Astrolab’s upcoming rover will run the first LLMs on the moon
Large language models are set to go lunar. A computer capable of running AI software is one of the payloads aboard Astrolab’s FLIP lunar rover, which is slated to head to Earth’s celestial companion as early as November 2026. The 480-kilogram FLIP rover, short for “FLEX Lunar Innovation Platform,” is the first in a series…
Astrolab's upcoming FLIP lunar rover, set to launch in November 2026, will carry the first high-performance computer capable of running large language models (LLMs) on the moon's surface. The 480-kilogram rover, designed to endure the moon's harsh environment, includes a lidar 3D mapper and a sensor to measure helium-3 concentrations in the lunar regolith.
HPE's Spaceborne-4 edge computer, featuring a high-performance 64-bit CPU and GPU, will power the LLMs, potentially enabling greater autonomy and real-time intelligent decision-making for future space missions. The time delay in receiving data from the moon can be up to 20 minutes, causing issues like those faced by the Soviet rovers in the past.
FLIP's LLMs will analyze camera and lidar data to assist with safe navigation and distill insights from the gathered information. While AI algorithms have been used in previous lunar missions and Mars rovers, FLIP's HPE computer is much more advanced than the weak systems on those rovers. HPE's technology monitors for radiation disturbances and adjusts power and speed to ensure the computer's reliability during the mission.
The FLIP rover's unique environment, with extreme temperature swings and intense cosmic radiation, presents new challenges for the computer's durability. Despite these challenges, the computer's simple design and software protections are expected to enable it to last for the entirety of the mission's planned 10 days on the moon.
Written by urgent.news from MIT Technology Review's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
