PRISM-Loc: a Lightweight Long-range LiDAR Localization in Urban Environments with Topological Maps

2025-06-18

AI Summary

To address the trade-off between real-time performance and memory overhead in long-range autonomous vehicle localization within large-scale urban environments, this paper proposes a lightweight LiDAR-based localization framework leveraging topological maps. The method adopts a two-stage paradigm: (1) efficient global place recognition via compact topological map matching using learned descriptors; and (2) high-precision local pose estimation through joint 2D edge/line feature extraction and geometric point-cloud optimization. This work is the first to introduce topological representation into long-range LiDAR localization and innovatively integrates 2D-feature-guided point-cloud refinement. Evaluated on the ITLP-Campus dataset over a 3 km urban route, the framework achieves superior localization accuracy compared to state-of-the-art metric mapping and place recognition approaches, while improving inference speed by 2.3× and reducing memory footprint by 68%.

Technology Category

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

Application Category

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

Abstract

Localization in the environment is one of the crucial tasks of navigation of a mobile robot or a self-driving vehicle. For long-range routes, performing localization within a dense global lidar map in real time may be difficult, and the creation of such a map may require much memory. To this end, leveraging topological maps may be useful. In this work, we propose PRISM-Loc -- a topological map-based approach for localization in large environments. The proposed approach leverages a twofold localization pipeline, which consists of global place recognition and estimation of the local pose inside the found location. For local pose estimation, we introduce an original lidar scan matching algorithm, which is based on 2D features and point-based optimization. We evaluate the proposed method on the ITLP-Campus dataset on a 3 km route, and compare it against the state-of-the-art metric map-based and place recognition-based competitors. The results of the experiments show that the proposed method outperforms its competitors both quality-wise and computationally-wise.

Problem

• Lightweight LiDAR localization for long-range urban navigation
• Efficient topological map-based localization to reduce memory usage
• Accurate lidar scan matching with 2D features and optimization

Innovation

• Topological map-based localization approach
• 2D feature lidar scan matching
• Lightweight long-range urban localization