You could help scientists learn more about the Red Planet.

By Stacey Leasca
June 24, 2020
Advertisement
NASA/JPL-CALTECH/MSSS / HANDOUT/Anadolu Agency/Getty Images

NASA’s Curiosity Rover has been exploring Mars since 2012. Since then, it’s helped us learn a great deal about our neighboring planet thanks to some extremely high-tech work by extremely smart scientists. But now, those same scientists are calling on people like you and me to help Curiosity’s work go even further.

As Space.com reported, researchers are now asking the public to assist Curiosity in learning about its surroundings on Mars using an open online tool called AI4Mars, hosted on Zooniverse.

The tool allows users to label the terrain surrounding Curiosity, which further assists the rover in learning about its environment so it can avoid any sharp objects, divots, or potholes that could derail the mission.

“We need YOUR help to make future Mars rovers safer,” Zooniverse explained on its website. “You’ll be using your superior cognitive and artistic abilities to label images from the Curiosity Rover, collectively creating the first open-source navigation-classification dataset of the Red Planet.”

Zooniverse added, the information you provide will be used by NASA teams to train all the rovers to understand Martian environments for future missions.

Specifically, this volunteer exercise may be important for the Curiosity Rover as its wheels are getting rather worn down after years of exploration and driving over objects it probably should have avoided.

"Typically, hundreds of thousands of examples are needed to train a deep learning algorithm,” Hiro Ono, an AI researcher at NASA’s Jet Propulsion Laboratory, said in a statement. "Algorithms for self-driving cars, for example, are trained with numerous images of roads, signs, traffic lights, pedestrians, and other vehicles. Other public datasets for deep learning contain people, animals, and buildings - but no Martian landscapes."

Ono added, in the future, the team is hoping all the volunteer help on the algorithm can help rovers “become accurate enough to do other useful tasks, like predicting how likely a rover's wheels are to slip on different surfaces,"

To date, more than 2,600 volunteers have signed up to help classify more than 122,000 objects. Check back regularly on the Zooniverse website for updated materials and volunteer needs.