The Future of Flying Robots | Vijay Kumar | TED Talks

755,090 views ・ 2015-11-04

TED


请双击下面的英文字幕来播放视频。

翻译人员: Zhiting Chen 校对人员: Yinchun Rui
00:13
In my lab, we build autonomous aerial robots
0
13280
3656
在我的实验室, 我们打造了自动飞行的机器人,
00:16
like the one you see flying here.
1
16960
1880
就是你们眼前的这种。
00:20
Unlike the commercially available drones that you can buy today,
2
20720
3696
不像当今市面上销售的那些,
00:24
this robot doesn't have any GPS on board.
3
24440
2640
这个机器人没有GPS定位系统。
00:28
So without GPS,
4
28160
1216
在没有GPS的情况下,
00:29
it's hard for robots like this to determine their position.
5
29400
3280
这样的机器人很难定位自己。
00:34
This robot uses onboard sensors, cameras and laser scanners,
6
34240
4736
这个机器人用机载传感器, 相机和激光扫描仪,
来扫描环境。
00:39
to scan the environment.
7
39000
1696
00:40
It detects features from the environment,
8
40720
3056
它能够探测到环境的特征,
00:43
and it determines where it is relative to those features,
9
43800
2736
并使用三角测量的方式来决定 不同的特征之间
00:46
using a method of triangulation.
10
46560
2136
有怎样的联系。
00:48
And then it can assemble all these features into a map,
11
48720
3456
然后它能够把所有这些信息 整合到一张地图上,
00:52
like you see behind me.
12
52200
1736
就是我背后的这张图。
00:53
And this map then allows the robot to understand where the obstacles are
13
53960
3936
这个地图能让机器人确定 障碍物的位置,
00:57
and navigate in a collision-free manner.
14
57920
2720
并巧妙地避开各种碰撞。
01:01
What I want to show you next
15
61160
2096
我接下来要展示的是
01:03
is a set of experiments we did inside our laboratory,
16
63280
3216
一组我们在户外进行的实验,
01:06
where this robot was able to go for longer distances.
17
66520
3480
证明机器人能够在户外 进行长距离飞行。
01:10
So here you'll see, on the top right, what the robot sees with the camera.
18
70400
5016
你们可以看到,在右上方, 是机器人通过照相机看到的影像。
01:15
And on the main screen --
19
75440
1216
在主屏幕上——
01:16
and of course this is sped up by a factor of four --
20
76680
2456
当然这是以4倍速度在播放展示——
01:19
on the main screen you'll see the map that it's building.
21
79160
2667
在主屏幕上,你们可以看到 地图的创建过程。
01:21
So this is a high-resolution map of the corridor around our laboratory.
22
81851
4285
这是一个高分辨率的地图, 展示了我们实验室周围走廊的样子。
01:26
And in a minute you'll see it enter our lab,
23
86160
2336
很快你们就能看到飞行机器人 进入了我们的实验室,
01:28
which is recognizable by the clutter that you see.
24
88520
2856
这么乱的地方,一看 就知道是我们的实验室。
01:31
(Laughter)
25
91400
1016
(笑声)
01:32
But the main point I want to convey to you
26
92440
2007
但我重点想说的是,
01:34
is that these robots are capable of building high-resolution maps
27
94472
3584
这些飞行器可以创建 高分辨率的地图,
01:38
at five centimeters resolution,
28
98080
2496
达到5厘米的分辨率,
01:40
allowing somebody who is outside the lab, or outside the building
29
100600
4176
可以使那些在实验室外, 或者是房屋外的人,
01:44
to deploy these without actually going inside,
30
104800
3216
无需进入房间即可观察到这些内容,
01:48
and trying to infer what happens inside the building.
31
108040
3760
并尝试了解房屋内发生的状况。
01:52
Now there's one problem with robots like this.
32
112400
2240
当然这样的机器人也有问题。
01:55
The first problem is it's pretty big.
33
115600
2200
首先,它有些大了。
01:58
Because it's big, it's heavy.
34
118120
1680
因为很大,所以很重。
02:00
And these robots consume about 100 watts per pound.
35
120640
3040
这些机器人每磅重量可以消耗 100瓦的电能。
02:04
And this makes for a very short mission life.
