the-changelog-670

**Jerod Santo:** Today, we're joined by Keenan Wyrobek, founder and CTO of Zipline, a company I'm very, very interested in.

**Jerod Santo：** 今天，我们邀请了 Zipline 的创始人兼首席技术官 Keenan Wyrobek，这是我非常非常感兴趣的公司。

Welcome to the show, Keenan.

欢迎来到这个节目，基南。

**Jerod Santo:** Pleasure to have you.

**杰罗德·桑托：** 很高兴有你。

Autonomous flying machines, all kinds of deliveries happening...

自主飞行器、各种交付活动……

I saw Zipline and I thought, "You know what, this one makes sense." There's a lot of people trying to do delivery...

我看到 Zipline 后就想：“你知道吗，这个很有意义。”很多人都在尝试送货...

Of course, you have autonomous cars upcoming, you have people that are doing tunneling, they're trying to put tunnels in the ground and ship it...

当然，自动驾驶汽车即将面世，有人正在进行隧道挖掘，他们试图在地下挖隧道并运送......

Kind of Futurama style, but underground Futurama...

有点飞出个未来的风格，但是地下飞出个未来......

And then we have drones, which - I don't think Zipline's the only one playing the drone game, but you guys are, I think, way ahead of the game.

然后我们还有无人机，我不认为 Zipline 是唯一玩无人机游戏的公司，但我认为你们在这场游戏中遥遥领先。

Been doing it for a long time.

已经做了很长时间了。

Tell us about the start of this company and where you're coming from.

告诉我们这家公司的起源以及您来自哪里。

**Keenan Wyrobek:** Yeah.

**基南·维罗贝克：** 是的。

So we started almost 12 years ago now, and we started in a niche of a niche, of delivering blood to hospitals in Rwanda.

所以我们大约 12 年前就开始了，我们从一个利基市场开始，向卢旺达的医院提供血液。

That's where we started.

这就是我们开始的地方。

**Keenan Wyrobek:** Yeah...

**基南·维罗贝克：** 是的......

So really, Rwanda earned this for -- we knew we wanted to start in health.

事实上，卢旺达赢得这一荣誉是因为——我们知道我们想从健康开始。

At the very beginning of this we started exploring this space based on really just stories from family and friends.

从一开始，我们就开始根据家人和朋友的故事来探索这个空间。

My wife's an epidemiologist, and she would tell me these stories about health intervention campaigns that would get stuck on logistics.

我的妻子是一名流行病学家，她会告诉我这些关于健康干预活动的故事，这些活动会陷入物流困境。

These would be lik vaccine campaigns where they had the vaccines, they had the doctors, but then the logistics got in the way, and they couldn't be successful.

这就像疫苗运动一样，他们有疫苗，有医生，但后勤工作阻碍了他们，所以他们无法成功。

So yeah, that's how we started.

是的，我们就是这样开始的。

Went deep on that...

深入探讨了这一点...

I'm personally not an early adopter, I'm very tech skeptic...

我个人不是早期采用者，我对技术持怀疑态度......

So I went deep in Central America and Africa at the time expecting to come away with a thousand reasons why we couldn't possibly make a difference.

所以当时我深入中美洲和非洲，希望能找到一千个我们无法做出改变的理由。

And the opposite happened.

而相反的情况却发生了。

The deeper we went, the more conviction we got that we could make a big difference.

我们走得越深入，就越相信我们可以做出巨大的改变。

And one of those places we were exploring with was Rwanda, and they turned out to be a phenomenal first customer for us, and really a partner figuring this out together.

我们正在探索的地方之一是卢旺达，事实证明他们是我们的第一个非凡客户，并且是真正共同解决这个问题的合作伙伴。

And blood, of course...

当然还有血...

Why blood?

为什么是血？

It's just this rare commodity everywhere.

这只是随处可见的稀有商品。

There's never enough of it...

永远都不够...

It's actually very expensive.

它实际上非常昂贵。

We think of it as free, because we donate it, but the cost of the collection, the testing, the transportation is very expensive.

我们认为它是免费的，因为我们捐赠它，但收集、测试、运输的成本非常昂贵。

Hundreds of dollars a unit; even in places like Rwanda, and way more in places like here.

几百元一个；即使在卢旺达这样的地方，在像这里这样的地方更是如此。

It has a very short shelf life, as little as seven days from the time it's donated, to the time it expires if you don't give it to somebody who needs it.

它的保质期很短，从捐赠之日起到如果您不将其送给需要的人则过期的时间只有 7 天。

So by centralizing blood in one place and then delivering it when you know what blood type is needed for what patient, at what time, it turns out you can virtually eliminate blood waste, saving a ton of money and a ton of lives for the health system.

因此，通过将血液集中在一个地方，然后在知道什么患者需要什么血型、什么时间需要什么血型时输送血液，事实证明，您实际上可以消除血液浪费，为卫生系统节省大量资金和挽救大量生命。

That's why we started there.

这就是我们从那里开始的原因。

**Adam Stacoviak:** What was the tactical nature of that when you went to Rwanda?

**亚当·斯塔科维亚克：** 当你去卢旺达时，战术本质是什么？

Was it discovery first, and then tech later?

是先发现，然后再技术吗？

How did you come to a technical solution?

您是如何得出技术解决方案的？

How did you think about it before you built something?

在你建造一些东西之前你是如何考虑的？

**Keenan Wyrobek:** Yeah.

**基南·维罗贝克：** 是的。

I mean, we had built nothing.

我的意思是，我们什么也没建造。

I literally called a friend of mine who was good at drawing, and he drew pencil sketches, and made a slide deck of the concept...

我真的打电话给我的一个擅长绘画的朋友，他画了铅笔草图，并制作了这个概念的幻灯片......

And we were using that to talk to people.

我们用它来与人们交谈。

In the early days, it was just talking to the operators in these health systems, that actually run the logistics, run this testing, run these labs...

早期，只是与这些卫生系统中的操作员交谈，他们实际上负责物流、测试、实验室……

But very quickly, we ended up having meetings with the offices of presidents in these countries, and that was a big sign that we were looking at a problem that was a really big deal for these health systems.

但很快，我们最终与这些国家的总统办公室举行了会议，这是一个重要迹象，表明我们正在考虑一个对这些卫生系统来说非常重要的问题。

And yeah, no technology whatsoever.

是的，没有任何技术。

A year or two before we were doing this, Amazon was like "Hey, drone delivery coming next year." So that drone delivery was an idea that was out there.

在我们这样做之前一两年，亚马逊就像“嘿，明年将推出无人机送货”。所以无人机送货是一个想法。

It wasn't a real thing yet anywhere...

这在任何地方都不是真实的东西......

And so we kind of thought of ourselves as like "Hey, if we're going to do something, let's find a niche where the value is really high to do this." Yeah, no technology.

所以我们认为自己就像“嘿，如果我们要做某事，让我们找到一个价值非常高的利基市场”。是的，没有技术。

And then of course, once the interest was there, we got moving fast.

当然，一旦产生了兴趣，我们就会快速行动。

**Jerod Santo:** Was there a point that you and your co-founders looked at each other -- you had saved countless lives with delivering blood around Africa, and thought "Burritos.

**杰罗德·桑托：** 您和您的联合创始人是否曾在某个时刻互相注视过——你们通过在非洲各地送血拯救了无数生命，并想到“墨西哥卷饼。

Burritos are next." Or was that from the start?

下一个是墨西哥卷饼。”或者从一开始就是这样？

**Keenan Wyrobek:** It was both there and not there.

**Keenan Wyrobek：** 它既存在又不存在。

In a lot of the countries we operate around the world, we start with health systems.

在我们在世界各地开展业务的许多国家，我们从卫生系统开始。

That's how we started in the United States.

这就是我们在美国起步的方式。

We started with health deliveries during COVID, and then expanded from there.

我们从新冠疫情期间的医疗服务开始，然后再扩大范围。

In the islands of Southeastern Japan we deliver healthcare supplies and bento boxes.

在日本东南部岛屿，我们提供医疗用品和便当盒。

In a lot of places in Africa we operate we started in human health and then expanded into various agricultural use cases, things like genetic diversity for milk cows; huge impact, but super-obscure.

在我们开展业务的非洲许多地方，我们从人类健康开始，然后扩展到各种农业用例，例如奶牛的遗传多样性；影响巨大，但又非常默默无闻。

We've just been layering on other use cases, and slowly worked our way into things like e-commerce and burritos.

我们刚刚在其他用例上进行了分层，并慢慢地进入了电子商务和墨西哥卷饼等领域。

\[07:55\] What's compelling -- when you think about Zipline, we talk a lot about the impact on health, which is really exciting.

[07:55] 令人信服的是——当您想到 Zipline 时，我们会谈论很多关于它对健康的影响，这确实令人兴奋。

We started with the impact of blood.

我们从血液的影响开始。

It's a super-visceral, high-impact, but very rare problem.

这是一个非常发自内心、影响力很大但非常罕见的问题。

Most of us don't need blood transfusions in our life, but when you need it, you really need it.

我们大多数人一生中并不需要输血，但是当你需要的时候，你真的需要它。

Then we slowly worked our way in health to preventative care, which is actually where the real cost savings for health systems is.

然后我们慢慢地从健康领域转向预防性护理，这实际上是卫生系统真正节省成本的地方。

Then we've worked our way into other areas, like animal health.

然后我们又进入了其他领域，比如动物健康。

One of the things that's really magical about this, as we step into new things like auto parts delivery - you know, what limits the mechanic's ability to service cars is usually how fast they can get the parts.

真正神奇的事情之一是，当我们涉足汽车零部件交付等新事物时 - 你知道，限制机械师维修汽车的能力通常是他们获得零部件的速度。

The way I think about it is basically for life, in the home or professionally, we're in the mission of getting you what you need, when you need it, and we do it in a way that's not just fast - we skip over the traffic; we're very reliable in that way - but just wildly environmentally friendly.

我的想法基本上是为了生活，无论是家庭还是职业，我们的使命是在你需要的时候为你提供你需要的东西，而且我们这样做的方式不仅是快速——我们跳过交通；我们还提供了快速的服务。我们在这方面非常可靠，而且非常环保。

We don't talk a lot about that, and we can get into that if that's interesting.

我们对此不多谈，如果感兴趣的话我们可以深入探讨。

We're talking about a 20x improvement in the overall environmental footprint of the supply chain, and almost every aspect, including things like bird safety.

我们正在谈论的是供应链的整体环境足迹以及几乎每个方面（包括鸟类安全等）的整体环境足迹改善了 20 倍。

That's something we don't talk about a lot.

这是我们不常谈论的事情。

There's just so many layers to this.

这有很多层。

**Adam Stacoviak:** Well, even -- I live here in Texas, and we have a lot of wind farms, because here in Texas we have multiple ways...

** Adam Stacoviak：** 好吧，甚至 - 我住在德克萨斯州，我们有很多风电场，因为在德克萨斯州我们有多种方式......

Probably like Nebraska, Jerod - you've got multiple ways you're getting electricity.

可能就像内布拉斯加州一样，杰罗德 - 你有多种获得电力的方式。

I'm not so much a fan of them; they're big and crazy, but I hear people get upset with the bird issue, essentially of that...

我不太喜欢他们；它们又大又疯狂，但我听说人们对鸟类问题感到不安，本质上是……

**Adam Stacoviak:** And maybe to the environmental aspect of it, that there's still so much of a cost to produce even wind energy that it's almost not worth it when you compare to how you talk about your efficiencies.

**Adam Stacoviak：** 也许从环境方面来看，即使是生产风能，成本仍然很高，当你与你谈论的效率相比时，它几乎不值得。

**Keenan Wyrobek:** Yeah.

**基南·维罗贝克：** 是的。

I care a lot about birds, so I pay a lot of attention to it...

我非常关心鸟类，所以我非常关注它......

We estimate that when we displace delivery by car, we reduce bird injuries by something like -- somewhere between 10x and 100x lower rate.

我们估计，当我们取代汽车送货时，鸟类受伤率会降低 10 倍到 100 倍。

We study that a lot.

我们对此进行了很多研究。

There's a lot of aspects to why we do what we do, and why we're excited about scaling what we do into all these different verticals.

我们为什么要做我们所做的事情，以及为什么我们对将我们所做的事情扩展到所有这些不同的垂直领域感到兴奋，这有很多方面的原因。

**Jerod Santo:** Let's talk about the design of the drone itself, because we mentioned the tactical approach coming out of the need of delivering these things in Rwanda...

**杰罗德·桑托：**让我们谈谈无人机本身的设计，因为我们提到了出于在卢旺达运送这些东西的需要而采取的战术方法......

When I saw your guys' design, I was very surprised by it.

当我看到你们的设计时，我感到非常惊讶。

There's kind of a more typical quadcopter, larger quadcopter-looking thing; almost like an airplane with blades on it.

有一种更典型的四轴飞行器，看起来更大的四轴飞行器；几乎就像一架带有叶片的飞机。

And then it doesn't actually do the delivery.

然后它实际上并不进行交付。

It delivers the delivery mechanism, which is a smaller kind of a baby-copter that comes down on a zip...

它提供传送机构，这是一种较小的婴儿直升机，可以通过拉链降落......

That's, I presume, where you guys get the name.

我想，这就是你们得到这个名字的地方。

It lowers it down to the ground, and then raises it back up again.

它将其降低到地面，然后再次升起。

Where did that design come from?

这个设计是从哪里来的？

**Keenan Wyrobek:** Yeah.

**基南·维罗贝克：** 是的。

That's sort of a double drone; a drone inside of a drone design.

这有点像双无人机；无人机设计中的无人机。

It came from just an obsession of figuring out what would actually work for our customers.

它源于对弄清楚什么对我们的客户真正有用的痴迷。

Our first platform, that does long range delivery, has a lot of great attributes, but it requires about two parking spots worth of space to deliver in, because it literally just flies over, drops the package with a little paper parachute on it, and the package floats to the ground.

我们的第一个平台，进行远程交付，有很多很棒的属性，但它需要大约两个停车位的空间来交付，因为它实际上只是飞过去，将上面有一个小纸降落伞的包裹扔下来，然后包裹会漂浮到地面。

But so many of our customers in the health space and otherwise were like "We want home delivery.

但我们的许多健康领域和其他领域的客户都说“我们想要送货上门。

We want in metro delivery", where you don't have that kind of space.

我们想要在地铁里送货”，但那里没有这样的空间。

And at the time, we're kind of like "Well, we don't do that." Eventually, they asked us enough times si we started thinking about "How would you do this?" And we knew from that platform that one of the things that makes people love our service is you don't hear our drones.

当时，我们有点像“好吧，我们不这样做。”最终，他们问了我们很多次，我们开始思考“你会怎么做？”我们从这个平台知道，人们喜欢我们服务的原因之一就是你听不到我们的无人机的声音。

And that's way harder than it sounds.

这比听起来要难得多。

And we're like "Well, we don't know how to do a super-precision delivery without hearing the drone." And we've seen other ways of doing this.

我们就像“好吧，我们不知道如何在没有听到无人机声音的情况下进行超精确的交付。”我们还看到了其他方法可以做到这一点。

It's usually loud, and noisy, and kicks up a dust storm, and can't deliver very precisely.

它通常声音很大，很吵，还会引发沙尘暴，而且不能非常精确地传送。

So this two-part architecture enables a bunch of things.

因此，这种由两部分组成的架构可以实现很多功能。

One thing it enables is quiet.

它带来的一件事是安静。

It lets the drone itself stay up at 100 meters, at 300 plus feet up in the air, which is one of the many things we do to make that just silent in even suburban places.

它可以让无人机本身保持在 100 米、300 多英尺的高空，这是我们为让无人机即使在郊区也能保持安静而采取的众多措施之一。

Then that little mini drone that comes to the ground - we call it the delivery zip.

然后，小型微型无人机降落在地面上 - 我们称之为送货拉链。

It comes to the ground, it actually delivers the package for you.

它到了地面，它实际上为你递送包裹。

It has its own little propellers on it, so in windy days and stuff it can still be super-precise and get into a tight space.

它有自己的小螺旋桨，所以在刮风的日子里它仍然可以超精确并进入狭窄的空间。

\[12:14\] So really, those two things - helping us be really quiet, and be super-precise; we can get into a really tight space with that little drone that comes to the ground, while the big drone stays up high, that does the heavy lifting.

[12:14] 所以说真的，这两件事——帮助我们变得非常安静，并且非常精确；我们可以用降落在地面的小型无人机进入一个非常狭窄的空间，而大型无人机则保持在高处，承担繁重的任务。

It's literally there to carry the weight, the distance.

它实际上是用来承载重量和距离的。

And yeah, that's why we have the little drone inside of a drone solution.

是的，这就是我们在无人机解决方案中使用小型无人机的原因。

**Adam Stacoviak:** It reminds me of how you see things happen in space, when you see a little jettison engine pushing it, nudging it...

**亚当·斯塔科维亚克：** 这让我想起了你如何看待太空中发生的事情，当你看到一个小型废弃发动机推动它、轻推它......

I'm a sci-fi guy, so I see these films all the time, and I'm like --

我是一个科幻迷，所以我一直看这些电影，我想——

**Adam Stacoviak:** It's kind of like little slight adjustments, but you just have -- is it one single large propeller, or is it multiple on the, I guess...

** Adam Stacoviak：** 这有点像细微的调整，但你只是 - 它是一个大型螺旋桨，还是多个，我猜......

What do you call the mini drone?

迷你无人机怎么称呼？

What is that name for that guy?

那家伙叫什么名字？

**Keenan Wyrobek:** Yeah, internally we call it the droid delivery zip.

**Keenan Wyrobek：** 是的，我们在内部将其称为“机器人送货邮政编码”。

We don't have a great name for it.

我们没有一个好听的名字。

I like delivery zip, but...

我喜欢邮政快递，但是...

Anyway, this little thing that comes to the ground - yeah, it's actually got three little thrusters, very similar in concept to what you're saying.

不管怎样，这个落地的小东西——是的，它实际上有三个小推进器，在概念上与你所说的非常相似。

It's got one big thruster in the back, and that thruster's job is to fight big, heavy winds; and so point it at the wind and it just makes sure it doesn't get blown off course.

它的后面有一个大推进器，这个推进器的作用是对抗大风；所以将它指向风，它只是确保它不会被吹离航线。

And then it's got a little bow thruster and a stern thruster, if you like boats, to think of it that way, that help it basically stay oriented, and do the side-to-side adjustments, as it's coming down and staying precise.

然后它有一个小船首推进器和船尾推进器，如果你喜欢船，可以这样想，这有助于它基本上保持方向，并进行左右调整，因为它下降并保持精确。

A lot of our team comes from space, and the control theory behind how you stay precise on that little delivery zip as it comes to the ground is very similar to how you think about reaction control thrusters on a spacecraft.

我们团队的很多成员都来自太空，当小传送带到达地面时如何保持精确的控制理论与航天器上的反应控制推进器的想法非常相似。

**Jerod Santo:** Because that thing can't spill your coffee.

**杰罗德·桑托：** 因为那东西不会弄洒你的咖啡。

I mean, sure, it can flip a burrito, no problem, but if you're lowering a coffee down - it has to stay oriented very well.

