NASA Drove Its Mars Rover Using AI for the First Time. Here’s How It Went

https://www.profitableratecpm.com/f4ffsdxe?key=39b1ebce72f3758345b2155c98e6709c

On Earth, we can enter an address into Google Maps and leave in seconds. But chart a path for NASA’s Perseverance rover140 million kilometers away, on Mars, is significantly more difficult. The rover’s path is usually plotted by a team at NASA’s Jet Propulsion Lab, which takes into account terrain, obstacles and potential dangers.

For the first time, NASA’s JPL used AI to chart the path forward for Perseverance, and it appears to have worked.

The two demonstrations, which took place on December 8 and 10, were planned by Claude AI from Anthropic models and double-checked by JPL to ensure the AI ​​didn’t accidentally drive the rover into a ditch. Perseverance traveled just under 1,500 feet on both journeys with no documented problems.

AI Atlas

NASA took a similar approach, plotting waypoints as it would with human operators. Claude was given the same satellite images and data from NASA’s Mars Reconnaissance Orbiter that JPL scientists would use, then asked to plot waypoints that Perseverance could safely handle.

The resulting path was slightly modified by NASA and then shipped to Perseverance, which then traveled the path autonomously.

“This demonstration shows how far our capabilities have advanced and expands how we will explore other worlds,” said NASA Administrator Jared Isaacman. “Autonomous technologies like this can help missions operate more efficiently, respond to challenging terrain, and increase scientific results as distance from Earth increases. This is a good example of teams applying new technologies carefully and responsibly in real-world operations.”

You can watch the December 10 ride on NASA’s YouTube channel, which has been condensed into a 52-second video.

The map of waypoints that Perseverance followed on December 8 and 10.

The route planned by Claude is indicated in magenta and the path actually taken is in orange. NASA scientists only had to make minor adjustments to the AI’s path.

NASA/JPL-Caltech/UofA

A more efficient way to do it

Although AI is widely known as a provider of slop, accused of rapidly degrading people’s Internet experience, it can be useful in some scientific activities. It takes time to analyze years of images and data, plot Perseverance’s waypoints, and then execute them.

According to NASA, waypoints are typically no more than 330 feet apart, meaning Perseverance is exploring the Red Planet one football field at a time. Make its epic climb out of Jezero Crater in 2024. The journey took Perseverance 3.5 months, and in total, the rover climbed a total of 1,640 feet in elevation. As of December 2025, the rover has traveled a total of just 25 miles in about four years.

The goal, according to JPL space roboticist Vandi Verma, is to let Perseverance (and other Mars rovers) travel much further while “minimizing operator workload”.

Verma also notes that AI could be used to flag interesting features on the planet, saving human science teams time by eliminating the need to manually check “huge volumes of rover images.”

“This demonstration shows how far our capabilities have advanced and expands how we will explore other worlds,” Isaacman said. “Autonomous technologies like this can help missions operate more efficiently, respond to challenging terrain, and increase scientific results as distance from Earth increases. This is a good example of teams applying new technologies carefully and responsibly in real-world operations.”

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button