You can help teach NASA rovers to explore Mars with the AI4Mars project

By Georgina Torbet October 30, 2021

Artificial intelligence could be a huge help to Mars rovers like NASA’s Curiosity or Perseverance, but first these A.I. systems need to be trained on what to look for. A NASA project invites members of the public to help identify features of the Martian landscape, in order to train an algorithm that future rovers could use to navigate around the red planet.

The robotic arm of NASA’s Perseverance rover is visible in this image used by the AI4Mars project. — The robotic arm of NASA’s Perseverance rover is visible in this image used by the AI4Mars project. Users outline and identify different rock and landscape features to help train an artificial intelligence algorithm that will help improve the capabilities of Mars rovers. NASA/JPL-Caltech

The AI4Mars project was launched last year, and users have already labeled nearly half a million images to help develop the Soil Property and Object Classification (SPOC) algorithm. This algorithm identifies features of the landscape like sand and rock, and does so correctly nearly 98% of the time. In the future, this algorithm could be incorporated into Mars rovers’ autonomous driving capabilities like the AutoNav technology used by Perseverance.

Recommended Videos

Now, the researchers want to expand SPOC to get more detailed information about rock formations such as the presence of float rocks or nodules. By automatically classifying the types of rock imaged by rovers, the researchers can send driving instructions back to the rovers more quickly.

“It’s not possible for any one scientist to look at all the downlinked images with scrutiny in such a short amount of time, every single day,” explained Vivian Sun, a JPL scientist who helps coordinate Perseverance’s daily operations and consulted on the AI4Mars project. “It would save us time if there was an algorithm that could say, ‘I think I saw rock veins or nodules over here,’ and then the science team can look at those areas with more detail.”

To help develop this algorithm, NASA is inviting members of the public to go to the AI4Mars page on Zooniverse and look at images of the Martian surface captured by the Curiosity rover. They are asked to draw polygons around particular features like sand, soil, bedrock, and large rocks. The results of thousands of classifications made by the public are then collated and checked by scientists to make sure that the labeling is accurate.

Over time, as more individual pieces of data are labeled, the algorithm can learn to distinguish features for itself.

“Machine learning is very different from normal software,” said lead researcher for the AI4Mars project, Hiro Ono. “This isn’t like making something from scratch. Think of it as starting with a new brain. More of the effort here is getting a good dataset to teach that brain and massaging the data so it will be better learned.”

Topics

Georgina Torbet

Space Writer

Georgina has been the space writer at Digital Trends space writer for six years, covering human space exploration, planetary…

Space

NASA selects 9 companies to work on low-cost Mars projects

This mosaic is made up of more than 100 images captured by NASA’s Viking 1 orbiter, which operated around Mars from 1976 to 1980. The scar across the center of the planet is the vast Valles Marineris canyon system.

NASA is expanding its plans for Mars, looking at not only a big, high-budget, long-term project to bring back a sample from Mars but also smaller, lower-cost missions to enable exploration of the red planet. The agency recently announced it has selected nine private companies that will perform a total of 12 studies into small-scale projects for enabling Mars science.

The companies include big names in aerospace like Lockheed Martin and United Launch Services, but also smaller companies like Redwire Space and Astrobotic, which recently landed on the surface of the moon. Each project will get a 12-week study to be completed this summer, with NASA looking at the results to see if it will incorporate any of the ideas into its future Mars exploration plans.

Space

NASA video maps all 72 flights taken by Mars Ingenuity helicopter

NASA's Ingenuity helicopter.

See Ingenuity’s Flight Map: 72 Helicopter Flights on Mars

NASA has shared a video (above) that maps all of the flights taken on Mars by its trailblazing Ingenuity helicopter.

Space

NASA needs a new approach for its challenging Mars Sample Return mission

An illustration of NASA's Sample Return Lander shows it tossing a rocket in the air like a toy from the surface of Mars.

NASA has shared an update on its beleaguered Mars Sample Return mission, admitting that its previous plan was too ambitious and announcing that it will now be looking for new ideas to make the mission happen. The idea is to send a mission to collect samples from the surface of Mars and return them to Earth for study. It's been a long-term goal of planetary science researchers, but one that is proving costly and difficult to put into practice.

The Perseverance rover has already collected and sealed a number of samples of Mars rock as it journeys around the Jezero Crater, and has left these samples in a sample cache ready to be collected. However, getting them back to Earth in the previous plan required sending a vehicle to Mars, getting it to land on the surface, sending out another rover to collect the samples and bring them back, launching a rocket from the planet's surface (something which has never been done before), and then having this rocket rendezvous with another spacecraft to carry them back to Earth. That level of complexity was just too much to be feasible within a reasonable budget, NASA Administrator Bill Nelson announced this week.