我的意思是，当然，它可以翻转墨西哥卷饼，没问题，但如果你要放下咖啡 - 它必须保持良好的定向。

**Keenan Wyrobek:** I assume - blood, they probably want that stuff spinning, or something, but there are certain fragile items that can't go...

**Keenan Wyrobek：** 我想 - 血，他们可能想要那些东西旋转，或者什么的，但有些易碎物品不能走......

So on the software side then --

那么在软件方面——

**Jerod Santo:** It is.

**杰罗德·桑托：** 是的。

On the software side, are those two divergent operating systems then?

在软件方面，这两个操作系统是不同的吗？

Because it seems like they have perhaps different concerns, but they probably have a lot of overlap as well.

因为看起来他们可能有不同的关注点，但他们也可能有很多重叠之处。

How did you tackle the software side of these two different drones?

您是如何解决这两种不同无人机的软件方面的问题的？

**Keenan Wyrobek:** Oh yeah, they're very different control problems.

**Keenan Wyrobek：** 哦，是的，它们是非常不同的控制问题。

Yeah, the drone that's up high - you're right, it has a wing, so to fly a fixed wing on the wing really efficiently it can hover in place for takeoff/landing, and while it's doing deliveries.

是的，高高的无人机 - 你是对的，它有一个机翼，所以要真正有效地在机翼上飞行固定翼，它可以悬停在适当的位置进行起飞/着陆，并且在进行交付时。

Yeah, it's a long story, the controls approach, and really it comes down to just massive amounts of testing.

是的，这是一个很长的故事，控制方法，实际上它归结为大量的测试。

Our high volume test sites have done hundreds of thousands of deliveries.

我们的大批量测试站点已完成数十万次交付。

We chase weather with a mobile test rig, so we go chasing like hail, and icing conditions, and these kinds of things.

我们用移动测试设备来追踪天气，所以我们去追踪冰雹、结冰条件以及诸如此类的事情。

A ton of simulation...

大量的模拟...

Literally, half of all the engineering we do at Zipline is test.

从字面上看，我们在 Zipline 所做的所有工程有一半是测试。

Just full on half of it.

只吃一半就满了。

That's how we can do this, is basically building the test systems, the various software platforms for simulation and things like that, the actual test scenarios, all the ground testing we do...

这就是我们要做到这一点的方法，基本上是构建测试系统、用于模拟等的各种软件平台、实际测试场景、我们所做的所有地面测试......

We have an entire building down the street from where I am, that all it is is just hundreds of ground test systems to simulate what we do in the air, on the ground.

我们在我所在的街道上有一整栋大楼，里面只有数百个地面测试系统来模拟我们在空中和地面上的工作。

Yeah, the answer to your question is a long one, but it's literally half of what we do is all the testing it takes to actually develop the control systems for these things to know that they're going to be both capable, but also safe.

是的，你的问题的答案很长，但实际上我们所做的一半就是实际开发这些东西的控制系统所需的所有测试，以确保它们既有能力又安全。

**Adam Stacoviak:** I also think about updating the software...

**Adam Stacoviak：** 我也考虑更新软件......

I mean, you mentioned the test facilities, so I imagine you do a lot of iteration there; you're constantly deploying potentially over the air updates...

我的意思是，你提到了测试设施，所以我想你在那里做了很多迭代；您不断地部署潜在的无线更新...

I have no idea how you accomplish that mission, but...

我不知道你是如何完成这个任务的，但是...

Divergent operating systems, and also a truly distributed update platform.

多样化的操作系统，也是真正的分布式更新平台。

How do you get new to the individualized?

如何适应个性化？

Is it an operating system delivery?

是操作系统交付吗？

Is it an individualized delivery?

是个性化交付吗？

Can you talk about that at all?

你能谈谈这个吗？

**Keenan Wyrobek:** \[15:55\] Yeah, absolutely.

**Keenan Wyrobek：** \[15:55\] 是的，绝对。

When we think about software and software deployment, there's two worlds for us.

当我们考虑软件和软件部署时，我们面临两个世界。

One we call flight software, and then cloud software.

我们称之为飞行软件，然后是云软件。

Flight software is all the pieces, a few parts of the cloud, but mostly things on the actual aircraft that we consider flight-critical.

飞行软件是所有的部分，云的几个部分，但主要是我们认为对飞行至关重要的实际飞机上的东西。

That software release process takes us about six weeks.

该软件发布过程大约需要六周时间。

So every six weeks we release software to that system.

因此，每六周我们就会向该系统发布软件。

And just in those six weeks we do tens of thousands of flight tests, we do a bunch of hardware in the loop testing...

就在这六周内，我们进行了数以万计的飞行测试，我们进行了一系列硬件在环测试......

Think of it as like the matrix, where you take the electronics of the aircraft and basically plug it into a simulation, literally, and fool it.

把它想象成一个矩阵，你把飞机的电子设备基本上插入到模拟中，从字面上看，然后愚弄它。

It thinks it's flying over in Dallas somewhere, but it's actually over in our basement, plugged into the simulation.

它认为它飞过达拉斯的某个地方，但实际上它在我们的地下室里，并插入了模拟中。

**Keenan Wyrobek:** Plus, of course, software in the loop simulation, where you're doing millions of flight tests.

**Keenan Wyrobek：** 当然，还有软件在环模拟，您可以在其中进行数百万次飞行测试。

And yeah, that whole journey takes us about six weeks to get to the point where we're like "Yup, this new software release is good to go." Then we release it, and then we have an over the air update system that updates all the processes, the software on the aircraft, and deploys.

是的，整个过程花了我们大约六周的时间才达到“是的，这个新软件版本很好用”的程度。然后我们发布它，然后我们就有了一个无线更新系统，可以更新所有流程、飞机上的软件并进行部署。

People often ask, "Do we do that in the air or not?" It's like ""No, no, no. When our aircrafts are docked, they update themselves." They check themselves, they're like "Okay, good.

人们经常问：“我们是否在空中这样做？”就像“”不，不，不。当我们的飞机停靠时，它们会自我更新。”他们检查自己，就像“好吧，很好。

Software's good to go", and then they'll fly again.

软件一切顺利”，然后他们就会再次飞翔。

**Adam Stacoviak:** How many of these problems are novel to you?

**Adam Stacoviak：** 这些问题中有多少对您来说是新奇的？

I know that the defense systems that we have here in the US probably have these problems and maybe have solved a lot of this, but maybe you don't have access to the DOD's tech platform, or maybe lack thereof...

我知道我们在美国拥有的防御系统可能存在这些问题，并且可能已经解决了很多问题，但也许您无法访问国防部的技术平台，或者可能缺乏该平台......

How much of this is invented here and how much of this is maybe a partner or vendor that you bring in to support over the air updates, for example?

例如，其中有多少是在这里发明的，有多少可能是您引入来支持无线更新的合作伙伴或供应商？

**Keenan Wyrobek:** Way more of this is done in-house than I would have ever thought we would have to do.

**Keenan Wyrobek：** 内部完成的工作比我想象的要多得多。

Actually, when we started Zipline, I was like "Great, I'm going to go find somebody who has a drone, buy it from them, modify it a little bit for deliveries and start serving our first customer." And the best quote I got back then from the companies making drones for defense was a $200,000 drone with a 200-flight warranty if I did not fly it in the rain.

事实上，当我们开始 Zipline 时，我就想“太棒了，我要去寻找拥有无人机的人，从他们那里购买，稍微修改一下以进行交付，然后开始为我们的第一个客户提供服务。”当时我从生产国防无人机的公司那里得到的最好的报价是一架价值 20 万美元的无人机，如果我不在雨中飞行的话，它可以保修 200 次。

And to be clear, in most of these countries it rains pretty much every day.

需要明确的是，在这些国家中的大多数，几乎每天都会下雨。

So that wasn't going to work.

所以那是行不通的。

Yeah, we do a lot in-house...

是的，我们在内部做了很多事情......

And a lot of that's because we fly in conditions that no one else flies in.

这很大程度上是因为我们在其他人无法飞行的条件下飞行。

Stormy weather, near the ground, or over mountains, stuff like that - no one flies in that.

暴风雨的天气，靠近地面，或者翻山越岭，诸如此类的事情——没有人能在那种情况下飞行。

So we've had to learn a lot of this stuff ourselves, and build our own datasets and experience and simulation approaches to actually develop these things.

因此，我们必须自己学习很多这些东西，并构建我们自己的数据集、经验和模拟方法来实际开发这些东西。

But then the other side of what makes us very unique is just the scale.

但让我们非常独特的另一面就是规模。

We operate at a very large scale.

我们的经营规模非常大。

Over the air updates is a good example, where we need that to be very, very easy and robust, in a way where if you're operating a smaller scale, a human can do a lot of double checking of that, and things like that, and it doesn't matter too much.

无线更新就是一个很好的例子，我们需要它非常非常简单和强大，如果你的操作规模较小，人类可以对其进行大量的双重检查，诸如此类的事情，而且这并不重要。

Even our over-the-air update system we've built ourselves.

甚至我们自己构建的无线更新系统。

**Jerod Santo:** Do you know how many drones are in your fleet roughly, worldwide, to give us an idea of the scale you're currently at?

**Jerod Santo：** 您是否知道您的机队在全球范围内大约有多少架无人机，以便我们了解您目前的规模？

**Jerod Santo:** Okay.

**杰罗德·桑托：** 好的。

And you've just started in the United States recently.

您最近刚刚开始在美国工作。

2021, I think, was the first non-medical flights...

我认为 2021 年是第一批非医疗航班……

This is what I've been told by Ian behind the scenes.

这是伊恩在幕后告诉我的。

And now you are in Dallas, and rolling out -- I just saw a video from your CEO and co-founder, that there's a whole bunch of drones getting built right now to just go crazy.

现在你在达拉斯，正在推出——我刚刚看到了你的首席执行官和联合创始人的视频，现在正在建造一大堆无人机，它们正在变得疯狂。

But 200 worldwide.

但全球有 200 个。

And how many of those are over there in Rwanda, doing their thing?

有多少人在卢旺达做他们的事情？

**Keenan Wyrobek:** I think it's close to 400 or so.

**Keenan Wyrobek：** 我认为接近 400 左右。

It's about 300 outside of our first generation, and well over 100, but I don't think 200 yet, of our precision delivery, the drone-in-the-drone system.

在我们的第一代之外，大约有 300 个，而我们的精确交付系统（无人机中的无人机系统）远超过 100 个，但我认为还不到 200 个。

**Jerod Santo:** Gotcha.

**杰罗德·桑托：**明白了。

So how much of your software is orchestration?

那么您的软件中有多少是编排的？

I assume that's the cloud side that you referenced, the control of the cloud.

我认为这就是您提到的云端，即云的控制。

**Jerod Santo:** I guess maybe tell us more about the cloud side and what all that entails.

**Jerod Santo：** 我想也许可以告诉我们更多关于云方面以及这一切所需要的内容。

**Keenan Wyrobek:** \[19:48\] Oh, there's a lot to it.

**Keenan Wyrobek：** \[19:48\] 哦，有很多内容。

There's obviously the pieces for people to place their orders...

显然有一些东西可供人们下订单......

Every partner we have, we have basically systems to integrate with our partner's data systems.

我们拥有的每个合作伙伴基本上都有与合作伙伴的数据系统集成的系统。

Then we have our basically dispatch...

然后我们就有了基本的调度...

I literally think of this as like there's cloud autonomy, or fleet level autonomy, and then aircraft level autonomy.

从字面上看，我认为这就像云自治，或机队级自治，然后是飞机级自治。

At the fleet level, you've got to decide which aircraft is going to go on which mission, at which time, and some of that is based on which aircraft is capable of that mission.

在机队层面，您必须决定哪架飞机将在何时执行哪项任务，其中一些取决于哪架飞机有能力执行该任务。

Some of that is based on making sure if we told someone "Hey, we'll deliver to you in this 60-second window", that we actually dispatch the right aircraft at the right time, get the order ready at the right time so that we'll hit that window.

其中一些是基于确保我们是否告诉某人“嘿，我们将在 60 秒的窗口内交付给您”，我们实际上在正确的时间派遣了正确的飞机，在正确的时间准备好订单，以便我们能够在该窗口内完成任务。

And some of it is stuff that -- other cloud stuff for us is weather forecasting.

其中一些对我们来说是天气预报。

We do our own weather forecasting.

我们自己做天气预报。

We can talk about that, it's a really fun problem.

我们可以讨论这个问题，这是一个非常有趣的问题。

Also, basically, we have to design our own highways.

此外，基本上，我们必须设计自己的高速公路。

If you think about autonomous vehicles, you take for granted that if you want an autonomous vehicle to drive from here to over the mountains, if you use the road network that's already been designed, you'll get there.

如果你想到自动驾驶汽车，你会理所当然地认为，如果你想让自动驾驶汽车从这里开到翻山越岭，如果你使用已经设计好的道路网络，你就能到达那里。

There's no such thing for drones, and so we have to do a lot of computation in the cloud to basically give enough prior to our aircraft, so that when they're flying, they have the equivalent of a highway system.

无人机没有这样的东西，所以我们必须在云中进行大量计算，以便基本上在我们的飞机之前提供足够的信息，这样当它们飞行时，它们就拥有相当于高速公路系统的能力。

It's not quite that simple...

事情没那么简单...

So that when they're doing an avoidance maneuver, for example, and planning that live, that they're doing that with enough prior that they're not going to get off track and not be able to make their delivery, if that makes sense.

因此，例如，当他们进行回避策略并实时计划时，他们会提前足够多的时间来这样做，这样他们就不会偏离轨道而无法完成交付（如果这是有意义的）。

**Jerod Santo:** 100 meters, 300 feet.

**杰罗德·桑托：** 100 米，300 英尺。

Thank you.

谢谢你。

What kind of stuff do you have to avoid?

什么样的事情是你必须避免的？

Obviously, birds, but at that -- I mean, cell towers, airstrips, perhaps?

显然，是鸟类，但是——我的意思是，也许是手机信号塔、飞机跑道？

What's the kind of stuff that has to be avoided at that height?

在那么高的地方，有哪些东西是必须避免的呢？

**Keenan Wyrobek:** Yeah, for sure.

**基南·维罗贝克：** 是的，当然。

So yeah, you can have very tall cranes, cell towers.

所以，是的，你可以拥有非常高的起重机、手机信号塔。

You can have inaccurate maps, so you may not be at the height you think you are, so there's a hill or a mountain there...

你的地图可能不准确，所以你可能没有达到你认为的高度，所以那里有一座小山或一座山......

Yeah, definitely other aircraft.

是的，肯定是其他飞机。

That's a big part of what we avoid.

这是我们要避免的很大一部分。

There's not a ton of passenger aircraft at that altitude, but there are some, and it's really important that we avoid them as well.

在这个高度上并没有大量的客机，但还是有一些，我们也避开它们非常重要。

Those are the kinds of things we avoid.

这些都是我们要避免的事情。

**Jerod Santo:** How much does regulation play into this rollout?

**Jerod Santo：** 监管对此次推出有何影响？

I assume every area probably has different rules about how you can go about flying your drones at 300 feet...

我想每个地区对于如何在 300 英尺的高度上驾驶无人机可能都有不同的规则......

**Jerod Santo:** Really?

**杰罗德·桑托：**真的吗？

\[laughs\] Usually, people say they want less rules when they're trying to scale up.

\[笑\]通常，人们会说，当他们试图扩大规模时，他们想要更少的规则。

**Keenan Wyrobek:** Yeah...

**基南·维罗贝克：** 是的......

I mean, when you're a startup and you go to a regulator and you're like "Cool, I would like to do this thing", and they're like "Well, that's not allowed", and then basically from there it's like all by exception.

我的意思是，当你是一家初创公司，你去找监管机构时，你会说“酷，我想做这件事”，他们会说“嗯，这是不允许的”，然后基本上从那里开始，一切都像是例外。

And so you have to kind of work it out, the rules by which you operate at the detail...

所以你必须弄清楚你在细节上运作的规则......

**Keenan Wyrobek:** And as a startup, that's a slow process, and startups need to go fast to survive...

**Keenan Wyrobek：** 作为一家初创公司，这是一个缓慢的过程，初创公司需要快速发展才能生存......

And yeah, that's why I said I wish there was some precedent.

是的，这就是为什么我说我希望有一些先例。

In some ways, obviously, there's some luxury in getting to help create the precedent...

显然，在某些方面，帮助创造先例是有一定奢侈的……

But yeah, it's a lot of working with the regulators.

但是，是的，这需要与监管机构进行大量合作。

Some things about airspaces between countries are very similar, harmonized, but other things are very different.

国家之间空域的某些方面非常相似、协调，但其他方面则非常不同。

And so yeah, things we have to do here in the US have been very different than Rwanda.

所以，是的，我们在美国要做的事情与卢旺达有很大不同。

Yeah, it's a big part of what we do, but it's also...

是的，这是我们工作的重要组成部分，但它也是......

We've gone from that being a big challenge maybe 10 years ago, to now it's something that we've gotten quite good at, and quite good at working with these partners and these regulators as partners, and working with them proactively enough that we can generally work out what needs to be worked out before we need it to serve a customer.

我们已经从大约 10 年前的一个巨大挑战，到现在我们已经非常擅长与这些合作伙伴和监管机构作为合作伙伴合作，并且足够积极主动地与他们合作，以便我们通常可以弄清楚在我们需要它为客户提供服务之前需要解决哪些问题。

But it takes a lot of effort, I will say that.

但这需要付出很多努力，我会这么说。

**Jerod Santo:** Yeah, I was thinking of the luxury of not having rules that are already defined, because those can slow you down.

**Jerod Santo：** 是的，我正在考虑没有已经定义的规则的奢侈，因为这些规则会减慢你的速度。

But actually, not having rules and not having a clear path towards engagement - that means you have to trailblaze.

但实际上，没有规则，也没有明确的参与路径——这意味着你必须开拓创新。

And to trailblaze, you've got to get out a machete and hack away a bunch of stuff, and that can be even slower and more laborious than if somebody else had already cleared the path for you.

为了开辟道路，你必须拿出一把砍刀砍掉一堆东西，这可能比其他人已经为你扫清道路更慢、更费力。

So that makes sense.

所以这是有道理的。

**Keenan Wyrobek:** Yeah.

**基南·维罗贝克：** 是的。

There's a great story -- here in the United States, starting about six years ago, we started working on the sensor system on the aircraft that can sense and avoid other aircraft.

有一个很棒的故事——在美国，大约从六年前开始，我们开始研究飞机上的传感器系统，该系统可以感知并避开其他飞机。

This is a system that uses machine learning, and machine learning is a class of software that the regulators have no experience with, literally.

这是一个使用机器学习的系统，从字面上看，机器学习是监管机构没有经验的一类软件。

And it took us about five years of working with them to go from the beginning of this to them approving us to operate.

从一开始到他们批准我们运营，我们花了大约五年的时间与他们合作。

And that was the first time they've ever approved AI/ML-based software for safety in the airspace.

