災(zāi)難救援機(jī)器人：未來(lái)不是夢(mèng)

2015年8月12日晚，天津?yàn)I海新區(qū)發(fā)生重大爆炸事故，事故造成多人傷亡，多名現(xiàn)場(chǎng)救援的消防官兵不幸遇難。看到這條消息，很多人除了震驚、惋惜、哀嘆，也不禁會(huì)想：可否讓救援機(jī)器人代替消防員去救援？確實(shí)，在很多國(guó)家，救援機(jī)器人已經(jīng)投入使用，但實(shí)際上它們能做的工作極為有限，而且研發(fā)也困難重重。不過(guò)，幸運(yùn)的是，很多科研機(jī)構(gòu)和機(jī)器人專(zhuān)家正致力于這方面的探索。相信在不久的將來(lái)，我們會(huì)看到救援機(jī)器人在災(zāi)難現(xiàn)場(chǎng)第一時(shí)間救人于危難。

Dennis Hong first spied Japan’s ruined nuclear power plant from a bus wrapped in plastic. A hefty layer of protection guarded the seats， floors and handles from radioactive dust. Hong wore a face mask and gloves to limit his exposure.

More than three years earlier， after an earthquake and tsunami battered Japan’s eastern coast， portions of the Fukushima Daiichi power station blew， blasting radiation into the sea and sky. Today， villages outside the plant still lie as barren as ghost towns. Along the coast， smashed buildings， flipped cars and train tracks twisted like taffy stand as reminders of the catastrophe.

“It’s like a disaster site frozen in time，” Hong says. “It’s surreal.”

Workers toiled day and night to save the plant， but they had to get out as radiation levels rose. Even today in disaster areas not tainted with radiation， picking through the destroyed buildings is treacherous： People need to dodge shards of glass and metal and duck1） clouds of smoke and dust.

Ideally， robots could take over2） for human crews. But seemingly simple tasks， such as moving， communicating and staying powered up， pose big challenges for3） machines.

Hong， a UCLA roboticist， is one of several engineers working to make robots that can come to the rescue in disasters. He and others from academia， industry， NASA’s Jet Propulsion Lab and the Defense Department’s research agency DARPA traveled to Fukushima last spring to see what they were up against.

“The take-home message4） was ‘Wow， it’s damn difficult，’ ” Hong says.

A Better Bot

Engineers have built impressive looking humanlike bots that can play trumpet and even compete against each other in slow-moving soccer games. But machines that can actually do the work of humans in disaster zones — climbing over rubble， digging through debris for survivors， opening doors and valves — don’t exist.

So DARPA kicked off5） a contest to create robots that someday could do the job. In 2012， the agency announced a competition —DARPA Robotics Challenge —designed to push disaster robotics technology miles past where it is today. In December 2013， 17 robotic contenders， including Hong’s human-shaped machine， THOR-OP， tackled a rugged obstacle course to try to gain a spot in the finals， to be held in June 2015.

Gill Pratt， a DARPA program manager， knows that it may take years to develop robots that might have saved the power plant. But he thinks the competition is a good place to start.

9/11 Lessons

In the past decade or so， disaster-response robots haven’t changed much. When the World Trade Center towers were destroyed in 2001， engineers deployed a handful of lightweight bots to burrow6） through the rubble.

“These guys went into spaces where the first responders couldn’t go，” remembers Robin Murphy， a field roboticist at Texas Aamp;M University. Because 110 floors of concrete and steel collapsed into dense piles of debris， she says， ground-penetrating radar couldn’t see through the rubble and search-and-rescue dogs had trouble sniffing out victims.

The robots， roughly the size of shoe boxes， offered a new way for rescue teams to take a look. Murphy considers the roving machines a success： A few tunneled deep within the wreckage and withstood extreme heat to find 10 sets of human remains. But the robots didn’t locate any survivors， and they ran into a slew7） of technical snags.

