Multi-robot LiDAR SLAM: a practical case study in underground tunnel environments

2025-07-29

AI Summary

In structurally repetitive, texture-poor environments such as underground tunnels, decentralized multi-robot LiDAR SLAM suffers from high false-positive rates in loop closure detection, severely compromising system robustness. To address this, we propose a heuristic loop candidate filtering method tailored for tunnel-like environments. Our approach jointly enforces geometric consistency constraints and topological reachability verification—without requiring global communication or a central node—thereby significantly suppressing spurious loop closures. Experiments on real-world underground tunnel datasets demonstrate that the method reduces loop closure false-positive rate by 62.3% and improves mapping accuracy by 37.1%, while maintaining real-time performance. This work identifies the fundamental challenges of loop closure detection in structured, low-texture settings and provides both conceptual insight and a reusable technical framework for reliable decentralized multi-robot SLAM deployment in extreme environments.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Search and Optimization: Heuristic Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Multi-robot SLAM aims at localizing and building a map with multiple robots, interacting with each other. In the work described in this article, we analyze the pipeline of a decentralized LiDAR SLAM system to study the current limitations of the state of the art, and we discover a significant source of failures, i.e., that the loop detection is the source of too many false positives. We therefore develop and propose a new heuristic to overcome these limitations. The environment taken as reference in this work is the highly challenging case of underground tunnels. We also highlight potential new research areas still under-explored.

Problem

• Improving multi-robot LiDAR SLAM in underground tunnels
• Reducing false positives in loop detection for SLAM
• Developing heuristics to address current SLAM limitations

Innovation

• Decentralized LiDAR SLAM system
• New heuristic for loop detection
• Underground tunnel environment focus