The team behind NASA’s six-wheeled Mars explorer tested a vision-enabled artificial intelligence system to map a safe route across the Martian surface without relying on human route planners.
NASA’s Perseverance rover has now completed the first drives on another planet that were planned by artificial intelligence. The milestone demonstration took place on Dec. 8 and 10 and was led by NASA’s Jet Propulsion Laboratory in Southern California. During the test, generative AI was used to select waypoints for the rover, a complex planning task that is normally handled by human experts on Earth.
“This demonstration shows how far our capabilities have advanced and broadens how we will explore other worlds,” said NASA Administrator Jared Isaacman. “Autonomous technologies like this can help missions to operate more efficiently, respond to challenging terrain, and increase science return as distance from Earth grows. It’s a strong example of teams applying new technology carefully and responsibly in real operations.”
How Vision AI Helped Navigate the Martian Surface
For the demonstration, engineers used a form of generative AI known as vision-language models to examine existing data from JPL’s surface mission dataset. The system analyzed the same images and information that human planners typically use, then identified waypoint locations so Perseverance could travel safely across difficult Martian terrain.
The work was coordinated from JPL’s Rover Operations Center (ROC) and carried out in collaboration with Anthropic, using the company’s Claude AI models.
Why Mars Rover Routes Are Hard to Plan
Mars sits an average of about 140 million miles (225 million kilometers) from Earth. That distance creates long communication delays, making real-time control of a rover impossible. For nearly three decades, rover navigation has depended on human drivers who carefully study terrain data and plan routes in advance.
These planners design paths made up of waypoints, usually spaced no more than 330 feet (100 meters) apart, to reduce the risk of encountering hazards. The completed plans are sent through NASA’s Deep Space Network, and the rover carries out the instructions on its own.
AI Takes Over Route Planning for Perseverance
During Perseverance’s drives on the 1,707 and 1,709 Martian days, known as sols, the mission team shifted that responsibility to generative AI. The system examined high-resolution orbital images captured by the HiRISE (High Resolution Imaging Science Experiment) camera aboard NASA’s Mars Reconnaissance Orbiter, along with terrain slope data from digital elevation models.
Using this information, the AI identified important surface features such as bedrock, outcrops, boulder fields, and sand ripples. It then produced a continuous driving path that included all necessary waypoints.
Before sending the commands to Mars, engineers ran the AI-generated instructions through JPL’s digital twin (virtual replica of the rover). This step checked more than 500,000 telemetry variables to ensure the plan would work safely with Perseverance’s flight software.
On Dec. 8, Perseverance traveled 689 feet (210 meters) using the AI-generated plan. Two days later, it drove another 807 feet (246 meters).
What This Means for Future Space Exploration
“The fundamental elements of generative AI are showing a lot of promise in streamlining the pillars of autonomous navigation for off-planet driving: perception (seeing the rocks and ripples), localization (knowing where we are), and planning and control (deciding and executing the safest path),” said Vandi Verma, a space roboticist at JPL and a member of the Perseverance engineering team. “We are moving towards a day where generative AI and other smart tools will help our surface rovers handle kilometer-scale drives while minimizing operator workload, and flag interesting surface features for our science team by scouring huge volumes of rover images.”
“Imagine intelligent systems not only on the ground at Earth, but also in edge applications in our rovers, helicopters, drones, and other surface elements trained with the collective wisdom of our NASA engineers, scientists, and astronauts,” said Matt Wallace, manager of JPL’s Exploration Systems Office. “That is the game-changing technology we need to establish the infrastructure and systems required for a permanent human presence on the Moon and take the U.S. to Mars and beyond.”
More About Perseverance
Managed for NASA by Caltech, JPL is home to the Rover Operations Center (ROC). The laboratory also oversees daily operations of the Perseverance rover for NASA’s Science Mission Directorate as part of the agency’s Mars Exploration Program portfolio.