English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

With the rapid development of robotics, multi-robot collaboration has becomecritical and challenging. One key problem is integrating data from multiplerobots to build a globally consistent and accurate map for robust cooperationand precise localization. While traditional multi-robot pose graph optimization(PGO) maintains basic global consistency, it focuses primarily on poseoptimization and ignores the geometric structure of the map. Moreover, PGO onlyuses loop closure as a constraint between two nodes, failing to fully exploitits capability to maintaining local consistency of multi-robot maps. Therefore,PGO-based multi-robot mapping methods often suffer from serious map divergenceand blur, especially in regions with overlapping submaps. To address thisissue, we propose Lemon-Mapping, a loop-enhanced framework for large-scalemulti-session point cloud map fusion and optimization, which reasonablyutilizes loop closure and improves the geometric quality of the map. Were-examine the role of loops for multi-robot mapping and introduce three keyinnovations. First, we develop a robust loop processing mechanism thateffectively rejects outliers and a novel loop recall strategy to recovermistakenly removed loops. Second, we introduce a spatial bundle adjustmentmethod for multi-robot maps that significantly reduces the divergence inoverlapping regions and eliminates map blur. Third, we design a PGO strategythat leverages the refined constraints of bundle adjustment to extend the localaccuracy to the global map. We validate our framework on several publicdatasets and a self-collected dataset. Experimental results demonstrate thatour method outperforms traditional map merging approaches in terms of mappingaccuracy and reduction of map divergence. Scalability experiments alsodemonstrate the strong capability of our framework to handle scenariosinvolving numerous robots.

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