SGM-SLAM: Scene Graph Matching for Data-Efficient Distributed SLAM
SGM-SLAM: Scene Graph Matching for Data-Efficient Distributed SLAM
This research introduces SGM-SLAM, a framework for simultaneous localization and mapping designed for multi-robot teams operating in GPS-denied and communication-constrained environments. The system utilizes fused RGB-LiDAR point clouds to construct scene graphs comprising semantically segmented layers and discrete bounded objects, facilitating collaborative trajectory estimation through neighbor-to-neighbor object data exchange. The approach is validated on real-world datasets featuring limited spatial overlap, viewpoint variation, repeated structures, and degraded visual conditions.
The paper proposes SGM-SLAM, a distributed SLAM framework utilizing scene graph matching on fused RGB-LiDAR data to enable multi-robot operation in GPS-denied environments with limited communication and trajectory overlap.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
Source：arXiv Robotics — research abstracts · arxiv.org