TEDGlobal 2013
Raffaello D'Andrea: The astounding athletic power of quadcopters
拉菲羅安德烈 (Raffaello D'Andrea): 四軸飛行器驚人的運動能力
Filmed:
Readability: 4.7
12,409,728 views
在 TEDGlobal 的機器人實驗室，拉菲羅安德烈 (Raffaello D'Andrea) 展示他的四軸飛行器：是可以像運動員一樣思考的機器人，用可以幫助它們學習的演算法，來解決物理的問題。經由一系列精采的示範，安德烈展示了無人機可以接球、平衡，以及共同做出決定－－注意還有用 Kinect 來控制四軸飛行器的示範，讓人好想立刻擁有。
Raffaello D'Andrea - Autonomous systems pioneer
Raffaello D'Andrea explores the possibilities of autonomous technology by collaborating with artists, engineers and entrepreneurs. Full bio
Raffaello D'Andrea explores the possibilities of autonomous technology by collaborating with artists, engineers and entrepreneurs. Full bio
Double-click the English transcript below to play the video.
00:23
So what does it mean for a machine to be athletic?
0
11307
3184
機器的運動能力好是什麼意思？
00:26
We will demonstrate the concept of machine athleticism
1
14491
3417
我們將展示機器運動能力的概念
00:29
and the research to achieve it
2
17908
1720
以及為了實現而進行的研究
00:31
with the help of these flying machines called quadrocopters,
3
19628
2511
靠的是這些飛行機器，叫做
「四軸飛行器」 (quadrocopters)
「四軸飛行器」 (quadrocopters)
00:34
or quads, for short.
4
22139
1887
簡稱為「四軸」
00:38
Quads have been around for a long time.
5
26034
2529
四軸已經存在很久了
00:40
The reason that they're so popular these days
6
28563
1599
最近很受歡迎的原因
00:42
is because they're mechanically simple.
7
30162
1965
是因為在機械方面很簡單
00:44
By controlling the speeds of these four propellers,
8
32127
2108
只要控制這四個螺旋槳的速度
00:46
these machines can roll, pitch, yaw,
9
34235
3048
這些機器可以側滾，俯仰，偏擺
00:49
and accelerate along their common orientation.
10
37283
2825
以及沿著共同方向加速
00:52
On board are also a battery, a computer,
11
40108
3071
上面還有電池及一台電腦
00:55
various sensors and wireless radios.
12
43179
3954
各種感測器和無線收發器
00:59
Quads are extremely agile, but this agility comes at a cost.
13
47133
4629
四軸極為靈活，但要付出代價
01:03
They are inherently unstable, and they need some form
14
51762
2992
它本質上不穩定，需要某種形式的
01:06
of automatic feedback control in order to be able to fly.
15
54754
3972
自動回饋控制，才可能飛行
01:16
So, how did it just do that?
16
64259
3238
要怎麼做到這點呢？
01:19
Cameras on the ceiling and a laptop
17
67497
1818
天花板上的攝影機
和一台筆記型電腦
和一台筆記型電腦
01:21
serve as an indoor global positioning system.
18
69315
2576
就像是室內的全球定位系統
01:23
It's used to locate objects in the space
19
71891
2185
用來為物體在空間中定位
01:26
that have these reflective markers on them.
20
74076
2527
物體上有這些反光標記
01:28
This data is then sent to another laptop
21
76603
2061
定位資料送到另一台筆記型電腦
01:30
that is running estimation and control algorithms,
22
78664
2211
執行估計與控制的演算法
01:32
which in turn sends commands to the quad,
23
80875
1886
再反過來把命令送到四軸
01:34
which is also running estimation and control algorithms.
24
82761
3485
四軸本身也在執行
估計與控制的演算法
估計與控制的演算法
01:41
The bulk of our research is algorithms.
25
89620
2510
我們的研究大部分都是演算法
01:44
It's the magic that brings these machines to life.
26
92130
4161
演算法是使這些機器活過來的魔法
01:48
So how does one design the algorithms
27
96291
2043
要怎麼設計演算法
01:50
that create a machine athlete?
