Swarm-SLAM : Sparse Decentralized Collaborative Simultaneous Localization and Mapping Framework for Multi-Robot Systems

TL;DR

Swarm-SLAM delivers a scalable, decentralized, sparse C-SLAM framework for swarms, capable of fusing inertial, lidar, stereo, and RGB-D data while minimizing inter-robot communication. The key novelty is a spectral, algebraic-connectivity-based prioritization of inter-robot loop closures that pre-sparsifies candidates before expensive verification and a neighbor-managed ad-hoc networking approach that supports sporadic rendezvous without a central server. The system combines a two-stage front-end (global matching with compact descriptors plus local verification) and a GNC-based back-end with an anchor mechanism to maintain a consistent global frame, demonstrated across multiple public datasets and real-world three-robot experiments. Practically, Swarm-SLAM reduces communication load (e.g., 94.95 MB in a real-world run) while maintaining high localization accuracy, making it suitable for large, bandwidth-constrained robot swarms and challenging GPS-denied environments.

Abstract

Collaborative Simultaneous Localization And Mapping (C-SLAM) is a vital component for successful multi-robot operations in environments without an external positioning system, such as indoors, underground or underwater. In this paper, we introduce Swarm-SLAM, an open-source C-SLAM system that is designed to be scalable, flexible, decentralized, and sparse, which are all key properties in swarm robotics. Our system supports inertial, lidar, stereo, and RGB-D sensing, and it includes a novel inter-robot loop closure prioritization technique that reduces communication and accelerates convergence. We evaluated our ROS-2 implementation on five different datasets, and in a real-world experiment with three robots communicating through an ad-hoc network. Our code is publicly available: https://github.com/MISTLab/Swarm-SLAM