Chain-SLAM improves map alignment for multi-session LiDAR mapping
Chain-SLAM: Globally Consistent Backend for Multi-Session LiDAR SLAM via Chained Loop Closure
Robotics
Summary
LiDAR SLAM helps create maps by tracking a sensor as it moves, but it can be hard to keep maps consistent when combining data from many sessions. The authors made Chain-SLAM, a system that better aligns and merges these maps by chaining together loop closures between sessions. This method helps correct errors over long distances and times, resulting in more accurate and stable maps. Their approach uses GPS data to start matching places and adjusts the entire map as new data arrives.
What this means in practice
- •For autonomous vehicle teams: Combine LiDAR scans collected over multiple days into a single consistent map supporting long-term navigation.
- •For robotics engineering teams: Build robots that can merge and update their environment maps across repeated missions without losing accuracy.
Authors
Zhiheng Li, Xinhao Liu, Juexiao Zhang, Yongqing Liang, Chen Feng
Abstract
Maintaining consistency over long spatial and temporal horizons remains a fundamental challenge in large-scale LiDAR SLAM, particularly when integrating maps collected across multiple sessions. We present Chain-SLAM, a LiDAR SLAM backend enabling online multi-session map alignment and reuse with global consistency at large scale. We implement a chained loop closure mechanism that efficiently propagates geometric constraints across inter-session keyframes through an adjacency graph, enabling robust long-horizon consistency triggered by reliable short-horizon loop closures. The system initializes inter-session alignment with GNSS-proximity place recognition, then performs on-the-fly loop closure detections and joint optimization of loaded maps and newly acquired trajectories within a unified factor graph, maintaining both inter- and intra-session geometric consistency without dynamic object removal, and cross-platform robustness with minimal hyperparameter tuning. Experimental results show improved trajectory accuracy and robust multi-session integration on large-scale datasets. We release our source code to support reproducible research in large-scale multi-session LiDAR SLAM. Project site: https://ai4ce.github.io/Chain-SLAM/