36
124360
2280
这使得它的运作时间很短。
02:08
The second problem
37
128000
1456
第二个问题就是,
02:09
is that these robots have onboard sensors that end up being very expensive --
38
129480
3896
这些机器人有机载传感器, 它们非常昂贵——
02:13
a laser scanner, a camera and the processors.
39
133400
3440
一个激光扫描仪,一个相机 以及处理器。
02:17
That drives up the cost of this robot.
40
137280
3040
这些让这个飞行机器人的 制造成本十分高昂。
02:21
So we asked ourselves a question:
41
141440
2656
因此我们问了自己一个问题:
02:24
what consumer product can you buy in an electronics store
42
144120
3776
你能在电子产品商店买到怎样的物品,
02:27
that is inexpensive, that's lightweight, that has sensing onboard and computation?
43
147920
6280
它既不昂贵,又很轻, 还有机载传感器和计算能力?
02:36
And we invented the flying phone.
44
156080
2656
于是我们发明了会飞的手机。
02:38
(Laughter)
45
158760
1936
(笑声)
02:40
So this robot uses a Samsung Galaxy smartphone that you can buy off the shelf,
46
160720
6176
这个机器人使用了你可以轻松购买到的 三星银河系列手机,
02:46
and all you need is an app that you can download from our app store.
47
166920
4016
你所需要的只是一个应用程序, 可以从我们的应用程序商店下载。
02:50
And you can see this robot reading the letters, "TED" in this case,
48
170960
4216
你们可以看到这个飞行机器人在读字, “TED”,
02:55
looking at the corners of the "T" and the "E"
49
175200
2936
观察字母“T”和“E”角落的位置,
02:58
and then triangulating off of that, flying autonomously.
50
178160
3480
再应用三角测量法,实现自主飞行。
03:02
That joystick is just there to make sure if the robot goes crazy,
51
182720
3256
那个手柄的作用仅限于 当飞行器失控时,
Giuseppe就能让它失去功能。
03:06
Giuseppe can kill it.
52
186000
1416
03:07
(Laughter)
53
187440
1640
(笑声)
03:10
In addition to building these small robots,
54
190920
3816
除了制造这些飞行机器人外,
03:14
we also experiment with aggressive behaviors, like you see here.
55
194760
4800
我们还试着让它们做更激烈的动作, 比如这样。
03:19
So this robot is now traveling at two to three meters per second,
56
199920
5296
这个飞行机器人目前的速度是 每秒钟2到3米,
03:25
pitching and rolling aggressively as it changes direction.
57
205240
3496
在转变方向的时候 激烈地起降和翻转。
03:28
The main point is we can have smaller robots that can go faster
58
208760
4256
重点是,我们还能制造更小,更快的 飞行机器人,
03:33
and then travel in these very unstructured environments.
59
213040
2960
它们可以在非常复杂的环境中飞行。
03:37
And in this next video,
60
217120
2056
下一个影片中,
03:39
just like you see this bird, an eagle, gracefully coordinating its wings,
61
219200
5896
你们可以看到这只鹰, 优雅地协调它的翅膀,
03:45
its eyes and feet to grab prey out of the water,
62
225120
4296
眼睛和爪子之间的配合, 把猎物抓出水面,
03:49
our robot can go fishing, too.
63
229440
1896
我们的机器人也能去捕鱼。
03:51
(Laughter)
64
231360
1496
(笑声)
03:52
In this case, this is a Philly cheesesteak hoagie that it's grabbing out of thin air.
65
232880
4056
在这个试验中,它在空中抓起了 这个特大号菲力芝士牛排三明治。
03:56
(Laughter)
66
236960
2400
(笑声)
03:59
So you can see this robot going at about three meters per second,
67
239680
3296
你们可以看到这个机器人 以每秒3米左右的速度飞行,
比步行的速度快一些, 同时还能协调它的手臂和爪子,
04:03
which is faster than walking speed, coordinating its arms, its claws
68
243000
5136
04:08
and its flight with split-second timing to achieve this maneuver.
69
248160
4120
以极快的速度完成整套动作。
04:14
In another experiment,
70
254120
1216
在另一个试验中,
04:15
I want to show you how the robot adapts its flight
71
255360
3656
我想要展示, 机器人是如何依据悬浮载重
04:19
to control its suspended payload,
72
259040
2376
来调整飞行模式的,
04:21
whose length is actually larger than the width of the window.