这是他们第一次批准基于人工智能/机器学习的空域安全软件。

And so it was near daily conversations with their teams, figuring that out over that five-year journey...

因此，他们几乎每天都与团队进行对话，在五年的旅程中弄清楚这一点……

And there's some people at the FAA and at Zipline who I respect a ton for working through the minutiae they had to work through to figure out how what would the requirements be, and how would you validate the system against those requirements.

我非常尊敬 FAA 和 Zipline 的一些人，因为他们必须解决细节问题，才能弄清楚需求是什么，以及如何根据这些需求验证系统。

And then actually doing all that work and all that analysis to bring it back to the FAA and be like "Okay, we did what we agreed to.

然后实际做所有这些工作和所有分析，将其带回美国联邦航空局，然后说“好吧，我们做了我们同意的事情。

Let's go through this together." And yeah, that was a five-year journey there, and it was a hard won battle.

让我们一起经历这件事吧。”是的，那是五年的旅程，这是一场来之不易的战斗。

When I say battle, I don't mean like Zipline versus the FAA.

当我说战斗时，我指的并不是 Zipline 与 FAA 之间的战斗。

It was very -- we were very much in it together, because they definitely wanted to figure it out, too.

我们非常在一起，因为他们也确实想弄清楚这一点。

Yeah, it was something else.

是的，那是别的东西。

**Adam Stacoviak:** \[27:50\] This is an example where the word "regulation" - which you haven't quite said yet - gets really weird.

**Adam Stacoviak：** \[27:50\] 这是一个例子，其中“监管”这个词 - 你还没有完全说出来 - 变得非常奇怪。

And I don't want to go into politics, but it seems to be the word that gets thrown around.

我不想涉足政治，但这似乎是一个经常被人们谈论的词。

Regulation, less regulation, more regulation...

监管，少监管，多监管……

But as a developer, I really lean back on what you said there was not a presence of, which was specifications, which is really what regulation is.

但作为一名开发人员，我真的依赖于你所说的不存在的东西，即规范，这实际上就是监管。

It's an adherence to a specification that everyone agrees on, for obvious reasons.

出于显而易见的原因，这是对每个人都同意的规范的遵守。

But you're in this kind of unique high stakes scenario where maybe regulation could be less pressured, so to speak, and in your case, you've got to be a high stakes scenario where if there's a crash, or if there's a break a leg situation, which - I'm not sure you like the word crash.

但你正处于这种独特的高风险场景中，可以这么说，监管压力可能会较小，就你的情况而言，你必须是一个高风险场景，如果发生撞车，或者如果有摔断腿的情况，我不确定你喜欢“撞车”这个词。

I wouldn't like the word crash if I was in your business, personally, but I just think about the need for that.

如果我从事您的业务，我个人不喜欢“崩溃”这个词，但我只是考虑这样做的必要性。

Can you speak to how that's played as an ally versus a foe?

您能谈谈作为盟友对抗敌人的情况吗？

**Keenan Wyrobek:** Yeah...

**基南·维罗贝克：** 是的......

I think there's a couple of layers for how we think about this.

我认为我们对此的思考有几个层面。

The first one is because everywhere we've been, everywhere we've gone, there hasn't been some, like you said, specification to follow, we've taken the mantra that our first job is to convince ourselves.

第一个是因为无论我们去过哪里，无论我们去过哪里，都没有像你所说的那样的规范可供遵循，我们的口头禅是我们的首要工作就是说服自己。

And not in like a handwavy way.

而且不是以手动方式。

It's like "No, no. This is over our house, over our kids.

就像“不，不。这是我们的房子，我们的孩子。

Are we convinced that we've taken a rigorous approach before we suggest that approach to a regulator?" And that's gone a long way.

在向监管机构建议这种方法之前，我们是否确信我们已经采取了严格的方法？”这已经走了很长一段路了。

That mindset is attracting some of the best talent, as figuring some of this stuff out is really complicated.

这种心态吸引了一些最优秀的人才，因为弄清楚其中一些东西确实很复杂。

It's trying to track the talent we need to actually figure this out, and then it's also forced us to do the work -- to convince ourselves, the analysis, all the testing, all that data review to convince ourself is also what the regulators want to see.

它试图追踪我们真正解决这个问题所需的人才，然后它也迫使我们去做工作——说服自己，分析、所有测试、所有数据审查以说服我们自己也是监管机构希望看到的。

And so if we've done that to ourselves and we've really been skeptical internally first, it helps a ton when you're then having these in-depth conversations with these folks on the regulatory side.

因此，如果我们对自己这样做，并且我们首先在内部确实持怀疑态度，那么当您与监管方面的这些人进行深入对话时，这会很有帮助。

They have the completely thankless job of "Okay, we've got to figure out the specification for this new thing that no one's done before." So if they underdo it and someone gets hurt, they look really bad.

他们的工作完全吃力不讨好，“好吧，我们必须找出这个以前没有人做过的新事物的规范。”因此，如果他们做得不够并且有人受伤，他们看起来就很糟糕。

And of course, if they overdo the regulation, then everybody in the industry complains of "Oh, they wrote down these regulations that are completely impractical." So they're stuck between a rock and a hard place.

当然，如果他们过度监管，那么行业内的每个人都会抱怨“哦，他们写下的这些监管完全不切实际。”所以他们进退两难。

And so by doing that legwork upfront and internally proving to ourselves something that we really believe in first, and then bringing it to them - that's been core from our perspective.

因此，通过预先进行跑腿工作，并在内部向自己证明我们真正相信的东西，然后将其带给他们 - 从我们的角度来看，这是核心。

And then the only other piece of it that I would say is it's all relationships.

我要说的唯一的另一部分是，这都是关系。

These are all people on the regulatory side, they've got a job to do, we've got a job to do, and so we spend a lot of time basically working together to make sure we understand what they're trying to do, they spend a lot of time working to understand what we're trying to do...

这些都是监管方面的人，他们有工作要做，我们也有工作要做，所以我们基本上花了很多时间一起工作，以确保我们了解他们想要做什么，他们花了很多时间来了解我们想要做什么......

Be really open-minded, make sure we're hearing each other out, like in any relationship, and try to make progress every day, even if it's not as fast as you might like.

保持真正开放的心态，确保我们能倾听彼此的心声，就像在任何关系中一样，并努力每天取得进步，即使进展没有你希望的那么快。

**Adam Stacoviak:** How would you frame -- this isn't an exact one-to-one when I say this, but how would you frame test coverage in terms of a coverage level, confidence level?

**Adam Stacoviak：** 你会如何构建——当我这么说时，这并不是精确的一对一，但是你会如何根据覆盖率水平、置信度来构建测试覆盖率？

When you ship something and it's in a regulation standpoint, or you have a specification you've got to adhere to - is there like 95%, 98%?

当您发货时，从法规的角度来看，或者您有必须遵守的规范 - 是不是有 95%、98% 之类的？

Like, what do you strive towards when it comes to adherence to a spec, or defining the spec?

例如，在遵守规范或定义规范时，您会努力实现什么目标？

What is confidence to you and your team?

您和您的团队的信心是什么？

**Keenan Wyrobek:** Oh, great question.

**基南·维罗贝克：**哦，好问题。

So there's a model for thinking about this that was called the Swiss Cheese Model.

因此，有一个思考这个问题的模型，称为瑞士奶酪模型。

I did not come up with that name, although I'm known for naming things with really dumb names...

我没有想出这个名字，尽管我以用非常愚蠢的名字命名事物而闻名......

It was actually a NASA name, the Swiss Cheese Model.

它实际上是美国宇航局的一个名字，瑞士奶酪模型。

Conceptually, basically what it is - every approach to testing is like one slice of your Swiss cheese.

从概念上讲，基本上就是这样 - 每种测试方法就像一片瑞士奶酪。

It's going to have good coverage of some aspects, but if you look at it, it's going to have holes, for every type of testing you do.

它将很好地覆盖某些方面，但如果你仔细观察，就会发现对于你所做的每种类型的测试，它都会有漏洞。

You obviously have many different layers of testing that you do, and the intent is if you stack up those layers of Swiss cheese and look at them through the stack, then you're not going to see through holes, if you're doing it well.

显然，您进行了许多不同的测试层，其目的是，如果您将这些瑞士奶酪层堆叠起来并透过堆叠查看它们，那么如果您做得很好，那么您将不会看到孔洞。

Examples of our layers of Swiss cheese - you're going to be familiar with things like unit testing, and static testing, and things like that, that are commonly done in software...

我们瑞士奶酪层的示例 - 您将熟悉诸如单元测试和静态测试之类的事情，这些事情通常在软件中完成......

Software in the loop testing - so this is where you have full on physics level simulation running of your full system, even your full fleet, and you're able to then write test scenarios on top of that.

软件在环测试 - 因此，您可以在整个系统（甚至整个机群）上进行完整的物理级模拟运行，然后您可以在此基础上编写测试场景。

\[32:10\] We talked a little bit about the hardware in the loop testing, where you take the hardware itself, the brain of the aircraft, plug it into a simulator and fool it into thinking it's in the real world...

[32:10]我们讨论了一些关于硬件在环测试，你将硬件本身，飞机的大脑，将其插入模拟器并欺骗它认为它是在现实世界中......

That's great for testing the actual hardware level components.

这对于测试实际的硬件级组件非常有用。

If you short out a certain bus, does the actual full software stack detect that short and do the right thing?

如果您短路某个总线，实际的完整软件堆栈是否会检测到该短路并执行正确的操作？

And then a lot of things in flight tests.

然后是飞行测试中的很多事情。

We do all kinds of different flight tests.

我们进行各种不同的飞行测试。

We do on the order of 10,000 plus flights a week at this point across our flight testing, and almost every single one of those flights is pushing the system to an extreme in some way.

目前，我们每周进行约 10,000 多次飞行测试，几乎每一次飞行都在某种程度上将系统推向极限。

We actually have this fully automated software system we call chaos monkey, where basically what it's doing as we're dispatching all of these flights is it is -- chaos monkey is literally throwing chaos into the system as those missions are happening, that either will cause the airplane to do something extraordinarily dynamic against the physics limits of the aircraft, or turning off subsystems of the software, killing various rotors, things like that...

我们实际上有一个完全自动化的软件系统，我们称之为混沌猴子，基本上，当我们调度所有这些航班时，它正在做的事情就是——混沌猴子实际上是在这些任务发生时向系统中注入混乱，这要么会导致飞机做出一些超出飞机物理极限的异常动态的事情，要么关闭软件的子系统，杀死各种旋翼，诸如此类的事情......

And making sure that the system, despite any given flight having dozens of weird things happen - nominal events, as we call them - in that flight, does the whole system handle it gracefully and safely?

并确保系统，尽管任何给定的航班都会发生数十种奇怪的事情（我们称之为名义事件），但整个系统是否能够优雅且安全地处理它？

And this is just on the software side.

这还只是在软件方面。

When we think about hardware, very similar things - many layers of testing of the hardware, to make sure we understand deeply its performance and its reliability.

当我们考虑硬件时，非常相似的事情 - 对硬件进行多层测试，以确保我们深入了解其性能和可靠性。

And there are entire teams of folks who look at all that testing, and basically are constantly questioning "Okay, in this release we have a new capability we're releasing.

有整个团队的人都会关注所有这些测试，并且基本上不断地质疑“好吧，在这个版本中，我们要发布一项新功能。

Did we add enough testing to all the different layers of the Swiss cheese, such that that's going to be responsible to ship?" And there are times we think we're ready and we do that review of everything we did, and we're like "Nope, this isn't ready.

我们是否对瑞士奶酪的所有不同层进行了足够的测试，以便负责运输？”有时我们认为我们已经准备好了，我们对我们所做的一切进行了审查，我们就像“不，这还没有准备好。

We're pulling this from this release.

我们将从这个版本中删除它。

It's got more work to do", just on the testing side, to get that confidence.

它还有更多的工作要做”，只是在测试方面，才能获得这种信心。

**Adam Stacoviak:** These releases, are they -- share as much as you like.

**Adam Stacoviak：** 这些版本是 — 随心所欲地分享。

You seem to be very sharing, and I like this.

你看起来很乐于分享，我喜欢这一点。

I think about releases and I think about "Well, if I released my test level from idea to new capability", as you said, into production, there's probably a several layers that are in that middle ground, which is like a true release, but not in a real world scenario, so to speak...

我想到发布，我想到“好吧，如果我将我的测试级别从想法发布到新功能”，正如您所说，进入生产，中间可能有几个层，这就像真正的发布，但不是在现实世界的场景中，可以这么说......

How do you plan releases?

您如何计划发布？

How do you graduate releases from tests, delivery, observability, test again, potentially...

您如何从测试、交付、可观察性、再次测试、潜在的……中毕业发布？

You said you do 10,000 flights a week.

您说您每周执行 10,000 次航班。

Seven days in a week - that's 1400 flights a day, roughly...

一周 7 天 - 每天大约有 1400 个航班......

Gosh, that's a lot of flights.

天哪，这么多航班。

But how do you release and do that in a way that's like "Okay, it's in production, but it's not real production." I'm assuming these things, so...

但是你如何发布并以类似于“好吧，它正在制作中，但它不是真正的制作”的方式做到这一点。我假设这些事情，所以......

Walk me through that kind of idea.

引导我了解这种想法。

**Keenan Wyrobek:** Okay.

**基南·维罗贝克：** 好的。

So depending on the scale of a given feature...

所以取决于给定特征的规模......

To talk about one of the biggest features we've ever released - we just released it recently.

谈谈我们曾经发布过的最重要的功能之一——我们最近刚刚发布了它。

So we talked about the drone that flies up high, it has a wing, and can hover.

所以我们谈到了飞得很高的无人机，它有翅膀，可以悬停。

Until about a month ago, in our releases and our operations, we were only hovering.

直到大约一个月前，在我们的发布和运营中，我们还只是徘徊。

We were not flying on that wing.

我们不是在那个机翼上飞行。

So we were flying it more like a traditional quadcopter.

所以我们更像传统的四轴飞行器一样飞行。

It's a pentacopter, but we're flying it like a traditional quadcopter, just hover, which means the range is very limited.

它是五轴飞行器，但我们像传统四轴飞行器一样飞行，只需悬停，这意味着范围非常有限。

But while we were working on actually being able to fly on the wing - and the software and systems to transition from hover onto fixed wing, as it's referred to in industry, and then back into hover, including when anything could be going wrong, like any of those rotors could not be working and that kind of thing...

但是，当我们致力于真正能够在机翼上飞行时，以及软件和系统从悬停过渡到固定翼（正如工业中所提到的那样），然后再回到悬停，包括当任何事情可能出现问题时，比如任何一个旋翼无法工作之类的事情......

There's a lot to that, and we've been working on those features, at some level of development and testing, for two years to enable this.

这有很多内容，两年来我们一直致力于这些功能的开发和测试，以实现这一目标。

So two or three months before, that release cuts.

所以两三个月前，该版本就被削减了。

So when I talk about releasing every six weeks, we cut basically at the beginning of that six weeks.

因此，当我谈到每六周发布一次时，我们基本上是在那六周开始时进行削减。

\[35:55\] We will look at all the new features that folks think are ready for a release, and we'll look at like "How tested are they?

[35:55] 我们将研究人们认为已准备好发布的所有新功能，我们将研究“它们经过了怎样的测试？

How proven are they?

它们的证明程度如何？

How good is the test coverage?" and all these layers of Swiss cheese.

测试覆盖率有多好？”以及所有这些瑞士奶酪层。

And then we'll decide "Yup, this feature is ready.

然后我们会决定“是的，这个功能已经准备好了。

This feature is ready.

这个功能已经准备好了。

That feature is not ready.

该功能尚未准备好。

It's not going to go in this release", and we will cut a release.

它不会出现在这个版本中”，我们将削减一个版本。

And then once we cut a release, there's a bit of a stabilization that takes us about a week, to make sure that release is really stable, and then it goes into this very structured release campaign that takes about five weeks on average, which - it depends on the release, but something like 50,000 flights, a whole bunch of hardware in the loop tests and software loop tests and all these other tests we will do again as well, as part of that process.

一旦我们削减了一个版本，就会需要大约一周的时间来进行稳定，以确保该版本真正稳定，然后进入这个非常结构化的发布活动，平均需要大约五周的时间，这取决于版本，但像 50,000 次飞行，一大堆硬件在循环测试和软件循环测试以及所有其他测试，作为该过程的一部分，我们也会再次进行。

And then the people -- all the teams are basically paying a ton of attention to all the data coming out of all that testing.

然后，人们——所有团队基本上都非常关注所有测试中得出的所有数据。

And over the years, we've developed all kinds of tooling and dashboards that help all the teams look at that data, and look for anything weird, anything that might we consider a near miss.

多年来，我们开发了各种工具和仪表板，帮助所有团队查看这些数据，并寻找任何奇怪的东西，任何我们可能认为差点错过的东西。

Obviously, the real miss is if we have a parachute landing during that testing, we're going to know exactly what goes on there.

显然，真正的失误是，如果我们在测试期间进行降落伞着陆，我们将确切地知道那里发生了什么。

But we're looking for anything that's at all weird.

但我们正在寻找任何奇怪的东西。

We call it a near miss.

我们称其为“险些失手”。

And studying it, and seeing if it needs to be addressed, or if it's fine.

研究它，看看是否需要解决，或者是否可以。

You can kind of think of that flight test as like the last leg.

您可以将飞行测试视为最后一程。

If we find something in flight test, that's a red flag to us.

如果我们在飞行测试中发现一些问题，这对我们来说就是一个危险信号。

Like "Hey, the other layers of Swiss cheese aren't good enough." So if we find something in the flight test during that campaign, we're immediately investing in those other levels of Swiss cheese to make them better, and improve their coverage.

就像“嘿，其他层的瑞士奶酪还不够好。”因此，如果我们在那次活动期间的飞行测试中发现了一些问题，我们将立即投资于其他级别的瑞士奶酪，以使其变得更好，并提高其覆盖范围。

And then only once the data says we've got a system that meets or exceeds the overall target level of safety of our last release, do we then say "This is ready to actually ship."

然后，只有当数据表明我们的系统达到或超过了上一个版本的总体安全目标水平时，我们才会说“该系统已准备好实际交付”。

**Adam Stacoviak:** Do you have the idea of a black box in your thing?

**Adam Stacoviak：** 你有在你的东西中加入黑匣子的想法吗？

I mean, I know that airplanes do, so I imagine you've got some version of a black box, where if it does - I'm sorry - crash, that you've got some sort of thing in there...

我的意思是，我知道飞机会这样做，所以我想你有某种版本的黑匣子，如果它发生了 - 对不起 - 坠毁，你里面有某种东西......

And then I also think about observability, because you've got all this testing happening...

然后我还考虑了可观察性，因为所有这些测试都在发生......

And I think about like traditional software in the cloud - it's kind of easy to orchestrate observability.

我认为就像云中的传统软件一样 - 它很容易协调可观察性。

But over the years I'm sure you've got some version of WiFi or access to the thing digitally, via a network of sorts, telemetry going...

但多年来，我确信你已经拥有某种版本的 WiFi 或通过某种网络、遥测技术以数字方式访问该东西......