28
98334
2277
才能創造出機器運動員？
01:52
We use something broadly called model-based design.
29
100611
2880
我們使用的方法
泛稱為模型化基礎設計
泛稱為模型化基礎設計
01:55
We first capture the physics with a mathematical model
30
103491
3154
我們首先用數學模型捕捉
01:58
of how the machines behave.
31
106645
2134
機器行為的物理法則
02:00
We then use a branch of mathematics
32
108779
2297
然後用數學的一個分支—
02:03
called control theory to analyze these models
33
111076
2831
「控制理論」來分析這些模型
02:05
and also to synthesize algorithms for controlling them.
34
113907
3913
並合成控制的演算法
02:09
For example, that's how we can make the quad hover.
35
117820
3048
例如我們想讓四軸原地懸停
02:12
We first captured the dynamics
36
120868
1408
我們首先捕捉動態
02:14
with a set of differential equations.
37
122276
1906
是一組微分方程式
02:16
We then manipulate these equations with the help
38
124182
2349
然後操縱這些方程式
02:18
of control theory to create algorithms that stabilize the quad.
39
126531
4640
在控制理論建立的演算法幫忙下
讓四軸得以穩定
讓四軸得以穩定
02:23
Let me demonstrate the strength of this approach.
40
131171
2946
讓我展示這種方法的優點
02:29
Suppose that we want this quad to not only hover
41
137198
2549
假設我們希望四軸不止是懸停
02:31
but to also balance this pole.
42
139747
2782
還要讓桿子平衡
02:34
With a little bit of practice,
43
142529
1844
經過一些練習
02:36
it's pretty straightforward for a human being to do this,
44
144373
2391
人類很容易可以做到
02:38
although we do have the advantage of having
45
146764
1755
雖然我們有優勢
02:40
two feet on the ground
46
148519
1328
雙腳可以著地
02:41
and the use of our very versatile hands.
47
149847
2957
還有極為靈活的手
02:44
It becomes a little bit more difficult
48
152804
2469
像這樣就有點困難：
02:47
when I only have one foot on the ground
49
155273
2296
如果只有一腳著地
02:49
and when I don't use my hands.
50
157569
2799
而且不准用手
02:52
Notice how this pole has a reflective marker on top,
51
160368
2951
請注意，桿子頂上有反光標記
02:55
which means that it can be located in the space.
52
163319
3894
表示可在空間中定到它的位置
03:04
(Applause)
53
172971
5976
（掌聲）
03:10
You can notice that this quad is making fine adjustments
54
178947
2826
你可以看到，這架四軸正進行微調
03:13
to keep the pole balanced.
55
181773
2195
以讓桿子保持平衡
03:15
How did we design the algorithms to do this?
56
183968
3059
我們是怎麼設計演算法來做到的？
03:19
We added the mathematical model of the pole
57
187027
2105
我們加入了桿子的數學模型
03:21
to that of the quad.
58
189132
1519
到四軸中
03:22
Once we have a model of the combined quad-pole system,
59
190651
2954
一旦我們有了
結合四軸與桿子的模型
結合四軸與桿子的模型
03:25
we can use control theory to create algorithms for controlling it.
60
193605
4933
就可以用控制理論
建立控制的演算法
建立控制的演算法
03:30
Here, you see that it's stable,
61
198538
1588
這裡，你看，很穩定
03:32
and even if I give it little nudges,
62
200126
2693
就算我輕輕推一下
03:34
it goes back to the nice, balanced position.
63
202819
5403
它仍可回到完全平衡的位置
03:40
We can also augment the model to include
64
208222
1663
我們還可以加強模型，以包括
03:41
where we want the quad to be in space.
65
209885
2441
我們希望四軸在空間的位置
03:44
Using this pointer, made out of reflective markers,
66
212326
3069
用這根有反光標記的指示棒
03:47
I can point to where I want the quad to be in space
67
215395
2224
可以指出我要四軸到的位置
03:49
a fixed distance away from me.
