Pilotless aircraft

　　無(wú)人機(jī)

　　Giving drones a thumbs up

　　向無(wú)人機(jī)打手勢(shì)

　　How to integrate the control of piloted andpilotless aircraft

　　如何讓指揮有人機(jī)的方法適用于無(wú)人機(jī)

　　DECK officers on American aircraft carriers use hand gestures to guide planes around theirvessels.

　　在美國(guó)的航空母艦上，甲板指揮員會(huì)用手勢(shì)指揮母艦附近的飛機(jī)。

　　These signals are fast, efficient and perfect for a noisy environment.

　　這種信號(hào)快速、高效，而且十分適用于嘈雜的環(huán)境。

　　Unfortunately, they work only with people.

　　但遺憾的是，只有人才能讀懂這些手勢(shì)。

　　They are utterly lost on roboticdronesand even if a drone is under the control of a remote pilot deep in the bowels ofthe ship,

　　在無(wú)人機(jī)上，這一套完全失效;而即便有飛行員在船艙深處遠(yuǎn)程操控這架飛機(jī)，

　　that pilot often has difficulty reading them.

　　他往往也很難識(shí)別那些手勢(shì)。

　　Since drones are becoming more and more important in modern warfare, this is a nuisance.

　　這是個(gè)麻煩，因?yàn)闊o(wú)人機(jī)在現(xiàn)代戰(zhàn)爭(zhēng)里變得越來(lái)越重要了。

　　Life would be easier for all if drones were smart enough to respond directly to a deckofficer s gesticulations.

　　若無(wú)人機(jī)的智能達(dá)到了足以直接響應(yīng)甲板指揮員手勢(shì)的程度，那一切都會(huì)好很多。

　　Making them that smart is the goal of Yale Song, a computer scientist at the MassachusettsInstitute of Technology.

　　讓無(wú)人機(jī)具備這樣的智能是麻省理工學(xué)院計(jì)算機(jī)科學(xué)家Yale Song的目標(biāo)。

　　He is not there yet but,

　　這個(gè)目標(biāo)雖尚未達(dá)成，

　　as he reports in ACM Transactions on Interactive Intelligent Systems,

　　不過(guò)正如他在《美國(guó)計(jì)算機(jī)學(xué)會(huì)交互式智能系統(tǒng)學(xué)報(bào)》所報(bào)告的，

　　he and his colleagues David Demirdjian and Randall Davis have developed a promisingprototype.

　　他和他的同事David Demirdjian和Randall Davis已開發(fā)了一個(gè)很有前景的原型系統(tǒng)。

　　To try teaching drones the language of hand signals Mr Song and his colleagues made a seriesof videos in which various deck officers performed to camera a set of 24 commonly usedgestures.

　　為了讓無(wú)人機(jī)讀懂手語(yǔ)，Yale Song和他的同事制作了一系列視頻，視頻記錄了多位甲板指揮員對(duì)著攝象機(jī)擺出的24個(gè)常用手勢(shì)。

　　They then fed these videos into an algorithm of their own devising that was designed toanalyse the position and movement of a human body, and told the algorithm what eachgesture represented.

　　然后他們用一個(gè)自己設(shè)計(jì)的算法來(lái)處理這些視頻，并讓算法知道每個(gè)手勢(shì)的意義。

　　The idea was that the algorithm would learn the association and, having seen the samegesture performed by different people,

　　他們的設(shè)想是，該算法會(huì)記住每個(gè)手勢(shì)所對(duì)應(yīng)的意義，而在對(duì)不同人擺出的相同手勢(shì)進(jìn)行處理后能夠概括出手勢(shì)本身的意義，

　　would be able to generalise what was going on and thus recognise gestures performed bystrangers.

　　從而識(shí)別任何人擺出的手勢(shì)。

　　Unfortunately, it did not quite work out like that.

　　很遺憾，實(shí)際與預(yù)想的不太一樣。

　　In much the same way that spoken language is actually a continuous stream of sound,

　　其實(shí)指揮飛行員所用的手語(yǔ)和人說(shuō)的話差不多。

　　so the language of gestures to pilots is also continuous, with one flowing seamlessly intothe next.

　　后者實(shí)際上是一串連續(xù)的聲音，而手語(yǔ)同樣也是連續(xù)的，因?yàn)閮蓚€(gè)動(dòng)作之間是連貫的。

　　And the algorithm could not cope with that.

　　但該算法無(wú)法處理這種連續(xù)的信息。

　　To overcome this difficulty Mr Song imposed gaps by chopping the videos up intothree-second blocks.

　　為了解決這個(gè)問(wèn)題，Yale Song以3秒為一段將視頻截開，在各段之間插入時(shí)間間隔。

　　That allowed the computer time for reflection.

