By Ron Schmelzer

罗恩·施梅泽(Ron Schmelzer)

Humanity is putting its mark throughout the world, and now on other worlds and planets as well. For the past many decades, humans have sent spacecraft, rovers, and machines to planets near and far, so it should come as little surprise that AI is becoming an increasing part of these remote systems. After all, if it can take hours or even days for communication and commands to be sent to and from devices sitting on other planets, so imbuing these systems with intelligent and autonomous capabilities to operate in the harsh environments of outer space and on planetary or rocky bodies makes a lot of sense.

人类在世界各地以及现在在其他世界和星球上都在树立自己的烙印。 在过去的几十年中，人类已经将航天器，漫游器和机器发送到了近或远的行星，因此AI成为这些远程系统中越来越重要的一部分也就不足为奇了。 毕竟，如果要花费数小时甚至几天的时间才能将通信和命令发送到其他行星上的设备或从其他行星上的设备发送命令，那么使这些系统具有智能和自主的功能，可以在恶劣的外太空环境以及行星或岩石环境中运行身体很有道理。

At the Amazon re:MARS conference in 2019, Tom Soderstrom, IT Chief Technology and Innovation Officer at NASA Jet Propulsion Laboratory shared his insights into how AI is increasingly being used by these remote devices and some insights into how the technology is being applied for space and planetary exploration. Mr. Soderstrom’s role at NASA is to plan for future missions and strategize based on where technology is heading.

在2019年的亚马逊re：MARS会议上， 美国宇航局喷气推进实验室IT首席技术和创新官Tom Soderstrom分享了他对这些远程设备如何越来越使用AI的见解以及对如何将该技术应用于太空的一些见解和行星探索。 Soderstrom先生在NASA的职责是计划未来的任务，并根据技术发展方向制定战略。

“We have created a sort of innovation experience center where we go into the room to experience the future in the current time,” said Mr. Soderstrom. “The purpose of this is to better understand which technologies are ready to be used, while filtering out which are worth pursuing to benefit JPL, NASA, and the enterprise.”

索德斯特罗姆先生说：“我们已经建立了一个创新体验中心，我们可以进入会议室体验当前的未来。” “这样做的目的是更好地了解准备使用哪些技术，同时过滤掉那些值得使JPL，NASA和企业受益的技术。”

In his talk at re:MARS, Mr. Soderstrom talked about “democratizing MARS”, referring to machine learning, automation, robotics, and space. Democratizing refers to using technology waves making it available to people. According to Soderstrom, this means to “make algorithms and data available for future explorers to stand on the shoulders of giants, not in decades or years, but now.”

在re：MARS的演讲中，Soderstrom先生谈到了“使MARS民主化”，涉及机器学习，自动化，机器人技术和太空。 民主化是指利用技术浪潮使之可供人们使用。 根据Soderstrom的说法，这意味着“要使算法和数据可供未来的勘探者站在巨人的肩膀上，而不是几十年或几年，而要到现在。”

As for AI specifically, the JPL is applying many aspects of the Seven Patterns of AI to the robots, rovers, and probes heading to distant planets. All these remotely-operated systems are using aspects of AI-enhanced computer vision to give greater insights into the images that the systems capture. They are also making use of various aspects of autonomous systems and control, using machine learning to help these systems deal more adaptively to changes. Machine learning-powered pattern and anomaly recognition is key to both space-bound and earth-bound systems to give better insights to all the data flowing back and forth between the various devices and systems. AI-enabled predictive analytics and predictive maintenance is likewise incredibly crucial to performance of systems that need to operate for years or decades with no ability for humans to service those systems.

特别是对于AI，JPL正在将AI的七种模式的许多方面应用于机器人，漫游者和前往遥远星球的探测器。 所有这些远程操作系统都使用AI增强的计算机视觉的各个方面来提供对系统捕获的图像的更深入的了解。 他们还利用自治系统和控制的各个方面，通过机器学习来帮助这些系统更适应变化。 机器学习驱动的模式和异常识别对于空间受限和对地受限的系统都是至关重要的，以便更好地洞察各种设备和系统之间来回流动的所有数据。 启用AI的预测分析和预测维护对于需要运行数年或数十年而人类无法为这些系统服务的系统的性能同样至关重要。

“Today we use satellites surrounding earth and in deep space, but say we want to know if something is about to go wrong,” states Mr. Soderstrom. “So, we use machine learning and we use the data from previous orbits or tracks and use current data to determine if things are going wrong through machine learning algorithms.”

索德斯特伦先生说：“今天，我们使用环绕地球和深空的卫星，但我们想知道是否会出问题。” “因此，我们使用机器学习，并使用先前轨道或轨道的数据，并使用当前数据来确定机器学习算法是否出了问题。”

The results are then visualized for people, so everyone stays updated. “Rather than calling it artificial intelligence, we call it intelligence assistance. Not only have we found the anomalies people have discovered, but also some that people have not yet found.”