68
217619
3367
和我保持固定的距離
04:07
The key to these acrobatic maneuvers is algorithms,
69
235763
2902
這些特技動作的關鍵是演算法
04:10
designed with the help of mathematical models
70
238665
2426
它的設計要靠數學模型
04:13
and control theory.
71
241091
1950
與控制理論
04:15
Let's tell the quad to come back here
72
243041
2214
我要告訴四軸回來這裡
04:17
and let the pole drop,
73
245255
1819
並讓桿子倒下來
04:19
and I will next demonstrate the importance
74
247074
1918
接下來我要展示
04:20
of understanding physical models
75
248992
2119
了解物理模型、
04:23
and the workings of the physical world.
76
251111
4120
以及實體世界運作的重要性
04:37
Notice how the quad lost altitude
77
265462
1770
注意四軸的高度降低了
04:39
when I put this glass of water on it.
78
267232
2082
我把這杯水放上去
04:41
Unlike the balancing pole, I did not include
79
269314
2801
不像平衡桿，我並未把玻璃杯
04:44
the mathematical model of the glass in the system.
80
272115
2584
的數學模型加到系統裡
04:46
In fact, the system doesn't even know that the glass of water is there.
81
274699
2919
事實上，系統根本不知道有杯水
04:49
Like before, I could use the pointer to tell the quad
82
277618
3292
我一樣可以用指示棒來告訴四軸
04:52
where I want it to be in space.
83
280910
2589
我希望它在空間中的位置
04:55
(Applause)
84
283499
9597
（掌聲）
05:05
Okay, you should be asking yourself,
85
293096
2110
好吧，你應該問自己
05:07
why doesn't the water fall out of the glass?
86
295206
2509
為什麼杯中的水不會灑出來？
05:09
Two facts: The first is that gravity acts
87
297715
3211
兩個事實：第一點是重力
05:12
on all objects in the same way.
88
300926
2125
對所有的物體作用相同
05:15
The second is that the propellers are all pointing
89
303051
2464
第二點是，推進器都指向
05:17
in the same direction of the glass, pointing up.
90
305515
3127
和杯子相同的方向，也就是向上
05:20
You put these two things together, the net result
91
308642
2377
兩個原因加在一起，最終結果是
05:23
is that all side forces on the glass are small
92
311019
2287
玻璃杯各方向的側向力都很小
05:25
and are mainly dominated by aerodynamic effects,
93
313306
2785
還是以空氣動力學效應為主
05:28
which as these speeds are negligible.
94
316091
3841
因此這些速度是微不足道的
05:35
And that's why you don't need to model the glass.
95
323336
2071
這就是為什麼不需要杯子的模型
05:37
It naturally doesn't spill no matter what the quad does.
96
325407
3848
水自然不會灑出來
不管四軸怎麼動
不管四軸怎麼動
05:50
(Applause)
97
338651
7051
（掌聲）
05:57
The lesson here is that some high-performance tasks
98
345702
4016
這裡學到的是，有些高性能任務
06:01
are easier than others,
99
349718
1397
比其他的容易
06:03
and that understanding the physics of the problem
100
351115
2296
還有，理解問題背後的物理
06:05
tells you which ones are easy and which ones are hard.
101
353411
2616
可告訴我們哪些容易、哪些困難
06:08
In this instance, carrying a glass of water is easy.
102
356027
2359
以此為例，載運水很容易
06:10
Balancing a pole is hard.
103
358386
3785
平衡桿子則很困難
06:14
We've all heard stories of athletes
104
362171
1802
我們都聽過運動員的故事
06:15
performing feats while physically injured.
105
363973
2493
雖然身體受傷，仍然完成壯舉
06:18
Can a machine also perform
106
366466
1519
機器可以在
06:19
with extreme physical damage?
