AI News, AI Learns to Guide Planetary Rovers Without GPS

AI Learns to Guide Planetary Rovers Without GPS

Instead, the robotic explorermust take panoramic pictures of the surrounding landscape so that a human back on Earth can painstakingly compare the groundimages with Mars satellite maps taken from above by orbiting spacecraft.

But the lack of similar GPS satellites orbiting the moon orMarsmeans that robotic or human missions to those destinationsmust rely on a process not unlike a person trying to read a map and visually eyeball the surrounding landscape.

The team initially wanted tomake their own virtual moon based on the real thingusingelevation maps of the moon created by past lunar orbiter missions, Wu explained.

During the training process, the team took pictures facing north, south, east, and west from specific lunar surface locations within the synthetic moon simulation.

Those four images were then combined and reprojected to create a crude top-down view similar to a satellite’s viewpoint from above—a process that transformed2.4 million ground images into approximately 600,000 reprojected images.

That set the stage for training the deep-learning algorithm to recognize certain synthetic lunar surface features and match them against locations on an orbital map of the moon simulation.

On the left, four ground-view camera images taken from the moon's simulated surface are reprocessed as a top-down aerial reprojection view of the lunar landscape.

On the right, a deep-learning algorithm uses moon satellite maps to come up with the five best candidate locations matching the aerial reprojection view.

“I don’t think using the virtual moon makes as much of a difference for the final solution,”saysPhilippe Ludivig, a computer scientist member of the FDL team and a researcher at a Japanesestartup called iSpace.“Essentially what we trained the deep-learning neural network to do was compare source images on the groundwith satellite images.” One possible next step could involve training a deep neural network from scratch specifically for the moon or Mars landscape detection task.

Using AI to Discover the Moon’s Hidden Treasures

With the help of artificial intelligence, NASA’s Frontier Development Lab and Intel are mapping the moon’s craters to find hidden lunar resources.

Craters in the permanently shadowed polar regions of the moon are potentially filled with water, ice and other volatile resources that can be used to produce rocket fuel, an air supply for astronauts or other essential materials, according to Jain.

Crews on long exploratory missions to outer space can’t carry all the resources they need, so finding things like water, hydrogen, carbon dioxide, nitrogen and methane may help NASA plan future missions to the moon or even to Mars.

Whereas machine learning allows machines to act or think without being explicitly directed to perform specific functions, deep learning can accelerate processes like image recognition, quickly identifying and mapping craters and other obstacles on the moon.

It took Jain six hours to manually find images containing a crater — but fully mapping the moon means looking at hundreds of millions of images.

Since lunar craters acted as critical registration points to align the two datasets into one unified map, the team developed a computer vision algorithm to quickly and reliably identify craters.

Other teams tackled planetary defense and space weather challenges, like long period comets, radar 3D shape modeling, solar-terrestrial interactions and solar storm prediction.

FDL 2017 AI Lunar Crater Detector

For information on how to train your own lunar crater algorithm, go to Intel partnered with the NASA Frontier Lab Development team to ..

NASA@60: The Role of the Robots

Original air date: Thursday, Sept. 6 at 7 p.m. PT (10 p.m. ET, 0200 UTC) As NASA celebrates its 60th anniversary, this panel discussion will look back over the ...

What AI is -- and isn't | Sebastian Thrun and Chris Anderson

Educator and entrepreneur Sebastian Thrun wants us to use AI to free humanity of repetitive work and unleash our creativity. In an inspiring, informative ...

Blue Planet II : The Prequel

New David Attenborough series Dynasties coming soon! Watch the first trailer here: --~-- This world-exclusive ..

Jason Dunn - The Future of Making Things in Space

NASA Ames 2016 Summer Series. Manufacturing of tools is why humans survive. Jason Dunn discusses Made In Space's achievements in bringing 3D printers ...

Imagining the Extraordinary: The Inspired

In a symposium on scientific illustration from the Renaissance to the digital age, historians specializing in the scientific illustrations of the Renaissance with ...

Rethinking the Rules of Reality

Keith R. Dienes Professor of Physics University of Arizona and Program Director, Physics National Science Foundation In this series kickoff lecture, we take a ...

Neal Stephenson & Friends: "Hieroglyph" | Talks at Google

Neal Stephenson, Ed Finn, Keith Hjelmstad, Kathryn Cramer, Rudy Rucker, & Annalee Newitz came to Google to talk about project Hieroglyph. Inspiration is a ...

Seattle Conference on Scalability

Google Tech Talks June, 23 2007 ABSTRACT Seattle Conference on Scalability: June 23, 2007 We care a lot about scalability at Google. An algorithm that ...

RubyConf 2017: Orbital Rocket Guidance with Ruby by Nate Berkopec

Orbital Rocket Guidance with Ruby by Nate Berkopec Using the popular space simulator Kerbal Space Program and some remote procedure calls, we're going ...