One robot slipped its tread and had to be pulled from the rubble and repaired. Another got wedged8） in a gap， stalled until a crew could tug it out by its safety tether. A third lost communication， broke loose from its tether and was never seen again.

A Far Cry from C-3PO9）

Years before Fukushima， Japan—a country known for its advanced robotics—had actually developed robots to respond to nuclear emergencies.

After a power plant accident in 1999， engineers created six huge， treaded robots to open doors， turn valves， carry heavy loads and even clean up radiation. But these bots weren’t maintained well enough for use at Fukushima. Even if they had been ready to go， they may have been too big and heavy to be useful， engineer Keiji Nagatani and colleagues reported in the Journal of Field Robotics in 2013.

A smaller robot， designed for disposing of explosives， was the first to enter Fukushima’s reactors， about a month after the disaster. Shin-height and light enough to be carried on a soldier’s back， the robot， called the PackBot， uses treads to haul itself over bumpy turf. A skinny arm mounted with a gripper claw and a camera lets the robot grasp and see. In the days following the Fukushima earthquake， iRobot， the Massachusetts company that produces the PackBot， rushed to add radiation and chemical sensors to the bots.

The sensors came in handy10）： Plant workers used them to find places inside the plant where humans could safely explore. But maneuvering the robots through the darkened plant was at times impossible. Though the machines could open doors， the bots’ operators had to use two PackBots to do so： one to turn the handle and the second to aim its camera at the first. What’s more， the robots struggled to climb the plant’s slick metal stairs.

Gizmos in the Lab

Japan’s lack of versatile， usable rescue robots surprised people in the field， says University of Pennsylvania roboticist Mark Yim. Not only did Japan have simple ground-roving bots， the country also had more humanoid machines than any other country， he says. Unfortunately， these fledgling gizmos weren’t ready to leave the lab. For some such devices， just making it across slightly uneven floors can be tricky.

“People see a humanoid robot and they think it can do anything a human can do，” Yim says. “In reality， it can do very little.”

Still， some type of limbed， humanlike machine might be the key to tackling disasters in urban areas， where stairs and doors have been designed for human legs to climb and human hands to open.

“At a disaster site， there are bulldozers， excavators， power tools—all this great equipment that people use for rescue missions，” Hong says. “So， naturally， a lot of people believe the robot needs to be in a human form.”

And in the DARPA Robotics Challenge trials11）， most contenders were. But these robots aren’t anywhere near the C-3PO machines of the movies. Today’s state-of-the-art12） humanoids have just begun venturing out of the lab， and they’re taking baby steps.

Clash of the Bots

Watching disaster-relief robots triumph—or fizzle13）—at even the simplest tasks can be thrilling. Last December， thousands of cheering spectators flocked to a Florida racetrack to see a medley of high-tech machines in action at the trials. The robots lumbered and lurched through a series of tasks， including opening doors， traveling over rubble and turning valves. Here was the future of disaster-relief robots， where the simple act of getting a bot to set a tool on a table is still considered showboating.

“A lot of these are tasks that a person could complete in a minute or less，” says software engineer Doug Stephen of the Florida Institute for Human and Machine Cognition in Pensacola. “But things we take for granted are incredibly hard for a robot.” And figuring out how to build a bot that can sail through14） all of these tasks， rather than designing a specialized door-opener or valve-turner， is even harder.

The competition， however， may have already begun to pay off15）. Teams at the trials dived into the problems that plague humanoid robots—walking， power usage， handling tools. “Historically，” Murphy says， “a lot of focus has been on just walking and not falling over.”

Humans don’t simply pick up and set down their feet， Stephen says. People tailor their steps on the fly16）， weaving through busy streets， striding over sidewalk cracks and swiftly rebalancing themselves after stumbles. And they make most of these adjustments subconsciously.

“But the robot has no brains of its own， so we have to tell it how to do things，” Stephen says. Capturing the hair-trigger17） tweaks and easy grace of human gait “is a tough nut to crack.” For the DARPA challenge， he and colleagues designed software that helps robots “think” on their feet18）.

