COVINS: Visual-Inertial SLAM for Centralized Collaboration

TL;DR

COVINS is a scalable collaborative SLAM system that enables multiple agents to independently localize and map large environments efficiently by sharing data with a centralized server, improving accuracy and reducing redundancy.

Contribution

The paper introduces COVINS, a novel multi-agent collaborative SLAM system that supports large teams and environments, with a centralized server for data integration and optimization.

Findings

Increased accuracy of collaborative SLAM estimates.

Efficient removal of redundant data and reduced coordination overhead.

Successful operation with 12 agents in a large-scale environment.

Abstract

Collaborative SLAM enables a group of agents to simultaneously co-localize and jointly map an environment, thus paving the way to wide-ranging applications of multi-robot perception and multi-user AR experiences by eliminating the need for external infrastructure or pre-built maps. This article presents COVINS, a novel collaborative SLAM system, that enables multi-agent, scalable SLAM in large environments and for large teams of more than 10 agents. The paradigm here is that each agent runs visual-inertial odomety independently onboard in order to ensure its autonomy, while sharing map information with the COVINS server back-end running on a powerful local PC or a remote cloud server. The server back-end establishes an accurate collaborative global estimate from the contributed data, refining the joint estimate by means of place recognition, global optimization and removal of redundant data, in order to ensure an accurate, but also efficient SLAM process. A thorough evaluation of COVINS reveals increased accuracy of the collaborative SLAM estimates, as well as efficiency in both removing redundant information and reducing the coordination overhead, and demonstrates successful operation in a large-scale mission with 12 agents jointly performing SLAM.