Meet the dazzling flying machines of the future | Raffaello D'Andrea

譯者: Allen Kuo 審譯者: Helen Chang

What started as a platform for hobbyists

我們從一個愛好者平台開始，

is poised to become a multibillion-dollar industry.

有望發展成一個數十億元的產業。

Inspection, environmental monitoring, photography and film and journalism:

偵查、環境監控、攝影、 電影和新聞業──

these are some of the potential applications for commercial drones,

這些都是商用無人飛行器的潛在機會，

而它們的實現

and their enablers are the capabilities being developed

得仰賴全球許多研究機構 所研發的各種功能。

at research facilities around the world.

For example, before aerial package delivery

舉個例，在空中包裹運送

entered our social consciousness,

進入我們的社會認知之前，

an autonomous fleet of flying machines built a six-meter-tall tower

一組自動化飛行機隊 就曾將一個6公尺高、

composed of 1,500 bricks

由1500個磚塊構成的塔，

in front of a live audience at the FRAC Centre in France,

就在法國當代藝術中心的 現場觀眾面前蓋了起來。

and several years ago, they started to fly with ropes.

而在那幾年之前， 它們從帶著繩索飛行開始。

By tethering flying machines,

透過繩索連結飛行器，

它們可以在非常狹小的空間內 用很高的速度及加速度飛行。

they can achieve high speeds and accelerations in very tight spaces.

They can also autonomously build tensile structures.

它們還能自動建造高張力的結構。

Skills learned include how to carry loads,

它們學會的技能包含如何裝載貨物、

how to cope with disturbances,

如何應付亂流、

and in general, how to interact with the physical world.

以及概括而言， 如何和實體世界互動。

Today we want to show you some new projects that we've been working on.

今天我們想讓各位看一些 我們正在進行的新專案。

Their aim is to push the boundary of what can be achieved

它們的目標是擴展自主飛行 所能達成的境界。

with autonomous flight.

Now, for a system to function autonomously,

那麼，要讓系統能自動運作，

it must collectively know the location of its mobile objects in space.

它必須知道所有移動物體 在空間上的位置。

Back at our lab at ETH Zurich,

在我們蘇黎世聯邦工學院的實驗室裡，

we often use external cameras to locate objects,

我們常用外部的攝影機來定位物體，

which then allows us to focus our efforts

這讓我們能全神貫注，

on the rapid development of highly dynamic tasks.

將精力用在快速開發高度動態的任務。

For the demos you will see today, however,

然而，今天各位看到的展示，

we will use new localization technology developed by Verity Studios,

我們將使用Verity Studios 所開發的新定位技術，

a spin-off from our lab.

他們是我們實驗室的一個分支機構。

There are no external cameras.

不用任何的外部攝影機，

Each flying machine uses onboard sensors to determine its location in space

每一個飛行器都用內建的感應器 判斷自己的位置，

and onboard computation to determine what its actions should be.

並用內建的電腦判斷該採取的動作。

The only external commands are high-level ones

只有高階的指令來自外部，

such as "take off" and "land."

例如「起飛」和「降落」。

This is a so-called tail-sitter.

這是一個所謂的立式起落機。

It's an aircraft that tries to have its cake and eat it.

它就像一台什麼都想做到的飛機。

Like other fixed-wing aircraft, it is efficient in forward flight,

如同其他固定機翼的飛機， 它可以很有效率地向前飛行，

much more so than helicopters and variations thereof.

效果比直升機或之類的飛行器好得多。

Unlike most other fixed-wing aircraft, however,

但它又和固定機翼的飛機不一樣，

it is capable of hovering,

它可以在空中盤旋，

which has huge advantages for takeoff, landing

這讓它在起飛、降落 和一些通用動作上有很大的優勢。

and general versatility.

There is no free lunch, unfortunately.

很不幸地，天下沒有白吃的午餐。

One of the limitations with tail-sitters

立式起落機一個很大的限制

is that they're susceptible to disturbances such as wind gusts.

就是它們對於陣風之類的干擾很敏感。

We're developing new control architectures and algorithms

我們正在開發新的控制架構和演算法

試著突破這個限制。

that address this limitation.

The idea is for the aircraft to recover

我們的想法是讓這個飛行器

no matter what state it finds itself in,

無論遭遇什麼情況都能復原。

and through practice, improve its performance over time.

而且透過練習，還能逐漸提高效能。

(Applause)

(掌聲)

OK.

好的。

When doing research,

進行研究時，

we often ask ourselves fundamental abstract questions

我們經常問自己一些基本的抽象問題，

that try to get at the heart of a matter.

讓我們能直搗問題核心。

For example, one such question would be,

比方說，其中一個問題是，

what is the minimum number of moving parts needed for controlled flight?

要控制飛行， 最少要有幾個會動的零件？

Now, there are practical reasons

我們有很實際的理由

探索這個問題的答案。

why you may want to know the answer to such a question.

Helicopters, for example,

以直升機為例，

are affectionately known as machines with a thousand moving parts

大家都認為這是一種 由上千個活動零件組成的機器，

all conspiring to do you bodily harm.

每個零件都可能會導致你受傷。

It turns out that decades ago,

事實是在數十年前，

skilled pilots were able to fly remote-controlled aircraft

技巧高超的駕駛就已能 遙控駕駛這種飛行器了，

that had only two moving parts:

而這個飛行器只有兩個會動的東西：

a propeller and a tail rudder.

螺旋槳和尾翼。

We recently discovered that it could be done with just one.

我們最近發現，其實只需要一個。

This is the monospinner,

這是「單軸機」，

the world's mechanically simplest controllable flying machine,

世上結構最簡單的可控式飛行機器，

invented just a few months ago.

