Event
Paper on MARE Open-Source Lunar Rover Simulation Suite Released
1 reports · 1 sources
Raúl Castilla-Arquillo et al. published a paper presenting MARE—an open-source lunar rover perception and autonomy simulation suite based on Unreal Engine 5 and ROS 2, consisting of three parts: terrain generation, dual-physics lunar rover sensor simulation, and GNC mission control. The simulator provides stereo, lidar, event, and SPAD camera data along with pixel-level ground truth. The paper states that at low solar elevation angles, the mean IoU between predicted shadows and rendered shadows is 0.79; stereo depth analysis shows that pixel coverage in shadowed regions is lower than in sunlit regions. The research context is that low solar elevation angles in the lunar polar regions produce long, high-contrast shadows, which pose difficulties for stereo vision, terrain segmentation, and localization.
Report timeline
- MARE: An open-source lunar rover simulator with shadow ground truth
The authors present MARE, an open-source lunar rover perception and autonomy simulation suite built on Unreal Engine 5 and ROS 2, comprising three parts: terrain generation, dual-physics lunar rover sensor simulation, and GNC mission control. The simulator provides stereo, lidar, event, and SPAD camera data along with pixel-level ground truth; at low solar elevation angles, the mean IoU between predicted shadows and rendered shadows is 0.79. Stereo depth analysis shows that pixel coverage in shadowed regions is lower than in sunlit regions.
arXiv cs.RO ·