These Robots Come to the Rescue after a Disaster | Robin Murphy | TED Talks

譯者: Regina Chu 審譯者: Marssi Draw

Over a million people are killed each year in disasters.

每年超過百萬人死於災難。

Two and a half million people will be permanently disabled or displaced,

二百五十萬人 永久傷殘或流離失所，

and the communities will take 20 to 30 years to recover

受災社區要花 二三十年重建恢復，

and billions of economic losses.

還有大量的經濟損失。

If you can reduce the initial response by one day,

如果你能將 初始應變時間縮短一天，

you can reduce the overall recovery

就能加快整體恢復時間

by a thousand days, or three years.

一千天，即三年。

See how that works?

這要如何達成？

If the initial responders can get in, save lives,

如果第一批救災人員 能進入災區、拯救生命、

mitigate whatever flooding danger there is,

減輕各種危險造成的災害，

that means the other groups can get in

那麼其他團體就能進入

to restore the water, the roads, the electricity,

恢復供水、供電、搶修道路，

which means then the construction people, the insurance agents,

也就是說之後 施工人員及保險公司

all of them can get in to rebuild the houses,

都可以進入重建房子，

which then means you can restore the economy,

也就是說你能恢復經濟，

and maybe even make it better and more resilient to the next disaster.

甚至還能變得更好， 更有能力應變下一場災害。

A major insurance company told me

一家大保險公司告訴我

that if they can get a homeowner's claim processed one day earlier,

如果他們能早一天 處理屋主的索賠，

it'll make a difference of six months

就能讓屋主

早六個月修好房屋。

in that person getting their home repaired.

And that's why I do disaster robotics --

這就是為什麼 我要做「救災機器人學」，

because robots can make a disaster go away faster.

因為機器人能讓災難更快消失。

Now, you've already seen a couple of these.

現在你們已經看到其中幾種了。

These are the UAVs.

這些是無人機。

These are two types of UAVs:

這裡有兩種無人機：

a rotorcraft, or hummingbird;

一種叫旋翼機，又稱蜂鳥；

a fixed-wing, a hawk.

一種是定翼機，又叫隼。

And they're used extensively since 2005 --

這兩種自 2005 年 颶風卡崔娜以後

Hurricane Katrina.

已被廣泛使用。

Let me show you how this hummingbird, this rotorcraft, works.

我跟大家展示一下 這種蜂鳥旋翼機如何運作。

Fantastic for structural engineers.

這是結構工程師的夢啊！

Being able to see damage from angles you can't get from binoculars on the ground

這些能從不同角度看受損狀況， 是你無法從地面用望遠鏡

or from a satellite image,

或從衛星圖，

or anything flying at a higher angle.

或從任何高一點的飛行角度看到。

But it's not just structural engineers and insurance people who need this.

但不只是結構工程師 及保險公司有這樣的需求。

You've got things like this fixed-wing, this hawk.

你還能從這種定翼機， 這個隼看到東西。

Now, this hawk can be used for geospatial surveys.

這個隼能拿來做地理空間調查。

That's where you're pulling imagery together

你能把成像組合起來

and getting 3D reconstruction.

得到立體影像重建。

We used both of these at the Oso mudslides up in Washington State,

這兩種機器人都曾用於 華盛頓州的奧所山崩上，

because the big problem

因為很大的問題出在

was geospatial and hydrological understanding of the disaster --

瞭解這場災難的 地理空間及水文狀況，

not the search and rescue.

而不是搜救。

The search and rescue teams had it under control

搜救隊伍已控制情況，

and knew what they were doing.

也很清楚知道他們要做什麼。

The bigger problem was that river and mudslide might wipe them out

但更大的問題是河水及山崩 可能會毀了他們，

and flood the responders.

並淹沒救災人員。

And not only was it challenging to the responders and property damage,

這不只對救災人員造成挑戰， 並造成財物損失，

it's also putting at risk the future of salmon fishing

這還對將來在華盛頓州

along that part of Washington State.

那一帶的釣鮭魚活動造成威脅。

So they needed to understand what was going on.

所以他們需要知道情況。

In seven hours, going from Arlington,

在七個小時內，從阿靈頓出發，

driving from the Incident Command Post to the site, flying the UAVs,

從事故指揮所開車到現場、 飛無人機、

processing the data, driving back to Arlington command post --

處理數據、 開車回阿靈頓的指揮所，

seven hours.

只花了七個小時。

We gave them in seven hours data that they could take

我們在七個小時內 就給他們數據，

only two to three days to get any other way --

用其他方法要花兩三天——

and at higher resolution.

