืชื ืขื•ืฉื™ื.
01:48
It also recognizes where you're looking, your head orientation.
35
108260
3000
ื”ื™ื ื’ื ืžื–ื”ื” ืœืืŸ ืืชื ืžื‘ื™ื˜ื™ื, ืืช ื”ืื•ืจื™ื™ื ื˜ืฆื™ื” ืฉืœ ื”ืจืืฉ ืฉืœื›ื.
01:51
We're emulating all the major facial expressions,
36
111260
2000
ืื ื—ื ื• ืžื“ืžื™ื ืืช ื›ืœ ื”ื‘ืขื•ืช ื”ืคื ื™ื ื”ื—ืฉื•ื‘ื•ืช,
01:53
and then controlling it with the software
37
113260
2000
ื•ืื– ืฉื•ืœื˜ื™ื ื‘ื”ืŸ ืขื ื”ืชื•ื›ื ื”
01:55
that we call the Character Engine.
38
115260
2000
ืฉื ืงืจืืช ืžื ื•ืข ื”ื˜ื™ืคื•ืกื™ื.
01:57
And here is a little bit of the technology that's involved in that.
39
117260
4000
ื•ื”ื ื” ืงืฆืช ืžื”ื˜ื›ื ื•ืœื•ื’ื™ื” ืฉืžืขื•ืจื‘ืช ื‘ื–ื”.
02:01
In fact, right now -- plug it from here, and then plug it in here,
40
121260
8000
ื‘ืขืฆื, ืขื›ืฉื™ื• -- ืชื—ื‘ืจื• ืื•ืชื• ืžืคื”, ื•ืื– ืชื—ื‘ืจื• ืื•ืชื• ืœื›ืืŸ,
02:09
and now let's see if it gets my facial expressions.
41
129260
3000
ื•ืขื›ืฉื™ื• ื‘ื•ืื• ื ืจืื” ืื ื”ื•ื ืžื–ื”ื” ืืช ื”ื‘ืขื•ืช ื”ืคื ื™ื ืฉืœื™.
02:12
Okay. So I'm smiling.
42
132260
5000
ืื•ืงื™, ืื– ืื ื™ ืžื—ื™ื™ืš.
02:17
(Laughter)
43
137260
2000
(ืฆื—ื•ืง)
02:19
Now I'm frowning.
44
139260
2000
ืขื›ืฉื™ื• ืื ื™ ื–ื•ืขืฃ.
02:21
And this is really heavily backlit.
45
141260
4000
ื•ื–ื” ืžื•ืืจ ื‘ื—ื•ื–ืงื” ืžืื—ื•ืจ.
02:25
Okay, here we go.
46
145260
2000
ืื•ืงื™, ื”ื ื” ืžืชื—ื™ืœื™ื.
02:27
Oh, it's so sad.
47
147260
2000
ืื•ื™, ื–ื” ื›ืœ ื›ืš ืขืฆื•ื‘.
02:29
Okay, so you smile, frowning.
48
149260
3000
ืื•ืงื™, ืื– ืืชื” ืžื—ื™ื™ืš, ื–ื•ืขืฃ.
02:32
So his perception of your emotional states
49
152260
2000
ืื– ื”ืชืคื™ืกื” ืฉืœื• ืฉืœ ื”ืžืฆื‘ื™ื ื”ืจื’ืฉื™ื™ื
02:34
is very important for machines to effectively become empathetic.
50
154260
4000
ื—ืฉื•ื‘ื” ืžืื•ื“ ื›ื“ื™ ืœื”ืคื•ืš ืžื›ื•ื ื•ืช ื‘ืฆื•ืจื” ืืคืงื˜ื™ื‘ื™ืช ืœืืžืคื˜ื™ื•ืช.
02:38
Machines are becoming devastatingly capable
51
158260
3000
ืžื›ื•ื ื•ืช ื ืขืฉื•ืช ื‘ืฆื•ืจื” ื ื•ืจืื™ืช ืžืกื•ื’ืœื•ืช
02:41
of things like killing. Right?
