Science & Technology

ATTN: NASA’s Mars Curiosity Rover Drivers Need Your Help

Three pictures from the device referred to as AI4Mars present completely different sorts of Martian terrain as seen by NASA’s Curiosity rover. By drawing borders round terrain options and assigning certainly one of 4 labels to them, you’ll be able to assist practice an algorithm that may routinely determine terrain varieties for Curiosity’s rover planners. Credit score: NASA/JPL-Caltech

Utilizing a web based device to label Martian terrain varieties, you’ll be able to practice a man-made intelligence algorithm that might enhance the best way engineers information the Curiosity rover.

You might be able to assist NASA’s Curiosity rover drivers higher navigate Mars. Utilizing the net device AI4Mars to label terrain options in photos downloaded from the Purple Planet, you’ll be able to practice a man-made intelligence algorithm to routinely learn the panorama.

Is {that a} huge rock to the left? Might it’s sand? Or perhaps it’s good, flat bedrock. AI4Mars, which is hosted on the citizen science web site Zooniverse, permits you to draw boundaries round terrain and select certainly one of 4 labels. These labels are key to sharpening the Martian terrain-classification algorithm referred to as SPOC (Soil Property and Object Classification).

Developed at NASA’s Jet Propulsion Laboratory, which has managed the entire company’s Mars rover missions, SPOC labels varied terrain varieties, creating a visible map that helps mission crew members decide which paths to take. SPOC is already in use, however the system might use additional coaching.

“Sometimes, tons of of hundreds of examples are wanted to coach a deep studying algorithm,” stated Hiro Ono, an AI researcher at JPL. “Algorithms for self-driving automobiles, for instance, are educated with quite a few pictures of roads, indicators, visitors lights, pedestrians and different autos. Different public datasets for deep studying include individuals, animals and buildings — however no Martian landscapes.”

Low-angle self-portrait of NASA’s Curiosity Mars rover. Credit score: NASA/JPL-Caltech/MSSS

As soon as absolutely in control, SPOC will be capable to routinely distinguish between cohesive soil, excessive rocks, flat bedrock and harmful sand dunes, sending pictures to Earth that may make it simpler to plan Curiosity’s subsequent strikes.

“Sooner or later, we hope this algorithm can grow to be correct sufficient to do different helpful duties, like predicting how seemingly a rover’s wheels are to slide on completely different surfaces,” Ono stated.

JPL engineers referred to as rover planners might profit probably the most from a better-trained SPOC. They’re answerable for Curiosity’s each transfer, whether or not it’s taking a selfie, trickling pulverized samples into the rover’s physique to be analyzed (video beneath), or driving from one spot to the following.

NASA’s Curiosity rover analyzed its first strong pattern of Mars with quite a lot of devices, together with the Pattern Evaluation at Mars (SAM) instrument suite. Developed at NASA’s Goddard House Flight Middle in Greenbelt, Md., SAM is a transportable chemistry lab tucked contained in the Curiosity rover. SAM examines the chemistry of samples it ingests, checking notably for chemistry related as to if an surroundings can help or might have supported life.

It could take 4 to 5 hours to work out a drive (which is now done virtually), requiring a number of individuals to jot down and evaluate tons of of strains of code. The duty entails in depth collaboration with scientists as effectively: Geologists assess the terrain to foretell whether or not Curiosity’s wheels might slip, be broken by sharp rocks or get caught in sand, which trapped each the Spirit and Alternative rovers.

Planners additionally think about which approach the rover will likely be pointed on the finish of a drive, since its high-gain antenna wants a transparent line of sight to Earth to obtain instructions. And so they attempt to anticipate shadows falling throughout the terrain throughout a drive, which might intervene with how Curiosity determines distance. (The rover makes use of a method referred to as visible odometry, evaluating digital camera pictures to close by landmarks.)

SPOC gained’t substitute the difficult, time-intensive work of rover planners. However it could actually free them to deal with different facets of their job, like discussing with scientists which rocks to review subsequent.

“It’s our job to determine safely get the mission’s science,” stated Stephanie Oij, one of many JPL rover planners concerned in AI4Mars. “Robotically producing terrain labels would save us time and assist us be extra productive.”

The advantages of a wiser algorithm would lengthen to planners on NASA’s subsequent Mars mission, the Perseverance rover, which launches this summer time. However first, an archive of labeled pictures is required. Greater than 8,000 Curiosity pictures have been uploaded to the AI4Mars web site thus far, offering loads of fodder for the algorithm. Ono hopes so as to add pictures from Spirit and Alternative sooner or later. Within the meantime, JPL volunteers are translating the positioning in order that members who converse Spanish, Hindi, Japanese and a number of other different languages can contribute as effectively.

Related posts

Sexting Isn’t Just About Sex – Surprising New Research Shows 3 Main Motivations


“Pump-Probe” Technique Explores How Molecules Respond to Light


BepiColombo Spacecraft Skims Past Venus