107
367985
2651
受重傷的情況下運作嗎？
06:22
Conventional wisdom says that you need
108
370636
1726
傳統觀念認為，你需要
06:24
at least four fixed motor propeller pairs in order to fly,
109
372362
3690
至少四個固定的馬達螺旋槳才能飛
06:28
because there are four degrees of freedom to control:
110
376052
2112
因為有四個自由度要控制：
06:30
roll, pitch, yaw and acceleration.
111
378164
3028
側滾、俯仰、偏擺、加速
06:33
Hexacopters and octocopters, with six and eight propellers,
112
381192
3245
六軸和八軸分別有六和八個螺旋槳
06:36
can provide redundancy,
113
384437
1483
可提供冗餘
06:37
but quadrocopters are much more popular
114
385920
1989
但四軸則普及多了
06:39
because they have the minimum number
115
387909
1815
因為它具有最小數目的
06:41
of fixed motor propeller pairs: four.
116
389724
2476
固定馬達螺旋槳：四個
06:44
Or do they?
117
392200
1965
是這樣嗎？
07:01
If we analyze the mathematical model of this machine
118
409476
2600
我們分析這台機器的數學模型
07:04
with only two working propellers,
119
412076
2176
如果只有兩個螺旋槳可運作
07:06
we discover that there's an unconventional way to fly it.
120
414252
6756
我們發現有種非傳統的方式可飛行
07:19
We relinquish control of yaw,
121
427980
1706
我們放棄控制偏擺
07:21
but roll, pitch and acceleration can still be controlled
122
429686
3070
仍然可以控制側滾、俯仰、加速
07:24
with algorithms that exploit this new configuration.
123
432756
5452
只要演算法能處理這種新配置
07:33
Mathematical models tell us exactly when
124
441668
2432
數學模型告訴我們何時
07:36
and why this is possible.
125
444100
2072
和為何這是可能的
07:38
In this instance, this knowledge allows us to design
126
446172
2368
此例中，這種知識讓我們能設計出
07:40
novel machine architectures
127
448540
2256
新穎的機器架構
07:42
or to design clever algorithms that gracefully handle damage,
128
450796
4176
或優雅應對損害的巧妙演算法
07:46
just like human athletes do,
129
454972
1724
就像人類運動員
07:48
instead of building machines with redundancy.
130
456696
3823
而不必建構具有冗餘的機器
07:52
We can't help but hold our breath when we watch
131
460519
2112
我們不禁屏住呼吸
07:54
a diver somersaulting into the water,
132
462631
2437
當我們看到跳水選手
翻個筋斗入水、
翻個筋斗入水、
07:57
or when a vaulter is twisting in the air,
133
465068
1790
或撐竿跳選手在空中扭轉、
07:58
the ground fast approaching.
134
466858
1718
同時快速接近地面
08:00
Will the diver be able to pull off a rip entry?
135
468576
2568
跳水選手入水時能否成功壓水花？
08:03
Will the vaulter stick the landing?
136
471144
2000
撐竿跳選手能否完美著地？
08:05
Suppose we want this quad here
137
473144
1668
假設我們希望四軸
08:06
to perform a triple flip and finish off
138
474812
2451
表演三轉空翻，並結束在
08:09
at the exact same spot that it started.
139
477263
2269
開始的同一地點
08:11
This maneuver is going to happen so quickly
140
479532
2347
這個動作太快了
08:13
that we can't use position feedback to correct the motion during execution.
141
481879
3629
無法用位置回饋信號
糾正執行過程中的動作
糾正執行過程中的動作
08:17
There simply isn't enough time.
142
485508
2274
時間根本不夠
08:19
Instead, what the quad can do is perform the maneuver blindly,
143
487782
3694
相反的，四軸只能盲目進行動作
08:23
observe how it finishes the maneuver,
144
491476
2232
觀察四軸如何完成動作
08:25
and then use that information to modify its behavior
145
493708
2424
再用這些資訊來修改行為
08:28
so that the next flip is better.
146
496132
2289
讓下次空翻更進步
08:30
Similar to the diver and the vaulter,
147
498421
1812
就像跳水選手和撐竿跳選手
08:32
it is only through repeated practice
148
500233
1919
只有通過反覆練習
08:34
that the maneuver can be learned and executed
149
502152
1925
才能學會動作
08:36
to the highest standard.