而且是更高的解析度。

It's a game changer.

這改變了局勢。

And don't just think about the UAVs.

而且不要只想到無人機。

I mean, they are sexy -- but remember,

我是說，它們是很迷人， 但你要記住，

80 percent of the world's population lives by water,

80% 的世界人口住在水邊，

and that means our critical infrastructure is underwater --

意指我們關鍵的 基礎建設都在水下，

the parts that we can't get to, like the bridges and things like that.

我們無法進入的地方， 像橋梁或是類似的東西。

And that's why we have unmanned marine vehicles,

這就是為什麼我們有 無人駕駛的海陸兩棲車，

one type of which you've already met, which is SARbot, a square dolphin.

你們已經看到的其中一種， 沙霸，方型海豚。

It goes underwater and uses sonar.

它可以進入水下，使用聲納。

Well, why are marine vehicles so important

為什麼兩棲車這麼重要？

and why are they very, very important?

為什麼它們真的非常重要？

They get overlooked.

它們都被忽視了。

Think about the Japanese tsunami --

想想日本海嘯。

400 miles of coastland totally devastated,

650 公里的沿海地區被徹底摧毀，

twice the amount of coastland devastated by Hurricane Katrina in the United States.

比美國的颶風卡崔娜 所破壞的沿岸區還大兩倍。

You're talking about your bridges, your pipelines, your ports -- wiped out.

你在談的是你的橋梁、 你的管線、你的港口——全沒了。

And if you don't have a port,

如果你沒有港口，

you don't have a way to get in enough relief supplies

你就沒有辦法 運進足夠的救災物資

to support a population.

以支援災民。

That was a huge problem at the Haiti earthquake.

這在海地地震 就造成很大的問題。

So we need marine vehicles.

所以我們需要兩棲車輛。

Now, let's look at a viewpoint from the SARbot

現在我們從沙霸的角度

of what they were seeing.

看他們看到的東西。

We were working on a fishing port.

我們在搶救一座漁港。

We were able to reopen that fishing port, using her sonar, in four hours.

我們能用沙霸的聲納系統 在四小時內重新開放那座漁港。

That fishing port was told it was going to be six months

那座漁港被告知要六個月

before they could get a manual team of divers in,

才能找到一組潛水員下去看，

and it was going to take the divers two weeks.

而且潛水員還要花兩個星期。

They were going to miss the fall fishing season,

他們會因此錯過秋季魚汛，

which was the major economy for that part, which is kind of like their Cape Cod.

那塊區域主要的經濟來源， 有點像麻省的勝地「鱈魚角」。

UMVs, very important.

自動兩棲車非常重要。

But you know, all the robots I've shown you have been small,

但是你知道嗎， 我展示給大家看的機器人都很小，

and that's because robots don't do things that people do.

那是因為機器人不做人做的事。

They go places people can't go.

他們去人到不了的地方。

And a great example of that is Bujold.

有個很好的例子就是「步足」。

Unmanned ground vehicles are particularly small,

無人駕駛的地面車輛都特別小，

so Bujold --

所以步足

(Laughter)

（笑聲）

Say hello to Bujold.

跟步足打個招呼吧！

(Laughter)

（笑聲）

Bujold was used extensively at the World Trade Center

步足在紐約世貿恐襲中 被大量使用，

to go through Towers 1, 2 and 4.

搜索 1、 2 及 4 號大樓。

You're climbing into the rubble, rappelling down, going deep in spaces.

你爬進廢墟、繞繩下降， 進入位於深處的空間。

And just to see the World Trade Center from Bujold's viewpoint, look at this.

從步足的眼光看紐約世貿， 看一下這個。

You're talking about a disaster where you can't fit a person or a dog --

你在談的是你不能用 人或狗來處理的災難，

and it's on fire.

而且還在燃燒。

The only hope of getting to a survivor way in the basement,

能到地下室找生存者的唯一希望，

you have to go through things that are on fire.

你得通過燃燒的火場。

It was so hot, on one of the robots, the tracks began to melt and come off.

現場非常熱，某個機器人的履帶 都開始熔化脫落。

Robots don't replace people or dogs,

機器人不能取代人或狗，

or hummingbirds or hawks or dolphins.

或蜂鳥或隼或海豚等無人機。

They do things new.

他們做新的事。

They assist the responders, the experts, in new and innovative ways.

他們以創新的方法 幫助救難人員及專家。

The biggest problem is not making the robots smaller, though.