然后将结果可视化，从而使每个人都保持最新状态。 “我们将其称为智能协助，而不是将其称为人工智能。 我们不仅发现了人们已经发现的异常现象，而且还发现了人们尚未发现的异常现象。”

Mr. Soderstrom shared another example about predictive maintenance. He explained, “When thinking about what NASA and JPL actually does, tracking space craft throughout our solar system, even beyond. To do this, because the earth is rotating, it requires antenna farms that have the ability to connect and communicate with the spacecraft no matter where it is. For instance, with Voyager it takes nearly 40 hours to send a signal there and back, so one antenna would send the signal, and another would receive it.”

索德斯特伦先生分享了另一个有关预测性维护的例子。 他解释说：“在思考NASA和JPL的实际作用时，请跟踪整个太阳系中甚至更远处的航天器。 为此，由于地球在自转，因此需要天线农场，无论其身在何处，它们都必须具有与航天器连接和通信的能力。 例如，使用Voyager，在该处往返发送信号要花费近40个小时，因此，一根天线可以发送信号，而另一根天线可以接收。”

Like with any piece of equipment, antennas require a lot of maintenance. So, AI is currently being used to help predict if and when maintenance is required, what parts may be about to go bad and needs repaired or replaced. According to Soderstrom, this allows them to switch antennas, then take an antenna offline for repairs without losing connection. Furthermore, he explained “this can be democratized to trains, cars, planes, etc. as we can learn from their methods as well to improve our machine learning.”

与任何设备一样，天线也需要大量维护。 因此，AI目前正用于帮助预测是否以及何时需要维护，哪些零件可能会变质并且需要维修或更换。 根据Soderstrom的说法，这使他们可以切换天线，然后将天线脱机进行维修，而不会失去连接。 此外，他解释说：“这可以民主化用于火车，汽车，飞机等，因为我们可以从它们的方法中学习，也可以改善我们的机器学习。”

Besides using AI to control the various systems on earth and in space, AI is being used to help provide more insight into the data and images that these systems are capturing. According to Mr Soderstrom, “Let’s begin with right here at home. There are many things happening at home and what we do at JPL and NASA is to look at earth from space. This provides a very different perspective. There are many satellites orbiting earth, taking around 90 minutes to orbit the whole planet. One use case example of AI is detecting forest fires.”

除了使用AI控制地球和太空中的各种系统外，AI还用于帮助提供对这些系统正在捕获的数据和图像的更多见解。 索德斯特伦先生说：“让我们从这里开始。 家里有很多事情发生，我们在JPL和NASA所做的就是从太空看地球。 这提供了非常不同的观点。 有许多卫星绕地球旋转，大约需要90分钟才能绕地球旋转。 AI的一个使用案例是检测森林大火。”

Therefore, thanks to AI-enabled satellites, imaging systems are capable of detecting smoke clouds, automatically triggering another satellite to zoom in closer for verification, location and alerting the local fire department, according to Soderstrom. This is just one way autonomous satellites work on our behalf. Another example he shared would be using satellites we’ve sent out to help us study water and ice patterns, so we can do machine learning on this and let people work with real data.

因此，得益于支持AI的卫星，成像系统能够检测烟雾云，自动触发另一颗卫星以拉近距离以进行验证，定位并向当地消防部门发出警报。 这只是自主卫星代表我们工作的一种方式。 他分享的另一个示例是使用我们发送的卫星来帮助我们研究水和冰的模式，因此我们可以对此进行机器学习，并让人们使用真实数据。

As for the future of AI, Mr. Soderstrom is very positive. “I think we have had a lot of AI winters, but we’re due for an AI summer. I think there are a lot of good things coming. If we look at the six technology waves coming, one is applied AI, which fits the theme of democratizing MARS. Applied AI, among other waves, all combine to what we call embedded AI everywhere. Essentially, this would result in a personal assistant no matter where you are. This could be from a smartphone, smart watch, or other product.”

对于AI的未来，Soderstrom先生非常乐观。 “我认为我们经历了很多AI冬季 ，但是我们应该在AI夏季来临。 我认为会有很多美好的事物来临。 如果我们看一下即将到来的六种技术浪潮，其中一种就是应用的AI，这正符合使MARS民主化的主题。 在其他浪潮中，应用AI到处都与我们所说的嵌入式AI相结合。 本质上，无论您身在何处，这都将导致您成为私人助理。 这可能来自智能手机，智能手表或其他产品。”

Indeed, the quest for space exploration has resulted in many products we use today such as Kevlar, Velcro, baby formula, and even safety glass. As we continue to push forward with our quest to explore space, AI will play an increasing role in this and help both in space and back here on Earth as well.

确实，对太空探索的追求导致了我们今天使用的许多产品，例如凯夫拉尔，维可牢尼龙搭扣，婴儿配方奶粉，甚至是安全玻璃。 随着我们继续探索太空的努力，人工智能将在其中发挥越来越重要的作用，并在太空和地球上都将提供帮助。

Follow me on Twitter or LinkedIn. Check out my website or some of my other work here.

在 Twitter 或 LinkedIn 上关注我 。 看看我 的网站 或我的一些其他的工作 在这里 。