150
504077
2133
並達到最完美的境界
08:46
(Applause)
151
514412
4752
（掌聲）
08:51
Striking a moving ball is a necessary skill in many sports.
152
519164
3472
打擊移動中的球
對許多運動是必要技能
對許多運動是必要技能
08:54
How do we make a machine do
153
522636
1795
我們如何讓一台機器做出
08:56
what an athlete does seemingly without effort?
154
524431
3753
對運動員看似毫不費力的動作？
09:15
(Applause)
155
543943
6599
（掌聲）
09:22
This quad has a racket strapped onto its head
156
550542
2650
這架四軸頂部綁了個球拍
09:25
with a sweet spot roughly the size of an apple, so not too large.
157
553192
3487
甜蜜點大約一個蘋果大小
所以不會太大
所以不會太大
09:28
The following calculations are made every 20 milliseconds,
158
556679
3167
以下的計算每二十毫秒執行一次
09:31
or 50 times per second.
159
559846
1756
也就是每秒執行五十次
09:33
We first figure out where the ball is going.
160
561602
2812
我們首先弄清楚球會飛到哪裡
09:36
We then next calculate how the quad should hit the ball
161
564414
2437
然後計算四軸如何擊中球
09:38
so that it flies to where it was thrown from.
162
566851
3099
四軸飛到球丟出的附近
09:41
Third, a trajectory is planned that carries the quad
163
569950
4456
第三，規劃出四軸由目前位置
09:46
from its current state to the impact point with the ball.
164
574406
3024
到擊球位置的軌道
09:49
Fourth, we only execute 20 milliseconds' worth of that strategy.
165
577430
3809
第四，只需執行這戰略二十毫秒
09:53
Twenty milliseconds later, the whole process is repeated
166
581239
2807
二十毫秒過後，再重複整個過程
09:56
until the quad strikes the ball.
167
584046
2243
直到四軸擊中球
10:07
(Applause)
168
595560
2646
（掌聲）
10:10
Machines can not only perform dynamic maneuvers on their own,
169
598206
3372
機器不僅可以自主執行動態操作
10:13
they can do it collectively.
170
601578
1863
還可以互相合作
10:15
These three quads are cooperatively carrying a sky net.
171
603441
3587
這三架四軸合作張開網子
10:28
(Applause)
172
616574
5411
（掌聲）
10:33
They perform an extremely dynamic
173
621985
2197
它們執行的，是非常動態
10:36
and collective maneuver
174
624182
2168
且需要合作的動作
10:38
to launch the ball back to me.
175
626350
1692
把球丟回給我
10:40
Notice that, at full extension, these quads are vertical.
176
628042
3511
請注意的，在完全伸展時
這些四軸是垂直的
這些四軸是垂直的
10:48
(Applause)
177
636486
1772
（掌聲）
10:50
In fact, when fully extended,
178
638258
2287
事實上，在完全伸展時
10:52
this is roughly five times greater than what a bungee jumper feels
179
640545
2685
大約產生五倍於高空彈跳
10:55
at the end of their launch.
180
643230
4588
最低點的力量
11:03
The algorithms to do this are very similar
181
651009
2677
做到這點的演算法非常相似於
11:05
to what the single quad used to hit the ball back to me.
182
653686
3384
單一四軸把球打回我身邊
11:09
Mathematical models are used to continuously re-plan
183
657070
2864
使用數學模型不斷重新規劃
11:11
a cooperative strategy 50 times per second.
184
659934
4515
合作策略，每秒五十次
11:16
Everything we have seen so far has been
185
664449
1877
到目前為止，我們看到的一切
11:18
about the machines and their capabilities.
186
666326
2463
都是關於機器及其功能
11:20
What happens when we couple this machine athleticism
187
668789
3015
我們若把這台機器的運動能力
11:23
with that of a human being?