　　這樣就給計(jì)算機(jī)留出了響應(yīng)時(shí)間。

　　Its accuracy was also increased by interpreting each block in light of those immediatelybefore and after it,

　　同時(shí)識(shí)別的準(zhǔn)確率也有所提高。因?yàn)檫@樣計(jì)算機(jī)就能根據(jù)前一段及后一段的視頻來(lái)理解當(dāng)前這一段，

　　to see if the result was a coherent message of the sort a deck officer might actually wish toimpart.

　　看看結(jié)果是不是那種甲板指揮員可能真的想擺出的有特定意義的手勢(shì)。

　　The result is a system that gets it right three-quarters of the time.

　　他們最終做出了一個(gè)正確率為75%的系統(tǒng)。

　　Obviously that is not enough:

　　顯然，那樣是不夠的：

　　you would not entrust the fate of a multi-million-dollar drone to such a system.

　　你不會(huì)將一架價(jià)值數(shù)百萬(wàn)美元的無(wú)人機(jī)交給這樣的系統(tǒng)。

　　But it is a good start.

　　但這是個(gè)好的開始。

　　If Mr Song can push the accuracy up to that displayed by a human pilot, then the task ofcontrolling activity on deck should become a lot easier.

　　若Yale Song能將無(wú)人機(jī)識(shí)別手勢(shì)的正確率提高至與真人飛行員相當(dāng)，那么在甲板指揮無(wú)人機(jī)會(huì)容易得多。

　　詞語(yǔ)解釋

　　1.aircraft n.飛機(jī)，航空器

　　Application for registration of mortgage in civilaircraft 1.

　　民用航空器抵押權(quán)登記申請(qǐng)書。

　　2.vessel n.容器;船，飛船

　　Your flesh is a relic, a mere vessel.

　　你的肉體已成廢物，只是個(gè)容器。

　　3.environment n.環(huán)境，外界;周圍

　　But is that a safe environment for a child?

　　但這樣的環(huán)境對(duì)孩子來(lái)說(shuō)安全嗎?

　　4.warfare n.戰(zhàn)爭(zhēng)，戰(zhàn)爭(zhēng)狀態(tài);斗爭(zhēng)

　　It is imperative to conduct psychological warfare.

　　進(jìn)行心理戰(zhàn)是必要的。

　　5.institute n.協(xié)會(huì);學(xué)會(huì);學(xué)院

　　He graduated from an institute of foreign trade.

　　他是外貿(mào)學(xué)院畢業(yè)的。

　　Pilotless aircraft

　　無(wú)人機(jī)

　　Giving drones a thumbs up

　　向無(wú)人機(jī)打手勢(shì)

　　How to integrate the control of piloted andpilotless aircraft

　　如何讓指揮有人機(jī)的方法適用于無(wú)人機(jī)

　　DECK officers on American aircraft carriers use hand gestures to guide planes around theirvessels.

　　在美國(guó)的航空母艦上，甲板指揮員會(huì)用手勢(shì)指揮母艦附近的飛機(jī)。

　　These signals are fast, efficient and perfect for a noisy environment.

　　這種信號(hào)快速、高效，而且十分適用于嘈雜的環(huán)境。

　　Unfortunately, they work only with people.

　　但遺憾的是，只有人才能讀懂這些手勢(shì)。

　　They are utterly lost on roboticdronesand even if a drone is under the control of a remote pilot deep in the bowels ofthe ship,

　　在無(wú)人機(jī)上，這一套完全失效;而即便有飛行員在船艙深處遠(yuǎn)程操控這架飛機(jī)，

　　that pilot often has difficulty reading them.

　　他往往也很難識(shí)別那些手勢(shì)。

　　Since drones are becoming more and more important in modern warfare, this is a nuisance.

　　這是個(gè)麻煩，因?yàn)闊o(wú)人機(jī)在現(xiàn)代戰(zhàn)爭(zhēng)里變得越來(lái)越重要了。

　　Life would be easier for all if drones were smart enough to respond directly to a deckofficer s gesticulations.

　　若無(wú)人機(jī)的智能達(dá)到了足以直接響應(yīng)甲板指揮員手勢(shì)的程度，那一切都會(huì)好很多。

　　Making them that smart is the goal of Yale Song, a computer scientist at the MassachusettsInstitute of Technology.

　　讓無(wú)人機(jī)具備這樣的智能是麻省理工學(xué)院計(jì)算機(jī)科學(xué)家Yale Song的目標(biāo)。

　　He is not there yet but,

　　這個(gè)目標(biāo)雖尚未達(dá)成，

　　as he reports in ACM Transactions on Interactive Intelligent Systems,

　　不過(guò)正如他在《美國(guó)計(jì)算機(jī)學(xué)會(huì)交互式智能系統(tǒng)學(xué)報(bào)》所報(bào)告的，

　　he and his colleagues David Demirdjian and Randall Davis have developed a promisingprototype.