73
261440
3800
它的总长度大于窗子的高度。
04:25
So in order to accomplish this,
74
265680
1696
为了完成任务,
04:27
it actually has to pitch and adjust the altitude
75
267400
3696
它需要向下倾斜,调整高度,
04:31
and swing the payload through.
76
271120
2320
然后把重物摆动过去。
04:38
But of course we want to make these even smaller,
77
278920
2296
但是,我们希望让机器人变得更小,
04:41
and we're inspired in particular by honeybees.
78
281240
3016
而蜜蜂启发了我们。
04:44
So if you look at honeybees, and this is a slowed down video,
79
284280
3256
如果你们观察一下蜜蜂, 在这个慢速的视频里,
04:47
they're so small, the inertia is so lightweight --
80
287560
3720
它们是这么小, 惯性是这么轻 ——
04:51
(Laughter)
81
291960
1176
(笑声)
04:53
that they don't care -- they bounce off my hand, for example.
82
293160
3536
它们并不在意—— 它们会撞击我的手,比如说。
04:56
This is a little robot that mimics the honeybee behavior.
83
296720
3160
这是个小机器人, 可以模拟蜜蜂的行为。
05:00
And smaller is better,
84
300600
1216
越小越好,
05:01
because along with the small size you get lower inertia.
85
301840
3536
因为尺寸小,惯性就会小。
05:05
Along with lower inertia --
86
305400
1536
惯性小——
05:06
(Robot buzzing, laughter)
87
306960
2856
(机器人嗡嗡声,笑声)
05:09
along with lower inertia, you're resistant to collisions.
88
309840
2816
惯性小,发生撞击的 可能性就低一些。
05:12
And that makes you more robust.
89
312680
1720
这使得机器人更耐用。
05:15
So just like these honeybees, we build small robots.
90
315800
2656
模仿这些蜜蜂, 我们制作了小型机器人。
05:18
And this particular one is only 25 grams in weight.
91
318480
3376
这个特殊的机器人只有25克重。
05:21
It consumes only six watts of power.
92
321880
2160
它的耗电量仅为6瓦。
05:24
And it can travel up to six meters per second.
93
324440
2536
它的飞行速度可达每秒6米。
因此,如果我把它的尺寸按比例放大,
05:27
So if I normalize that to its size,
94
327000
2336
05:29
it's like a Boeing 787 traveling ten times the speed of sound.
95
329360
3640
就好比一架波音787飞机 以10倍于音速的速度飞行。
05:36
(Laughter)
96
336000
2096
(笑声)
05:38
And I want to show you an example.
97
338120
1920
我还要给你们展示一个例子。
05:40
This is probably the first planned mid-air collision, at one-twentieth normal speed.
98
340840
5256
这可能是第一个计划中的 以20分之1正常速度进行的空中相撞。
05:46
These are going at a relative speed of two meters per second,
99
346120
2858
它们的相对速度为每秒2米,
这里展示了基本的原理。
05:49
and this illustrates the basic principle.
100
349002
2480
05:52
The two-gram carbon fiber cage around it prevents the propellers from entangling,
101
352200
4976
两克重的碳纤维笼子包围着它 使螺旋桨不会受损,
05:57
but essentially the collision is absorbed and the robot responds to the collisions.
102
357200
5296
但最关键的是,撞击被吸收了, 机器人能够对撞击做出反应。
06:02
And so small also means safe.
103
362520
2560
并且,小也意味着安全。
06:05
In my lab, as we developed these robots,
104
365400
2016
在我的实验室, 最初开发这些机器人的时候,
06:07
we start off with these big robots
105
367440
1620
我们从大的机器人开始
06:09
and then now we're down to these small robots.
106
369084
2812
现在着手做小的机器人。
06:11
And if you plot a histogram of the number of Band-Aids we've ordered
107
371920
3456
如果你们看一下我们购买 创可贴的数量统计图,
06:15
in the past, that sort of tailed off now.
108
375400
2576
就知道现在我们已经几乎不需要买了。
因为这些机器人非常安全。
06:18
Because these robots are really safe.
109
378000
1960
06:20
The small size has some disadvantages,
110
380760
2456
小尺寸也有一些缺点,
06:23
and nature has found a number of ways to compensate for these disadvantages.
111
383240
4080
但是自然界有很多方法 来弥补这些缺陷。
06:27
The basic idea is they aggregate to form large groups, or swarms.