188
671804
1776
和人結合，會發生什麼事？
11:25
What I have in front of me is a commercial gesture sensor
189
673580
3805
在我面前的是一具
商業的人體動作感測器
商業的人體動作感測器
11:29
mainly used in gaming.
190
677385
1309
主要用於遊戲
(Kinect)
(Kinect)
11:30
It can recognize what my various body parts
191
678694
1804
可以即時識別我身體
11:32
are doing in real time.
192
680498
2048
各部位的動作
11:34
Similar to the pointer that I used earlier,
193
682546
2116
就像剛才我用指示棒
11:36
we can use this as inputs to the system.
194
684662
2792
我們可用這個作為系統的輸入
11:39
We now have a natural way of interacting
195
687454
2396
我們就有了自然的互動方式
11:41
with the raw athleticism of these quads with my gestures.
196
689850
4944
用我的手勢和四軸的
原始運動能力互動
原始運動能力互動
12:22
(Applause)
197
730453
4400
（掌聲）
12:35
Interaction doesn't have to be virtual. It can be physical.
198
743982
4007
互動不一定是虛擬
也可以是實體的
也可以是實體的
12:39
Take this quad, for example.
199
747989
1725
以此四軸為例
12:41
It's trying to stay at a fixed point in space.
200
749714
2628
它試著要待在空間裡固定的一點
12:44
If I try to move it out of the way, it fights me,
201
752342
3837
如果我試著將它移開，它會抵抗
12:48
and moves back to where it wants to be.
202
756179
4155
並移回它想待的地方
12:52
We can change this behavior, however.
203
760334
3039
但我們可以改變這種行為
12:55
We can use mathematical models
204
763373
1699
我們可以用數學模型
12:57
to estimate the force that I'm applying to the quad.
205
765072
3133
估算出我對四軸施力的大小
13:00
Once we know this force, we can also change the laws of physics,
206
768205
3238
一旦知道了力量大小
我們也可以改變物理規則
我們也可以改變物理規則
13:03
as far as the quad is concerned, of course.
207
771443
4499
當然是對四軸而言
13:07
Here the quad is behaving as if it were
208
775942
2263
這架四軸的行為就好像它
13:10
in a viscous fluid.
209
778205
4365
在黏性流體中一樣
13:14
We now have an intimate way
210
782570
2174
我們現在有了親密的方式
13:16
of interacting with a machine.
211
784744
1849
可與機器互動
13:18
I will use this new capability to position
212
786593
2506
我要用這新功能
把載著相機的四軸
把載著相機的四軸
13:21
this camera-carrying quad to the appropriate location
213
789099
2577
定位到適當位置
13:23
for filming the remainder of this demonstration.
214
791676
3186
以拍攝接下來的示範
13:36
So we can physically interact with these quads
215
804222
2768
我們可以與四軸進行實體互動
13:38
and we can change the laws of physics.
216
806990
2403
我們也可以改變物理定律
13:41
Let's have a little bit of fun with this.
217
809393
2313
讓我們來玩一下
13:43
For what you will see next, these quads
218
811706
1704
接下來你會看到這些四軸
13:45
will initially behave as if they were on Pluto.
219
813410
3496
一開始像是在冥王星的引力
13:48
As time goes on, gravity will be increased
220
816906
2312
隨著時間過去，重力逐漸增加
13:51
until we're all back on planet Earth,
221
819218
2120
直到全都回到地球的引力
13:53
but I assure you we won't get there.
222
821338
1719
但我保證不會發生
13:55
Okay, here goes.
223
823057
3501
好的，開始
14:05
(Laughter)
224
833667
3412
（笑聲）
14:34
(Laughter)
225
862778
3208
（笑聲）
14:37
(Applause)
226
865986
3386
（掌聲）
14:41
Whew!
227
869372
1207
呼！
14:46
You're all thinking now,
228
874779
1517
各位現在可能在想
14:48
these guys are having way too much fun,
229
876296
1975
這些傢伙也太愛玩了吧
14:50
and you're probably also asking yourself,
230
878271
2079
你可能也在問自己
14:52
why exactly are they building machine athletes?