　　他和他的同事David Demirdjian和Randall Davis已開發(fā)了一個(gè)很有前景的原型系統(tǒng)。

　　To try teaching drones the language of hand signals Mr Song and his colleagues made a seriesof videos in which various deck officers performed to camera a set of 24 commonly usedgestures.

　　為了讓無(wú)人機(jī)讀懂手語(yǔ)，Yale Song和他的同事制作了一系列視頻，視頻記錄了多位甲板指揮員對(duì)著攝象機(jī)擺出的24個(gè)常用手勢(shì)。

　　They then fed these videos into an algorithm of their own devising that was designed toanalyse the position and movement of a human body, and told the algorithm what eachgesture represented.

　　然后他們用一個(gè)自己設(shè)計(jì)的算法來(lái)處理這些視頻，并讓算法知道每個(gè)手勢(shì)的意義。

　　The idea was that the algorithm would learn the association and, having seen the samegesture performed by different people,

　　他們的設(shè)想是，該算法會(huì)記住每個(gè)手勢(shì)所對(duì)應(yīng)的意義，而在對(duì)不同人擺出的相同手勢(shì)進(jìn)行處理后能夠概括出手勢(shì)本身的意義，

　　would be able to generalise what was going on and thus recognise gestures performed bystrangers.

　　從而識(shí)別任何人擺出的手勢(shì)。

　　Unfortunately, it did not quite work out like that.

　　很遺憾，實(shí)際與預(yù)想的不太一樣。

　　In much the same way that spoken language is actually a continuous stream of sound,

　　其實(shí)指揮飛行員所用的手語(yǔ)和人說(shuō)的話差不多。

　　so the language of gestures to pilots is also continuous, with one flowing seamlessly intothe next.

　　后者實(shí)際上是一串連續(xù)的聲音，而手語(yǔ)同樣也是連續(xù)的，因?yàn)閮蓚€(gè)動(dòng)作之間是連貫的。

　　And the algorithm could not cope with that.

　　但該算法無(wú)法處理這種連續(xù)的信息。

　　To overcome this difficulty Mr Song imposed gaps by chopping the videos up intothree-second blocks.

　　為了解決這個(gè)問(wèn)題，Yale Song以3秒為一段將視頻截開，在各段之間插入時(shí)間間隔。

　　That allowed the computer time for reflection.

　　這樣就給計(jì)算機(jī)留出了響應(yīng)時(shí)間。

　　Its accuracy was also increased by interpreting each block in light of those immediatelybefore and after it,

　　同時(shí)識(shí)別的準(zhǔn)確率也有所提高。因?yàn)檫@樣計(jì)算機(jī)就能根據(jù)前一段及后一段的視頻來(lái)理解當(dāng)前這一段，

　　to see if the result was a coherent message of the sort a deck officer might actually wish toimpart.

　　看看結(jié)果是不是那種甲板指揮員可能真的想擺出的有特定意義的手勢(shì)。

　　The result is a system that gets it right three-quarters of the time.

　　他們最終做出了一個(gè)正確率為75%的系統(tǒng)。

　　Obviously that is not enough:

　　顯然，那樣是不夠的：

　　you would not entrust the fate of a multi-million-dollar drone to such a system.

　　你不會(huì)將一架價(jià)值數(shù)百萬(wàn)美元的無(wú)人機(jī)交給這樣的系統(tǒng)。

　　But it is a good start.

　　但這是個(gè)好的開始。

　　If Mr Song can push the accuracy up to that displayed by a human pilot, then the task ofcontrolling activity on deck should become a lot easier.

　　若Yale Song能將無(wú)人機(jī)識(shí)別手勢(shì)的正確率提高至與真人飛行員相當(dāng)，那么在甲板指揮無(wú)人機(jī)會(huì)容易得多。

　　詞語(yǔ)解釋

　　1.aircraft n.飛機(jī)，航空器

　　Application for registration of mortgage in civilaircraft 1.

　　民用航空器抵押權(quán)登記申請(qǐng)書。

　　2.vessel n.容器;船，飛船

　　Your flesh is a relic, a mere vessel.

　　你的肉體已成廢物，只是個(gè)容器。

　　3.environment n.環(huán)境，外界;周圍

　　But is that a safe environment for a child?

　　但這樣的環(huán)境對(duì)孩子來(lái)說(shuō)安全嗎?

　　4.warfare n.戰(zhàn)爭(zhēng)，戰(zhàn)爭(zhēng)狀態(tài);斗爭(zhēng)

　　It is imperative to conduct psychological warfare.

　　進(jìn)行心理戰(zhàn)是必要的。

　　5.institute n.協(xié)會(huì);學(xué)會(huì);學(xué)院

　　He graduated from an institute of foreign trade.

　　他是外貿(mào)學(xué)院畢業(yè)的。