DVM-SLAM: Decentralized Visual Monocular Simultaneous Localization and Mapping for Multi-Agent Systems

2025-03-06

AI Summary

To address robustness degradation, severe drift, and limited scalability in collaborative simultaneous localization and mapping (C-SLAM) for multi-agent systems operating in unknown environments, this paper introduces the first open-source, fully decentralized monocular visual C-SLAM system. Methodologically, it integrates lightweight monocular feature extraction and tracking, inter-agent sparse feature matching, distributed pose-graph optimization, and a customized collision-avoidance framework—eliminating reliance on any central server or global communication topology. Experimental results demonstrate real-time distributed computation and successful deployment on physical robots; mapping accuracy matches state-of-the-art centralized monocular C-SLAM systems, while cumulative drift is significantly suppressed. The system further enhances exploration range and scalability. All source code and datasets are publicly released.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Multi-modal Vision
• Multiagent Systems: Distributed Problem Solving

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Cooperative Simultaneous Localization and Mapping (C-SLAM) enables multiple agents to work together in mapping unknown environments while simultaneously estimating their own positions. This approach enhances robustness, scalability, and accuracy by sharing information between agents, reducing drift, and enabling collective exploration of larger areas. In this paper, we present Decentralized Visual Monocular SLAM (DVM-SLAM), the first open-source decentralized monocular C-SLAM system. By only utilizing low-cost and light-weight monocular vision sensors, our system is well suited for small robots and micro aerial vehicles (MAVs). DVM-SLAM's real-world applicability is validated on physical robots with a custom collision avoidance framework, showcasing its potential in real-time multi-agent autonomous navigation scenarios. We also demonstrate comparable accuracy to state-of-the-art centralized monocular C-SLAM systems. We open-source our code and provide supplementary material online.

Problem

• Decentralized SLAM for multi-agent systems
• Low-cost monocular vision for small robots
• Real-time autonomous navigation with collision avoidance

Innovation

• Decentralized monocular SLAM for multi-agent systems
• Low-cost monocular vision sensors for small robots
• Real-time autonomous navigation with collision avoidance