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

TL;DR

Swarm-SLAM is a scalable, decentralized multi-robot SLAM system that efficiently integrates various sensors and employs a novel loop closure prioritization to enhance convergence in environments lacking external positioning.

Contribution

The paper introduces Swarm-SLAM, a novel open-source decentralized C-SLAM framework with a unique inter-robot loop closure prioritization technique for improved efficiency.

Findings

Successfully evaluated on five datasets and real-world multi-robot experiment.

Achieved faster convergence with reduced communication overhead.

Supports multiple sensor modalities including lidar and RGB-D.

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