Engineers competing in the finals agree that even the best bots of the competition probably wouldn’t be ready for another Fukushima. But， Engineer Brett Kennedy at NASA JPL in Pasadena， Calif. says， “I think that we would be able to do better.” And the range of technology the competition inspires may lead to many different types of disaster-ready robots.

“Someday， it would be really cool to have a robot that does everything a fireman can do，” Kennedy says， “burst through the door， save the baby， the whole nine yards19）.”

丹尼斯·洪從一輛裹在塑料保護(hù)層里的公共汽車(chē)上第一次看到了日本已毀的核電站。巨大的保護(hù)層保護(hù)著座椅、地板和手柄，使其免被蒙上放射性塵埃。洪戴著面罩和手套，以減少皮膚暴露在外的可能性。

三年多之前（編注：英文原文發(fā)表于2014年12月），在地震和海嘯重創(chuàng)日本東海岸后，福島第一核電站部分設(shè)施發(fā)生爆炸，爆炸產(chǎn)生的輻射污染了海洋和天空。如今，核電站外面的村莊依舊荒蕪，像一座座鬼城。海岸線一帶，坍塌的房屋、被掀翻的汽車(chē)和扭曲成太妃糖形狀的火車(chē)鐵軌提醒著人們?cè)?jīng)發(fā)生過(guò)的災(zāi)難。

“這就像一個(gè)被時(shí)間凝固了的災(zāi)難現(xiàn)場(chǎng)，”洪說(shuō)，“跟幻境一般。”

工人們不分晝夜地辛苦工作來(lái)挽救核電站，但輻射水平一升高，他們就不得不離開(kāi)。即使今天，在沒(méi)有受到輻射污染的災(zāi)區(qū)，在毀壞的建筑里進(jìn)行搜尋也是非常危險(xiǎn)的：人們要躲避玻璃和金屬碎片，避開(kāi)煙塵團(tuán)。

理想情況下，機(jī)器人可以代替人類(lèi)工作人員。但如移動(dòng)、交流及保持通電等一些看似簡(jiǎn)單的任務(wù)都給機(jī)器人帶來(lái)了巨大挑戰(zhàn)。

洪是加州大學(xué)洛杉磯分校的一位機(jī)器人專(zhuān)家，他同另外幾位工程師正致力于制造可用于災(zāi)難救援的機(jī)器人。他和其他來(lái)自學(xué)術(shù)界、產(chǎn)業(yè)界、美國(guó)宇航局噴氣推進(jìn)實(shí)驗(yàn)室和美國(guó)國(guó)防部的研究機(jī)構(gòu)國(guó)防高級(jí)研究計(jì)劃局的研究人員在去年春天去了福島，去看他們面臨的困難是什么。

“我們獲得的關(guān)鍵信息就是：‘哇，這實(shí)在是太難了。’”洪說(shuō)。

更加出色的機(jī)器人

工程師們已經(jīng)制造出外表令人印象深刻的人形機(jī)器人。這些機(jī)器人可以吹喇叭，甚至能在慢速的足球比賽中相互對(duì)抗。但是，實(shí)際上能夠在災(zāi)區(qū)代替人類(lèi)工作的機(jī)器人是不存在的，人類(lèi)在災(zāi)區(qū)的工作包括翻越瓦礫堆、在廢墟里挖幸存者、打開(kāi)門(mén)和閥門(mén)。

因此，美國(guó)國(guó)防高級(jí)研究計(jì)劃局啟動(dòng)了一項(xiàng)競(jìng)賽，希望能夠發(fā)明出未來(lái)可以做這些工作的機(jī)器人。2012年，該機(jī)構(gòu)宣布開(kāi)展一項(xiàng)比賽，即國(guó)防高級(jí)研究計(jì)劃局機(jī)器人挑戰(zhàn)賽，旨在推動(dòng)救災(zāi)機(jī)器人技術(shù)在當(dāng)前的基礎(chǔ)上向前邁進(jìn)一大步。2013年12月，包括洪的人形機(jī)器人THOR-OP在內(nèi)的17個(gè)參賽機(jī)器人，在一條崎嶇不平的障礙賽道上對(duì)決（編注：此處指參賽隊(duì)參加在佛羅里達(dá)州舉辦的機(jī)器人挑戰(zhàn)賽預(yù)賽），試圖在即將于2015年6月舉行的總決賽中占有一席之地。