Is there a black box, and how does observability happen in those scenarios?

是否存在黑匣子，在这些场景中可观察性是如何发生的？

**Keenan Wyrobek:** Yeah, absolutely.

**基南·维罗贝克：** 是的，绝对如此。

So we log a ton of data on the vehicles, at all times.

因此，我们始终记录大量有关车辆的数据。

And that's of course done in all this testing, but also in production.

当然，这不仅在所有测试中完成，而且还在生产中完成。

And the philosophy is that anything that could possibly go wrong, or be a near miss, you've got to study.

我们的理念是，任何可能出错或侥幸成功的事情，你都必须进行研究。

And you mentioned crashes - I should mention we have a parachute system for the aircraft, that's kind of the backup to the redundancy.

你提到了坠机事件 - 我应该提到我们为飞机配备了降落伞系统，这是对冗余的备份。

So there's redundancy in the aircraft, so it can nominally fly when things don't work, but the backup to the backup is a parachute.

所以飞机上有冗余，所以名义上它可以在出现故障时飞行，但备用的备用是降落伞。

So it'll float to the ground like a -- it's actually made for us by a skydiving parachute company.

所以它会像一个跳伞一样漂浮到地面——它实际上是一家跳伞降落伞公司为我们制造的。

So it's like a skydiver coming to the ground.

所以这就像一个跳伞运动员来到地面。

So yeah, if we ever have a parachute landing in tests, or operations, or anything that's even close to a weird data, we go study that, to basically deeply, deeply understand it, because quite often it's a new insight.

所以，是的，如果我们在测试、操作或任何接近奇怪数据的情况下进行降落伞着陆，我们就会去研究它，基本上深入地理解它，因为通常这是一个新的见解。

We're so far in the long tail of the problem that many of the problems we see now, they happen one in hundreds of thousands of flights.

到目前为止，我们已经陷入了这个问题的长尾，以至于我们现在看到的许多问题都是在数十万次航班中发生的。

And so you basically -- like, if we didn't log it, think of it as like "Oh no, now we have to wait for this to happen again, in hundreds of thousands of flights", which is a total shame.

所以你基本上 - 就像，如果我们没有记录它，你会认为它就像“哦，不，现在我们必须等待这种情况再次发生，在数十万次航班中”，这完全是一种耻辱。

**Keenan Wyrobek:** Exactly.

**基南·维罗贝克：** 没错。

No, that's not the shame.

不，这不是耻辱。

The shame is not logging it.

耻辱是没有记录它。

So we log these things.

所以我们记录这些事情。

Now, in addition to the logging, to enable us to like go through those logs and understand everything that happened -- we use those logs not just for like root causing a specific problem, we use those logs to understand things in aggregate.

现在，除了日志记录之外，为了使我们能够浏览这些日志并了解发生的一切 - 我们不仅使用这些日志来导致特定问题，我们还使用这些日志来总体理解事物。

So we have tools where you can mine those logs longitudinally, across thousands and thousands of flights, to deeply understand the statistics of a certain thing.

因此，我们拥有工具，您可以在数千次航班中纵向挖掘这些日志，以深入了解特定事物的统计数据。

That's really important as well.

这也非常重要。

And then of course, during live operations - yeah, the aircraft are reporting over radios, live, what's going on.

当然，在现场操作期间 - 是的，飞机通过无线电实时报告正在发生的情况。

We have a remote operation center that's monitoring all of that...

我们有一个远程操作中心来监控所有这一切......

And so during live operations we have certain things that basically -- our pilots, I think of them more like an air traffic controller, where they can be like "Okay, you go back and dock", and that kind of thing, and understand what's going on at a very sort of fleet level.

因此，在现场操作期间，我们基本上有一些东西 - 我们的飞行员，我认为他们更像是空中交通管制员，他们可以说“好吧，你回去靠岸”，诸如此类的事情，并了解在机队层面上正在发生的事情。

**Keenan Wyrobek:** Hah, we've definitely -- yeah.

**Keenan Wyrobek：** 哈，我们绝对 - 是的。

So the closest thing we've logged -- we've logged some very small...

所以我们记录的最接近的东西——我们记录了一些非常小的......

I don't think you'd call them a tornado.

我不认为你会称它们为龙卷风。

They're basically -- the things are too small to be considered tornadoes.

它们基本上是——这些东西太小了，不能被视为龙卷风。

At some of our testing, we're actually chasing some tornadoes right now, as we look for hail and more extreme weather events with our mobile test rigs.

在我们的一些测试中，我们现在实际上正在追逐一些龙卷风，因为我们使用移动测试设备寻找冰雹和更极端的天气事件。

The craziest thing we have a lot of log data on is what's called a microburst.

我们拥有大量日志数据的最疯狂的事情就是所谓的微爆。

So it's the beginning of a thunderhead formation, about first 90 seconds of a thunderhead.

所以这是雷云形成的开始，大约是雷云形成的前 90 秒。

You have the vertical winds at like 50, 60, 70 miles an hour vertically, in the middle of the microburst; on the sides of the microburst, the same thing goes down.

在微暴流的中间，垂直风速约为每小时 50、60、70 英里；在微爆的侧面，同样的事情也会发生。

Those are some of the most extreme weather events, that are hard for the drones to handle.

这些是一些最极端的天气事件，无人机很难应对。

**Jerod Santo:** What do they do in those circumstances?

**杰罗德·桑托：** 在这种情况下他们会做什么？

Do they turn around and leave, or do they land immediately, or what's their protocol?

他们是转身离开，还是立即着陆，或者他们的协议是什么？

**Keenan Wyrobek:** So it really depends how big it is.

**Keenan Wyrobek：** 所以这实际上取决于它有多大。

this is actually one of the first things we developed AI to forecast.

这实际上是我们开发人工智能首先要预测的事情之一。

It's because if this is really big, if it's kilometers across, and really strong, if we're in it we're going to end up parachute landing.

这是因为，如果它真的很大，如果它有几公里宽，而且真的很坚固，如果我们在里面，我们最终会跳伞着陆。

And we know this because in a lot of our operations around the world when we're doing emergency deliveries for a patient on the table, delivering blood situations, we will take -- we will basically ignore our weather limits and fly in very extreme weather.

我们知道这一点，因为在我们在世界各地的许多业务中，当我们为桌上的病人紧急运送、运送血液时，我们基本上会忽略天气限制，在非常极端的天气下飞行。

So we go through these things.

所以我们会经历这些事情。

But then for non-emergency deliveries, we rely on our forecasting to keep us out of this stuff, in those really extreme events.

但对于非紧急交付，我们依靠我们的预测来避免在那些真正极端的事件中发生这种情况。

If they're small enough - yeah, the control system will fight its way through it.

如果它们足够小——是的，控制系统会奋力穿过它。

But of course, the aircraft has its physics limits.

但当然，飞机有其物理限制。

It can only climb so fast, it can only do so much.

它只能爬这么快，它只能做这么多。

And so in certain situations it can't overcome them, and yeah, that's when the parachute kicks in.

所以在某些情况下它无法克服它们，是的，那就是降落伞发挥作用的时候。

**Jerod Santo:** I assume there's some sort of wind limit that there's just no chance for anything to fly through successfully.

**杰罗德·桑托：** 我认为存在某种风的限制，任何东西都没有机会成功飞过。

It's gotta be around a hundred miles per hour or so, maybe a little bit less...

每小时大约一百英里左右，也许少一点......

I don't know, but there's certain storms where it's just like, you'd better just parachute out, because there's no there-there; there's no success as a possibility, regardless of the size of this thing.

我不知道，但在某些暴风雨中，你最好跳伞，因为那里不存在；无论这件事有多大，都没有成功的可能性。

30 seconds at 150 miles per hour is knocking down massive trees here...

30 秒以 150 英里每小时的速度撞倒这里的大树......

And so I'm assuming it's taken a drone off its course quite a bit.

所以我假设它使无人机偏离了航线相当多。

**Keenan Wyrobek:** Oh, yeah.

**基南·维罗贝克：** 哦，是的。

There's a certain mountain pass in Rwanda I'm very familiar with, because we have to fly through this mountain pass to serve about a third of the country there...

卢旺达有一个山口我非常熟悉，因为我们必须飞过这个山口才能服务那里大约三分之一的国家......

And in this mountain pass the winds get whipping.

在这山口，狂风呼啸。

The winds can be higher than we fly.

风可能比我们飞的还要高。

We fly that aircraft at 60-70 miles an hour, and the winds get up to a hundred miles an hour...

我们以每小时 60-70 英里的速度驾驶飞机，风速可达每小时一百英里......

And you'll see our drones flying backwards as it tries to fight through it, developing the control system and logic to...

你会看到我们的无人机向后飞行，试图穿过它，开发控制系统和逻辑......

Because most of those winds are gusty, so if you can stay in the air long enough and then punch through it at the right moment, you can get to mountain pass.

因为这些风大多是阵风，所以如果你能在空中停留足够长的时间，然后在适当的时候穿过它，你就可以到达山口。

And yeah, it was a big breakthrough when we figured out how to make that logic robust.

是的，当我们弄清楚如何使该逻辑变得稳健时，这是一个重大突破。

And you see the drone is flying backwards for a while, flying backwards for a while, flying backwards for a while, and then flying through at the right second; it's estimating the winds dying down online, and then it punches through the mountain pass and gets through.

你看到无人机一会儿向后飞，一会儿向后飞，一会儿向后飞，然后在适当的时候飞过去；它在线估计风势减弱，然后冲过山口并通过。

**Jerod Santo:** Do you have any video feeds?

**杰罗德·桑托：** 你有视频吗？

Because you're going to come up with some great drama in those moments if you could capture a video, just when it's really gnarly, you know?

因为如果你能捕捉一段视频，你就会在那些时刻想出一些精彩的戏剧，就在它真的很粗糙的时候，你知道吗？

**Keenan Wyrobek:** I've got a great video of the logs of that.

**Keenan Wyrobek：** 我有一段很棒的日志视频。

It's not \[unintelligible 00:43:28.29\] You can see the position on the maps, going backwards and things...

这不是\[无法理解的00:43:28.29\]你可以看到地图上的位置、向后走等等......

**Jerod Santo:** Yeah, I don't think Hollywood's going to call you for the log file.

**杰罗德·桑托：** 是的，我认为好莱坞不会打电话给你索要日志文件。

**Jerod Santo:** Let's talk more about that wing.

**杰罗德·桑托：**让我们更多地讨论一下那个侧翼。

So did you guys just put the wing on there because you knew eventually you were going to use it, and so you just had it in manufacturing for a long time, but couldn't use it?

那么，你们只是把机翼放在那里，因为你们知道最终你们会使用它，所以你们只是在制造中使用了很长一段时间，但无法使用它？

**Keenan Wyrobek:** \[43:47\] Yeah, absolutely.

**Keenan Wyrobek：** \[43:47\] 是的，绝对。

We knew we needed the range.

我们知道我们需要这个范围。

You get about 10x more range flying on a wing, for the same energy, than hovering.

在能量相同的情况下，用机翼飞行的航程比悬停的航程多大约 10 倍。

And our customers need that range.

我们的客户需要这个范围。

So many of our use cases need that range.

我们的许多用例都需要这个范围。

And so yeah, we always knew we needed the range of flying on a wing, and we decided to launch without having developed that system yet...

所以，是的，我们一直都知道我们需要机翼的飞行范围，并且我们决定在尚未开发该系统的情况下发射......

Really just because that's how we're wired.

真的只是因为我们就是这样连接的。

We want to get out into the real world fast, because we just know - when you're in the real world, serving customers, you're going to learn a lot of things you just can't learn any other way...

我们希望快速进入现实世界，因为我们知道 - 当您在现实世界中为客户提供服务时，您将学到很多其他方式无法学到的东西......

And so we want to get out there earlier.

所以我们想早点出去。

Yeah, and that hardware was there, and the teams that spent all this time developing that hardware were like "We want to see a fly on the wing..." And of course, we didn't have the test sites for a long time as we've been developing that capability.

是的，硬件就在那里，花费所有时间开发该硬件的团队就像“我们希望看到一只苍蝇在翅膀上......”当然，我们很长一段时间没有测试场地，因为我们一直在开发这种能力。

It is one of those things where you kind of develop it, and then wait, and then once you can get -- yeah...

这是你开发它的事情之一，然后等待，然后一旦你能得到——是的......

One of the things...

其中一件事...

You're talking about regulations and safety - that is also part of our ethos.

您谈论的是法规和安全——这也是我们精神的一部分。

And a difficult thing in a startup is we hire people who like inherent urgency, because if you set a deadline on safety, you can end up in a really bad situation.

在初创公司中，一件困难的事情是我们雇用那些喜欢内在紧迫感的人，因为如果你设定安全期限，你最终可能会陷入非常糟糕的境地。

If you're like "Cool, we must ship this on this date." Some of the stories you hear about, of 80 companies that have hurt people in the past - they take that mindset, and then they'll fool themselves into thinking they're ready, as opposed to saying "No, no, no. We set a safety bar, and we decide how we're going to measure ourselves against that safety bar, and that's when we ship." It means your dates aren't quite as predictable, but you still need to move fast, and so you need people with a very inherent sense of urgency to work through those problems and get there, as opposed to a more traditional "We have a date and we're going for it" management approach.

如果您觉得“酷，我们必须在这个日期发货。”你听到的一些故事，是关于过去伤害过人们的 80 家公司的 - 他们采取了这种心态，然后他们会欺骗自己，认为自己已经准备好了，而不是说“不，不，不。我们设定了一个安全标准，然后我们决定如何根据该安全标准来衡量自己，然后我们就发货了。”这意味着你的日期不太可预测，但你仍然需要快速行动，因此你需要具有内在紧迫感的人来解决这些问题并实现目标，而不是更传统的“我们有一个日期，我们会去争取它”的管理方法。

**Jerod Santo:** So what was the range prior to the wing, of a typical drone?

**Jerod Santo：** 那么，典型无人机在机翼之前的射程是多少？

...assume good conditions - how far do they go, and how long a time, and then...

...假设良好的条件 - 他们走了多远，需要多长时间，然后...

You said 10x, so I can do the math, but...

你说的是 10 倍，所以我可以算一下，但是......

That's a huge win.

这是一个巨大的胜利。

**Keenan Wyrobek:** Yeah.

**基南·维罗贝克：** 是的。

Great.

伟大的。

Yeah, so we're doing about a mile and a half hovering, and we'll be able to do -- right now we're at about five miles on the wing, and we'll be able to take that to about 10 miles over time...

是的，所以我们正在盘旋大约一英里半，我们将能够做到——现在我们在机翼上飞行大约五英里，随着时间的推移，我们将能够将其提升到大约 10 英里......

Again, as we continue to validate and sort of work our way up to it, once we feel confident in it.

再次强调，一旦我们对它充满信心，我们就会继续验证并努力实现这一目标。

**Jerod Santo:** And I assume each drone launches from a location, and then has to return to the same location, at least until you get multiple hubs in a city, or something.

**杰罗德·桑托：** 我假设每架无人机从一个位置发射，然后必须返回同一位置，至少直到你在一个城市或其他地方获得多个枢纽。

**Keenan Wyrobek:** Yeah.

**基南·维罗贝克：** 是的。

That's actually a software feature that's coming in and released next year, is that ability to go from one doc, go make a delivery, and then dock somewhere else.

这实际上是明年推出并发布的一项软件功能，即能够从一个文档开始交付，然后停靠在其他地方。

But yeah, you're exactly right.

但是，是的，你是完全正确的。

We don't have the density of docking locations yet to need that feature.

我们还没有达到需要该功能的对接位置密度。

**Jerod Santo:** Right.

**杰罗德·桑托：** 对。

So that cuts your range in half, because you have to get out there, and you've got to get back.

这样你的活动范围就减少了一半，因为你必须出去，也必须回来。

**Jerod Santo:** Okay.

**杰罗德·桑托：** 好的。

So when you say five miles - if I live five miles from your facility, do I get deliveries, or I've gotta be two and a half miles?

因此，当您说五英里时，如果我住在距离您的设施五英里的地方，我是否可以收到送货服务，或者我必须在两英里半的地方？

**Keenan Wyrobek:** Yeah.

**基南·维罗贝克：** 是的。

So once we have that...

所以一旦我们有了那个...

If we can dock at a different location, nearby the delivery site - yeah, we can do more than 10 miles.

如果我们可以停靠在送货地点附近的其他位置 - 是的，我们可以行驶超过 10 英里。

That's actually an interesting thing...

这其实是一件很有趣的事情...

We've learned over the years that it's way better when you're working with these partners to talk about a conservative range, than like where you're going to go in the future...

多年来我们了解到，与这些合作伙伴讨论保守的范围比谈论未来要走的路要好得多......

Because it's so complicated to talk about that when you get into the details of your terrain, and your physics, and your local weather, and all that stuff.

因为当你了解地形、物理学、当地天气以及所有这些东西的细节时，谈论这个问题非常复杂。

It's like "No, no, no. We're just talking about this little circle." And then they're thrilled that we can do more than that.

就像“不，不，不。我们只是在谈论这个小圈子。”然后他们很高兴我们可以做更多的事情。

**Jerod Santo:** Right.

**杰罗德·桑托：** 对。

I was just flying my drone the other day - I have a little DJI Flip, and I was flying it...

前几天我刚刚在驾驶我的无人机 - 我有一个小 DJI Flip，我正在驾驶它......

Too far away, slightly too far away, to where it was telling me to come back...

太远了，有点太远了，到了它告诉我要回来的地方……

And I'm like "Yeah, I'm coming back." So I started flying it back, and then the wind picks up, going against it on the way back...

我说：“是的，我会回来的。”所以我开始把它飞回来，然后风刮起来了，在回来的路上逆风而行……

And I'm sitting there, thinking "Oh man, it's just not going to make it back." Because the battery percentage continues to go down, and it's still 1200 meters away, and...

我坐在那里，心想：“天哪，这一切都回不来了。”因为电量百分比持续下降，而且距离还有1200米，而且……

It was very dramatic.

这是非常戏剧性的。

It did make it back to the house, thankfully, but just barely.

谢天谢地，它确实回到了房子，但只是勉强回到了房子。

So I've got to imagine that's a stressful -- you know, we're talking about range anxiety with all of our new EVs.

所以我必须想象这是一个压力 - 你知道，我们正在谈论我们所有新电动汽车的里程焦虑。

I'm sure you probably have extreme forms of range anxiety with your -- because these are expensive machines, right?

我确信您可能有极端形式的里程焦虑——因为这些都是昂贵的机器，对吧？

What's an all-in cost on one, if you can share that?

如果您可以分担的话，一个人的总成本是多少？

...to build and manufacture.

...建造和制造。

What are we talking about?

我们在说什么？

**Keenan Wyrobek:** I can't share that specifically, but it's lower than you would think.

**Keenan Wyrobek：** 我无法具体分享这一点，但它比您想象的要低。

And this kind of -- this is part of the reasons we develop our own drones.

这就是我们开发自己的无人机的部分原因。

Both for this range problem you're talking about, and for the cost.

