🚀HPE LLMs to Run on Moon Rover This November
LLMs to Navigate the Moon's Surface
TL;DR
HPE's high-performance computer will run large language models on Astrolab's FLIP lunar rover starting November 2026. LLMs will analyze data for navigation and reduce data transmission back to Earth.
HPE's high-performance computer will run large language models (LLMs) on Astrolab's FLIP lunar rover starting November 2026. This marks the first time LLMs will operate in the harsh lunar environment, aiding in navigation and data analysis. The rover will carry 20 scientific payloads, including a lidar 3D mapper and a sensor for measuring helium-3. The HPE Spaceborne-4 computer features a 64-bit CPU and GPU, designed to handle computational tasks in parallel. The mission aims to prove the reliability of LLMs in space, with potential applications for future Mars missions where communication delays are a concern.
Key Points
HPE's Spaceborne-4 computer will run LLMs on Astrolab's FLIP lunar rover, set to launch in November 2026.
The rover will carry 20 scientific payloads, including a lidar 3D mapper and a sensor for measuring helium-3 in lunar regolith.
Spaceborne-4 features a high-performance 64-bit CPU and GPU, designed to run large numbers of computational tasks in parallel.
Previous Spaceborne computers ran Meta's Llama 3.2 LLM on the ISS in 2025, testing tech in low Earth orbit.
LLMs on the rover will analyze data from cameras and lidar to aid in safe navigation of the lunar terrain.
Why It Matters
LLMs running on the FLIP rover will analyze data from cameras and lidar to aid in safe navigation of the lunar terrain. This technology could be crucial for future Mars missions where communication delays make real-time assistance from Earth impractical. However, the potential for inaccuracies in space poses serious risks.
Comments
Be the first to comment
Enjoyed this article?
Get it daily. 7am. Free. Reads in 5 minutes.
Join 3,569 builders reading daily.