The simulation, created by a group at NASAs Jet Propulsion Laboratory, asks users to assist categorize Martian surface. Youll identify images taken by Curiosity from Mars surface (as sand or bedrock, for example), and researchers will use the crowdsourced information to train a future rover to much better browse around harmful obstacles.
Mars rovers tend to get stuck in the sand– and sometimes arent able to get themselves out– so the task intends to make rovers like self-driving cars. In order to check out area without a human crew, the automobiles have to know “where its safe to drive, land, sleep and hibernate.”
When you open the classification tool, youll be advised to select different surface area types (rocks or soil) and note locations of a surface area image using a drawing tool that include your picked type of terrain. Once youve recognized whatever in the image, choose “Done” to move onto the next photo.
Picture: Shutterstock
If youve ever desired be a real-life Mark Watney– gathering samples of rocks and dirt on Mars– now is your chance. With NASAs AI4Mars task, you can take a virtual trip around the red world in the Curiosity rover.
Screenshot: Emily Long
G/O Media might get a commission
To be clear, you will not in fact be piloting Curiosity around the Martian surface area, even virtually– this is not a computer game. You will get a close look at the surface area of Mars and contribute to scientific discovery at the same time.
Theres a handy guide popover (click “Tutorial”) and a discussion board where you can ask concerns or fix the tool.
This exact same crowdsourcing concept has actually been used to train neural networks on cityscapes and house numbers back on Earth.