既针对您正在谈论的范围问题，又针对成本。

But for the range - take our fixed wing platforms.

但对于范围 - 采用我们的固定翼平台。

This is what we do with these very long range deliveries.

这就是我们对这些超长距离交付所做的事情。

There's no hover capability, it just flies like a plane...

没有悬停能力，它只是像飞机一样飞行......

We advertise, basically, a 50-mile service radius, but if it wasn't windy and there wasn't a mountain in the way, it could easily do a hundred mile service radius.

我们宣传的基本上是 50 英里的服务半径，但如果没有风并且路上没有山，它可以轻松实现一百英里的服务半径。

So we literally have twice as much energy as you would need nominally, so that we can make it back on those windy days reliably.

因此，我们实际上拥有的能源是您名义上所需的两倍，这样我们就可以在那些有风的日子里可靠地恢复能源。

And that's just really important, because once you start serving a hospital, delivering blood, you can't be like "Oh, it's too windy today.

这真的很重要，因为一旦你开始为医院提供服务、输送血液，你就不能说“哦，今天风太大了。

Sorry, guys, we don't serve you.

对不起，伙计们，我们不为你们服务。

We only reach the people closer."

我们只会接触到更亲近的人。”

**Keenan Wyrobek:** \[48:22\] It's like, no, we turn you on, and we want to serve you all the time.

**Keenan Wyrobek：** \[48:22\] 就好像，不，我们让你兴奋，我们想一直为你服务。

**Adam Stacoviak:** Does anybody get underwhelmed by the range, when you say five miles?

**Adam Stacoviak：** 当你说五英里时，有人会对范围感到不知所措吗？

I'm not throwing stones here, but I'm just saying...

我不是在这里扔石头，但我只是说......

I know you're innovating, but does anyone ever go like "That kind of seems small"?

我知道你在创新，但有人会说“这看起来很小”吗？

**Keenan Wyrobek:** It all just depends on the use case.

**Keenan Wyrobek：** 这一切都取决于用例。

The 10 miles was developed going really deep with our health partners, and exactly on all the use cases that they want to use the drones in metro areas.

10 英里是与我们的健康合作伙伴深入合作开发的，并且完全针对他们希望在都市区使用无人机的所有用例。

And of course, when you're going out of metro areas, that's where the 50-mile range drone comes in handy.

当然，当您要离开都会区时，50 英里范围的无人机就可以派上用场。

And all of this has been developed just basically technology second, customer first.

所有这一切的开发基本上都是技术第二，客户第一。

\[unintelligible 00:49:02.29\] with the customers.

\[无法理解的 00:49:02.29\] 与客户。

For this precision delivery platform, we had contracts with partners while we were still in what we would call the conceptual phase of that project.

对于这个精确交付平台，当我们仍处于该项目的概念阶段时，我们就与合作伙伴签订了合同。

Nothing was locked in yet.

一切还没有被锁定。

And having those contracts with the partners gets them to give you -- that gets them invested enough in us to give us the feedback and the data to make sure that we make something that's going to be useful for them.

与合作伙伴签订这些合同会让他们给你——这会让他们对我们进行足够的投资，向我们提供反馈和数据，以确保我们做出对他们有用的东西。

And so yeah, some people get overwhelmed, but we just have that confidence because we've had so much time in these use cases, analyzing them, going deep with our partners to just have confidence we're making a platform that'll serve their use cases well.

所以，是的，有些人不知所措，但我们有信心，因为我们在这些用例上花了很多时间，分析它们，与我们的合作伙伴深入交流，以确信我们正在创建一个能够很好地服务于他们的用例的平台。

**Jerod Santo:** Could you walk us through the user experience that either exists now, or will be existing as you guys roll out domestically in the United States?

**Jerod Santo：** 您能否向我们介绍一下现在存在的用户体验，或者你们在美国国内推出时将会存在的用户体验？

...from the end user perspective, but then also as we go, maybe explain the software systems that have to support that...

...从最终用户的角度来看，但随着我们的发展，也许会解释必须支持该功能的软件系统...

Because I'm fascinated where software meets the real world and there are all sorts of weird situations that you have to account for.

因为我着迷于软件与现实世界的结合，并且你必须考虑到各种奇怪的情况。

I know there's an app.

我知道有一个应用程序。

I assume it's similar to a DoorDash kind of a thing, where I'm going to order - let's just say I'm going to get a Chipotle burrito, because I already cracked that earlier...

我认为它类似于 DoorDash 之类的东西，我要在那里订购 - 假设我要买一份 Chipotle 墨西哥卷饼，因为我之前已经破解了......

And I'm a fan.

我是粉丝。

Not a sponsor, but I'm a fan of the old Chipotle burrito.

不是赞助商，但我是老墨西哥卷饼的粉丝。

And I know it's under eight pounds, so it's going to fit into my zip...

我知道它的重量不到八磅，所以它可以装进我的拉链......

Unless I get the double.

除非我得到双倍。

I don't know, can you get a 10-pound burrito from Chipotle?

我不知道，你能从 Chipotle 买一份 10 磅的墨西哥卷饼吗？

Maybe not yet.

也许还没有。

Someday.

有一天。

Someday we can dream.

有一天我们可以梦想。

I open up the Zipline app, I assume...

我打开 Zipline 应用程序，我想……

Or do I open up the Chipotle app?

或者我应该打开 Chipotle 应用程序吗？

Maybe that's where we start.

也许这就是我们开始的地方。

Do I start in the Chipotle app?

我要从 Chipotle 应用程序开始吗？

Do I start in the Zipline app?

我要从 Zipline 应用程序开始吗？

Where do I start?

我从哪里开始？

**Keenan Wyrobek:** Yeah.

**基南·维罗贝克：** 是的。

So soon you'll be able to start in the Chipotle app.

很快您就可以开始使用 Chipotle 应用程序了。

Today you start in the Zipline app.

今天您将开始使用 Zipline 应用程序。

And depending on where you live -- if you live in the best place in Dallas-Fort Worth area, you open that app and you're going to see a bunch of different store fronts.

取决于你住在哪里——如果你住在达拉斯-沃斯堡地区最好的地方，你打开该应用程序，你会看到一堆不同的店面。

You'll see Walmart, very soon Walmart Pharmacy, you'll see Blue Bell Ice Cream, you'll see Chipotle...

你会看到沃尔玛，很快就会看到沃尔玛药房，你会看到蓝铃冰淇淋，你会看到Chipotle......

**Keenan Wyrobek:** ...you'll see just a whole bunch of great restaurants.

**Keenan Wyrobek：** ...您会看到一大堆很棒的餐厅。

Buffalo Wild Wings, and others.

布法罗野翼等。

And yeah, you pick what you want...

是的，你选择你想要的......

That part of the experience feels a lot like DoorDash, or someone driving the thing to you...

这部分体验感觉很像 DoorDash，或者有人把东西开给你......

Then they'll start prepping it, our partners will prep the food or prep the order...

然后他们会开始准备，我们的合作伙伴将准备食物或准备订单......

And then we put it in this thing that we call a zipping point, which is this fun little kiosk you put the package into.

然后我们把它放在一个我们称之为压缩点的东西里，这是一个有趣的小亭子，你可以把包裹放进去。

And similar to how we deliver, the drone stays up high and the delivery zip comes down 100 meters, grabs the package out of the kiosk, and brings it to you.

与我们的送货方式类似，无人机保持在高处，送货拉链下降 100 米，从售货亭中取出包裹，并将其送到您面前。

And this is where things are very different than delivering by car.

这就是事情与汽车送货截然不同的地方。

We actually have to warn people "Hey, your food may be too hot to eat."

我们实际上必须警告人们“嘿，你的食物可能太热了，无法食用。”

**Keenan Wyrobek:** So we deliver so fast that we've had people be like "Oh, yeah, I just assumed my hot wings would be soggy", and they just stuck them in their mouth and burnt their mouth...

**Keenan Wyrobek：** 所以我们交货速度如此之快，以至于人们会说“哦，是的，我只是以为我的热翅膀会湿透的”，然后他们就把它们塞进嘴里，烧焦了他们的嘴......

Because they're so used to how long it takes for deliveries to happen the old fashioned way, that when it takes only a few minutes, and it's well insulated and controlled the way we do it, the food's actually fresh, and sometimes very hot still.

因为他们已经习惯了传统的送货方式需要多长时间，所以当只需要几分钟，并且我们的方式隔热和控制良好时，食物实际上是新鲜的，有时甚至还很热。

**Jerod Santo:** Yeah.

**杰罗德·桑托：** 是的。

That's a great problem to have.

这是一个很大的问题。

So show me the Chipotle side.

那就给我看看 Chipotle 的一面吧。

From your integrators, your restaurants...

来自您的集成商、您的餐厅...

And I'm just picking on them because I know they're a partner of yours.

我只是对他们挑剔，因为我知道他们是你的合作伙伴。

Obviously, there's going to be a bunch of them.

显然，会有很多这样的人。

But imagine that I do order a Chipotle burrito out of zip line.

但想象一下，我确实从高空滑索上点了一份 Chipotle 墨西哥卷饼。

I assume an API call kicks off over to the Chipotle, and makes the order, and then they have to somehow tell the zip when it's ready...

我假设 API 调用开始向 Chipotle 发起，并下订单，然后他们必须以某种方式告诉 zip 何时准备好......

How do they do that?

他们是怎么做到的？

**Keenan Wyrobek:** Yeah, so with Chipotle they use their software system the way they use it for any order.

**Keenan Wyrobek：** 是的，所以在 Chipotle 中，他们使用软件系统的方式就像处理任何订单一样。

If you're ordering over the counter, or you place an order to the Chipotle app, and it shows up on their -- they call it their make line.

如果你在柜台订购，或者你在 Chipotle 应用程序上下订单，它就会显示在他们的订单上——他们称之为他们的生产线。

That's the people that actually put the order together.

这些人实际上是下订单的人。

So they're going to make this like any other food they're making; our system gets hit over the API, so we know when they started that, and we know when they're done...

所以他们会像他们制作的任何其他食物一样制作它；我们的系统通过 API 受到攻击，所以我们知道他们什么时候开始这样做，我们也知道他们什么时候完成......

And then when they're done, we'll put it in that kiosk, dispatch the zip, the drone over to come get it, it'll come pick it up...

然后当他们完成后，我们会把它放在那个亭子里，发送拉链，无人机过来拿它，它会来接它......

That's usually about a minute or two after it's ready.

通常在准备好后大约一两分钟。

And then we deliver it anywhere from one to five minutes later, depending how far away you are.

然后我们会在一到五分钟后将其交付到任何地方，具体取决于您的距离有多远。

**Keenan Wyrobek:** We deliver it in your in your yard.

**Keenan Wyrobek：** 我们将其运送到您的院子里。

And yeah, we have a fun little app that shows you the drone coming, and it gives you that really super-precise ETA.

是的，我们有一个有趣的小应用程序，可以向您展示无人机的到来，并为您提供非常精确的预计到达时间。

**Jerod Santo:** I think one of the things I didn't appreciate about this kind of delivery that's really cool is just how human-centered it is...

**杰罗德·桑托：** 我认为我不欣赏这种很酷的交付方式的一件事是它是多么以人为中心......

As opposed to whenever that driver is going to show up, and sometimes it's like "Wait, why did they take that crazy route?

相反，每当那个司机出现时，有时就会说“等等，他们为什么要走那条疯狂的路线？

My kids are hungry." We tell you "No, no. Within a minute \[unintelligible 00:57:38.12\] actually show up and you can walk outside and pick it up.

我的孩子们饿了。”我们告诉你“不，不。一分钟内\[无法理解的00:57:38.12\]实际上出现了，你可以走到外面把它捡起来。

It's just there."

它就在那里。”

**Jerod Santo:** That can be a cool feature there, Keenan, come on.

**Jerod Santo：** 这可能是一个很酷的功能，Keenan，来吧。

Put your hand out, and we'll put -- you have a third little...

伸出你的手，我们会放——你还有第三个小……

So you have the big zip, and the little zip, and then like a hand that comes down; it just drops a little bit lower, and...

所以你有大拉链和小拉链，然后就像一只手落下来；它只是下降了一点点，而且......

**Keenan Wyrobek:** \[58:06\] I literally tested -- the way we talk about this is we don't want people to do stuff like that, but we test in case people do that kind of thing.

**Keenan Wyrobek：** \[58:06\] 我确实进行了测试——我们谈论这个的方式是我们不希望人们做那样的事情，但我们测试以防人们做那样的事情。

So it's delivered into my arms, and I love it...

于是它就被送到了我的怀里，我喜欢它......

**Adam Stacoviak:** Do you pause the delivery then, when you detect anomalies you don't want to be present in?

**Adam Stacoviak：** 当您检测到您不想出现的异常情况时，您会暂停交付吗？

I assume that's probably a phrase or terminology...

我认为这可能是一个短语或术语......

**Keenan Wyrobek:** Yeah, it's actually kind of funny...

**Keenan Wyrobek：** 是的，这实际上有点有趣......

So we do a little bit of avoidance.

所以我们做了一点回避。

So if we're coming down and we see the person standing right there, we'll scoot over and deliver next to them.

因此，如果我们下来时看到那个人站在那里，我们就会迅速跑过去，在他们旁边送货。

**Keenan Wyrobek:** Exactly.

**基南·维罗贝克：** 没错。

If you do that -- you can make a really fun game for kids, and we don't want to be a fun game.

如果你这样做，你就可以为孩子们制作一款非常有趣的游戏，而我们不想成为一款有趣的游戏。

You know what I mean?

你知道我的意思？

We don't want to make this to be a game of "Oh, it turns out if you chase this thing, it'll become a game", and then everybody wants to chase these things, and we can't deliver...

我们不想让这成为一个“哦，原来如果你追逐这个东西，它就会变成一个游戏”的游戏，然后每个人都想追逐这些东西，而我们无法交付......

And so basically, what we've found to work really well is just slow down.

所以基本上，我们发现真正有效的就是放慢速度。

One of the things we like about that little delivery zip is it's very benign.

我们喜欢这个小送货拉链的原因之一是它非常温和。

If someone touches it or something, it's not a safety concern.

如果有人触摸它或其他东西，这不是安全问题。

And so yeah, we just slow down and keep going, and make that delivery, and get out of there.

所以，是的，我们只是放慢速度，继续前进，完成交付，然后离开那里。

And basically, the way I think to talk about it is like "We be boring", so that we're not creating a fun game for every kid.

基本上，我认为谈论它的方式就像“我们很无聊”，所以我们不会为每个孩子创造一个有趣的游戏。

As a parent of young kids, I've brought them to the test site too, and I know exactly what -- if you did that avoidance with my three-year-old, she would have so much fun, and we would never make deliveries.

作为年幼孩子的父母，我也曾带他们到测试地点，我很清楚 - 如果你对我三岁的孩子这样做，她会很开心，我们永远不会送货。

**Jerod Santo:** Right.

**杰罗德·桑托：** 对。

Well, it might be a consideration for down the road, of getting even more human-centric; it's like, allow the orderer to set a mode.

嗯，这可能是未来的一个考虑因素，变得更加以人为中心；就像，允许订购者设置模式。

"Do I want to have fun with it?

“我想玩得开心吗？

Do I just want my food?" I know you guys want to save energy and battery and all that, but...

我只想要我的食物吗？”我知道你们想节省能源和电池等等，但是......

You're already pretty happy to have your food delivered from the sky.

你已经很高兴能收到从天上送来的食物了。

I can imagine that's a moment already.

我可以想象那已经是一个时刻了。

But to have a little bit of a personality with the thing - it might take it over the top, to where it's the only way we're ever going to get food, is to just give us...

但要对这件事有一点个性——它可能会超越它的极限，成为我们获得食物的唯一途径，就是给我们……

That's why I think the handoff would be actually amazing, but...

这就是为什么我认为切换实际上会很棒，但是......

Yeah, too dangerous perhaps to do that today.

是的，今天这样做可能太危险了。

**Keenan Wyrobek:** I love that idea.

**Keenan Wyrobek：** 我喜欢这个主意。

Your head is exactly where my head is.

你的头正好在我的头所在的地方。

To me it's not a question of if, it's a question of when.

对我来说，这不是是否的问题，而是何时的问题。

So I look forward to it.

所以我很期待。

**Adam Stacoviak:** Well, someone will always mess around too in those scenarios, but...

** Adam Stacoviak：** 好吧，在这些情况下总会有人乱搞，但是......

Did you mention at all when, time of day, you can't deliver?

您是否提到过您无法送货的时间？

Is there like danger zones where you can't deliver in the evening, or after dusk?

是否存在晚上或黄昏后无法送货的危险区域？

Or is there light concerns?

还是有轻微的担忧？

Do you have lights on these things?

这些东西你有灯吗？

**Keenan Wyrobek:** Right now that's just limited by our partner hours.

**Keenan Wyrobek：** 目前这仅受我们合作伙伴工作时间的限制。

And most of the places we operate in the world, we deliver 24/7 with the health systems.

在我们在世界上开展业务的大多数地方，我们都提供 24/7 的卫生系统服务。

And it's always interesting to see - you'll work with a restaurant partner, and all of a sudden they'll realize just how much volume we're adding to their normal business, and they're kind of like "Oh, wait a minute...

看到这一点总是很有趣 - 你将与餐厅合作伙伴合作，突然他们会意识到我们给他们的正常业务增加了多少数量，他们有点像“哦，等一下......

If we operate with you all, and you can go 24/7...

如果我们与你们一起运作，你们就可以 24/7 去...

You're already operating 24/7 for other people, so we could be open at night..." There's a huge part of our economy that works at night.

你已经在为其他人提供 24/7 的运营，所以我们可以在晚上营业……”我们的经济有很大一部分是在夜间运作的。

Night shift workers, and things like that...

夜班工人之类的...

We know that because all the health people we work with, they work 24 hours a day...

我们知道，因为与我们一起工作的所有卫生人员，他们每天 24 小时工作......

But obviously, lots of manufacturing operates 24 hours a day, and a lot of our partners are seeing it like "Wow", there's a whole part of commerce they can address, and a big part of the demand they can address by operating more hours.

但显然，许多制造业每天 24 小时运营，我们的许多合作伙伴都看到这样的情况“哇”，他们可以解决很大一部分商业问题，并且可以通过延长运营时间来解决很大一部分需求。

And obviously, partnering with us, we can do that in a way that's people really like.

显然，通过与我们合作，我们可以以人们真正喜欢的方式做到这一点。

Yeah, it's really cool.

是的，这真的很酷。

You'll get whatever you need, 24 hours a day.

您每天 24 小时都会得到您需要的一切。

As a parent -- just simple things, like kid was spiking with a fever at night, and you've ran out of medication to bring that fever down...

作为父母——只是一些简单的事情，比如孩子晚上发烧，而你已经没有退烧的药物了……

The only thing worse than having a kid with a fever is taking your kid to a 24-hour pharmacy at night to go grab that stuff you don't have.

唯一比孩子发烧更糟糕的就是晚上带着孩子去24小时营业的药店去买你没有的东西。

**Adam Stacoviak:** \[01:01:56.01\] Yeah.

**亚当·斯塔科维亚克：** \[01:01:56.01\] 是的。

Croup is a big deal for parents.