112
387960
4000
最基本的想法是, 它们可以聚集在一起组成大型的群落。
06:32
So, similarly, in our lab, we try to create artificial robot swarms.
113
392320
3976
因此,在实验室里, 我们也试着去组建机器人群组。
06:36
And this is quite challenging
114
396320
1381
这是非常有难度的工作,
06:37
because now you have to think about networks of robots.
115
397725
3320
因为我们要考虑飞行机器人网络。
06:41
And within each robot,
116
401360
1296
在每一个飞行器中,
06:42
you have to think about the interplay of sensing, communication, computation --
117
402680
5616
我们都需要考虑传感,沟通和计算, 这些互相影响的因素——
06:48
and this network then becomes quite difficult to control and manage.
118
408320
4960
这样的机器人网络 不易控制和管理。
06:54
So from nature we take away three organizing principles
119
414160
3296
从大自然中,我们汲取了 三个组织原则,
06:57
that essentially allow us to develop our algorithms.
120
417480
3160
最终帮助我们完成了算法的发展。
07:01
The first idea is that robots need to be aware of their neighbors.
121
421640
4536
第一个是,机器人 需要注意到它的邻居们。
07:06
They need to be able to sense and communicate with their neighbors.
122
426200
3440
它们要有能力去感知相邻的机器人 并与它们交流。
07:10
So this video illustrates the basic idea.
123
430040
2656
这个视频展示了最基本的想法。
07:12
You have four robots --
124
432720
1296
有4个机器人——
其中的一个被人手动控制了。
07:14
one of the robots has actually been hijacked by a human operator, literally.
125
434040
4240
07:19
But because the robots interact with each other,
126
439217
2239
但是因为机器人会相互通讯,
07:21
they sense their neighbors,
127
441480
1656
它们能够感知到旁边机器人的行动,
07:23
they essentially follow.
128
443160
1296
也会跟着它移动。
07:24
And here there's a single person able to lead this network of followers.
129
444480
5360
这个人能够领导整个 飞行机器人群体的行动。
07:32
So again, it's not because all the robots know where they're supposed to go.
130
452000
5056
再强调一次,这并不是因为 所有的机器人都知道它们要去哪里。
07:37
It's because they're just reacting to the positions of their neighbors.
131
457080
4320
而是它们能根据相邻机器人位置变化 做出相应的反应。
07:43
(Laughter)
132
463720
4120
(笑声)
07:48
So the next experiment illustrates the second organizing principle.
133
468280
5240
下一个实验展示了第二个组织原则。
07:54
And this principle has to do with the principle of anonymity.
134
474920
3800
这个原则与匿名原则有关。
07:59
Here the key idea is that
135
479400
4296
其中的关键在于,
08:03
the robots are agnostic to the identities of their neighbors.
136
483720
4240
机器人是不知道与它们相邻的 机器人的身份的。
08:08
They're asked to form a circular shape,
137
488440
2616
它们被要求形成一个圆圈,
08:11
and no matter how many robots you introduce into the formation,
138
491080
3296
不管你往这个阵列中放多少个机器人,
08:14
or how many robots you pull out,
139
494400
2576
或者是你拿出来多少个机器人,
每个机器人都会很简单地 根据它相邻机器人的行为做出反应。
08:17
each robot is simply reacting to its neighbor.
140
497000
3136
08:20
It's aware of the fact that it needs to form the circular shape,
141
500160
4976
它清楚地知道需要形成圆圈,
08:25
but collaborating with its neighbors
142
505160
1776
与它的相邻机器人配合行动,
08:26
it forms the shape without central coordination.
143
506960
3720
这个过程不需要中枢系统协调。
08:31
Now if you put these ideas together,
144
511520
2416
综合这两个想法之后,
08:33
the third idea is that we essentially give these robots
145
513960
3896
第三个想法就是我们会
08:37
mathematical descriptions of the shape they need to execute.
146
517880
4296
用数学方式来描述 它们需要组成的阵列形状。
08:42
And these shapes can be varying as a function of time,
147
522200
3496
这些形状会根据时间发生变化,
08:45
and you'll see these robots start from a circular formation,
148
525720
4496
你们看到这些飞行器 从一个圆形开始,
08:50
change into a rectangular formation, stretch into a straight line,
149
530240
3256
接着变为长方形, 然后变成一条直线,
08:53
back into an ellipse.
