Emerging Technologies

NASA is making a GPS for space - using AI

A photo taken by NASA astronaut Randy Bresnik from the International Space Station on August 3, 2017. From his vantage point in low Earth orbit Bresnik pointed his camera toward the rising Moon. Looking forward to the August 21 total solar eclipse, Bresnik wrote, "Gorgeous moon rise! Such great detail when seen from space. Next full moon marks #Eclipse2017. We’ll be watching from @Space_Station."   NASA/Handout via REUTERS    ATTENTION EDITORS - THIS IMAGE WAS PROVIDED BY A THIRD PARTY

The researchers built a virtual moon. Image: REUTERS

Kristin Houser
Writer, Futurism

Off-world navigation.

Today, all you have to do to find your way around a new city is fire up Google Maps, Waze, or one of the many other GPS-based navigation apps available. Follow the steps, and, bam, you get where you need to go.

We don’t have that same luxury in space. But now, researchers from NASA’s Frontier Development Lab (FDL) and Intel are working to change that. They’ve found a way to make it just as easy to navigate a new planet — they just needed a little help from artificial intelligence (AI) to do it.

They presented their planetary navigation research during an Intel-hosted event on August 16.

Image: Statista

Non-global GPS.

GPS stands for “global positioning system,” and it’s just that: global. The satellites that let the system know your location so your app can give you directions to that new restaurant don’t work when you’re not on Earth.

Since positioning a similar system of satellites around every moon or planet we’d like to explore would be really difficult and expensive, NASA and Intel set out to create a different kind of planetary navigation system.

If we could feed an AI enough pictures of the surface of a celestial body, they determined, a person could simply take a photo of their surroundings and the system would be able to figure out where they were and give them directions to the place they wanted to be.

From the moon to Mars.

To see if this kind of system could work, the researchers built a virtual moon.

“[F]or our approach, using the real Moon isn’t actually critical,” researcher Andy Chung told Futurism. “It would likely improve performance in a real mission, but a key point of our work is that it teaches a network to learn general distortions caused by general landscape topologies.”

To construct this moon, the team first created 2.4 million images of its surface that were taken by a rover (or, at least would have been if the planet had been real). They fed the images captured by these hypothetical cameras to their AI, which put them together to create the virtual moon.

Have you read?

According to the team’s presentation, this was enough to effectively enable navigation on the virtual moon’s surface.

Next, they want to try to do the same thing with a real (not virtual) celestial body: Mars. They think they have enough satellite images to make it happen. If they’re right, the first people to walk on the Red Planet could find that all they have to do to navigate around the Martian surface is just take a picture.

Don't miss any update on this topic

Create a free account and access your personalized content collection with our latest publications and analyses.

Sign up for free

License and Republishing

World Economic Forum articles may be republished in accordance with the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Public License, and in accordance with our Terms of Use.

The views expressed in this article are those of the author alone and not the World Economic Forum.

Stay up to date:

United States

Share:
The Big Picture
Explore and monitor how United States is affecting economies, industries and global issues
World Economic Forum logo

Forum Stories newsletter

Bringing you weekly curated insights and analysis on the global issues that matter.

Subscribe today

Here’s why it’s important to build long-term cryptographic resilience

Michele Mosca and Donna Dodson

December 20, 2024

How digital platforms and AI are empowering individual investors

About us

Engage with us

  • Sign in
  • Partner with us
  • Become a member
  • Sign up for our press releases
  • Subscribe to our newsletters
  • Contact us

Quick links

Language editions

Privacy Policy & Terms of Service

Sitemap

© 2024 World Economic Forum