对于父母来说，哮吼是一件大事。

I know that we've battled several late night ER visits for croup, and generally - I don't want to go into the medical scenario here, but basically, you have to be seen by some sort of medical professional to get a special medicine that is for croup, that sort of helps your vocal cords and things reduce, or whatever.

我知道我们已经在深夜因哮吼而去急诊室就诊了，一般来说，我不想在这里讨论医疗情况，但基本上，你必须由某种医疗专业人员去看，以获得治疗哮吼的特殊药物，这可以帮助你的声带和​​东西减少，或者其他什么。

And it's kind of a pain in the butt, because you kind of know, as a parent -- you're like "You know what, I'm Dr. Mom or I'm Dr. Dad.

这有点让人头疼，因为你知道，作为父母，你会说“你知道吗，我是妈妈医生，或者我是爸爸医生。

I've been down this road before with my child.

我以前和我的孩子也走过这条路。

I just need that particular prescription." So if you had a relationship where you could do telehealth, which is super-popular, we would not have to leave the house at all.

我只需要那个特殊的处方。”因此，如果您有一种可以进行远程医疗的关系（这是非常受欢迎的），我们根本不必离开家。

If that were a scenario, we can make a phone call in our telehealth, and maybe 10 or 15 minutes later we've got a delivery from zip that says "Hey, here's your croup medicine." You didn't have to leave the house, you can do it efficiently...

如果出现这种情况，我们可以在远程医疗中拨打电话，也许 10 或 15 分钟后，我们会收到 zip 的快递，上面写着“嘿，这是您的哮吼药。”您不必离开家，就可以高效地完成...

You didn't have to be on the road...

你不必在路上...

You talk about the efficiencies and environmental effects...

您谈到了效率和环境影响......

Like, we didn't have to drive, we didn't have to lose sleep and maybe ruin our day the next day more; so we got the medicine -- and there's so many unintended consequences in that scenario that just make it so interesting to think about how you can reorient the world around this being a thing.

就像，我们不必开车，我们不必失眠，也许第二天会更加毁了我们的一天；所以我们得到了药物——在这种情况下会产生很多意想不到的后果，这让思考如何围绕这件事重新定位世界变得非常有趣。

**Keenan Wyrobek:** Oh, totally.

**Keenan Wyrobek：** 哦，完全可以。

I mean, Adam, I'm so excited about this.

我的意思是，亚当，我对此感到非常兴奋。

And we have partnerships now with about a dozen regional US health systems, and all of them have this use case in that partnership.

我们现在与大约十几个美国地区卫生系统建立了合作伙伴关系，所有这些系统都在该合作伙伴关系中拥有此用例。

They have some other ones as well, but this is -- they call it the physical side of telehealth.

他们还有其他一些，但这是——他们称之为远程医疗的物理方面。

Telehealth is obviously becoming a really predominant thing here...

远程医疗显然正在成为这里的一个非常重要的事情......

And like you said, for so many things - there's a physical side, too.

就像你说的，对于很多事情来说，也有身体方面的问题。

And so if you can get that inhaler delivered right away, or that croup medication delivered right away, it's huge for the family.

因此，如果您能立即获得吸入器或哮吼药物，这对家庭来说意义重大。

It's huge for -- yeah, and you're touching on something too that I didn't appreciate when starting Zipline, that I now I appreciate a lot...

这对于——是的，你也触及了一些我在开始 Zipline 时并不欣赏的东西，但现在我非常欣赏......

It's just how much health affects basically the economy.

这只是健康对经济的影响程度。

You mentioned just - yeah, the parents not being exhausted the next day; their work is going to be better, and they're going to be more productive in the economy, and just keeping people healthy in that sort of preventative way is something that I've become extremely passionate about, because I've just seen this cause and effect in my own life, and in all the patients we serve around the world...

你刚才提到——是的，父母第二天并没有精疲力竭；他们的工作会更好，他们在经济中会更有生产力，以这种预防性的方式保持人们的健康是我非常热衷的事情，因为我刚刚在自己的生活中以及我们在世界各地服务的所有患者中看到了这种因果关系......

Just how powerful that is when a parent doesn't have to stay home, or a parent doesn't have to basically be affected in their professional world by what could be a very preventable sort of health -- some of these things kind of feel like inconveniences even, right?

当父母不必呆在家里，或者父母基本上不必在职业世界中受到本来可以预防的健康问题的影响时，这是多么强大——其中一些事情甚至感觉像是不便，对吧？

Blood, obviously - very acute, big, life threatening...

血，显然——非常急、大、危及生命……

But a lot of this stuff, it's just -- a little bit of convenience just goes a long way for people staying healthy and productive.

但很多这样的东西，只是——一点点的便利对于人们保持健康和生产力大有帮助。

**Adam Stacoviak:** Have you -- I imagine you probably have, but have you imagined a world where Zipline's at scale, and you don't have a couple hundred in production, you have, I don't know, half a million; I don't know, a lot.

**Adam Stacoviak：** 你有吗——我想你可能有，但是你有没有想象过一个 Zipline 规模化的世界，你没有生产几百个，但我不知道，你有 50 万个；我不知道，很多。

Just an astronomical number that you don't even consider today.

这只是一个你今天根本不会考虑的天文数字。

How the world changes, maybe even how we see the world...

世界如何变化，甚至我们如何看待世界......

Because I can't imagine \[unintelligible 01:04:58.18\] Zipline delivering something to me.

因为我无法想象\[无法理解的01:04:58.18\] Zipline 会给我送东西。

I'm sure it'd be cool once I have it in my own life, but...

我确信一旦我在自己的生活中拥有它就会很酷，但是......

Once this kind of technology, whether it's you or just generally, like flights, isn't only owned by United or Southwest, for example, when this kind of delivery or scenario becomes ubiquitous, have you imagined that world and how that changes the world?

一旦这种技术，无论是你还是一般情况下，比如航班，不只是美联航或西南航空拥有，例如，当这种交付或场景变得无处不在时，你是否想象过那个世界以及它如何改变世界？

**Keenan Wyrobek:** Yeah.

**基南·维罗贝克：** 是的。

I mean, I'm super-excited about it.

我的意思是，我对此感到非常兴奋。

This is part of the reason we spend so much time on things like making the system silent, is -- one of the things we know is I don't want to notice these things.

这是我们花费大量时间在诸如让系统静音之类的事情上的部分原因，我们知道的一件事是我不想注意到这些事情。

Just like a bird flying over your house.

就像一只鸟飞过你的房子。

How many birds flew over your house today?

今天有多少只鸟飞过你家？

You have no idea.

你不知道。

Why?

为什么？

Because you don't hear them.

因为你听不到他们的声音。

And we spent a lot of time on things like that, because we just know that as these things scale, there's certain things that we've learned from our experience that just matter a lot, like it being quiet.

我们在类似的事情上花了很多时间，因为我们知道，随着这些事情的规模扩大，我们从我们的经验中学到了一些非常重要的东西，比如保持安静。

\[01:05:49.24\] So there's certain things like that that we spent a lot of time on, to make sure that when this scales, it's a world we actually want to live in.

[01:05:49.24] 因此，我们在某些事情上花了很多时间，以确保当这种规模扩大时，这是一个我们真正想要生活的世界。

And then, of course, the net effects of this kind of instant delivery...

当然，这种即时交付的净效应......

I live in a small town here in California, and - yeah there's, there's two bakeries...

我住在加利福尼亚州的一个小镇上，而且 - 是的，那里有两家面包店......

They're so excited for when they get their little kiosk and they can just send out fresh bread in the morning to people.

当他们拥有自己的小售货亭并且可以在早上向人们发送新鲜面包时，他们感到非常兴奋。

**Keenan Wyrobek:** Exactly.

**基南·维罗贝克：** 没错。

And there's so many things on the personal life side like that, like getting fresh bread delivered, there's so many things on the work side...

个人生活方面有很多这样的事情，比如送新鲜面包，工作方面有很多事情......

There's so many jobs that just require stuff.

有很多工作只需要东西。

Obviously, doctors, medicines - it's so obvious.

显然，医生、药物——这是显而易见的。

And auto mechanics - it's so obvious.

还有汽车修理工——这是显而易见的。

Just yesterday, my HVAC system in my house went out; a little blower had failed, and the guy came out and he's like "I'll be back in two days with the part." And it's like "No, no." You would deliver the part right while he's there.

就在昨天，我家的暖通空调系统坏了；一个小鼓风机坏了，那家伙出来了，他说：“我会在两天内带着这个零件回来。”就像“不，不”。当他在的时候你就可以交付零件。

And I looked it up, the part he needed - it weighs less than eight pounds.

我查了一下，是他需要的零件——重量不到八磅。

We can deliver it.

我们可以交付。

**Adam Stacoviak:** Oh, that would have been so cool.

** Adam Stacoviak：** 哦，那真是太酷了。

If you're like "Hey, I've got a solution for this.

如果你像“嘿，我有一个解决方案。

Hang on.

坚持住。

There's no delay.

没有延迟。

I got the part."

我得到了这个角色。”

**Keenan Wyrobek:** Yeah.

**基南·维罗贝克：** 是的。

Even just talking to him about his business.

甚至只是和他谈论他的事情。

This is an independent guy, who does a lot of these kinds of HVAC repairs, and fixing heaters and stuff...

这是一个独立的人，做了很多暖通空调维修，修理加热器之类的东西......

And his customers, they hate it when he charges for these visits just to figure out what he needs.

而他的客户则讨厌他对这些访问收取费用只是为了弄清楚他需要什么。

If he could just fix it there on the spot, not only would he be able to serve so many more customers, but those customers would be so much happier.

如果他能当场修复它，他不仅能够为更多的客户提供服务，而且这些客户也会更加高兴。

And he has somebody who hates that part of the customer conversation, of like "I've got to charge you the 200 bucks for just coming by and seeing this thing." He'd love that to go away, because he hates that part of his job.

他有一个人讨厌客户谈话中的这一部分，比如“我必须向你收取 200 美元，因为你只是过来看到这个东西。”他希望这种情况能够消失，因为他讨厌这部分工作。

And anyway, there's so many pieces like that, I just can't wait to see what people imagine, and how they will use it.

不管怎样，这样的作品有很多，我迫不及待地想看看人们的想象以及他们将如何使用它。

Because every country we operate in, people are using it in ways I never expected.

因为我们开展业务的每个国家/地区，人们都以我意想不到的方式使用它。

I'll tell you one fun story from Dallas.

我会告诉你一个来自达拉斯的有趣故事。

This summer we were looking at our usage data, and most people would either order at one address, or order to maybe two addresses.

今年夏天，我们查看了我们的使用数据，大多数人要么在一个地址订购，要么向两个地址订购。

But we saw this one person who was ordering to a different address almost every single day.

但我们看到这个人几乎每天都向不同的地址订购。

Like, what is this?

比如，这是什么？

What's going on here?

这是怎么回事？

And so we send this user an email saying "Would you share how you're using the service?" And so this is a postal delivery carrier, and his New Year's resolution for this year was to eat healthier...

因此，我们向该用户发送一封电子邮件，内容是“您能分享一下您如何使用该服务吗？”这是一名邮政投递员，他今年的新年决心是吃得更健康……

And he was getting a salad delivered to him along his route every day, for lunch.

每天午餐时，他都会沿途收到一份沙拉。

And I just -- anyway, I just loved that.

我只是——无论如何，我就是喜欢这样。

I would have never have guessed.

我绝对不会猜到。

I would have never guessed.

我绝对不会猜到。

We call him the Johnny Appleseed of Zipline, you can see...

我们称他为 Zipline 的 Johnny Appleseed，你可以看到......

**Jerod Santo:** What about gifting?

**杰罗德·桑托：** 送礼怎么样？

It's a great way to gift.

这是送礼的好方法。

It's just like "Hey." Call somebody up, "Go outside." "Why?" "There's a delivery coming for you." And this thing just drops a gift out of the sky.

就像“嘿”一样。叫人过来，“出去吧。” “为什么？” “有快递给你。”这东西简直就是从天而降的礼物。

**Keenan Wyrobek:** Oh, we did this.

**Keenan Wyrobek：** 哦，我们做到了。

So we did a really fun thing for Easter this year, where we basically loaded up the little delivery zip with a bunch of Easter eggs; no packaging, just Easter eggs.

所以今年我们为复活节做了一件非常有趣的事情，我们基本上在小送货拉链上装满了一堆复活节彩蛋；没有包装，只有复活节彩蛋。

And by the way, one cool thing about what we do is it doesn't require packaging.

顺便说一句，我们所做的一件很酷的事情是它不需要包装。

That's another part of the future I'm excited about.

这是我感到兴奋的未来的另一部分。

None of this cardboard jungle we all have in our garage from Amazon boxes.

我们的车库里没有亚马逊盒子里的纸板丛林。

**Keenan Wyrobek:** And so we put a bunch of Easter eggs in there, and it was really interesting to see how many -- we had grandparents in other States, outside of Dallas (we were just delivering in Dallas) place orders for their grandkids to deliver this pile of Easter eggs into the yard.

**Keenan Wyrobek：** 所以我们在那里放了一堆复活节彩蛋，看到有多少真的很有趣 - 我们在达拉斯以外的其他州有祖父母（我们刚刚在达拉斯送货）下订单让他们的孙子们将这堆复活节彩蛋送到院子里。

And the kids loved it, and the grandparents loved it...

孩子们喜欢它，祖父母也喜欢它......

We had just sort of this out of state gifting, and it was so cool.

我们刚刚收到了这种州外的礼物，真是太酷了。

**Keenan Wyrobek:** And there's so many things like this, that I can't wait to try.

**Keenan Wyrobek：** 像这样的事情有很多，我迫不及待地想尝试。

**Jerod Santo:** There's so many places you can go with eight pounds, but at a certain point that becomes your limit; I don't think you guys are anywhere near that point.

**杰罗德·桑托：** 你可以带着八磅去很多地方，但在某个时刻，这就会成为你的极限；我认为你们还没有接近那个点。

And we all know that.

我们都知道这一点。

But at some point, have you thought "Okay, what's the next -- where's the zip line jumbo?

但在某些时候，您是否想过“好吧，下一步是什么——巨型滑索在哪里？

What's the weight that we need to go to expand to a new set of things?" And then "What do we need to manufacture in terms of drones to actually get that done?" I know there's a long range one.

我们需要多大的权重才能扩展到一系列新事物？”然后“我们需要制造什么无人机才能真正完成这个任务？”我知道有一个远程的。

Is there like a heavy weight one, or is that just too far down the line to care about?

是否有一个重量级的，或者是太远了以至于不需要关心？

**Keenan Wyrobek:** \[01:09:49.14\] It's a great question.

**Keenan Wyrobek：** \[01:09:49.14\] 这是一个很好的问题。

Eight pounds gets us really far, as you're alluding to.

正如你所提到的，八磅让我们走得很远。

Something like 80% plus of Amazon packages are less than eight pounds.

亚马逊 80% 以上的包裹重量都不超过 8 磅。

So many of the use cases that we are really focused on...

我们真正关注的许多用例......

A meal for a family of four, from almost any restaurant, is less than eight pounds, as an example.

例如，几乎任何一家餐馆的四口之家的一顿饭都不到八英镑。

And then, yeah, if you need more, we just send two deliveries, back to back.

然后，是的，如果您需要更多，我们只需连续发送两次。

It's two little bags of food.

这是两小袋食物。

It's no boxes, none of this other stuff.

没有盒子，也没有其他东西。

It'll be interesting to see how it evolves.

看看它如何演变将会很有趣。

If I was a betting person, I think we will increase our payload over time beyond eight pounds.

如果我是一个打赌的人，我认为随着时间的推移，我们的有效载荷将增加到超过八磅。

There's a good chance it won't go a ton past that.

很有可能它不会超过这个范围。

Maybe 10, maybe 12 pounds...

也许10磅，也许12磅......

And really, what it comes down to is what doesn't fit.

事实上，归根结底就是什么不适合。

Once we get to that scale, we can deliver a very full bag of groceries at that scale.

一旦我们达到这个规模，我们就可以按照这个规模交付一袋非常满的杂货。

And the advantage of having one platform, as opposed to like different variants, is we can drive the cost down further and further, just from scale.

与不同的变体相比，拥有一个平台的优势在于，我们可以从规模上进一步降低成本。

And so as the cost per delivery goes down, there's a chance that we'll never be able to compete with -- if we made a drone that could deliver four bags of grocery at once, that will always be more expensive than a smaller drone delivering four bags just 30 seconds apart onto your picnic table in your backyard.

因此，随着每次送货成本的下降，我们有可能永远无法与之竞争——如果我们制造一架可以一次运送四袋杂货的无人机，那么它总是比一架较小的无人机更昂贵，该无人机间隔仅 30 秒将四袋杂货运送到您后院的野餐桌上。

And then there's stuff left out, like the flat screen TVs...

然后还有一些东西被遗漏了，比如平板电视……

We obviously can't deliver those.

我们显然无法交付这些。

**Adam Stacoviak:** I was thinking about the TV, honestly.

** Adam Stacoviak：** 老实说，我正在考虑电视。

I was like "Can you bring the TV to me?" I'm just kidding, I was not thinking that.

我当时就想“你能把电视拿给我吗？”我只是开玩笑，我并没有这么想。

That's cool.

这很酷。

**Keenan Wyrobek:** Yeah.

**基南·维罗贝克：** 是的。

We've been looking at the car -- the partner will be launching within Dallas, and we can deliver something like 90% of their car parts...

我们一直在关注这辆车——合作伙伴将在达拉斯推出，我们可以交付他们 90% 的汽车零部件......

But obviously, 10% we can't do.

但显然，10%我们做不到。

And yeah, we think about that.

是的，我们考虑过这一点。

Zipline has always just kind of been like customer-first.

Zipline 一直秉承客户至上的理念。

So once we get the data, once enough customers ask us for the same thing over and over again, and we go deep with them, if we have conviction that there's a thing that will work for them, that will make sense for the business...

因此，一旦我们获得数据，一旦有足够多的客户一遍又一遍地向我们询问同样的事情，我们就会深入了解他们，如果我们确信有一种东西对他们有用，那对业务也有意义......

You know, that's how this precision delivery drone inside of a drone system came from...

你知道，这就是无人机系统内的精确投递无人机的来源……

So yeah, we'll do more things in the future.

所以是的，我们将来会做更多的事情。

**Jerod Santo:** Is anybody else doing this?

**Jerod Santo：** 还有其他人这样做吗？

Like, who's the Southwest to your United?

比如，谁是你们曼联的西南方向？

I know that Amazon announced the thing, like you said, years ago, about drone deliveries, and then that got canceled, or sidelined, or whatever; maybe it's happening, but...

我知道亚马逊几年前就宣布了关于无人机送货的事情，就像你说的那样，然后就被取消了，或者被搁置了，或者其他什么；也许它正在发生，但是...

I hope there's other people that are tackling the same problem, because we want diverse and unique solutions, and learning from each other...

