ARMOR: Adaptive Meshing with Reinforcement Optimization for Real-time 3D Monitoring in Unexposed Scenes
Preprint
Abstract
Unexposed environments, such as lava tubes, mines, and tunnels, are among the most complex yet strategically significant domains for scientific exploration and infrastructure development. Accurate and real-time 3D meshing of these environments is essential for applications including automated structural assessment, robotic-assisted inspection, and safety monitoring. Implicit neural Signed Distance Fields (SDFs) have shown promising capabilities in online meshing; however, existing methods often suffer from large projection errors and rely on fixed reconstruction parameters, limiting their adaptability to complex and unstructured underground environments such as tunnels, caves, and lava tubes. To address these challenges, this paper proposes ARMOR, a scene-adaptive and reinforcement learning-based framework for real-time 3D meshing in unexposed environments. The proposed method was validated across more than 3,000 meters of underground environments, including engineered tunnels, natural caves, and lava tubes. Experimental results demonstrate that ARMOR achieves superior performance in real-time mesh reconstruction, reducing geometric error by 3.96\% compared to state-of-the-art baselines, while maintaining real-time efficiency. The method exhibits improved robustness, accuracy, and adaptability, indicating its potential for advanced 3D monitoring and mapping in challenging unexposed scenarios. The project page can be found at: https://yizhezhang0418.github.io/armor.github.io/Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- Geometric implicit neural representations for signed distance functionsComputers & Graphics, 2024
- Graph-based adaptive weighted fusion SLAM using multimodal data in complex underground spacesISPRS Journal of Photogrammetry and Remote Sensing, 2024
- Legged robot-aided 3D tunnel mapping via residual compensation and anomaly detectionISPRS Journal of Photogrammetry and Remote Sensing, 2024
- Scale-aware deep reinforcement learning for high resolution remote sensing imagery classificationISPRS Journal of Photogrammetry and Remote Sensing, 2024
- Statistical analysis of the severity of occupational accidents in the mining sectorJournal of Safety Research, 2023
- Pressurized lunar lava tubes for habitationActa Astronautica, 2022
- Direct generation of finite element mesh using 3D laser point cloudStructures, 2022
- Data on point cloud scanning and ground radar of composite lining in jointly constructed tunnelData in Brief, 2022
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis2020
- Automated construction of the Paghuashan tunnel for Taiwan High Speed Rail (THSR) projectAutomation in Construction, 2006