Teach the Curiosity rover how to drive on Mars
A new online tool called AI4Mars, hosted on Zooniverse, allows anyone to label parts of the terrain in the landscape surrounding Curiosity, which has been roving on Mars since 2012. The tool is a form of ‘machine learning’ that allows rover planners assisting with Curiosity’s movements to train the rover’s intelligence for safe route planning.
Picking an appropriate pathway is a pressing problem for Martian rovers. Curiosity’s wheels wore down in the early years of its mission from driving over sharp rocks, while another Mars rover called Spirit got permanently stuck in a sand trap in 2010.
The first stage of training the algorithm, called SPOC – short for Soil Property and Object Classification – will allow it to distinguish between different types of terrain. SPOC is already used by Martian rover drivers, but bringing in the public will provide more training information at a faster pace.
The Curiosity rover’s challenges are distinct from the self-driving car algorithms available, as the rover isn’t working with roads, pedestrians or traffic signs. This means more help is needed to get the algorithm trained quickly.
“In the future we hope this algorithm can become accurate enough to do other useful tasks, like predicting how likely a rover’s wheels are to slip on different surfaces,” Masahiro Ono, an artificial intelligence researcher at NASA’s Jet Propulsion Laboratory (JPL) in Pasadena, California, said. Curiosity’s training will also give a boost to NASA’s new Perseverance rover, which is expected to launch no earlier than 20 July for a landing on Mars in 2021. More than 8,000 Curiosity images are available on the AI4Mars site already, allowing the public to start labelling images to help Curiosity, and eventually Perseverance.