52
161260
4000
ืœื“ื‘ืจื™ื ื›ืžื• ืœื”ืจื•ื’. ื ื›ื•ืŸ?
02:45
Those machines have no place for empathy.
53
165260
2000
ื‘ืžื›ื•ื ื•ืช ื”ืืœื” ืื™ืŸ ืžืงื•ื ืœืืžืคื˜ื™ื”.
02:47
And there is billions of dollars being spent on that.
54
167260
2000
ื•ื™ืฉ ืžื™ืœื™ืืจื“ื™ ื“ื•ืœืจื™ื ืฉืžื•ืฆื™ืื™ื ืขืœ ื–ื”.
02:49
Character robotics could plant the seed
55
169260
2000
ืจื•ื‘ื•ื˜ื™ืงื” ื”ื‘ืขืชื™ืช ื™ื›ื•ืœื” ืœืฉืชื•ืœ ืืช ื”ื–ืจืข
02:51
for robots that actually have empathy.
56
171260
2000
ืœืจื•ื‘ื•ื˜ื™ื ืฉื™ืฉ ืœื”ื ืืžืคื˜ื™ื”.
02:53
So, if they achieve human level intelligence
57
173260
2000
ืื–, ืื ื”ื ื™ื’ื™ืขื• ืœืจืžืช ืื™ื ื˜ื™ืœื™ื’ื ืฆื™ื” ืื ื•ืฉื™ืช
02:55
or, quite possibly, greater than human levels of intelligence,
58
175260
4000
ืื•, ืžืื•ื“ ืืคืฉืจื™, ืจืžืช ืื™ื ื˜ื™ืœื™ื’ื ืฆื™ื” ื’ื‘ื•ื”ื” ืžืฉืœ ื”ืื“ื,
02:59
this could be the seeds of hope for our future.
59
179260
3000
ื–ื” ื™ื›ื•ืœ ืœื”ื™ื•ืช ื–ืจืข ื”ืชืงื•ื” ืœืขืชื™ื“ ืฉืœื ื•.
03:02
So, we've made 20 robots in the last eight years, during the course of getting my Ph.D.
60
182260
4000
ืื–, ื™ืฆืจื ื• 20 ืจื•ื‘ื•ื˜ื™ื ื‘ืฉืžื•ื ื” ื”ืฉื ื™ื ื”ืื—ืจื•ื ื•ืช, ื‘ืžื”ืœืš ื”ืฉื’ืช ื”ื“ื•ืงื˜ื•ืจื˜ ืฉืœื™.
03:06
And then I started Hanson Robotics,
61
186260
2000
ื•ืื– ื”ืงืžืชื™ ืืช Hanson Robotics.
03:08
which has been developing these things for mass manufacturing.
62
188260
4000
ืฉืคื™ืชื—ื” ืืช ืืœื” ืœื™ืฆื•ืจ ื”ืžื•ื ื™.
03:12
This is one of our robots
63
192260
2000
ื–ื” ืื—ื“ ืžื”ืจื•ื‘ื•ื˜ื™ื ืฉืœื ื•
03:14
that we showed at Wired NextFest a couple of years ago.
64
194260
2000
ืฉื”ืจืื ื• ื‘ Wired NextFest ืœืคื ื™ ื›ืžื” ืฉื ื™ื.
03:16
And it sees multiple people in a scene,
65
196260
3000
ื•ื”ื•ื ืจื•ืื” ื›ืžื” ืื ืฉื™ื ื‘ืกืฆื ื”,
03:19
remembers where individual people are,
66
199260
2000
ื–ื•ื›ืจ ืื™ืคื” ืื ืฉื™ื ื ืžืฆืื™ื,
03:21
and looks from person to person, remembering people.
67
201260
4000
ื•ืžื‘ื™ื˜ ืžืื“ื ืœืื“ื, ื–ื•ื›ืจ ืื ืฉื™ื.
03:25
So, we're involving two things.
68
205260
2000
ืื–, ืื ื—ื ื• ืžืขืจื‘ื™ื ืฉื ื™ ื“ื‘ืจื™ื.
