Mars Perseverance rover now uses AI in the search for Martian life

We dream of exploring strange, new worlds and discovering new life forms — ideally without having to do all the work ourselves. NASA’s Perseverance Mars Rover is leading the way by giving us a sneak peek of what can be achieved with AI in space.

With the help of its onboard AI, the Perseverance rover has been engaging in a unique kind of treasure hunt on the red planet’s rocky landscape. But instead of gold and jewels, it’s after something arguably more valuable – minerals.

Perseverance, AI, and Martian minerals

For almost three years, the rover has been using AI to hunt for minerals in Martian rocks, making it the first-ever Mars mission to use AI for autonomous, real-time analysis of rock composition.

Behind this innovative use of AI is Planetary Instrument for X-ray Lithochemistry (PIXL), a spectrometer developed by NASA’s Jet Propulsion Laboratory (JPL) in Southern California.

According to Abigail Allwood, JPL’s principal investigator for PIXL, this clever instrument uses the artificial intelligence onboard Perseverance to zero in on minerals of interest in Martian rocks, in real-time.

“We use PIXL’s AI to home in on key science,” Allwood explained. “Without it, you’d see a hint of something interesting in the data and then need to rescan the rock to study it more. This lets PIXL reach a conclusion without humans examining the data.”

Another feather in Perseverance’s cap is its ability to determine when it’s time to drill a core of rock and set it aside for future study back on our home planet.

It’s all part and parcel of NASA’s ambitious Mars Sample Return campaign, a crucial part of our efforts to understand Mars’ geologic history and, potentially, its capacity to host life.

“Advanced sampling” and the power of AI

Perseverance’s AI-driven approach to mineral hunting is known as “adaptive sampling.” In simple terms, this means that the rover’s AI scans a rock, identifies minerals of interest, and then autonomously decides where to focus its research further.

All this is done without needing to communicate with mission control back on Earth, saving both time and resources.

Peter Lawson, who spearheaded the implementation of adaptive sampling before retiring from JPL, puts it in perspective.

“The idea behind PIXL’s adaptive sampling is to help scientists find the needle within a haystack of data, freeing up time and energy for them to focus on other things,” explained Lawson. “Ultimately, it helps us gather the best science more quickly.”

Adaptive sampling aids scientists in uncovering the all-important needle in the haystack of data, allowing them to channel their attention and energy elsewhere.

The result? High-quality Mars science delivered at an accelerated pace.

AI helps Perseverance snap the perfect photo

AI enhances PIXL’s functionality in two significant ways. Initially, it ensures precise positioning of the instrument once it is near a rock target.

Positioned at the end of Perseverance’s robotic arm, PIXL’s spectrometer is mounted on six minute robotic legs, known as a hexapod.

This intricate setup allows PIXL’s camera to continuously monitor the distance between the instrument and the rock target, facilitating precise positioning.

The considerable temperature fluctuations on Mars cause Perseverance’s arm to expand or contract minutely, potentially disrupting PIXL’s aim.

To counter this, the hexapod autonomously adjusts the instrument, enabling it to achieve proximity to the rock target without making contact.

“We need micrometer-scale adjustments to achieve the required accuracy,” Allwood explained. “PIXL gets close enough to the rock to make an engineer’s hair stand on end.”

This synergy between AI and robotics exemplifies the cutting-edge technology at the heart of our Mars exploration missions, highlighting the precision and adaptability required to navigate and study the Red Planet’s challenging environment.

Final Step: Creating a Mineral map

Once PIXL is positioned, another advanced AI system takes center stage. PIXL meticulously scans a postage-stamp-sized section of a rock, deploying an X-ray beam thousands of times to create a grid of microscopic dots. Each dot offers a treasure trove of information about the chemical composition of the minerals within.

Understanding these minerals is pivotal for answering profound questions about Mars. For instance, scientists might search for carbonates in certain rocks, which could reveal how water once shaped them.

Alternatively, they may seek phosphates, potential nutrient sources for ancient Martian microbes, if such life ever existed.

Predicting which of the hundreds of X-ray zaps will uncover specific minerals is impossible. However, when PIXL identifies particular minerals, it can autonomously halt to gather additional data—a process known as a “long dwell.” As machine learning enhances the system, the repertoire of minerals PIXL can analyze with a long dwell continues to expand.

Curiosity rover is also involved

But don’t think that Mars is the sole realm of AI in space; it’s being put to work over 2,300 miles away by NASA’s Curiosity rover.

From autonomous rock laser-zapping based on shape and color to self-navigation, Curiosity has been a pioneer in AI-led space exploration.

Its successor, Perseverance, has upped the ante with more sophisticated AI capabilities, although mission planning still remains a largely human endeavor with dozens of engineers and scientists involved in the planning process.

AI and the future of space exploration

With AI making leaps and bounds in its Martian field trials, David Thompson, a software developer at JPL, emphasizes that these advances are particularly important for future missions venturing deeper into the solar system.

“PIXL is akin to a Swiss army knife, adaptable based on what scientists are investigating at any given moment,” Thompson explained. “Mars provides an excellent testing ground for AI, as our daily communications allow us to refine and improve the system continuously.”

Future missions venturing deeper into the solar system will encounter prolonged communication delays compared to current Mars missions.

Therefore, advancing autonomy in these missions is crucial, allowing them to explore and conduct science independently for the collective benefit of humanity.

As communication windows dwindle for more distant missions, the importance of autonomous AI will only grow, paving the way for the next generation of smart spacecraft.

As we continue to push the boundaries of space exploration, it’s becoming apparent that our dreams of exploring the universe might not be such a distant reality after all.

Thanks to the continued efforts of dedicated scientists like the team at NASA’s JPL and the power of AI, we’re inching closer to unveiling the mysteries of our solar system. After all, who knows what mineral treasures await in the rocks of distant worlds?

—–

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates.

Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.

—–