Placeholder Image

字幕列表 影片播放

  • So, robots.

    譯者: Helen Chang 審譯者: S Sung

  • Robots can be programmed

    機器人,

  • to do the same task millions of times with minimal error,

    能夠編寫程式以最少出錯的次數

  • something very difficult for us, right?

    讓機器人完成數百萬次相同的任務,

  • And it can be very impressive to watch them at work.

    但對我們人類來說相當困難,對吧?

  • Look at them.

    看它們工作,可能令人印象很深刻。

  • I could watch them for hours.

    看它們。

  • No?

    我可以連看幾個小時。

  • What is less impressive

    不是嗎?

  • is that if you take these robots out of the factories,

    不太令人印象深刻的是

  • where the environments are not perfectly known and measured like here,

    如果這些機器人到了工廠外,

  • to do even a simple task which doesn't require much precision,

    和這裡全然已知和測量過的 環境不一樣,

  • this is what can happen.

    即使做個簡單、無須太精密的任務,

  • I mean, opening a door, you don't require much precision.

    可能會這樣。

  • (Laughter)

    我是說,開一扇門無須太精密。

  • Or a small error in the measurements,

    (笑聲)

  • he misses the valve, and that's it --

    或者測量中的一個小錯誤,

  • (Laughter)

    使它錯過了閥門,就這樣,完了。

  • with no way of recovering, most of the time.

    (笑聲)

  • So why is that?

    大多數時候沒有辦法恢復。

  • Well, for many years,

    為什麼呢?

  • robots have been designed to emphasize speed and precision,

    多年來,

  • and this translates into a very specific architecture.

    機器人的設計強調速度和精密度,

  • If you take a robot arm,

    轉化成為非常具體的架構。

  • it's a very well-defined set of rigid links

    如果拿一隻機器手臂,

  • and motors, what we call actuators,

    用的是一套很明確的剛性鏈接

  • they move the links about the joints.

    和被稱為執行器的機電,

  • In this robotic structure,

    移動關節周圍的鏈接。

  • you have to perfectly measure your environment,

    在這機器人結構裡

  • so what is around,

    周圍的環境必須被完美地測量,

  • and you have to perfectly program every movement

    周圍有什麼,

  • of the robot joints,

    也必須完美地編寫

  • because a small error can generate a very large fault,

    每個機器人關節動作的指令,

  • so you can damage something or you can get your robot damaged

    因為一個小錯誤可能會 導致非常大的錯誤,

  • if something is harder.

    可能損毀東西;

  • So let's talk about them a moment.

    或者,如果那東西比較硬, 就會損毀機器人。

  • And don't think about the brains of these robots

    讓我們來談一會兒,

  • or how carefully we program them,

    不要考慮這些機器人的腦

  • but rather look at their bodies.

    或它的程式寫得多仔細,

  • There is obviously something wrong with it,

    而是看它們的身體。

  • because what makes a robot precise and strong

    身體顯然有點不對勁,

  • also makes them ridiculously dangerous and ineffective in the real world,

    因為使機器人精確和強大的因素

  • because their body cannot deform

    也使它們在現實世界中 危險和沒效率,

  • or better adjust to the interaction with the real world.

    因為它們的身體不能變形,

  • So think about the opposite approach,

    也無法更適應 與真實世界的相互作用。

  • being softer than anything else around you.

    因此反向思考,

  • Well, maybe you think that you're not really able to do anything if you're soft,

    比周圍的其他事物更柔軟。

  • probably.

    也許你認為柔軟就辦不了事。

  • Well, nature teaches us the opposite.

    或許吧。

  • For example, at the bottom of the ocean,

    然而,大自然告訴我們的恰恰相反。

  • under thousands of pounds of hydrostatic pressure,

    例如,在海底,

  • a completely soft animal

    在數千磅的靜水壓力下,

  • can move and interact with a much stiffer object than him.

