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

翻译人员: Gabriella Hu 校对人员: Hong Li

Over a million people are killed each year in disasters.

每年超过100万人在灾难中丧生。

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

250万人因意外而终生残疾或流离失所，

and the communities will take 20 to 30 years to recover

重建家园需要20到30年的时间，

and billions of economic losses.

花费高达数十亿。

If you can reduce the initial response by one day,

如果最初的应急响应能提前一天，

you can reduce the overall recovery

灾后重建工作就能缩短

by a thousand days, or three years.

1000天，大约3年。

See how that works?

知道为什么吗？

If the initial responders can get in, save lives,

如果应急响应小组 能够（及时）行动，拯救遇难者，

mitigate whatever flooding danger there is,

缓解洪水或者其他灾害的影响，

that means the other groups can get in

其他团队就可以（尽快）开始

to restore the water, the roads, the electricity,

恢复供水，交通，电力，

which means then the construction people, the insurance agents,

这样的话，施工人员，保险代理人，

all of them can get in to rebuild the houses,

所有人都可以（尽快）开始重建房屋，

which then means you can restore the economy,

经济就能（迅速）恢复，

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

甚至变得更好， 提高今后对灾难的抗打击能力。

A major insurance company told me

一家大型的保险公司曾告诉我

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

如果他们能够提早一天处理房主的理赔申请，

it'll make a difference of six months

房主的房屋就可以

in that person getting their home repaired.

提前六个月修好。

And that's why I do disaster robotics --

这就是为什么我研究救灾机器人——

because robots can make a disaster go away faster.

因为机器人能够更快地应对灾难。

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

相信大家以前都见过无人机。

These are the UAVs.

这些是无人机

These are two types of UAVs:

这里有两种无人机：

a rotorcraft, or hummingbird;

一种是旋翼机，也叫“蜂鸟”；

a fixed-wing, a hawk.

另一种是固定翼的，也叫“雄鹰”。

And they're used extensively since 2005 --

它们从2005年卡特里娜飓风起

Hurricane Katrina.

就被广泛使用。

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

我们来看看“蜂鸟”是如何工作的。

Fantastic for structural engineers.

“蜂鸟”对结构工程师帮助巨大。

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

能帮助你从不同角度观察受损情况， 而这些角度无论是地面望远镜，

or from a satellite image,

还是卫星图像，

or anything flying at a higher angle.

或者其他任何高空飞行器都无法提供。

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

（无人机）不光能帮助 结构工程师和保险业者。

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

比如这架“雄鹰”固定翼无人机，

Now, this hawk can be used for geospatial surveys.

可以用来做地理空间测绘。

That's where you're pulling imagery together

将它拍摄的图像拼在一起，

and getting 3D reconstruction.

就能生成3D图像。

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

我们在华盛顿州的奥索泥石流灾害 中用到了这两种无人机，

because the big problem

因为难点在于

was geospatial and hydrological understanding of the disaster --

了解灾害的地理和水文性质，

not the search and rescue.

而不是搜寻和救援。

The search and rescue teams had it under control

这是搜寻救援队的工作，

and knew what they were doing.

他们是专业的。

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

更严重的问题是河水和泥石流可能会把

and flood the responders.

救援队冲走。

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

这不仅会造成救援队人身和财产损失，

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

还会对未来华盛顿州地区的三文鱼捕捞

along that part of Washington State.

带来不利影响。

So they needed to understand what was going on.

所以他们需要了解灾害情况。

In seven hours, going from Arlington,

在7小时内，（我们）从阿灵顿的

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

灾难指挥所开车到事发现场，操控无人机，

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

处理得到的数据，开车回到阿灵顿指挥所，

seven hours.

（总共）七个小时。

We gave them in seven hours data that they could take

我们在七个小时内提供给他们的数据，

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

如果用别的方式可能需要两三天。

and at higher resolution.

而且（我们的数据）分辨率更高。

It's a game changer.

这是一个巨大的突破。

And don't just think about the UAVs.

但还有比它们更厉害的。

I mean, they are sexy -- but remember,

没错，无人机确实很神奇——但请记住，

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

世界上80%的人口都生活在水边，

and that means our critical infrastructure is underwater --

这就意味着我们关键的基础设施都在水里——

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

而我们无法到达，比如桥梁等设施。

And that's why we have unmanned marine vehicles,

于是我们发明了水下无人机器人，

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

大家看到的这个是SARbot， 又叫“方形海豚”。

It goes underwater and uses sonar.

它能潜入水中并使用声纳。

Well, why are marine vehicles so important

为什么水下机器人如此重要？

and why are they very, very important?

原因是什么？

They get overlooked.

（因为）它们常被人忽视。

Think about the Japanese tsunami --

回顾一下日本海啸——

400 miles of coastland totally devastated,

总共400英里的海岸线被完全摧毁，

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

是美国卡特里娜飓风 摧毁的海岸线长度的两倍。

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

所有的桥梁，管道，港口都被完全摧毁。

And if you don't have a port,

如果没有港口，

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

就无法运输足够的救灾物资

to support a population.

去支援受灾人群。

That was a huge problem at the Haiti earthquake.

这在海地地震时就是一个巨大的难题。

So we need marine vehicles.

所以，我们需要水下机器人。

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

现在，我们从SARbot的角度

of what they were seeing.

看看它能看见什么。

We were working on a fishing port.

