LEMON-Mapping: Loop-Enhanced Large-Scale Multi-Session Point Cloud Merging and Optimization for Globally Consistent Mapping

Figure 1: The merging map of our framework in island sequence of MARS-L VIG [1] dataset, the details in the figure are framed and shown in two forms: side view (SV) and bird's eye view (BEV). Abstract --Multi-robot collaboration is becoming increasingly critical and presents significant challenges in modern robotics, especially for building a globally consistent, accurate map. Traditional multi-robot pose graph optimization (PGO) methods ensure basic global consistency but ignore the geometric structure of the map, and only use loop closures as constraints between pose nodes, leading to divergence and blurring in overlapping regions. T o address this issue, we propose LEMON-Mapping, a loop-enhanced framework for large-scale, multi-session point cloud fusion and optimization. We re-examine the role of loops for multi-robot mapping and introduce three key innovations. First, we develop a robust loop processing mechanism that rejects outliers and a loop recall strategy to recover mistakenly removed but valid loops. Second, we introduce spatial bundle adjustment for multi-robot maps, reducing divergence and eliminating blurring in overlaps. Third, we design a PGO-based approach that leverages refined bundle adjustment constraints to propagate local accuracy to the entire map. Scalability experiments also demonstrate its strong capability to handle scenarios involving numerous robots. ARGE-SCALE 3D mapping is a fundamental capability in modern robotics, providing rich geometric information that supports tasks such as drone-based inspection [2]-[4], autonomous driving [5], and long-term exploration with ground robots [6]. Furthermore, large-scale 3D maps are critical for emerging fields such as embodied AI, where agents interact with complex environments based on spatial understanding [7]. They also play a key role in end-to-end visuomotor navigation systems [8], which rely on accurate environmental priors to enhance generalization and robustness. Especially, multi-robot 3D mapping is essential for large-scale and complex tasks, where robot teams provide greater coverage and robustness compared to a single agent.