我希望还有其他人正在解决同样的问题，因为我们想要多样化和独特的解决方案，并互相学习......

So who else is working in this space that maybe is either your competition, or even that you admire what they're up to?

那么还有谁在这个领域工作，可能是您的竞争对手，甚至您钦佩他们的所作所为？

**Keenan Wyrobek:** Yeah, so Amazon has started doing some deliveries, quite limited as far as I understand.

**Keenan Wyrobek：** 是的，所以亚马逊已经开始进行一些送货，据我了解，相当有限。

Google has a project called Wing.

谷歌有一个名为 Wing 的项目。

I admire a lot of how they're thinking about the problem, and we collaborate with them a lot on some of the projects with the FAA.

我非常钦佩他们对问题的思考方式，并且我们在美国联邦航空局的一些项目上与他们进行了很多合作。

I really like how they think about some of some aspects of safety, for example, and things like that.

我真的很喜欢他们对安全某些方面的思考，例如，诸如此类的事情。

I admire that a lot.

我非常钦佩这一点。

There's a fair bit out there...

那里有相当多的东西......

I'll be honest, I don't think a lot about the competition.

老实说，我对比赛并没有想太多。

For us, it's just about the customer, and just "What can we do?

对我们来说，这只是关于客户，只是“我们能做什么？

How can we do better every day?" and really measure ourselves on our own velocity towards delighting those customers.

我们怎样才能每天做得更好？”并真正根据我们取悦这些客户的速度来衡量我们自己。

**Jerod Santo:** Yeah.

**杰罗德·桑托：** 是的。

What's 2026 going to be about?

2026 年将会发生什么？

Scale?

规模？

Other things?

其他的事情？

What's it going to look like?

它会是什么样子？

**Keenan Wyrobek:** It's a lot about scale.

**Keenan Wyrobek：** 这与规模息息相关。

Our long range platform is scaling around the world, so that will continue in 2026...

我们的远程平台正在全球范围内扩展，因此这种情况将在 2026 年继续下去……

And yeah, this precision delivery platform is scaling...

是的，这个精准交付平台正在扩展......

Yeah, it is scaling really fast.

是的，它的扩展速度非常快。

So a lot of what 2026 is about is building up the supply chain capability to manufacture faster, building all the internal muscles to launch the charging sites, and things like that, to enable scale.

因此，2026 年的重点是建立供应链能力以加快制造速度、建立所有内部力量来启动充电站等，以实现规模化。

Yeah.

是的。

And just getting better and better at that user journey you were asking about, of like "How do people order, and how does that all work for all the different use cases?" We've found -- you can't be super-generic there.

在您所询问的用户旅程中变得越来越好，例如“人们如何订购，以及这一切如何适用于所有不同的用例？”我们发现——你不能做到超级通用。

Different use cases need a tailored user experience for it to really be magical...

不同的用例需要量身定制的用户体验才能真正变得神奇......

And so we'll spend a lot of time there as well.

所以我们也会在那里度过很多时间。

**Keenan Wyrobek:** How do you pick your next city, and why is it going to be Omaha?

**Keenan Wyrobek：** 您如何选择下一个城市，为什么是奥马哈？

\[laughter\]

\[笑声\]

**Keenan Wyrobek:** \[01:13:50.14\] It's really about the testing and validation story.

**Keenan Wyrobek：** \[01:13:50.14\] 这实际上是关于测试和验证的故事。

So I can't announce the next city, but we'll be launching our next cities in the first half of 2026.

所以我无法宣布下一个城市，但我们将在 2026 年上半年推出下一个城市。

Part of how we choose those cities is they're very similar to the Dallas-Fort Worth area.

我们选择这些城市的部分原因是它们与达拉斯-沃斯堡地区非常相似。

Similar in terms of weather, similar in terms of terrain, that kind of thing.

天气相似，地形相似，诸如此类。

And that's because that's what we validate the system for.

那是因为这就是我们验证系统的目的。

In parallel, we're validating the system for expanded weather, more complex terrain, smaller yards, all those kinds of things.

与此同时，我们正在验证该系统是否适用于更广泛的天气、更复杂的地形、更小的庭院以及所有这些类型的情况。

And so basically, once we validate the system to go into metros that aren't like -- we refer to like the Sunbelt metros; then we'll move into these other metros as well.

基本上，一旦我们验证了系统可以进入那些不像我们所说的阳光地带（Sunbelt）地铁那样的地铁；然后我们也会搬进其他地铁。

Yeah, it's really fun.

是的，这真的很有趣。

We have a test site up in the Cascades, where we're doing a lot of testing to validate the system for metros that aren't at all like Dallas and Fort Worth, but...

我们在喀斯喀特有一个测试站点，我们正在那里进行大量测试，以验证与达拉斯和沃斯堡完全不同的地铁系统，但是......

Yeah, it'll be Sunbelt metros first, and then we'll keep going from there.

是的，首先是 Sunbelt 地铁，然后我们将从那里继续前进。

**Jerod Santo:** Yeah.

**杰罗德·桑托：** 是的。

You've solved a ton of technical problems to get here, and now you're trying to take it in lots of places.

为了到达这里，你已经解决了大量的技术问题，现在你正试图在很多地方实现它。

What are the big technical problems that are ahead of you?

您面临的重大技术问题是什么？

If you had a checklist as CTO, like "Here's the things we need to solve." What's unsolved for Zipline?

如果您作为 CTO 有一份清单，例如“这是我们需要解决的问题”。 Zipline 有什么未解决的问题？

**Keenan Wyrobek:** Almost every front, there's more work to do.

**Keenan Wyrobek：** 几乎每个方面，都有更多的工作要做。

I've been thinking a lot recently about weather forecasting...

最近想了很多关于天气预报的事

So we spend a lot of time to validate the system for certain weather.

因此，我们花了很多时间来验证系统是否适合某些天气。

But then when you operate, you've got to know how -- like, how do you not go in that weather you can't go in?

但是当你进行手术时，你必须知道如何——比如，在你不能进去的天气里你如何不去？

And that's harder than it sounds to do at scale.

大规模地做到这一点比听起来更难。

There's some easy things, like wind limits.

有一些简单的事情，比如风的限制。

Forecasting that is fairly straightforward.

预测相当简单。

But there's much more complicated things, like icing conditions.

但还有更复杂的事情，比如结冰条件。

Right now we're testing to understand exactly what level of icing conditions we can handle, and how to handle that well, but there will be a limit there that we're gonna need to forecast.

目前，我们正在测试以准确了解我们可以处理什么程度的结冰条件，以及如何很好地处理，但我们需要预测一个限制。

Forecasting icing conditions is notoriously very hard to do.

众所周知，预测结冰情况非常困难。

This is like when you have fog, and clouds, and cold weather; oftentimes you fly through that and you just cover your aircraft in ice.

这就像有雾、有云、天气寒冷时；通常，当你飞过那里时，你的飞机就会被冰覆盖。

Another good example is lightning conditions.

另一个很好的例子是闪电条件。

We are currently chasing lightning with our mobile test rigs right now, to really understand how does lightning interact with the system.

我们目前正在使用移动测试设备追踪闪电，以真正了解闪电如何与系统交互。

We think it won't based on analysis, but lightning is one of those things where you don't trust the analysis.

我们认为它不会基于分析，但闪电是您不信任分析的事物之一。

You've got to go in the real world and get real amounts of data to get confidence in that analysis.

您必须进入现实世界并获取大量数据才能对分析充满信心。

So there's a lot of work, both on the capability side, to expand the kind of weather we can fly in, and on the weather forecasting side.

因此，无论是在能力方面还是在天气预报方面，都需要做很多工作来扩大我们可以飞行的天气类型。

There's a lot of work there.

那里有很多工作要做。

There's a lot of work in the airspace side, of just "How do you manage this fleet at scale?" You were talking about going from one charging point to a delivery, then landing at a different charging point...

空域方面有很多工作要做，比如“如何大规模管理这支机队？”你说的是从一个充电点到送货地点，然后降落在另一个充电点......

There are some things there that are just way harder than they sound, where you can end up with your fleet kind of like migrating organically in a direction away from where the supply is...

有些事情比听起来要困难得多，你的舰队最终可能会像有机地向远离供应地的方向迁移......

That can happen.

这可能会发生。

**Jerod Santo:** Like a beehive.

**杰罗德·桑托：** 就像蜂巢一样。

They're swarming.

他们蜂拥而至。

They're going somewhere else.

他们要去别的地方。

Oh, no...!

哦，不……！

**Keenan Wyrobek:** Exactly.

**基南·维罗贝克：** 没错。

So you've got to manage that carefully, to make sure you can keep delivering for people.

因此，您必须谨慎管理，以确保您能够继续为人们提供服务。

So there's a lot of -- almost every front of what we do at Zipline, there's a reimagining happening for the scale, for new capabilities.

因此，我们在 Zipline 所做的事情几乎每一个方面都在重新构想规模和新功能。

We've talked about some of healthcare use cases...

我们讨论了一些医疗保健用例......

There's a lot of new capabilities we need to build, both into how we operate the drones, and into the tools that the humans use on the healthcare side, systems side, and on the patient side to use the system...

我们需要构建许多新功能，包括我们如何操作无人机，以及人类在医疗保健方面、系统方面和患者方面使用系统的工具......

So there's all kinds of exciting things ahead of us.

因此，我们面前还有各种令人兴奋的事情。

I think of us as like -- we're at the very beginning of this journey, and there's a really exciting roadmap ahead.

我认为我们正处于这段旅程的开始，前面有一个非常令人兴奋的路线图。

**Jerod Santo:** I love it, man.

**杰罗德·桑托：** 我喜欢它，伙计。

I'm excited.

我很兴奋。

I love that one of your teams is like a group of storm chasers, and they're just like "Our job is to find lightning in the world, and then go fly these drones up into it and see what happens."

我喜欢你们的一个团队就像一群风暴追逐者，他们就像“我们的工作是在世界上寻找闪电，然后让这些无人机飞入其中，看看会发生什么。”

**Keenan Wyrobek:** It's a badass team.

**Keenan Wyrobek：** 这是一支糟糕的团队。

And they're hardcore too, because chasing storms when you have basically a big old trailer, we have these docks mounted to a trailer that they use...

它们也很硬核，因为当你基本上拥有一辆大型旧拖车时追逐风暴，我们将这些码头安装在他们使用的拖车上......

And obviously, with the storms, it's just hard to get around in these places...

显然，在暴风雨的影响下，在这些地方出行非常困难……

It's really cool, how they work and their dedication.

他们的工作方式和奉献精神真的很酷。

**Jerod Santo:** Is there a manual override on those things that you could just take over if you needed to, or no?

**Jerod Santo：** 是否有手动覆盖那些您可以在需要时接管的事情，或者没有？

**Keenan Wyrobek:** \[01:17:50.26\] Yeah, but it's very high level.

**Keenan Wyrobek：** \[01:17:50.26\] 是的，但水平非常高。

You basically have three buttons.

你基本上有三个按钮。

A button to tell it to go back and dock, a button to tell it to loiter right where it is, like stay put, and a button to deploy that whole aircraft parachute and land where it is.

一个按钮告诉它返回并停靠，一个按钮告诉它在原地徘徊，比如原地不动，还有一个按钮让整个飞机降落伞并降落在原地。

That third button we've never pushed, but every regulator wants it...

我们从未按下过第三个按钮，但每个监管机构都希望它......

And then mostly it's the other two buttons.

然后主要是其他两个按钮。

You can't jump in there and stick fly the thing.

你不能跳进去然后把那东西粘起来。

It'd be extraordinarily hard to.

那就异常的难了。

These aircraft fly themselves in a sort of superhuman way.

这些飞机以一种超人的方式自行飞行。

How fast they make adjustments, how fast they can self-diagnose, and handle faults, and still fly nicely...

它们调整的速度有多快，自我诊断和处理故障的速度有多快，并且仍然能很好地飞行......

Yeah, if you try to put a human in the loop of that, it would be extraordinarily hard to do.

是的，如果你试图让人类参与其中，那将是非常困难的。

**Adam Stacoviak:** I was actually just watching a video from Mark Rober, and it was a goalie.

**亚当·斯塔科维亚克：** 我实际上只是在观看马克·罗伯的视频，那是一名守门员。

It was an AI goalie, essentially.

本质上，它是一个人工智能守门员。

And I forget the soccer player's name, because I'm not a soccer fan to that level where I know the person's name, but I imagine it's probably like Messi, somebody who's super-famous.

我忘记了足球运动员的名字，因为我不是一个足球迷，我知道这个人的名字，但我想这可能就像梅西，一个超级有名的人。

And they were going against the goalie, and they could not beat the goalie, because the reaction time was just so uncanny, like how fast they could react.

他们对抗的是守门员，他们无法击败守门员，因为反应时间太不可思议了，就像他们的反应速度一样快。

And I take that kind of example, which is sort of a fun experiment, which Mark Rober is a scientist, and he's super-serious...

我举这样的例子，这是一个有趣的实验，马克·罗伯是一位科学家，而且他非常认真......

But at the same time, it's meant to be fun, and not really an experiment of seriousness on a large scale.

但与此同时，它的目的是为了好玩，而不是大规模的严肃实验。

**Adam Stacoviak:** And to what level your advancements may be well beyond that, to truly say what you said.

**Adam Stacoviak：** 你的进步可能会远远超出这个水平，才能真正说出你所说的话。

Because I'm sure there's a lot of people who say "You know, Keenan, I hear you saying that, but I still don't believe it..." Because they can't believe it until they see the truth of the superhuman ability to fly these aircrafts.

因为我确信有很多人会说“你知道，基南，我听到你这么说，但我仍然不相信......”因为他们无法相信，直到他们看到驾驶这些飞机的超人能力的真相。

I just think back to maybe the Mark Rober thing; that soccer goalie that was AI totally demolished the human, could not beat the AI goalie.

我只是回想起马克·罗伯的事；那个人工智能足球守门员完全摧毁了人类，无法击败人工智能守门员。

**Keenan Wyrobek:** Yeah.

**基南·维罗贝克：** 是的。

It is surreal to see these things handle the -- when I saw the first...

看到这些东西处理这些事情真是超现实——当我看到第一个……

I mean, all this fault tolerance we test extensively.

我的意思是，我们广泛测试了所有这些容错能力。

\[unintelligible 01:19:51.18\] one rotor fails, and the system handles it, and goes back and docks.

\[无法理解的01:19:51.18\]一个转子发生故障，系统会处理它，然后返回并停靠。

When that is working well, when you're watching it happen, if you don't know what happened, you won't even notice it.

当这一切运作良好时，当你看着它发生时，如果你不知道发生了什么，你甚至不会注意到它。

You have people with binoculars watching that thing, because the only way you're going to see it is if you actually see the propeller blade, that one probably stopped spinning.

人们用双筒望远镜观察那个东西，因为你看到它的唯一方法是如果你真的看到螺旋桨叶片，那个螺旋桨叶片可能停止旋转。

But the aircraft handles it so seamlessly, it barely moves.

但飞机处理得如此顺利，几乎没有移动。

And if it's windy at all, it doesn't move more than it does normally in the wind.

即使有风，它也不会比正常情况下在风中移动得更多。

This is one of the exciting things about autonomous systems, is they can get super-robust, which means we can operate and serve customers and deliver to patients and hospitals in all kinds of really crazy conditions.

这是自主系统令人兴奋的事情之一，它们可以变得超级强大，这意味着我们可以在各种非常疯狂的条件下操作和服务客户​​，并为患者和医院提供服务。

Again, the conditions that -- you know, flying low altitude in these storms, nobody does it.

再说一次，你知道，在这些风暴中低空飞行的条件，没有人这样做。

And when I say nobody, I didn't even realize this when we started Zipline.

当我说没有人时，当我们开始 Zipline 时我什至没有意识到这一点。

I thought like at least Medevac helicopters and this kind of things, the Coast Guard must do it...

我认为至少像医疗后送直升机之类的事情，海岸警卫队必须这样做......

And we ended up calling some of them, because we were struggling to figure this out...

我们最终给他们中的一些人打电话，因为我们正在努力解决这个问题......

And we're like "Cool, do you have any data?" And they were just like "No, we stopped flying those missions in the '70s.

我们就像“酷，你有数据吗？”他们就像“不，我们在 70 年代就停止执行这些任务了。

Way too many people died." And yeah, you can only do it if you use an autonomous system.

太多人死了。”是的，只有使用自治系统才能做到这一点。

And yeah, it's quite wild to see these systems perform, because they just -- they're so fast, and so superhuman.

是的，看到这些系统的表现真是太疯狂了，因为它们是如此之快，如此超人。

And then they can get these deliveries through these conditions that if you're on the road...

然后他们可以通过这些条件获得这些交付，如果你在路上......

Some of these conditions are so crazy if you're on a good road, you're kind of feeling like "I should not be on this road", but the drone is doing alright.

如果你在一条好的道路上，其中一些情况会非常疯狂，你会感觉“我不应该在这条路上”，但无人机表现得很好。

**Jerod Santo:** Yeah, I used to listen to the Bill Burr podcast quite a bit; I don't anymore, but he is a hobbyist, but a trained helicopter pilot.

**Jerod Santo：** 是的，我以前经常听 Bill Burr 播客；我不再这么想了，但他是一名业余爱好者，而且是一名训练有素的直升机飞行员。

And so he would chronicle some of his -- it's just him talking for an hour, so he needs a funny person to listen \[unintelligible 01:21:32.00\] so it's enjoyable.

所以他会记录他的一些内容——这只是他一个小时的讲话，所以他需要一个有趣的人来听\[难以理解的01:21:32.00\]所以这是令人愉快的。

But he would chronicle some of his efforts at just flying a helicopter...

但他会记录他在驾驶直升机方面所做的一些努力......

And I mentally understood that it was difficult, but hearing somebody try to learn it, and the maneuvers they're going through just to get down the basics of flying a helicopter...

我心里明白这很困难，但听到有人试图学习它，以及他们正在经历的演习只是为了掌握驾驶直升机的基础知识......

\[01:21:52.03\] It's so fraught and dangerous to fly helicopters in adverse conditions...

\[01:21:52.03\] 在不利的条件下驾驶直升机是非常令人担忧和危险的......

I mean, it's a death knell.

我的意思是，这是丧钟。

And we know that we've had famous people like Kobe Bryant dying in helicopter crashes, just because of fog, or because of bad systems.

我们知道，像科比·布莱恩特这样的名人在直升机失事中丧生，仅仅是因为大雾，或者是因为糟糕的系统。

And humans struggle, and have to have extreme training to be able to fly those things...

人类挣扎着，必须接受极限训练才能驾驶这些东西......

And computers can fly them so much better now, that it's like "Why even put a human behind the sticks?", so to speak.

计算机现在可以更好地驾驶它们，可以这么说，就像“为什么还要把人类放在棍子后面？”。

**Keenan Wyrobek:** Yeah, absolutely.

**基南·维罗贝克：** 是的，绝对如此。

And what our system can do literally in the blink of a human eye is the tech side handle almost everything that can go wrong, but faster than a human blinks.