幾個月前才發明的。

It has only one moving part, a propeller.

它只有一個會動的零件，就是螺旋槳。

It has no flaps, no hinges, no ailerons,

沒有襟翼，沒有絞鍊，沒有副翼，

no other actuators, no other control surfaces,

沒有其他的驅動器和控制面板，

just a simple propeller.

就只有一個簡單的螺旋槳。

Even though it's mechanically simple,

即使在結構上非常簡單，

there's a lot going on in its little electronic brain

它小小的電腦裡卻裝了很多東西，

to allow it to fly in a stable fashion and to move anywhere it wants in space.

讓它可以穩定飛行 並移動到任何想去的位置。

Even so, it doesn't yet have

儘管如此，它還沒有

the sophisticated algorithms of the tail-sitter,

像立式起落機那種複雜的演算法，

which means that in order to get it to fly,

也就是說如果要讓它飛起來，

I have to throw it just right.

我得用很精確的方式把它丟出去。

And because the probability of me throwing it just right is very low,

但考量到我成功丟出它的機率非常低，

given everybody watching me,

因為這麼有多人在盯著我，

what we're going to do instead

所以我打算還是讓你們 看看昨晚錄的影片就好。

is show you a video that we shot last night.

(Laughter)

(笑聲)

(Applause)

(掌聲)

If the monospinner is an exercise in frugality,

如果單軸機是一種簡潔的應用，

this machine here, the omnicopter, with its eight propellers,

那這台有8個螺旋槳的「全向直升機」

is an exercise in excess.

就是一種「超額」的應用。

What can you do with all this surplus?

這些額外的配備可以做什麼？

The thing to notice is that it is highly symmetric.

值得注意的是，它的結構高度對稱，

As a result, it is ambivalent to orientation.

因此它沒有一定的方向性。

This gives it an extraordinary capability.

這讓它擁有不同凡響的能力，

It can move anywhere it wants in space

可以移動到空間中的任何位置，

irrespective of where it is facing

不用考慮它面對哪個方向，

and even of how it is rotating.

甚至不用管它如何旋轉。

It has its own complexities,

它有其複雜性，

mainly having to do with the interacting flows

主要和它的8個螺旋槳 之間的互動有關。

from its eight propellers.

Some of this can be modeled, while the rest can be learned on the fly.

這些互動有一部分可透過程式達成， 其他的則可從飛行中自行學習。

Let's take a look.

我們來看看吧。

(Applause)

(掌聲)

If flying machines are going to enter part of our daily lives,

如果飛行機器要成為 我們日常生活的一部份，

they will need to become extremely safe and reliable.

它們就得變得非常安全可靠。

This machine over here

那邊那台機器

is actually two separate two-propeller flying machines.

實際上由兩個分開的雙軸飛行器構成。

This one wants to spin clockwise.

其中一個試圖順時針旋轉，

This other one wants to spin counterclockwise.

另一個則試圖逆時針旋轉。

When you put them together,

當你將它們結合，

they behave like one high-performance quadrocopter.

就會變成一個高效能的四軸飛行器。

If anything goes wrong, however --

然而，如果有東西出錯，

a motor fails, a propeller fails, electronics, even a battery pack --

像是馬達故障、螺旋槳故障， 電子零件，甚至電池組件故障，

the machine can still fly, albeit in a degraded fashion.

它還是可以用效能較低的方式飛行。

We're going to demonstrate this to you now by disabling one of its halves.

我們來示範一下 關掉它其中一個飛行器會怎樣。

(Applause)

(掌聲)

This last demonstration

最後要展示的

is an exploration of synthetic swarms.

是人造螢火蟲群的研究成果。

The large number of autonomous, coordinated entities

為數眾多自動化且互相配合的機群

offers a new palette for aesthetic expression.

為美的展現帶來一種全新型態。

We've taken commercially available micro quadcopters,

我們利用商品化的微型四軸飛行器，

each weighing less than a slice of bread, by the way,

順道一提，每個都比一片麵包還輕，

and outfitted them with our localization technology

我們為它們裝上自己的定位科技

and custom algorithms.

和客製化的演算法。

Because each unit knows where it is in space

因為每個飛行器都知道自己的位置，

and is self-controlled,

又都可以自我控制，

there is really no limit to their number.

所以它們的數量完全沒有限制。

(Applause)

(掌聲)

(Applause)

(掌聲)

(Applause)

(掌聲)

Hopefully, these demonstrations will motivate you to dream up

希望這些展示讓各位能夠想像

new revolutionary roles for flying machines.

飛行機器能在未來扮演的革命性角色，

That ultrasafe one over there for example

例如我們那個超安全的飛行器，

has aspirations to become a flying lampshade on Broadway.

它想必很渴望成為百老匯的飛行燈罩。

(Laughter)

(笑聲)

The reality is that it is difficult to predict

事實上，要預測新興科技 帶來的影響是很困難的。

the impact of nascent technology.

And for folks like us, the real reward is the journey and the act of creation.

而對我們這樣的人來說，

創造新事物的旅程和行動， 才是真正的回報。

It's a continual reminder

它不斷提醒我們，

of how wonderful and magical the universe we live in is,

我們生活的這個宇宙 有多精彩和神奇。

that it allows creative, clever creatures

它讓有創造力、聰明的生物

to sculpt it in such spectacular ways.

將其雕塑成如此壯闊的面貌。

The fact that this technology

而這個科技

has such huge commercial and economic potential

所擁有的龐大經濟和商業潛力，

is just icing on the cake.

不過是錦上添花罷了。

Thank you.

謝謝各位。

(Applause)

(掌聲)