03:27
One, the perception of people,
69
207260
2000
ืื—ื“, ื”ื”ื‘ื ื” ื”ืชืคื™ืกืชื™ืช ืฉืœ ืื ืฉื™ื
03:29
and two, the natural interface,
70
209260
4000
ื•ืฉืชื™ื™ื, ื”ืžืžืฉืง ื”ื˜ื‘ืขื™,
03:33
the natural form of the interface,
71
213260
2000
ื”ืฆื•ืจื” ื”ื˜ื‘ืขื™ืช ืฉืœ ื”ืžืžืฉืง,
03:35
so that it's more intuitive for you to interact with the robot.
72
215260
3000
ื›ืš ืฉื™ื•ืชืจ ืื™ื ื˜ื•ืื™ื˜ื™ื‘ื™ ืœื›ื ืœืชืงืฉืจ ืขื ื”ืจื•ื‘ื•ื˜.
03:38
You start to believe that it's alive and aware.
73
218260
3000
ืืชื ืžืชื—ื™ืœื™ื ืœื”ืืžื™ืŸ ืฉื”ื•ื ื—ื™ ื•ืžื•ื“ืข.
03:41
So one of my favorite projects was bringing all this stuff together
74
221260
3000
ืื– ืื—ื“ ื”ืคืจื•ื™ื™ืงื˜ื™ื ื”ื—ื‘ื™ื‘ื™ื ืขืœื™ ื”ื•ื ื—ื™ื‘ื•ืจ ื›ืœ ื”ื“ื‘ืจื™ื
03:44
in an artistic display of an android portrait
75
224260
3000
ื‘ืžื•ืฆื’ ืื•ืžื ื•ืชื™ ืฉืœ ื“ื™ื•ืงืŸ ืฉืœ ืื ื“ืจื•ืื™ื“
03:47
of science-fiction writer Philip K. Dick,
76
227260
2000
ืฉืœ ืกื•ืคืจ ื”ืžื“ืข ื”ื‘ื™ื“ื™ื•ื ื™ ืคื™ืœื™ืค ืง. ื“ื™ืง,
03:49
who wrote great works like, "Do Androids Dream of Electric Sheep?"
77
229260
3000
ืฉื›ืชื‘ ืขื‘ื•ื“ื•ืช ื’ื“ื•ืœื•ืช ื›ืžื•, "ื”ืื ืื ื“ืจื•ืื™ื“ื™ื ื—ื•ืœืžื™ื ืขืœ ื›ื‘ืฉื™ื ื—ืฉืžืœื™ื•ืช?",
03:52
which was the basis of the movie "Bladerunner."
78
232260
2000
ืฉื”ื™ื” ื”ื‘ืกื™ืก ืœืกืจื˜ "ื‘ืœื™ื™ื“ืจืื ืจ."
03:54
In these stories, robots often think
79
234260
3000
ื‘ืกื™ืคื•ืจื™ื ื”ืืœื”, ืจื•ื‘ื•ื˜ื™ื ื—ื•ืฉื‘ื™ื
03:57
that they're human, and they sort of come to life.
80
237260
2000
ืฉื”ื ืื ื•ืฉื™ื™ื. ื•ื”ื ื›ืื™ืœื• ืžืชืขื•ืจืจื™ื ืœื—ื™ื™ื.
03:59
So we put his writings, letters,
81
239260
3000
ืื– ืื ื—ื ื• ืฉืžื™ื ืืช ื”ื›ืชื‘ื™ื, ืžื›ืชื‘ื™ื,
04:02
his interviews, correspondences,
82
242260
3000
ื”ืจืื™ื•ื ื•ืช ืฉืœื•, ื”ื”ืชื›ืชื‘ื•ื™ื•ืช,
04:05
into a huge database of thousands of pages,
83
245260
2000
ืœืžืื’ืจ ืžื™ื“ืข ืขืฆื•ื ืฉืœ ืืœืคื™ ื“ืคื™ื,
04:07
and then used some natural language processing
84
247260
2000
ื•ืื– ืžืฉืชืžืฉื™ื ื‘ืขื™ื‘ื•ื“ ืฉืคื” ื˜ื‘ืขื™
04:09
to allow you to actually have a conversation with him.