150
533520
1375
又变回椭圆形。
08:54
And they do this with the same kind of split-second coordination
151
534919
3617
它们通过瞬间的协调 来完成这些动作,
08:58
that you see in natural swarms, in nature.
152
538560
3280
就像自然界里的蜂群一样。
09:03
So why work with swarms?
153
543080
2136
为什么要模仿蜂群呢?
09:05
Let me tell you about two applications that we are very interested in.
154
545240
4120
我们对这项技术的两种应用 非常感兴趣。
09:10
The first one has to do with agriculture,
155
550160
2376
第一个有关于农业,
09:12
which is probably the biggest problem that we're facing worldwide.
156
552560
3360
农业应该是全球面临最严峻的问题。
09:16
As you well know,
157
556760
1256
大家都知道,
地球上每7个人中就有1个营养不良。
09:18
one in every seven persons in this earth is malnourished.
158
558040
3520
09:21
Most of the land that we can cultivate has already been cultivated.
159
561920
3480
我们耕种了绝大部分可耕的土地。
09:25
And the efficiency of most systems in the world is improving,
160
565960
3216
世界上很多系统的效率都在提高,
09:29
but our production system efficiency is actually declining.
161
569200
3520
但是我们生产系统的 效率事实上却是在下降。
09:33
And that's mostly because of water shortage, crop diseases, climate change
162
573080
4216
很大程度上源于水源短缺, 作物病害,气候变化
09:37
and a couple of other things.
163
577320
1520
和许多其他的原因。
09:39
So what can robots do?
164
579360
1480
那么,这些机器人能做什么呢?
09:41
Well, we adopt an approach that's called Precision Farming in the community.
165
581200
4616
我们称之为社区里的精密耕作。
09:45
And the basic idea is that we fly aerial robots through orchards,
166
585840
5376
我们基本的想法是 让这些飞行机器人飞越果园,
09:51
and then we build precision models of individual plants.
167
591240
3120
为每一株植物搭建精密的模型。
09:54
So just like personalized medicine,
168
594829
1667
就像个性化的机器,
09:56
while you might imagine wanting to treat every patient individually,
169
596520
4816
想象每个病人都有一对一服务,
10:01
what we'd like to do is build models of individual plants
170
601360
3696
我们要做的就是 为每株植物单独建立模型,
10:05
and then tell the farmer what kind of inputs every plant needs --
171
605080
4136
然后告诉农民 每株植物各需要些什么——
10:09
the inputs in this case being water, fertilizer and pesticide.
172
609240
4440
需要的因素在这里指的是水, 肥料和杀虫剂。
10:14
Here you'll see robots traveling through an apple orchard,
173
614640
3616
你们现在看到的是 机器人飞过一片苹果园,
10:18
and in a minute you'll see two of its companions
174
618280
2256
很快你们就会看到另外两个机器人
10:20
doing the same thing on the left side.
175
620560
1810
在左侧做着同样的事。
10:22
And what they're doing is essentially building a map of the orchard.
176
622800
3656
它们在制作果园的地图。
10:26
Within the map is a map of every plant in this orchard.
177
626480
2816
这个地图里有果园里每株植物的位置。
10:29
(Robot buzzing)
178
629320
1656
(机器人嗡嗡声)
我们来看一下 这些地图是什么样子的。
10:31
Let's see what those maps look like.
179
631000
1896
10:32
In the next video, you'll see the cameras that are being used on this robot.
180
632920
4296
在下一个视频中,你们会看到 机器人上安装的各种摄像头。
10:37
On the top-left is essentially a standard color camera.
181
637240
3240
左上角的是一个高清彩色摄像机。
10:41
On the left-center is an infrared camera.
182
641640
3296
左边中间的是一个红外线摄像机。
10:44
And on the bottom-left is a thermal camera.
183
644960
3776
左下方的是一个热成像摄像机。
10:48
And on the main panel, you're seeing a three-dimensional reconstruction
184
648760
3336
在主面板上,你们会看到 每一株果树的三维图像。
10:52
of every tree in the orchard as the sensors fly right past the trees.
185
652120
6120
这是当机器人飞过果树时 传感器采集到的数据。
10:59
Armed with information like this, we can do several things.
186
659640
4040
有了这些信息, 我们就可以做很多事情。
11:04
The first and possibly the most important thing we can do is very simple:
187
664200
4256
我们能做的第一件也可能是最重要的事 非常简单:
11:08
count the number of fruits on every tree.
