Cyber-roaches

賽博蟑螂

Robotised insects may search collapsed buildings for survivors

機(jī)械化昆蟲(chóng)可能成為廢墟搜救奇兵

They can detect movement, body warmth and exhaled carbon dioxide

它們可以探測(cè)人體活動(dòng)、體溫和呼出的二氧化碳【新知】

WHY GO TO all the trouble of designing and building a drone if nature has already done most of the job for you? That is the attitude taken by the small but determined band of researchers who are trying to robotise insects. Some are working on turning flying critters like beetles into such cyborgs—perhaps for use in military reconnaissance or espionage. Others prefer to concentrate on the creepy-crawly side of entomology, by taking electronic control of cockroaches.

既然大自然差不多已經(jīng)提供了現(xiàn)成的，何必還要費(fèi)那么大勁去設(shè)計(jì)和制造無(wú)人機(jī)呢？一群為數(shù)不多但意志堅(jiān)定的研究人員就是這個(gè)態(tài)度，他們正試圖對(duì)昆蟲(chóng)做機(jī)械化改造。一些人研究如何把甲殼蟲(chóng)之類的飛蟲(chóng)改造成半機(jī)器生物——或許可以用于軍事偵察或間諜活動(dòng)。另一些人選擇搗鼓爬來(lái)爬去有點(diǎn)嚇人的那一類——對(duì)蟑螂實(shí)施電子化操控。

The first cyber-roach goes back to 1997, when Shimoyama Isao of Tokyo University sent electrical signals to a cockroach’s antennae, causing it to turn either left or right depending on which antenna was stimulated. Others have built on this approach by recruiting extra sense organs, such as the rear-facing cerci. They have also begun fitting the insects with instrument packs that might let them do a useful job: searching collapsed buildings for survivors.

第一只賽博蟑螂可以追溯到1997年，當(dāng)時(shí)東京大學(xué)的下山勲向蟑螂的觸須發(fā)送電信號(hào)，使其向左或向右轉(zhuǎn)動(dòng)——待看受刺激的是哪側(cè)的觸須。在此基礎(chǔ)上，其他研究者嘗試操控其他感覺(jué)器官，例如向后的尾須。他們還開(kāi)始給蟑螂裝上儀器包，這樣它們說(shuō)不定就可以做一項(xiàng)有用的工作：在倒塌的建筑物中搜尋幸存者。

One such is Sato Hirotaka of Nanyang Technological University, in Singapore. He has been working on cyber-insects (including flying versions, in the form of giant flower beetles) for 15 years. Now, he has added another twist to cyber-roaches. Instead of having their movements dictated by remote control, his are autonomous agents. They are run by algorithms that respond directly to sensors in their backpacks.

新加坡南洋理工大學(xué)的佐藤裕崇就是其中一位研究者。15年來(lái)，他一直在研究賽博昆蟲(chóng)（包括會(huì)飛的巨型花金龜)。現(xiàn)在，他又給賽博蟑螂增添了新花樣。它們的行動(dòng)不再受遠(yuǎn)程控制，而是成為自主行動(dòng)的主體。算法根據(jù)儀器背包里傳感器的信號(hào)直接驅(qū)使它們行動(dòng)。?

The insects thus fitted out by Dr Sato are Madagascar hissing cockroaches, which are about 6cm long. The backpacks contain a communications chip, a carbon-dioxide sensor, a motion sensor, an infrared camera and a tiny battery.

佐藤使用的是馬達(dá)加斯加發(fā)聲蟑螂，體長(zhǎng)約六厘米。它們扛上的儀器背包里裝有通信芯片、二氧化碳傳感器、運(yùn)動(dòng)傳感器、紅外攝像機(jī)和微型電池。

For search-and-rescue operations in collapsed buildings, fleets of these roaches would be released into the rubble, to crawl their way through while searching for signs of life such as movement, body heat and elevated CO2 levels from respiration. The artificial intelligence that decides whether a set of signals actually indicate the presence of a human being is programmed directly into the camera. If it thinks it has spotted someone, it alerts a rescuer.

在倒塌的建筑物里開(kāi)展搜救時(shí)，這些蟑螂將被成批釋放到廢墟中，四處爬行尋找生命跡象，如人體移動(dòng)、體溫，以及由呼吸引起的二氧化碳濃度升高。攝像機(jī)中直接編入了人工智能程序，可以判斷一組信號(hào)是否真的顯示有人存在。如果程序認(rèn)為自己發(fā)現(xiàn)了幸存者，就會(huì)向救援人員發(fā)出警報(bào)。

To test this arrangement, Dr Sato and his team ran trials in a simulated disaster zone. They laid out concrete blocks of various shapes and sizes in an area of 25 square metres. Interspersed among these were a number of people, and also some decoys, such as a heat lamp, a microwave oven and a laptop. They then released the cyber-roaches, having first programmed into them the search’s start and end points. The software proved able to recognise humans correctly 87% of the time, a success rate Dr Sato thinks could be improved still further by collecting multiple images from different angles.

為了驗(yàn)證效果，佐藤和他的團(tuán)隊(duì)在一個(gè)模擬災(zāi)區(qū)進(jìn)行了試驗(yàn)。他們?cè)?5平方米的范圍內(nèi)布置了各種形狀和大小的混凝土塊，當(dāng)中散布著一些人，也放置了一些干擾物，如保溫?zé)?、微波爐和筆記本電腦。他們將搜索的起點(diǎn)和終點(diǎn)輸入程序，然后釋放了這些賽博蟑螂。結(jié)果證明，該軟件成功識(shí)別人類的準(zhǔn)確率達(dá)到87%。佐藤認(rèn)為如果從不同角度采集多個(gè)圖像，成功率還可以進(jìn)一步提高。

The next phase of the project is to refine the system for use out of doors. That done, manufacture of the backpacks and automation of their attachment to the insects will need to be commercialised. If all goes well, Dr Sato reckons the result could be available for deployment within five years.

該項(xiàng)目的下一步是改進(jìn)系統(tǒng)以應(yīng)用于戶外。這一步完成后，將需要實(shí)現(xiàn)背包制造以及背包與蟑螂自動(dòng)裝配的商業(yè)化。如果一切順利，佐藤估計(jì)這一成果將在五年內(nèi)投入使用。