Interactive Multi-Trajectory SLAM for Large-Scale Mapping

Simultaneous localization and mapping (SLAM) has shown significant success in constructing environmental map. However, as the scale of the environment expands, the accuracy and global consistency of these maps tend to decrease. In response to this challenge, we introduce an interactive multi-trajectory SLAM framework designed for large-scale mapping, with the aim of enhancing both the quality and scale of the generated maps. This framework optimizes a pose graph comprising initial constraints generated by an automatic SLAM process, supplemented by additional map merging and correction constraints created by users via a graphical user interface (GUI). We propose a human-assisted inter-trajectory loop closing technique for manually adding map merging constraints. Evaluation results confirm the efficacy of our proposed framework in achieving a large-scale, consistent environmental map with minimal human effort. Furthermore, it demonstrates robustness for large-scale incremental mapping.