    完全柔軟的動物能移動,

  • He walks by carrying around this coconut shell

    也能與比牠硬的物體相互作用。

  • thanks to the flexibility of his tentacles,

    牠帶著這個椰子殼走來走去,

  • which serve as both his feet and hands.

    牠的觸手靈活,

  • And apparently, an octopus can also open a jar.

    既是腳,也是手。

  • It's pretty impressive, right?

    很顯然,章魚能開罐。

  • But clearly, this is not enabled just by the brain of this animal,

    令人印象深刻,對吧?

  • but also by his body,

    但顯然,牠辦得到不僅由於腦,

  • and it's a clear example, maybe the clearest example,

    也由於身體。

  • of embodied intelligence,

    這是個明顯,也許最明顯

  • which is a kind of intelligence that all living organisms have.

    展現智能的例子,

  • We all have that.

    一種生物具有的智能。

  • Our body, its shape, material and structure,

    我們都有。

  • plays a fundamental role during a physical task,

    我們的身體、形狀、材質和結構,

  • because we can conform to our environment

    在做動作時起至關重要的作用;

  • so we can succeed in a large variety of situations

    因為我們符合環境,

  • without much planning or calculations ahead.

    因此能在各種情況下成功,

  • So why don't we put some of this embodied intelligence

    無需提前計劃或計算。

  • into our robotic machines,

    那為什麼不把這些展現的身體智能

  • to release them from relying on excessive work

    放入機器人,

  • on computation and sensing?

    讓它們擺脫

  • Well, to do that, we can follow the strategy of nature,

    過度依賴計算和感知的工作呢?

  • because with evolution, she's done a pretty good job

    為了做到這一點, 我們可以遵循自然的戰略;

  • in designing machines for environment interaction.

    因為演化過程中的機器

  • And it's easy to notice that nature uses soft material frequently

    與環境的交互作用設計得非常好。

  • and stiff material sparingly.

    容易注意到大自然常用軟質的材料,

  • And this is what is done in this new field or robotics,

    很少用堅硬的材料。

  • which is called "soft robotics,"

    這就是在「軟式機器人」

  • in which the main objective is not to make super-precise machines,

    這個新的機器人技術領域裡做的。

  • because we've already got them,

    主要的目標不是製造超精密的機器,

  • but to make robots able to face unexpected situations in the real world,

    因為我們已經有了;

  • so able to go out there.

    而是要讓機器人能夠面對 現實世界中的意外情況,

  • And what makes a robot soft is first of all its compliant body,

    能夠走出去。

  • which is made of materials or structures that can undergo very large deformations,

    要讓機器人柔軟 先要讓的它的身體柔順,

  • so no more rigid links,

    用可承受大變形的材料或結構構成,

  • and secondly, to move them, we use what we call distributed actuation,

    不用剛性的連接。

  • so we have to control continuously the shape of this very deformable body,

    其次,用分佈式驅動來移動它們,

  • which has the effect of having a lot of links and joints,

    必須不斷地控制 這種變形身體的形狀,

  • but we don't have any stiff structure at all.

    這種變形身體 有很多連接和關節的效果,

  • So you can imagine that building a soft robot is a very different process

    但沒有任何僵硬的結構。

  • than stiff robotics, where you have links, gears, screws

    可以想像建造軟式機器人 是個非常不一樣的過程,

  • that you must combine in a very defined way.

    不是用鏈接、齒輪、 螺絲的僵硬機器人,

  • In soft robots, you just build your actuator from scratch

    必須以一種非常明確的方式結合。

  • most of the time,

    做軟式機器人

  • but you shape your flexible material

    大多時候只需從頭開始建造執行器,

  • to the form that responds to a certain input.

    但是將柔性的材料

  • For example, here, you can just deform a structure

    塑造成會回應特定輸入的形式。

  • doing a fairly complex shape

    例如在這裡,

  • if you think about doing the same with rigid links and joints,

    如果用剛性的鏈接和關節,

  • and here, what you use is just one input,

    結構將會相當複雜;

  • such as air pressure.

