SGM-SLAM: Scene Graph Matching for Data-Efficient Distributed SLAM
For multi-robot SLAM, this work reduces communication overhead by matching scene graphs instead of raw features, enabling more scalable distributed mapping.
SGM-SLAM introduces a distributed SLAM framework that uses scene graph matching with only object labels and centroids to identify inter-robot constraints, achieving data-efficient communication. Experiments on simulation and real-world datasets show effective multi-robot mapping.
We introduce a data-efficient distributed Simultaneous Localization and Mapping (SLAM) framework designed for a team of robots equipped with LiDAR, cameras, and inertial sensors. Our framework uses scene graph matching to identify inter-robot measurement constraints. Unlike prior approaches that rely on feature-level matching, our framework is the first to perform scene graph matching using only object labels and centroids. Our approach constructs a scene graph by using fused RGB-LiDAR point clouds to generate both a semantically segmented point cloud layer, and a layer of discrete bounded objects, to accompany estimated robot trajectories. Scene graph matching is performed collaboratively through exchanging and matching object data with neighboring robots. To maximize communication efficiency, we utilize a multi-step data exchange and optimization process. We demonstrate the effectiveness and efficiency of our approach using both simulation and real-world datasets collected by legged robots in indoor and outdoor environments.