NASA's Perseverance Rover Completes First AI-Planned Mars Drives

The autonomous navigation demonstration marks a milestone in self-driving space exploration.

Jan. 30, 2026 at 6:07pm

NASA's Perseverance rover has successfully completed its first AI-planned drives on Mars, navigating complex terrain without human-designed waypoints. The demonstration, led by NASA's Jet Propulsion Laboratory, used generative AI to create safe driving paths for the rover, proving that autonomous technologies can help future missions operate more efficiently and increase scientific return.

Why it matters

This breakthrough in AI-assisted navigation represents a significant step forward for autonomous space exploration. By reducing reliance on human operators, AI-driven planning could streamline daily rover operations and enable longer, more ambitious drives to scientifically interesting targets on Mars and beyond.

The details

In early December, Perseverance followed routes generated by artificial intelligence rather than human planners, navigating Mars using machine-driven decision-making for the first time. The JPL team relied on vision-language models, a form of generative AI, to analyze rover imagery, terrain maps, and hazard data, then select a safe driving path. The rover completed two AI-planned drives, covering 689 feet and 807 feet respectively, without incident.

  • On December 8, 2026, Perseverance completed its first AI-planned drive on Mars.
  • Two days later, on December 10, 2026, the rover completed a second AI-planned drive.

The players

NASA

The National Aeronautics and Space Administration, the independent agency of the executive branch of the United States federal government responsible for the civilian space program, as well as aeronautics and space research.

Perseverance Rover

NASA's latest Mars rover, designed to explore the Jezero Crater and search for signs of ancient microbial life.

Jet Propulsion Laboratory (JPL)

A federally funded research and development center and NASA field center located in Pasadena, California, that specializes in robotic spacecraft and instruments for planetary exploration.

Anthropic

An artificial intelligence research company that provided its Claude AI models to help power the autonomous navigation demonstration.

Vandi Verma

A space roboticist at JPL and a Perseverance engineer.

Got photos? Submit your photos here. ›

What they’re saying

“This demonstration shows how far our capabilities have advanced and broadens how we will explore other worlds. 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.”

— Jared Isaacman, NASA Administrator (interestingengineering.com)

“The fundamental elements of generative AI are showing a lot of promise in streamlining the pillars of autonomous navigation for off-planet driving. 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.”

— Vandi Verma, Space Roboticist at JPL and Perseverance Engineer (interestingengineering.com)

What’s next

NASA plans to continue testing and refining the AI-driven navigation capabilities of the Perseverance rover, with the goal of enabling longer, more autonomous drives on the Martian surface to support future exploration and scientific discovery.

The takeaway

This successful demonstration of AI-planned drives on Mars represents a significant milestone in the development of autonomous space exploration technologies. By reducing reliance on human operators, these advancements could streamline daily rover operations and enable more ambitious, science-focused missions on the Red Planet and beyond.