Mapping Perseverance’s Route With AI
NASA/JPL-Caltech/UofA
Description
This annotated image from NASA’s HiRISE (High Resolution Imaging Science Experiment) camera aboard the agency’s Mars Reconnaissance Orbiter image depicts the AI-planned route and the actual route taken by NASA’s Perseverance Mars rover during its 807-foot (246-meter) drive on Dec. 10, 2025, the 1,709th Martian day, or sol, of the mission. The drive was the second of two demonstrations — the first being on Dec. 8 — showing that generative artificial intelligence could be incorporated in the rover’s route planning.
The magenta lines depict the path the rover’s wheels would take if it were to follow AI-processed waypoints, which are indicated with the magenta circles. (Waypoints are fixed locations where the rover takes up a new set of instructions.) The orange lines are based on data downlinked after the drive was complete and depict the actual path the rover took. The short, bold segments of the blue lines at the start of the route, in the upper right, show the portion of the drive that was determined by the mission’s rover drivers and based on imagery taken by the rover of the surface ahead. The surface areas in pale green boxes are called “keep-in zones.” Perseverance’s self-driving software is only allowed to pick routes inside those zones.
The graphic was generated using Hyperdrive, part of the software suite used to plan rover drives and manage the massive influx of engineering data from the Perseverance rover.
NASA’s Jet Propulsion Laboratory, which is managed for the agency by Caltech, built and manages operations of the Perseverance rover.
For more about Perseverance: science.nasa.gov/mission/mars-2020-perseverance/
The University of Arizona in Tucson, operates HiRISE, which was built by BAE Systems in Boulder, Colorado. JPL manages the Mars Reconnaissance Orbiter for SMD.