我们曾帮助过一个渔港。

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

在（SARbot的）声纳帮助下， 我们在四个小时内就让渔港恢复了工作。

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

渔港原本被告知，潜水员

before they could get a manual team of divers in,

要六个月之后才能开始工作，

and it was going to take the divers two weeks.

工作时间还需要两个星期。

They were going to miss the fall fishing season,

这样一来他们会错过秋季渔汛，

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

那是当地的主要经济来源， 有点像咱们的鲟鱼角。

UMVs, very important.

水下机器人，非常重要。

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

我给大家展示的机器人都很小，

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

因为它们需要做的， 是人类做不了的事。

They go places people can't go.

需要前往的， 是人类去不了的地方。

And a great example of that is Bujold.

其中具有代表性的机器人是布约德。

Unmanned ground vehicles are particularly small,

陆地无人机都特别小，

so Bujold --

布约德

(Laughter)

（笑声）

Say hello to Bujold.

向布约德问好。

(Laughter)

（笑声）

Bujold was used extensively at the World Trade Center

布约德在世贸中心救援中被广泛使用，

to go through Towers 1, 2 and 4.

它可以穿过一、二和三号大楼，

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

从上方钻入废墟， 一路向下，进到很深的地方。

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

这是从布约德的角度来看世界贸易中心。

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

在这场灾难中，你无法派人或狗进入现场，

and it's on fire.

而且到处都是大火。

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

想要救出被困在地下室的幸存者，

you have to go through things that are on fire.

只能通过熊熊燃烧的火场。

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

现场温度很高，其中一个机器人 的履带都融化脱落了。

Robots don't replace people or dogs,

机器人并不能取代人或者狗，

or hummingbirds or hawks or dolphins.

也不能取代蜂鸟，老鹰或海豚。

They do things new.

它们能够做与众不同的事。

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

它们用创新的方式协助救援队和专家。

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

现在最大的挑战 并不是把机器人变得更小。

It's not making them more heat-resistant.

也不是让它们更加耐热。

It's not making more sensors.

也不是安装更多的传感器。

The biggest problem is the data, the informatics,

最大的难题是（处理）数据和信息，

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

因为人们需要在正确的时间得到准确的信息。

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

如果专家们能实时获取机器人取得的数据，

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

不需要等机器人回到指挥所，

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

可以直接在线使用机器人，那该有多棒。

Well, let's think about that.

让我们想象一下。

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

如果一列装载化学品的列车 在偏远地区脱轨，

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

专家们，比如化学工程师，

your railroad transportation engineers,

铁道运输工程师，

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

有多大的几率当地正好有 他们会使用的无人机呢？

Probably, like, none.

也许完全没有。

So we're using these kinds of interfaces

所以我们开发了一种（通用）界面，

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

人们即使对自己使用的机器人不熟悉， 也能（正常）操纵它们，

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

甚至都不需要知道他们在操纵机器人。

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

机器人提供给我们的，给专家的，是数据。

The problem becomes: who gets what data when?

接下来的问题是： （如何决定）谁在什么时候得到何种数据？

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

一种办法是把所有的信息给所有的人

and let them sort it out.

让他们自己筛选。

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

但这样做可能会导致 （传输数据的）网络超载。

and worse yet, it overwhelms the cognitive abilities

更糟的是，它可能超越了 人类认知能力（的极限），

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

因为每个人都需要从（海量）数据中 筛选出自己所需要的那一小部分，

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

来作决定，而这决定可能关乎生死。

So we need to think about those kinds of challenges.

所以我们要再三斟酌。

So it's the data.

这是关于数据的难题。

Going back to the World Trade Center,

再来看世贸中心救援，

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

我们是在布约德进入废墟深处后

only when she was deep in the rubble,

才开始记录数据的，

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

因为这是坍塌搜救专队的要求。

What we didn't know at the time

而有一件事我们当时不知道，

was that the civil engineers would have loved,

就是土木工程师十分需要了解

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

箱型梁的编号和位置， 而这些数据在机器人刚进入废墟时，

the locations, as we went into the rubble.

就应该开始记录。

We lost valuable data.

我们失去了重要的数据。

So the challenge is getting all the data

所以难题就在于收集所有的数据

and getting it to the right people.

并交给需要的人。

Now, here's another reason.

还有另一个原因。

We've learned that some buildings --

我们得知一些建筑物——

things like schools, hospitals, city halls --

比如学校、医院、市政府——

get inspected four times by different agencies

在应急响应过程中被不同的机构

throughout the response phases.

检查了四次。

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

如果我们能够分享机器人收集的数据，

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

我们不仅能简化响应程序，

to shorten the response time,

缩短响应时间，

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

我们还可以同时开展多项工作。

Everybody can see the data.

（因为）数据是共享的，

We can shorten it that way.

我们可以节约时间。

So really, "disaster robotics" is a misnomer.

其实，“灾难机器人”这个描述不是很贴切。

It's not about the robots.

因为关键不在于机器人，

It's about the data.

而是数据。

(Applause)

（掌声）

So my challenge to you:

交给大家一项任务：

the next time you hear about a disaster,

如果之后听到关于灾难的报道，

look for the robots.

多关注一下机器人。

They may be underground, they may be underwater,

它们可能在地下，可能在水底，

they may be in the sky,

也可能在空中，

but they should be there.

但是它们肯定在现场。

Look for the robots,

去找一找机器人的身影，

because robots are coming to the rescue.

因为机器人来救援了。

(Applause)

（掌声）