188
668480
2440
清点每株果树上果实的数量。
11:11
By doing this, you tell the farmer how many fruits she has in every tree
189
671520
4536
这样,你就能告诉农民 每株果树上有多少果实,
11:16
and allow her to estimate the yield in the orchard,
190
676080
4256
农民就能估算出果园的产量,
11:20
optimizing the production chain downstream.
191
680360
2840
并调整下游的生产链。
11:23
The second thing we can do
192
683640
1616
我们能做的第二件事是
11:25
is take models of plants, construct three-dimensional reconstructions,
193
685280
4496
给植物建构三维立体图,
11:29
and from that estimate the canopy size,
194
689800
2536
从而推算出树冠的尺寸,
11:32
and then correlate the canopy size to the amount of leaf area on every plant.
195
692360
3776
然后通过树冠尺寸推算出 每株植物的树叶面积。
11:36
And this is called the leaf area index.
196
696160
2176
这被称为树叶面积指数。
11:38
So if you know this leaf area index,
197
698360
1936
那么如果我们知道一棵树的 树叶面积指数,
11:40
you essentially have a measure of how much photosynthesis is possible in every plant,
198
700320
5456
就能大概测算出这株果树 在进行多少光合作用,
11:45
which again tells you how healthy each plant is.
199
705800
2880
就能知道这株果树的健康状况。
11:49
By combining visual and infrared information,
200
709520
4216
将视觉信息和红外线信息合起来,
11:53
we can also compute indices such as NDVI.
201
713760
3296
我们还能计算出一些指数, 例如常态化差值植生指数。
11:57
And in this particular case, you can essentially see
202
717080
2816
在这个例子中, 你们可以明显看到
11:59
there are some crops that are not doing as well as other crops.
203
719920
3016
有一些植物并不像其他植物那样健康。
12:02
This is easily discernible from imagery,
204
722960
4056
在图像中很容易识别,
不仅是在视觉图像中,而是结合了
12:07
not just visual imagery but combining
205
727040
2216
12:09
both visual imagery and infrared imagery.
206
729280
2776
视觉和红外线的图像中。
12:12
And then lastly,
207
732080
1336
最后,
12:13
one thing we're interested in doing is detecting the early onset of chlorosis --
208
733440
4016
我们感兴趣的另一件事 是检测早期的植被萎黄病——
12:17
and this is an orange tree --
209
737480
1496
这是一棵橘子树——
你们可以看到泛黄的树叶。
12:19
which is essentially seen by yellowing of leaves.
210
739000
2560
12:21
But robots flying overhead can easily spot this autonomously
211
741880
3896
当机器人飞过这棵树的顶部 就能很快自主识别出来,
12:25
and then report to the farmer that he or she has a problem
212
745800
2936
然后报告农民 他/她遇到问题了,
12:28
in this section of the orchard.
213
748760
1520
就在果园的这个区域。
12:30
Systems like this can really help,
214
750800
2696
这样的系统真的非常实用,
12:33
and we're projecting yields that can improve by about ten percent
215
753520
5816
我们估计这能帮助农业产量提升10%,
12:39
and, more importantly, decrease the amount of inputs such as water
216
759360
3216
更重要的是,通过使用飞行器蜂群,
12:42
by 25 percent by using aerial robot swarms.
217
762600
3280
水资源的用量能够降低25%。
12:47
Lastly, I want you to applaud the people who actually create the future,
218
767200
5736
最后,我希望大家为创造未来的人们 致以热烈的掌声,
12:52
Yash Mulgaonkar, Sikang Liu and Giuseppe Loianno,
219
772960
4920
Yash Mulgaonkar, Sikang Liu 和Giuseppe Loianno,
12:57
who are responsible for the three demonstrations that you saw.
220
777920
3496
你们看到的三次演示都是他们完成的。
13:01
Thank you.
221
781440
1176
谢谢。
13:02
(Applause)
222
782640
5920
(掌声)
关于本网站

这个网站将向你介绍对学习英语有用的YouTube视频。你将看到来自世界各地的一流教师教授的英语课程。双击每个视频页面上显示的英文字幕,即可从那里播放视频。字幕会随着视频的播放而同步滚动。如果你有任何意见或要求,请使用此联系表与我们联系。

https://forms.gle/WvT1wiN1qDtmnspy7