吉爾·普拉特是國(guó)防高級(jí)研究計(jì)劃局的項(xiàng)目經(jīng)理。他明白可能需要花費(fèi)數(shù)年時(shí)間才能研發(fā)出能夠挽救福島核電站的機(jī)器人。但他認(rèn)為這場(chǎng)競(jìng)賽不啻為一個(gè)好的開(kāi)端。

9/11的教訓(xùn)

在過(guò)去十年左右的時(shí)間里，救災(zāi)機(jī)器人并沒(méi)有太大的改變。2001年世界貿(mào)易中心大樓被毀時(shí)，工程師安排了幾個(gè)輕巧的機(jī)器人到廢墟中進(jìn)行搜尋。

“這些機(jī)器人鉆進(jìn)那些第一批救災(zāi)人員無(wú)法進(jìn)入的地方。”得克薩斯州Aamp;M大學(xué)野外機(jī)器人專(zhuān)家羅賓·墨菲如此回憶道。她說(shuō)，由于110層的混凝土和鋼筋坍塌成了堅(jiān)實(shí)的瓦礫堆，探地雷達(dá)無(wú)法穿透廢墟，搜救犬也無(wú)法準(zhǔn)確嗅出受害者的方位。

這些機(jī)器人有差不多鞋盒大小，為救援隊(duì)提供了一種新的勘察方式。墨菲認(rèn)為這些可四處活動(dòng)的機(jī)器人是成功的：有幾個(gè)機(jī)器人深入廢墟，經(jīng)受極端高溫的考驗(yàn)，最終找到了十具人類(lèi)遺骸。但是這些機(jī)器人沒(méi)有找到任何幸存者，并出現(xiàn)了許多技術(shù)故障。

有個(gè)機(jī)器人從履帶上脫落，工作人員不得不把它從廢墟中拉出來(lái)，加以修復(fù)。另一個(gè)卡在了縫隙中，停在原地，直到工作人員用它身上的安全繩將它拉出來(lái)。第三個(gè)則失去了聯(lián)系，從安全繩上脫落，之后再也沒(méi)了蹤影。

與C-3PO相差甚遠(yuǎn)

福島事件發(fā)生幾年前，以先進(jìn)機(jī)器人聞名的日本實(shí)際上已研發(fā)出應(yīng)對(duì)核突發(fā)事件的機(jī)器人。

1999年，在一座核電站發(fā)生事故之后，工程師們制造了六個(gè)大型的履帶式機(jī)器人，用他們來(lái)開(kāi)門(mén)、打開(kāi)閥門(mén)、搬重物，甚至清理核輻射。但這些機(jī)器人沒(méi)有得到足夠好的維護(hù)，無(wú)法用于福島核電站。即便這些機(jī)器人當(dāng)時(shí)可以使用，也可能由于過(guò)于龐大和笨重而無(wú)法發(fā)揮作用，工程師永谷圭司及同事在2013年的《野外機(jī)器人雜志》發(fā)文稱(chēng)。

災(zāi)難發(fā)生約一個(gè)月后，一種專(zhuān)門(mén)用于處理爆炸物的小型機(jī)器人最早進(jìn)入福島核電站的核反應(yīng)堆。這種機(jī)器人名為PackBot，約有人的小腿那么高，非常輕，士兵可將其背在背上。該機(jī)器人利用履帶使機(jī)身得以在不平坦的草皮路面上行進(jìn)。它纖細(xì)的手臂上裝有一只鉗爪和一個(gè)攝像頭，使其能抓、能看。在福島地震后的那些日子里，生產(chǎn)PackBot的位于馬薩諸塞州的iRobot公司立即為這種機(jī)器人安裝了輻射和化學(xué)傳感器。

