Organizations: Space Robotics Lab. (SRL) in Department of Aerospace Engineering, Graduate School of Engineering, Tohoku University, Sendai 980-8579, Japan · Department of Electrical Engineering, Graduate School of Science and Technology, Tokyo University of Science, Noda 278-8510, Japan
Long-term human habitation and in-situ development on the Moon open a new era of space utilization. In this context, robots are a key technology for facilitating the construction of future human outposts. Toward the deployment and establishment of human habitation modules on the lunar surface, we propose a combined system consisting of inflatable modules and a modular, reconfigurable robotic system. This paper presents a report demonstrating various robot-assisted task executions using real hardware, namely the modular and reconfigurable robot MoonBot and the inflatable module HIDAS, to enhance the reliability of their deployment and maintenance. The demonstrated tasks include robotic inspection during inflation, module position alignment, final safety locking, and three-dimensional mapping for post-deployment maintenance. All demonstrations were conducted either in a laboratory environment or at a lunar analogue test site. Finally, lessons learned are discussed to provide essential insights for this robotic application to future lunar habitation.
Figures & tables
Fig. 1: MoonBot, a modular and reconfigurable robot (left), assisting in the deployment of inflatable module HIDAS (right). For the Earth-gravity demonstration, a half-scale inflatable module (diameter: 2 m) was used. The robots monitor the inflation status using a hand-mounted camera, assist in positioning the module by applying external forces, and subsequently insert rolling-proof stoppers to prevent unintended movement.
Fig. 2: Conceptual rendering illustrating the assumed scenario of robot-assisted construction of a human habitation base.
Fig. 3: Concept of the robot teleoperation framework based on shared autonomy.
Fig. 4: Robot teleoperation user interface. Top left: Robot view monitor, top right: joint states visualizer, bottom: telemetry data monitor (active modules, battery life, etc.).
Metric
Take 1
Take 2
Take 3
Mean ± s.d.
Δd [mm]
3.72
4.52
5.29
4.51±0.64
Δθ [deg]
0.55
0.53
0.69
0.59±0.07
TABLE I: Terminal alignment residuals from repeated trials.
Fig. 6: Initial inspection of the inflatable module by the robot: (a) Vision-based inspection during inflation and (b) Contact-based inspection after inflation.
Class
Precision
Recall
mAP@50
mAP@50:95
HIDAS
0.995
0.991
0.995
0.988
Anomaly cell
0.765
0.779
0.793
0.551
All
0.880
0.885
0.894
0.770
TABLE II: Cell-inspection model (YOLOv11n-seg) performance on the held-out validation split. “All” is the unweighted mean over the two classes.
Fig. 7: Well-positioning of the inflated module by two mobile robots, assuming a scenario in which the module is docked to another module. (a) The lateral position was adjusted by applying rolling forces from the left and right sides. Subsequently, (b) the longitudinal position was aligned by pushing the module cooperatively using the two robots.
Fig. 8: Demonstration of inflatable module deployment assistance by MoonBot. Once the inflatable module had been fully deployed and properly positioned, the robot placed stopper objects to further enhance stability (top: pick-up, bottom: insertion).
Fig. 9: Three-dimensional reconstruction of the inflatable modules after deployment. Multiple MoonBots scanned the HIDAS modules using LiDAR sensors mounted on top of the wheel bases (top images) to generate point cloud data (bottom graphics). The complete geometry of HIDAS was reconstructed by fusing multiple scans; the magenta and cyan lines indicate the robot traveling trajectories estimated during two different scanning runs.
Space Robotics Lab. (SRL), Department of Aerospace Engineering, Graduate School of Engineering, Tohoku University, Sendai 980–8579, Japan · École Centrale de Lille, France · Institut Teknologi Bandung, Indonesia
Institute of Automation, Chinese Academy of Sciences, China, and also with the Faculty of Innovation Engineering, Macau University of Science and Technology, Macau · OpenSpace Lab, China · College of Artificial Intelligence, China University of Petroleum (Beijing) +5
FZI Forschungszentrum für Informatik, Karlsruhe, Germany · Machine Intelligence and Robotics Lab (MaiRo), Karlsruhe Institute for Technology (KIT), Karlsruhe, Germany · Robotic Systems Lab (RSL), ETH Zürich, Zürich, Switzerland +1