Getting to the Moon was the first chapter. Interlune and Astrolab are working on how to operate there.
Updated
March 6, 2026 1:32 AM
Apollo 17 Astronaut's Snapshot of Taurus-Littrow Valley. PHOTO: UNSPLASH
As plans for a long-term human presence on the Moon pick up pace, the focus is shifting from landing there to working there. It is one thing to reach the surface. It is another to build roads, prepare sites and extract materials in a way that can support real activity.
That is where Interlune and Astrolab come in. Interlune is a space resources company. Astrolab builds planetary rovers. The two are now working together to mount Interlune’s lunar digging system onto Astrolab’s Flexible Logistics and Exploration (FLEX) rover. They have completed a concept study and are planning hardware testing in Houston.
The aim is straightforward: combine a rover that can move reliably across the Moon with equipment that can dig, collect and handle lunar soil. Interlune is focused on harvesting natural resources from the Moon, starting with helium-3. To do that at scale, the system cannot sit in one place. It has to move across the surface, handle dust and operate in harsh conditions. "Reliable, autonomous mobility is crucial to the Interlune harvesting system and broader lunar infrastructure development", said Rob Meyerson, co-founder and CEO of Interlune. "Astrolab's FLEX is the right vehicle for the job".
By fitting its digging and collection hardware onto FLEX, Interlune is working toward a mobile system that can gather large amounts of lunar soil and support future construction needs. Beyond helium-3, the same setup could help prepare base sites, level ground, build protective barriers and lay the groundwork for other structures. In simple terms, it is about turning a rover into a working machine for the Moon.
The partnership also connects to Interlune’s work with Vermeer Corporation to develop equipment for continuous, high-volume digging adapted to lunar conditions. Taken together, the goal is to build systems that can support both commercial and government missions — whether that means resource extraction or preparing land for future bases.
For Astrolab, the collaboration strengthens the role of FLEX as more than just a transport vehicle.
"Working with Interlune further differentiates FLEX as the rover of choice for commercial and government Moon missions", said Jaret Matthews, Astrolab founder and CEO. "Interlune's expertise in developing and testing highly specialized regolith simulant will further enhance FLEX's ability to mitigate dust and operate in extreme environments".
Testing will be centered in Houston, which is becoming an important hub for commercial space development. Astrolab was the first company to lease space at the Texas A&M University Space Institute, currently under construction at NASA’s Johnson Space Center. Interlune operates the Houston-based Interlune Research Lab, where it creates and tests simulated versions of lunar soil.
That detail matters. Moon dust is fine, abrasive and difficult to manage. Before any hardware flies, it needs to prove it can survive and function in those conditions. By testing their systems in realistic soil simulants, the companies can refine how the rover moves and how the digging system performs.
The Houston lab is partially funded by the Texas Space Commission, reflecting the growing role of regional space initiatives in supporting private companies building beyond Earth. Overall, the collaboration is not about grand promises. It is about integrating hardware, running real tests and taking practical steps toward operating on the Moon.
Keep Reading
Robots that learn on the job: AgiBot tests reinforcement learning in real-world manufacturing.
Updated
January 8, 2026 6:34 PM
A humanoid robot works on a factory line, showcasing advanced automation in real-world production. PHOTO: AGIBOT
Shanghai-based robotics firm AgiBot has taken a major step toward bringing artificial intelligence into real manufacturing. The company announced that its Real-World Reinforcement Learning (RW-RL) system has been successfully deployed on a pilot production line run in partnership with Longcheer Technology. It marks one of the first real applications of reinforcement learning in industrial robotics.
The project represents a key shift in factory automation. For years, precision manufacturing has relied on rigid setups: robots that need custom fixtures, intricate programming and long calibration cycles. Even newer systems combining vision and force control often struggle with slow deployment and complex maintenance. AgiBot’s system aims to change that by letting robots learn and adapt on the job, reducing the need for extensive tuning or manual reconfiguration.
The RW-RL setup allows a robot to pick up new tasks within minutes rather than weeks. Once trained, the system can automatically adjust to variations, such as changes in part placement or size tolerance, maintaining steady performance throughout long operations. When production lines switch models or products, only minor hardware tweaks are needed. This flexibility could significantly cut downtime and setup costs in industries where rapid product turnover is common.
The system’s main strengths lie in faster deployment, high adaptability and easier reconfiguration. In practice, robots can be retrained quickly for new tasks without needing new fixtures or tools — a long-standing obstacle in consumer electronics production. The platform also works reliably across different factory layouts, showing potential for broader use in complex or varied manufacturing environments.
Beyond its technical claims, the milestone demonstrates a deeper convergence between algorithmic intelligence and mechanical motion.Instead of being tested only in the lab, AgiBot’s system was tried in real factory settings, showing it can perform reliably outside research conditions.
This progress builds on years of reinforcement learning research, which has gradually pushed AI toward greater stability and real-world usability. AgiBot’s Chief Scientist Dr. Jianlan Luo and his team have been at the forefront of that effort, refining algorithms capable of reliable performance on physical machines. Their work now underpins a production-ready platform that blends adaptive learning with precision motion control — turning what was once a research goal into a working industrial solution.
Looking forward, the two companies plan to extend the approach to other manufacturing areas, including consumer electronics and automotive components. They also aim to develop modular robot systems that can integrate smoothly with existing production setups.