傳感器派上了用場(chǎng)：核電站的工人們用其在工廠內(nèi)部找到人類(lèi)可以安全探索的地方。但有時(shí)，工人們無(wú)法操縱機(jī)器人通過(guò)黑暗的廠房。雖然機(jī)器人能夠開(kāi)門(mén)，但機(jī)器人操作員必須使用兩個(gè)PackBots才能做到這一點(diǎn)：一個(gè)去轉(zhuǎn)動(dòng)門(mén)把手，另一個(gè)將其攝像頭對(duì)準(zhǔn)第一個(gè)機(jī)器人。而且，機(jī)器人攀爬核電站光滑的金屬樓梯時(shí)很費(fèi)力。

實(shí)驗(yàn)室中的小發(fā)明

日本竟然缺少多功能且可使用的救援機(jī)器人，這令該領(lǐng)域的人們感到很驚訝，賓夕法尼亞大學(xué)的機(jī)器人專(zhuān)家馬克·因這樣說(shuō)道。他還說(shuō)，日本不僅擁有簡(jiǎn)單的地面移動(dòng)機(jī)器人，而且比其他國(guó)家擁有更多的人形機(jī)器人。不幸的是，這些新發(fā)明的裝置還沒(méi)有準(zhǔn)備好離開(kāi)實(shí)驗(yàn)室。對(duì)于某些這樣的機(jī)器人來(lái)說(shuō)，即便是經(jīng)過(guò)略有不平的地面都會(huì)有些困難。

“人們看到人形機(jī)器人，以為只要人類(lèi)能做到的事它都可以做到，”因說(shuō)，“事實(shí)上，它能做的事情很少。”

不過(guò)，要應(yīng)對(duì)城市里的災(zāi)難，一些有四肢的人形機(jī)器人可能會(huì)起到關(guān)鍵作用。因?yàn)樵诔鞘欣铮瑯翘菔菫槿送扰逝蓝O(shè)計(jì)的，門(mén)是為人手打開(kāi)而設(shè)計(jì)的。

“在災(zāi)難現(xiàn)場(chǎng)，有推土機(jī)、挖掘機(jī)、電動(dòng)工具，人們使用所有這些大型設(shè)備來(lái)實(shí)施救援任務(wù)，”洪說(shuō)，“因此，很自然地，許多人就認(rèn)為機(jī)器人需要有人的外形。”

在國(guó)防高級(jí)研究計(jì)劃局機(jī)器人挑戰(zhàn)賽預(yù)賽中，大多數(shù)參賽機(jī)器人都有著人類(lèi)的外形。但這些機(jī)器人與電影里的C-3PO完全不同。如今最先進(jìn)的人形機(jī)器人才剛開(kāi)始冒險(xiǎn)走出實(shí)驗(yàn)室，正處于蹣跚學(xué)步階段。

機(jī)器人之戰(zhàn)

目睹災(zāi)難救援機(jī)器人執(zhí)行哪怕最簡(jiǎn)單的任務(wù)，無(wú)論它們勝利還是落敗，都讓人激動(dòng)不已。去年12月，數(shù)千名興奮的觀眾涌入佛羅里達(dá)州的一個(gè)賽場(chǎng)，觀看一幫形態(tài)各異的高科技機(jī)器人參加預(yù)賽。機(jī)器人們笨拙地蹣跚前行，完成一系列任務(wù)，包括開(kāi)門(mén)、越過(guò)碎石、旋轉(zhuǎn)閥門(mén)。這就是災(zāi)難救援機(jī)器人的未來(lái)—在這里，讓機(jī)器人把工具放在桌子上這樣一個(gè)簡(jiǎn)單的動(dòng)作都還被認(rèn)為是炫耀。

