Multi-session Localization and Mapping Exploiting Topological Information

TL;DR

The paper addresses the need for robust, scalable operation in previously visited environments by moving beyond full SLAM in every session. It introduces a graph-based multi-session framework that couples map-based localization with selective mapping, guided by a topology-informed decision module that analyzes pose-graph connectivity. Key contributions include transforming the reference map into an active localization target, employing weighted connectivity metrics $\bar{d}$ and $\bar{\lambda}_2$ to drive a two-step consensus that switches between localization and mapping, and robust inter-session loop closure. Experimental results on public datasets and a mine deployment demonstrate improved global consistency, reduced graph complexity, and strong performance in unmapped regions, highlighting practical viability for lifelong mapping tasks.

Abstract

Operating in previously visited environments is becoming increasingly crucial for autonomous systems, with direct applications in autonomous driving, surveying, and warehouse or household robotics. This repeated exposure to observing the same areas poses significant challenges for mapping and localization -- key components for enabling any higher-level task. In this work, we propose a novel multi-session framework that builds on map-based localization, in contrast to the common practice of greedily running full SLAM sessions and trying to find correspondences between the resulting maps. Our approach incorporates a topology-informed, uncertainty-aware decision-making mechanism that analyzes the pose-graph structure to detect low-connectivity regions, selectively triggering mapping and loop closing modules. The resulting map and pose-graph are seamlessly integrated into the existing model, reducing accumulated error and enhancing global consistency. We validate our method on overlapping sequences from datasets and demonstrate its effectiveness in a real-world mine-like environment.

Figures (8)

• Figure 1: Map and pose-graph built after processing three overlapping sessions of the Newer College Extension dataset zhang21 (Quad M, Quad H, Cloister); each depicted in a different color for visualization.
• Figure 2: Overview of the proposed method.
• Figure 3: Visualization of the different graphs used in the multi-session approach. The active graph (blue) is constructed from selected key frames from the odometry graph (gray) along with their condensed measurements, as well as vertices from the reference graph (orange) that are connected via inter-session correspondences. When triggered by the topological decision-making module (e.g., in unmapped regions), a subset of the active graph (candidate graph, green) is integrated into the reference model. Finally, LC and global PGO are performed to reconcile measurements across sessions and ensure consistency.
• Figure 4: Illustration of the evolution over time of the weighted connectivity indices (blue: $\bar{d}$, red: $\bar{\lambda}_2$) during the traversal of previously unmapped regions. Stage I corresponds to traversal within previously mapped regions, where localization is performed. Stage II indicates entry into unmapped regions, resulting in disconnection between the reference and active graphs, and necessitating mapping. Stage III marks reconnection with the prior model and re-establishes map-based localization. The topmost images illustrate examples of these phases: the orange map and PG are the reference model, while the blue ones correspond to the online point cloud and sliding graph.
• Figure 5: Multi-session mapping results in NC and NCE datasets: Quad-e (orange), Quad-m (teal), Quad-h (red), Cloister (purple), and Short (blue). Notably, overlapping regions are modeled only once (both in the map and the PG).