    而(軟式結構)這裡只需一個輸入,

  • OK, but let's see some cool examples of soft robots.

    例如氣壓。

  • Here is a little cute guy developed at Harvard University,

    讓我們看一些軟式機器人的酷例子。

  • and he walks thanks to waves of pressure applied along its body,

    這裡有個哈佛大學開發的 可愛的小伙子,

  • and thanks to the flexibility, he can also sneak under a low bridge,

    由身體上施加的壓力波而行走;

  • keep walking,

    並且靈活到可以在低矮的橋下潛行,

  • and then keep walking a little bit different afterwards.

    一直走,

  • And it's a very preliminary prototype,

    一直走,然後有些不同。

  • but they also built a more robust version with power on board

    這是個極為初步的原型,

  • that can actually be sent out in the world and face real-world interactions

    還有個配有電源板的進階版,

  • like a car passing it over it ...

    能實際在現實世界面對面交流,

  • and keep working.

    例如汽車開過它的身旁,

  • It's cute.

    它繼續向前走。

  • (Laughter)

    它真可愛。

  • Or a robotic fish, which swims like a real fish does in water

    (笑聲)

  • simply because it has a soft tail with distributed actuation

    還有機器魚,像真魚一樣游在水中,

  • using still air pressure.

    只因它有柔軟的尾巴,

  • That was from MIT,

    用靜止空氣壓來分佈式驅動它。

  • and of course, we have a robotic octopus.

    是麻省理工學院做的。

  • This was actually one of the first projects

    當然,我們還有機器章魚。

  • developed in this new field of soft robots.

    實際上是軟式機器人 這新領域開發的第一批專案之一。

  • Here, you see the artificial tentacle,

    這裡看得到人造的觸手,

  • but they actually built an entire machine with several tentacles

    實際上他們造了 帶有幾隻觸手的整個機器,

  • they could just throw in the water,

    可以把它扔進水中,

  • and you see that it can kind of go around and do submarine exploration

    它可以四處走動,

  • in a different way than rigid robots would do.

    以不同於硬式機器人的 方式在水裡探索,

  • But this is very important for delicate environments, such as coral reefs.

    這對珊瑚礁等微妙環境非常重要。

  • Let's go back to the ground.

    讓我們回到地面。

  • Here, you see the view

    這裡看得到史丹佛大學的同事

  • from a growing robot developed by my colleagues in Stanford.

    正開發的機器人的圖。

  • You see the camera fixed on top.

    相機固定在頂部。

  • And this robot is particular,

    這機器人很特別,

  • because using air pressure, it grows from the tip,

    因為用氣壓,它向上長,

  • while the rest of the body stays in firm contact with the environment.

    而身體的其餘部分 維持與環境的緊密接觸。

  • And this is inspired by plants, not animals,

    它的靈感來自於植物,不是動物,

  • which grows via the material in a similar manner

    植物以類似的方式生長,

  • so it can face a pretty large variety of situations.

    因此能面對各式各樣的狀況。

  • But I'm a biomedical engineer,

    我是生物醫學工程師,

  • and perhaps the application I like the most

    我最喜歡醫學領域的應用,

  • is in the medical field,

    難以想像還有更為緊密的 與人體的相互作用,

  • and it's very difficult to imagine a closer interaction with the human body

    除非實際進入人體的內部,

  • than actually going inside the body,

    例如,執行微創手術。

  • for example, to perform a minimally invasive procedure.

    在此機器人能對外科醫師很有幫助,

  • And here, robots can be very helpful with the surgeon,

    因為醫師們必須使用小孔 和直的器械進入人體,

  • because they must enter the body

    這些器械必須在很不確定的環境中

  • using small holes and straight instruments,

    與非常微妙的結構相互作用,

  • and these instruments must interact with very delicate structures

    且必須安全地進行。

  • in a very uncertain environment,

    將相機帶入身體內部,

  • and this must be done safely.