“很多這樣的任務(wù)，人在一分鐘或更少的時(shí)間內(nèi)就可以完成，”位于彭薩科拉的佛羅里達(dá)人類(lèi)和機(jī)器認(rèn)知學(xué)院的軟件工程師道格·斯蒂芬說(shuō)，“但我們認(rèn)為理所當(dāng)然的事情對(duì)機(jī)器人來(lái)說(shuō)卻無(wú)比困難。”而要想出如何制造能夠輕松完成所有這些任務(wù)的機(jī)器人，而不是設(shè)計(jì)專(zhuān)門(mén)開(kāi)門(mén)或旋轉(zhuǎn)閥門(mén)的機(jī)器人，就更加困難了。

不過(guò)，這項(xiàng)競(jìng)賽可能已經(jīng)初見(jiàn)成效。預(yù)賽中的各小組已著手解決困擾人形機(jī)器人的各種問(wèn)題，比如行走、電量使用、工具操作。“過(guò)去，很多研究焦點(diǎn)只是放在了走路和不摔倒上。”墨菲說(shuō)道。

斯蒂芬說(shuō)，人類(lèi)走路時(shí)并不只是簡(jiǎn)單地抬腳和放下。人們會(huì)在匆忙中調(diào)整步伐，穿過(guò)繁忙的街道，跨過(guò)人行道上的裂縫，踉蹌時(shí)迅速找回平衡。而且人們做的這些調(diào)整動(dòng)作多數(shù)都是下意識(shí)的。

“但機(jī)器人沒(méi)有自己的大腦，所以我們要告訴它如何做事。”斯蒂芬說(shuō)。學(xué)會(huì)人類(lèi)走路時(shí)靈敏的調(diào)整和輕松優(yōu)雅“是個(gè)難解決的問(wèn)題”。為了參加美國(guó)國(guó)防高級(jí)研究計(jì)劃局的比賽，他和同事們?cè)O(shè)計(jì)了一款軟件，用來(lái)幫助機(jī)器人用腳“思考”，快速反應(yīng)。

晉級(jí)總決賽的工程師們都一致認(rèn)為，即便是競(jìng)賽中最出色的機(jī)器人或許也無(wú)法用于再一次福島事件。但是位于加利福尼亞州帕薩迪納市的美國(guó)航空航天局噴氣推進(jìn)實(shí)驗(yàn)室的工程師布雷特·肯尼迪說(shuō)：“我認(rèn)為我們能做得更好。”這場(chǎng)競(jìng)賽促成的一系列技術(shù)可能會(huì)催生出許多不同類(lèi)型的救災(zāi)機(jī)器人。

“有一天，機(jī)器人要是能做消防員能做的所有事，那就太好了！”肯尼迪說(shuō)，“破門(mén)而入，解救嬰兒，所有這些事。”

1. duck [d?k] vt.〈口〉躲避

2. take over：接替

3. pose for：給……造成困難（或帶來(lái)問(wèn)題）

4. take-home message：關(guān)鍵信息

5. kick off：開(kāi)始（討論或活動(dòng)）

6. burrow [?b?r??] vi. 搜尋，翻找

7. slew [slu?] n. 許多;大量

8. wedge [wed?] vt. 擠入;塞入

9. C-3PO：指電影《星球大戰(zhàn)》（Star Wars）中用廢棄的殘片和回收物拼湊而成的機(jī)器人，神經(jīng)質(zhì)且多愁善感。

10. come in handy：有用，派得上用場(chǎng)

11. trial [?tra??l] n. [復(fù)]選拔賽;預(yù)賽

12. state-of-the-art：十分先進(jìn)的;應(yīng)用最新理念（或方法）的

13. fizzle [?f?z（?）l] n. 失敗

14. sail through：輕易完成;順利通過(guò)

15. pay off：取得成功，得到好結(jié)果

16. on the fly：急忙地，忙忙碌碌地

17. hair-trigger：反應(yīng)迅速的

18. think on one’s feet：才思敏捷;行動(dòng)果斷

19. the whole nine yards：一切，全部