但是最大的問題 不是把機器人做得更小。

It's not making them more heat-resistant.

也不是把他們弄得更耐熱。

It's not making more sensors.

也不是加更多的感應器。

The biggest problem is the data, the informatics,

最大的問題是數據， 是資訊學，

because these people need to get the right data at the right time.

因為這些人需要 在適當的時間取得正確的資料。

So wouldn't it be great if we could have experts immediately access the robots

如果專家能立刻從機器人 取得數據不是很棒嗎？

without having to waste any time of driving to the site,

不用浪費時間開車到現場，

so whoever's there, use their robots over the Internet.

所以無論是誰在那， 都可以用網路操縱機器人。

Well, let's think about that.

好好想一下。

Let's think about a chemical train derailment in a rural county.

想一下載了化學品的火車 在郊區縣城脫軌。

What are the odds that the experts, your chemical engineer,

你想這機率有多高， 你的專家、化學工程師、

your railroad transportation engineers,

你的鐵路運輸工程師，

have been trained on whatever UAV that particular county happens to have?

剛好就在那個縣城， 還受過無人機訓練？

Probably, like, none.

大概是零吧？

So we're using these kinds of interfaces

所以我們用這種介面

to allow people to use the robots without knowing what robot they're using,

讓大家使用機器人， 無須知道他們在用哪種機器人，

or even if they're using a robot or not.

或根本不用知道 他們有沒有在用機器人。

What the robots give you, what they give the experts, is data.

機器人給你的、 給專家的是數據。

The problem becomes: who gets what data when?

問題變成： 誰在什麼時候拿到什麼數據？

One thing to do is to ship all the information to everybody

有一個方法是把所有的數據 送給每一個人，

and let them sort it out.

讓他們自己選。

Well, the problem with that is it overwhelms the networks,

這個方法的問題是 這樣會讓網路超載，

and worse yet, it overwhelms the cognitive abilities

最糟的是，這還會讓

試著得到那塊數據的人 認知能力不勝負荷。

of each of the people trying to get that one nugget of information

they need to make the decision that's going to make the difference.

他們做的決定會改變一切。

So we need to think about those kinds of challenges.

所以我們必須考慮那種挑戰。

So it's the data.

所以數據才是大問題。

Going back to the World Trade Center,

再回頭來看世界貿易中心，

we tried to solve that problem by just recording the data from Bujold

我們試著解決這個問題， 所以讓步足在深入廢墟後

only when she was deep in the rubble,

才記錄下數據，

because that's what the USAR team said they wanted.

因為那是坍塌搜救專隊 說他們要的。

What we didn't know at the time

那時候我們不知道

was that the civil engineers would have loved,

土木工程師會很愛、

needed the data as we recorded the box beams, the serial numbers,

很需要我們在進入廢墟時

錄下來的箱型梁序號、地點。

the locations, as we went into the rubble.

We lost valuable data.

我們錯失了珍貴的數據。

So the challenge is getting all the data

所以挑戰是得到所有的數據，

and getting it to the right people.

及把數據送到對的人手上。

Now, here's another reason.

現在還有另一個原因。

We've learned that some buildings --

我們得知某些建築物，

things like schools, hospitals, city halls --

像是學校、醫院、市政廳等，

get inspected four times by different agencies

在整個救災反應期， 要被不同的單位檢查四次，

throughout the response phases.

Now, we're looking, if we can get the data from the robots to share,

現在我們來看，如果我們能從機器人 得到數據給大家共用，

not only can we do things like compress that sequence of phases

我們不但能縮短反應期各個階段

to shorten the response time,

以縮短反應時間，

but now we can begin to do the response in parallel.

我們現在還能開始 同時進行不同反應。

Everybody can see the data.

每個人都能看到數據。

We can shorten it that way.

我們可以用那種方法縮短。

So really, "disaster robotics" is a misnomer.

所以說真的， 「救災機器人」學是個誤稱。

It's not about the robots.

這跟機器人無關。

It's about the data.

這跟數據有關。

(Applause)

（掌聲）

So my challenge to you:

所以我給大家的挑戰是，

the next time you hear about a disaster,

下一次你聽到某個災難，

look for the robots.

去找機器人。

They may be underground, they may be underwater,

他們可能在地下， 可能在水下，

they may be in the sky,

也可能在天上，

but they should be there.

但是它們應該就在那兒。

Look for the robots,

去找機器人，

because robots are coming to the rescue.

因為機器人要來拯救大家了！

(Applause)

（掌聲）