我们的系统实际上可以在人眼眨眼之间完成的事情是技术方面处理几乎所有可能出错的事情，但比人眨眼的速度还要快。

And that's powerful for making autonomy scalable and safe.

这对于使自治具有可扩展性和安全性非常强大。

**Jerod Santo:** One last question for you, Keenan - what's your tech stack?

**Jerod Santo：** 最后一个问题，基南 - 你的技术堆栈是什么？

So if you were to describe -- I know you have lots of different tech...

所以，如果你要描述——我知道你有很多不同的技术……

If you were to pull out all the tools in your CTO tool belt - programming languages, frameworks...

如果您要拿出 CTO 工具带中的所有工具 - 编程语言、框架......

What's Zipline built on?

Zipline 是基于什么构建的？

**Keenan Wyrobek:** Right.

**基南·维罗贝克：** 对。

Yeah, I mean, for high-performance stuff in the cloud we go for -- almost everything on the aircraft is moving to Rust.

是的，我的意思是，对于我们追求的云中的高性能东西——几乎飞机上的所有东西都在转向 Rust。

There's various parts of the tech stack...

技术堆栈有各个部分......

Almost every part of the tech stack kind of has its own little world.

技术堆栈的几乎每个部分都有自己的小世界。

A lot of -- we've built our own in-house simulation system we call Phoenix.

很多——我们已经建立了自己的内部模拟系统，我们称之为 Phoenix。

That was how we do basically a lot of the simulation and testing.

这就是我们基本上进行大量模拟和测试的方式。

Boy, the tech stack is broad.

天哪，技术堆栈很广泛。

I worked a lot on ROS, the open source robotics platform back in the day, and everybody always asked me "Cool, you must run on ROS." And I'm like "Oh, man...

我在 ROS 这个开源机器人平台上做了很多工作，每个人总是问我“酷，你必须在 ROS 上运行。”我就像“哦，伙计......

No, we don't." If ROS 2 had come along early enough, we would have, but unfortunately we kind of went down that path before ROS 2 was ready for that.

不，我们不。”如果 ROS 2 出现得足够早，我们就会这么做，但不幸的是，在 ROS 2 准备好之前我们就走上了这条路。

Yeah, we use open source where we can; of course, we contribute to open source where we can.

是的，我们尽可能使用开源；当然，我们会尽我们所能为开源做出贡献。

I'm a big proponent of open source.

我是开源的坚定支持者。

One of the things we actually did on the tech stack, what we spent a lot of time on, is basically the future of autonomous flight.

我们在技术堆栈上实际做的事情之一，我们花了很多时间，基本上就是自主飞行的未来。

Even today in Dallas we share the airspace with some of these other drone operators we mentioned...

即使今天在达拉斯，我们也与我们提到的其他一些无人机操作员共享空域......

And I think of the -- no one really knows how autonomous flight's going to scale in the airspace...

我想到——没有人真正知道自主飞行将如何在空域扩展……

And I can tell you what we do today in the airspace is not going to scale.

我可以告诉你，我们今天在空域所做的事情不会规模化。

It barely works for the scale we have today, which is very low compared to where the future is going.

它对于我们今天的规模来说几乎不起作用，与未来的发展相比，这个规模非常低。

And there's a lot of need for folks in industry and Academia to like bring the best ideas to the table, make sure the best ideas win, so that we are both scalable in the airspace, and safe in the airspace as we scale.

工业界和学术界的人们非常需要将最好的想法带到桌面上，确保最好的想法获胜，这样我们既可以在空域中进行扩展，又可以在扩展时保证空域的安全。

So Zipline's working on a bunch of projects like that, that we have or intend to make open to the community, so we can kind of prove it internally as like "Hey, this is how our drones don't collide at scale with each other", and make those technologies available so everybody can share that.

因此，Zipline 正在开展一系列类似的项目，我们已经或打算向社区开放这些项目，这样我们就可以在内部证明这一点，就像“嘿，这就是我们的无人机不会大规模相互碰撞的原因”，并让这些技术可用，以便每个人都可以分享。

That's a big part of the tech stack that we think a lot about, because -- well, again, I just love the...

这是我们经常思考的技术堆栈的重要组成部分，因为——好吧，再说一次，我只是喜欢……

To me, the open source mindset comes from this thing of like "Hey, we're all in this together." And as I think about the future of the airspace, we're all in this together; it's going to be great for Zipline if all companies that need to use the airspace and all users of the airspace can use the airspace safely.

对我来说，开源思维来自于“嘿，我们都在一起”。当我思考空域的未来时，我们都在一起；如果所有需要使用该空域的公司和该空域的所有用户都能够安全地使用该空域，这对 Zipline 来说将是一件好事。

But the future of autonomous flight is still to be figured out, and we're spending a lot of time on that.

但自主飞行的未来仍有待弄清楚，我们在这方面花费了大量时间。

**Jerod Santo:** Do you see a world where there's some sort of open orchestration communication channel where you're not just detecting objects and avoiding them, but maybe you're actually publishing your future path, and so other systems can know, like, "There's zips going this way and that, and so I can avoid those paths"?

**Jerod Santo：** 你是否看到这样一个世界：存在某种开放的编排通信渠道，你不仅可以检测对象并避开它们，而且也许你实际上正在发布你的未来路径，这样其他系统就可以知道，比如“有拉链这样那样走，所以我可以避开这些路径”？

**Keenan Wyrobek:** Yeah, absolutely.

**基南·维罗贝克：** 是的，绝对如此。

So today there's a version of that that we use in Dallas.

今天我们在达拉斯使用了一个版本。

And it's not live, it's done before you take off.

而且这不是实时的，而是在您起飞之前完成的。

Basically, there's a federated cloud-based system where the different operators' systems talk to each other.

基本上，有一个基于云的联合系统，不同运营商的系统可以在其中相互通信。

And basically, it's very rudimentary today.

基本上，今天它还非常初级。

You can kind of think of it a little bit like a game of Battleship, of like "Okay, I'm trying to share my intended path in the air", sort of a tube in time, and I share it with the others and they're kind of like "Nope, that collides with something I've already reserved." And then you try to find another tube, and then it finds a tube, and then you're expected to stay in that tube about 95% of the time.

你可以把它想象成有点像战舰游戏，就像“好吧，我正在尝试分享我在空中的预期路径”，有点像时间管，我与其他人分享它，他们有点像“不，这与我已经保留的东西相撞”。然后你尝试找到另一个管子，然后它找到一个管子，然后你预计大约 95% 的时间都会留在那个管子里。

Not very scalable.

可扩展性不太好。

It's not a very efficient way to use the airspace, which is plentiful.

这并不是一种非常有效的利用空域的方式，因为空域资源丰富。

\[01:26:13.12\] Internally, our aircrafts share information live with each other over a point-to-point radio link, where they share their intent of "Where I'm going in the next 10 seconds" or so.

[01:26:13.12] 在内部，我们的飞机通过点对点无线电链路相互实时共享信息，共享“接下来 10 秒内我要去哪里”左右的意图。

And they do that also over the IP network.

他们还通过 IP 网络实现这一点。

I can't announce the partner yet, but there's a commercial drone operator in Dallas and we're going to be announcing a partnership later this year.

我还不能宣布合作伙伴，但达拉斯有一家商业无人机运营商，我们将在今年晚些时候宣布合作伙伴关系。

They'll be using that same protocol, so we can share the airspace without those big reservations.

他们将使用相同的协议，因此我们可以共享空域而无需进行大量保留。

And that's to kind of explore "Hey, is this more scalable?

这是为了探索“嘿，这更具可扩展性吗？

Alright, can we build up the data and then share it with the rest of the regulators and industry to kind of bring everybody along and make the case for what we think is a better idea than what we have today?" And then we'll move to that idea.

好吧，我们能否建立这些数据，然后与其他监管机构和行业分享，以吸引所有人，并证明我们认为比现在更好的想法？”然后我们将转向这个想法。

So yeah, I think what you're describing is going to be the beginning of where we go with this.

所以，是的，我认为你所描述的将是我们讨论这个问题的开始。

I think there's going to end up being a fair bit of structure, a lot of real-time sharing to make sure we use the airspace really efficiently, and scalably.

我认为最终将会有相当多的结构和大量的实时共享，以确保我们真正有效且可扩展地使用空域。

**Adam Stacoviak:** It's like a DNS in the cloud, basically; in the sky, literally the clouds...

**Adam Stacoviak：** 基本上，它就像云中的 DNS；天空中，顾名思义，就是云朵……

Pluralized, not the internet cloud as we know it.

复数，而不是我们所知的互联网云。

But it's kind of like that; it's like a phone system, in a way, or a route system, or a flight path you now have to have predefined or known things.

但它有点像那样；在某种程度上，它就像一个电话系统，或者一个路线系统，或者一个飞行路径，你现在必须有预定义或已知的东西。

It's like "Well, we have these coordinates, and we know where we're at in the world", so maybe they're logistically like that, or something like that.

就像“嗯，我们有这些坐标，我们知道我们在世界上的哪个位置”，所以也许它们在逻辑上是这样的，或者类似的东西。

**Keenan Wyrobek:** Exactly.

**基南·维罗贝克：** 没错。

Yeah, we spent a lot of time talking to the original folks who created ICANN, which created the DNS system, to like "How did that actually come to be?" Because in some ways it's kind of a miracle, how open the internet is, and how it evolves...

是的，我们花了很多时间与创建 ICANN（即 DNS 系统）的最初创建者交谈，以了解“这实际上是如何实现的？”因为从某些方面来说，这有点像一个奇迹，互联网是多么开放，以及它是如何演变的......

**Keenan Wyrobek:** And it's like "Alright, cool.

**Keenan Wyrobek：** 就像“好吧，酷。

We want to learn all the lessons from that", because we really want the future of the airspace to be similarly democratized and open and innovative and evolving.

我们希望从中吸取所有教训”，因为我们确实希望空域的未来也能同样民主化、开放、创新和发展。

**Adam Stacoviak:** Right.

**亚当·斯塔科维亚克：** 对。

So you're studying DNS to learn how to do things in the sky?

所以你学习 DNS 是为了了解如何在空中做事？

**Keenan Wyrobek:** And not just the technical layer of DNS, but also like -- if you've heard of ICANN, the international...

**Keenan Wyrobek：** 不仅是 DNS 的技术层，而且还包括——如果您听说过 ICANN，这个国际组织……

It's a corporation of names and numbers, I think.

我认为这是一个由名称和数字组成的公司。

Anyway, it's basically the people behind sort of the internet, that agree internationally of how it's going to work.

不管怎样，基本上是互联网背后的人们在国际上就互联网的运作方式达成了一致。

They figured out how to be a group of people that doesn't make bad decisions, you know?

他们想出了如何成为一群不会做出错误决定的人，你知道吗？

And we want to learn from that as well, because I can see -- if you don't get the right incentives and the right people and the right mindset, and the right kind of structure, I think it's really clear how this kind of gets stuck in gridlock, and doesn't evolve and innovate.

我们也想从中学习，因为我可以看到，如果你没有得到正确的激励、正确的人员、正确的心态以及正确的结构，我认为很明显这种情况会陷入僵局，并且无法发展和创新。

**Jerod Santo:** Right.

**杰罗德·桑托：** 对。

So when you operate on a 2D plane, everybody gets one place.

因此，当您在 2D 平面上操作时，每个人都占据一席之地。

So like my house address leads to one place.

就像我的家庭地址通向一个地方一样。

Now, there's many paths to that place, so you can alternate routes, and that's all well and good.

现在，有很多条路可以到达那个地方，所以你可以替换路线，这一切都很好。

But on a 3D plane, if you have conflicting paths, how feasible is it to just change the Z axis and say "Well, we're going to fly five feet lower than we were going to, and now we just completely have free airspace"?

但在 3D 平面上，如果路径相互冲突，仅更改 Z 轴并说“好吧，我们将比预期飞行低 5 英尺，现在我们完全拥有自由空域”，这有多可行？

Is that like foolish thought, or is that legit thought...?

这是愚蠢的想法，还是合法的想法……？

**Keenan Wyrobek:** \[01:29:03.02\] No, that's exactly how our drones don't hit each other.

**Keenan Wyrobek：** \[01:29:03.02\] 不，这正是我们的无人机不会互相撞击的原因。

**Jerod Santo:** Okay.

**杰罗德·桑托：** 好的。

So they're just like "Well, I'll go up or down a little bit."

所以他们就像“好吧，我会向上或向下一点。”

**Keenan Wyrobek:** Exactly.

**基南·维罗贝克：** 没错。

There's a distributed algorithm, they share their 10 seconds out intent with each other, and there's a distributed algorithm based on what they hear from the people around them, that they'll adjust their course in a way where you get an emergent behavior you're talking about, of like "Okay, great--" You end up with that nice passage, and very efficiently and dynamically.

有一个分布式算法，他们互相分享 10 秒的意图，还有一个基于他们从周围人那里听到的信息的分布式算法，他们会以一种方式调整他们的路线，让你得到你正在谈论的紧急行为，比如“好吧，太棒了——”你最终会得到那个漂亮的段落，而且非常高效和动态。

Yeah.

是的。

I think you're describing exactly how this needs to happen.

我认为你正在准确地描述这需要如何发生。

But the challenge is it has to happen in a very robust way.

但挑战在于它必须以非常稳健的方式发生。

It can't be like "Oh, if you can reach a server on the cloud, and your cell connection is working, and the server's working, and everybody's talking at the same time, and there's some central orchestration that doesn't have a problem, then it works..." We have a lot of experience to learn the hard way that you just can't scale that way.

它不能是这样的：“哦，如果你可以连接到云上的服务器，并且你的单元连接正在工作，服务器正在工作，每个人都在同时说话，并且有一些中央编排没有问题，那么它就可以工作......”我们有很多经验来了解你无法以这种方式扩展的困难。

It's gotta be simpler, and the aircrafts themselves have to have many layers that they can do without any radio connections to things that will still give you layers of safety.

它必须更简单，而且飞机本身必须有很多层，它们可以在没有任何无线电连接的情况下完成，但仍然可以为您提供安全层。

That's really important.

这真的很重要。

**Jerod Santo:** When you bring up layers, it makes me think "Is there an advantage in formalizing around some kind of layering, vertical layering of lanes, so to speak?" ...so you're not just having the emergent behavior of height, but you're actually pre-planning like "Well, I fly at this altitude, and this other company always flies at that, and so we're pretty much cool."

**杰罗德·桑托：**当你提出分层时，这让我想到“可以这么说，围绕某种分层、垂直分层的车道进行形式化是否有优势？” ...所以你不仅仅是有高度的紧急行为，而且你实际上是预先计划的，比如“嗯，我在这个高度飞行，而另一家公司总是在那个高度飞行，所以我们非常酷。”

**Keenan Wyrobek:** I think that'll happen.

**Keenan Wyrobek：** 我认为这会发生。

And I think it'll be more than vertical.

我认为这将不仅仅是垂直的。

I think it'll be more like sort of highways or lanes.

我认为它更像是高速公路或小巷。

And the reason -- there's a lot of things we do to optimize for safety, but one thing you'll do is you'll avoid certain areas.

原因是——我们做了很多事情来优化安全性，但你要做的一件事就是避开某些区域。

The classic example is a stadium.

典型的例子是体育场。

If there's a game happening, you're just not going to fly over that stadium, because why would you?

如果有比赛正在进行，你就不会飞越那个体育场，因为你为什么要飞呢？

It's not that you're going to have to parachute landing there, but you might, statistically speaking...

这并不是说你必须跳伞降落在那里，但从统计学上来说，你可能......

And flying around it, statistically speaking, is going to be safer.

从统计角度来看，围绕它飞行将会更加安全。

**Keenan Wyrobek:** Yeah.

**基南·维罗贝克：** 是的。

Exactly.

确切地。

So everybody in the air is avoiding similar things, and so you'll end up with this congestion, kind of going around these keepouts, or these soft keepouts, as we call them...

所以空中的每个人都在避免类似的事情，所以你最终会遇到这种拥堵，有点绕过这些禁区，或者这些软禁区，正如我们所说的那样......

And sometimes hard keep outs.

有时很难排除。

So there's certain government places where the government is like "You cannot fly over this area.

因此，在某些政府场所，政府会说“你不能飞越这个区域。

We consider that to be something you can't fly over." So these hard keepouts and soft keepouts end up funneling their traffic into these places, where I think you'll have -- in the early days, vertical separation might be enough, but in the long term, it may be like "Yeah, if you're going this way, stay to the right, and up high.

我们认为这是你无法飞越的地方。”因此，这些硬禁区和软禁区最终将他们的交通集中到这些地方，我认为在早期，垂直隔离可能就足够了，但从长远来看，可能会像“是的，如果你要走这条路，请靠右边，在高处。

And if you're going the other way, stay down low and to the left." And you end up with literal kind of corridors that create more and more efficiency, especially when you have these kinds of forced congestions.

如果你要走另一条路，请保持低位并靠左。”最终你会得到真正的走廊，它会创造越来越多的效率，特别是当你遇到这种被迫拥堵的情况时。

So there's a lot of cool things that are going to be needed to really scale.

因此，要真正实现规模化，需要很多很酷的东西。

**Jerod Santo:** That's so cool.

**杰罗德·桑托：** 那太酷了。

So cool.

太酷了。

Well, we've taken enough of your time...

好吧，我们已经花了你足够的时间了......

We appreciate you answering all of our questions.

我们感谢您回答我们所有的问题。

**Jerod Santo:** I think this is one of the coolest things there is.

**Jerod Santo：** 我认为这是最酷的事情之一。

I'm both happy with you, and jealous of you that you get to work on Zipline all the time, because I just feel like there's so many hard problems, there's so much benefit on the other side of it...

我对你感到很高兴，也很嫉妒你一直在 Zipline 上工作，因为我觉得有很多难题，但另一方面也有很多好处......

And so congrats, and good luck, I guess, on scaling out/up.

所以恭喜你，祝你好运，我想，在扩展/扩展方面。

**Keenan Wyrobek:** Thank you.

**基南·维罗贝克：** 谢谢。

It's a fun place to work.

这是一个有趣的工作场所。

Just yesterday I came to work a bit earlier, I was on a call in my car, and I was watching everybody walk into the office and everybody kind of has like a skip in their step...

就在昨天，我提前上班了，我在车里打电话，我看着每个人走进办公室，每个人的脚步都有点跳跃……

And I was just like -- anyway, just reminding myself how lucky I am to work in a place that's like that, where people are fun, the culture is fun, and the technical challenges are real, the customer challenges are real...

我当时想——无论如何，我只是提醒自己，能在这样一个地方工作是多么幸运，这里的人们很有趣，文化很有趣，技术挑战是真实的，客户挑战也是真实的……

Yeah, and everybody's skipping to work.

是的，每个人都逃课去上班。

It's like a good sign that life is good.

这就像一个好兆头，表明生活是美好的。

So...

所以...

I'm feeling lucky.

我感觉很幸运。

**Keenan Wyrobek:** Yeah.

**基南·维罗贝克：** 是的。

Great to talk with both of you, too.

很高兴与你们俩交谈。

I really enjoyed this conversation.

我真的很喜欢这次谈话。