85
249260
2000
ื›ื“ื™ ืœืืคืฉืจ ืœื›ื ืžืžืฉ ืœื ื”ืœ ืฉื™ื—ื” ืื™ืชื•.
04:11
And it was kind of spooky, because he would say these things
86
251260
2000
ื•ื–ื” ื”ื™ื” ื“ื™ ืžืคื—ื™ื“. ืžืคื ื™ ืฉื”ื•ื ื”ื™ื” ืื•ืžืจ ื“ื‘ืจื™ื
04:13
that just sounded like they really understood you.
87
253260
3000
ืฉื ืฉืžืข ื›ืื™ืœื• ื”ื•ื ื‘ืืžืช ืžื‘ื™ืŸ ืืชื›ื.
04:16
And this is one of the most exciting projects that we're developing,
88
256260
3000
ื•ื–ื” ืื—ื“ ื”ืคืจื•ื™ื™ืงื˜ื™ื ื”ื›ื™ ืžืจื’ืฉื™ื ืฉืื ื—ื ื• ืžืคืชื—ื™ื,
04:19
which is a little character that's a spokesbot
89
259260
3000
ืฉื”ื•ื ื“ืžื•ืช ืงื˜ื ื” ืฉื”ื™ื ื“ื•ื‘ืจ
04:22
for friendly artificial intelligence, friendly machine intelligence.
90
262260
3000
ืœืื™ื ื˜ื™ืœื™ื’ื ืฆื™ื” ืžืœืื›ื•ืชื™ืช ื—ื‘ืจื•ืชื™ืช, ืื™ื ื˜ื™ืœื™ื’ื ืฆื™ื” ืžื›ืื ื™ืช ื—ื‘ืจื•ืชื™ืช.
04:25
And we're getting this mass-manufactured.
91
265260
2000
ื•ืื ื—ื ื• ืžื™ื™ืฆืจื™ื ืื•ืชื• ื‘ื™ืฆื•ืจ ื”ืžื•ื ื™.
04:27
We specked it out to actually be doable
92
267260
3000
ืืคื™ื™ื ื• ืื•ืชื• ื›ื“ื™ ืฉื™ื”ื™ื™ื” ื‘ืจ ื™ืฆื•ืจ
04:30
with a very, very low-cost bill of materials,
93
270260
3000
ืขื ืจืฉื™ืžืช ื—ื•ืžืจื™ื™ื ืžืžืฉ ืžืžืฉ ื–ื•ืœื”,
04:33
so that it can become a childhood companion for kids.
94
273260
4000
ื›ืš ืฉื”ื•ื ื™ื•ื›ืœ ืœื”ืคื•ืš ืœื—ื‘ืจ ื™ืœื“ื•ืช ืœื™ืœื“ื™ื.
04:37
Interfacing with the Internet, it gets smarter over the years.
95
277260
3000
ืžืชืžืžืฉืง ืœืื™ื ื˜ืจื ื˜, ื”ื•ื ืžื—ื›ื™ื ืขื ื”ืฉื ื™ื.
04:40
As artificial intelligence evolves, so does his intelligence.
96
280260
3000
ื›ืฉืื™ื ื˜ื™ืœื™ื’ื ืฆื™ื” ืžืœืื›ื•ืชื™ืช ืžืชืคืชื—ืช, ื›ืš ื’ื ื”ืื™ื ื˜ื™ืœื™ื’ื ืฆื™ื” ืฉืœื•.
04:43
Chris Anderson: Thank you so much. That's incredible.
97
283260
2000
ื›ืจื™ืก ืื ื“ืจืกื•ืŸ: ืชื•ื“ื” ืจื‘ื” ืœืš. ื–ื” ืžื“ื”ื™ื.
04:45
(Applause)
98
285260
7000
(ื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