    將外科醫師的眼睛帶入手術區域

  • Also bringing the camera inside the body,

    如果用剛性棒可能極具挑戰,

  • so bringing the eyes of the surgeon inside the surgical field

    像傳統的內視鏡之類的。

  • can be very challenging if you use a rigid stick,

    我與以前在歐洲的研究小組一起

  • like a classic endoscope.

    開發這款手術用的軟式照相機器人,

  • With my previous research group in Europe,

    與傳統的內視鏡很不同,它能移動,

  • we developed this soft camera robot for surgery,

    這要歸功於模塊的靈活性,

  • which is very different from a classic endoscope,

    可以向各個方向彎曲或伸長。

  • which can move thanks to the flexibility of the module

    實際上,外科醫師用這種方法

  • that can bend in every direction and also elongate.

    從不同的角度 觀察其他儀器進行的操作,

  • And this was actually used by surgeons to see what they were doing

    無須分心去在乎觸及了什麼。

  • with other instruments from different points of view,

    在這裡看得到軟式機器人在行動,

  • without caring that much about what was touched around.

    它進入體內,

  • And here you see the soft robot in action,

    這是一具模擬的人體, 不是真正的人體。

  • and it just goes inside.

    它四處走動。

  • This is a body simulator, not a real human body.

    有個燈,

  • It goes around.

    因為體內通常沒亮光。

  • You have a light, because usually,

    最好沒有。

  • you don't have too many lights inside your body.

    (笑聲)

  • We hope.

    但有時候,甚至可以 用單針完成外科手術,

  • (Laughter)

    我們現今在史丹佛大學 研究一種非常靈活的針頭,

  • But sometimes, a surgical procedure can even be done using a single needle,

    它是一種非常小巧的軟式機器人,

  • and in Stanford now, we are working on a very flexible needle,

    被設計來與組織相互作用,

  • kind of a very tiny soft robot

    在堅實的器官內轉來轉去,

  • which is mechanically designed to use the interaction with the tissues

    所以通過單個插入孔

  • and steer around inside a solid organ.

    就能到達實體器官深處的腫瘤

  • This makes it possible to reach many different targets, such as tumors,

    或許多不同目標。

  • deep inside a solid organ

    甚至還可以繞過

  • by using one single insertion point.

    避開到達目標前的其他結構。

  • And you can even steer around the structure that you want to avoid

    顯然對於機器人來說 這是個非常來勁的時刻。

  • on the way to the target.

    有了軟式結構的機器人,

  • So clearly, this is a pretty exciting time for robotics.

    給機器人業界帶來新的、 極具挑戰性的問題,

  • We have robots that have to deal with soft structures,

    而我們實際上才剛剛 開始學習如何控制,

  • so this poses new and very challenging questions

    如何將傳感器放在這些 非常靈活的結構上。

  • for the robotics community,

    但是當然我們還離自然界

  • and indeed, we are just starting to learn how to control,

    數百萬年演變過程中的 發現還遠得很。

  • how to put sensors on these very flexible structures.

    但有一點我很肯定:

  • But of course, we are not even close to what nature figured out

    機器人會更柔軟、更安全,

  • in millions of years of evolution.

    它們能幫人的還多著呢。

  • But one thing I know for sure:

    謝謝。

  • robots will be softer and safer,

    (掌聲)

  • and they will be out there helping people.

  • Thank you.

  • (Applause)

So, robots.

譯者: Helen Chang 審譯者: S Sung

字幕與單字

影片操作 你可以在這邊進行「影片」的調整,以及「字幕」的顯示

B1 中級 中文 美國腔 TED 機器人 身體 柔軟 結構 鏈接

【TED】Giada Gerboni:柔性、軟性機器人的不可思議的潛力(The incredible potential of flexible, soft robots | Giada Gerboni)。 (【TED】Giada Gerboni: The incredible potential of flexible, soft robots (The incredible potential of flexible, soft robots | Giada Gerboni))

  • 501 54
    林宜悉 發佈於 2021 年 01 月 14 日
影片單字