MLATC: Fast Hierarchical Topological Mapping from 3D LiDAR Point Clouds Based on Adaptive Resonance Theory

2025-11-27

AI Summary

To address scalability bottlenecks in global topological mapping from 3D LiDAR point clouds within large-scale, dynamic, and unknown environments, this paper proposes a multi-layer hierarchical mapping framework grounded in Adaptive Resonance Theory (ART). The method introduces a hierarchical node structure coupled with a dynamic layer-growth mechanism to circumvent the high computational cost of conventional nearest-neighbor searches. By integrating a coarse-to-fine hierarchical nearest-neighbor strategy with ART-based clustering, it enables online, incremental generation of topological nodes while mitigating catastrophic forgetting. Evaluated on both simulated and real-world campus-scale datasets, the approach achieves millisecond-level per-frame processing; search time scales nearly logarithmically with the number of nodes. It significantly outperforms ATC-DT in mapping efficiency, enabling real-time, scalable global environmental perception.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This paper addresses the problem of building global topological maps from 3D LiDAR point clouds for autonomous mobile robots operating in large-scale, dynamic, and unknown environments. Adaptive Resonance Theory-based Topological Clustering with Different Topologies (ATC-DT) builds global topological maps represented as graphs while mitigating catastrophic forgetting during sequential processing. However, its winner selection mechanism relies on an exhaustive nearest-neighbor search over all existing nodes, leading to scalability limitations as the map grows. To address this challenge, we propose a hierarchical extension called Multi-Layer ATC (MLATC). MLATC organizes nodes into a hierarchy, enabling the nearest-neighbor search to proceed from coarse to fine resolutions, thereby drastically reducing the number of distance evaluations per query. The number of layers is not fixed in advance. MLATC employs an adaptive layer addition mechanism that automatically deepens the hierarchy when lower layers become saturated, keeping the number of user-defined hyperparameters low. Simulation experiments on synthetic large-scale environments show that MLATC accelerates topological map building compared to the original ATC-DT and exhibits a sublinear, approximately logarithmic scaling of search time with respect to the number of nodes. Experiments on campus-scale real-world LiDAR datasets confirm that MLATC maintains a millisecond-level per-frame runtime and enables real-time global topological map building in large-scale environments, significantly outperforming the original ATC-DT in terms of computational efficiency.

Problem

• Building global topological maps from 3D LiDAR point clouds for autonomous robots in large-scale dynamic environments
• Overcoming scalability limitations of exhaustive nearest-neighbor searches in growing topological maps
• Enabling real-time topological mapping with adaptive hierarchical structure and reduced computational cost

Innovation

• Hierarchical organization of nodes for efficient search
• Adaptive layer addition mechanism to deepen hierarchy
• Sublinear scaling of search time with node count