231
880350
3936
他們到底為何要建造機械運動員？
14:56
Some conjecture that the role of play in the animal kingdom
232
884286
2652
一個推測是，就像動物王國中
遊戲的作用
遊戲的作用
14:58
is to hone skills and develop capabilities.
233
886938
2752
可以磨練技能和發展能力
15:01
Others think that it has more of a social role,
234
889690
2066
其他人則認為
這有更多的社會角色
這有更多的社會角色
15:03
that it's used to bind the group.
235
891756
1674
可讓團體聚在一起
15:05
Similarly, we use the analogy of sports and athleticism
236
893430
3533
同樣，我們用運動和運動能力類比
15:08
to create new algorithms for machines
237
896963
2079
來建立機器的新演算法
15:11
to push them to their limits.
238
899042
2147
將其能力推昇到極限
15:13
What impact will the speed of machines have on our way of life?
239
901189
3677
機器的速度會對我們的生活方式
產生什麼影響？
產生什麼影響？
15:16
Like all our past creations and innovations,
240
904866
2389
就像我們過去的各種創作及創新
15:19
they may be used to improve the human condition
241
907255
2827
它們可能被用來改善人類生活條件
15:22
or they may be misused and abused.
242
910082
2501
也可能會被誤用和濫用
15:24
This is not a technical choice we are faced with;
243
912583
1923
我們面臨的，不是技術選擇
15:26
it's a social one.
244
914506
1755
而是社會選擇
15:28
Let's make the right choice,
245
916261
1390
讓我們做出正確的選擇
15:29
the choice that brings out the best in the future of machines,
246
917651
2405
最能發揮未來機器優點的選擇
15:32
just like athleticism in sports
247
920056
1812
就像運動的能力
15:33
can bring out the best in us.
248
921868
2161
能讓人類發揮出最好的部分
15:36
Let me introduce you to the wizards behind the green curtain.
249
924029
3450
讓我來介紹
綠色布幕後面的魔法師
綠色布幕後面的魔法師
15:39
They're the current members of the Flying Machine Arena research team.
250
927479
2900
他們是飛行機器競技場
研究團隊的現任成員
研究團隊的現任成員
15:42
(Applause)
251
930379
4769
（掌聲）
15:47
Federico Augugliaro, Dario Brescianini, Markus Hehn,
252
935148
3046
Federico Augugliaro,
Dario Brescianini, Markus Hehn,
Dario Brescianini, Markus Hehn,
15:50
Sergei Lupashin, Mark Muller and Robin Ritz.
253
938194
2824
Sergei Lupashin, Mark Muller
和 Robin Ritz
和 Robin Ritz
15:53
Look out for them. They're destined for great things.
254
941018
1932
注意他們，他們將會有偉大成就
15:54
Thank you.
255
942950
1178
謝謝
15:56
(Applause)
256
944128
6354
（掌聲）
ABOUT THE SPEAKER
Raffaello D'Andrea - Autonomous systems pioneerRaffaello D'Andrea explores the possibilities of autonomous technology by collaborating with artists, engineers and entrepreneurs.
Why you should listen
Raffaello D'Andrea combines academics, business, and the arts to explore the capabilities of autonomous systems. As part of his research as professor of dynamic systems and control at the Swiss Federal Institute of Technology (ETH Zürich), he and his collaborators enchant viewers with works like the self-destructing, self-assembling Robotic Chair, or the Balancing Cube that can perch itself on its corners.
D’Andrea and his team created the Flying Machine Arena to test the gravity-defying abilities of their athletic flying robots. Building on research in the Flying Machine Arena, ETH Zürich partnered with its spin-off company Verity Studios and with Cirque du Soleil to create “Sparked,” a short film showcasing the unexpected airborne dexterity of quadcopters. D’Andrea is the co-founder of Kiva Systems, a robotics company that develops intelligent automated warehouse systems and that was acquired by Amazon in 2012.
Raffaello D'Andrea | Speaker | TED.com