A Chefs KISS -- Utilizing semantic information in both ICP and SLAM framework

2025-04-02

AI Summary

Dynamic objects (e.g., moving or parked vehicles) severely degrade HD map construction and relocalization in urban autonomous driving. Method: This paper proposes a semantic-enhanced LiDAR SLAM framework comprising two core components: (i) a lightweight, generalizable semantic weighting scheme integrated into KISS-ICP for robust point cloud registration; and (ii) an extended Cartographer backend supporting semantic-aware dynamic object removal and semantic-constrained loop closure optimization. The framework unifies semantic point cloud filtering, semantic-aware ICP registration, enhanced SLAM mapping, and LiDAR odometry. Contribution/Results: Experimental evaluation demonstrates significantly lower absolute trajectory error (ATE) compared to baseline KISS-ICP. Moreover, the system enables semantic-category-specific map filtering (e.g., excluding “parked vehicle” points), substantially improving relocalization stability and long-term mapping consistency in dynamic urban environments.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services

Abstract

For utilizing autonomous vehicle in urban areas a reliable localization is needed. Especially when HD maps are used, a precise and repeatable method has to be chosen. Therefore accurate map generation but also re-localization against these maps is necessary. Due to best 3D reconstruction of the surrounding, LiDAR has become a reliable modality for localization. The latest LiDAR odometry estimation are based on iterative closest point (ICP) approaches, namely KISS-ICP and SAGE-ICP. We extend the capabilities of KISS-ICP by incorporating semantic information into the point alignment process using a generalizable approach with minimal parameter tuning. This enhancement allows us to surpass KISS-ICP in terms of absolute trajectory error (ATE), the primary metric for map accuracy. Additionally, we improve the Cartographer mapping framework to handle semantic information. Cartographer facilitates loop closure detection over larger areas, mitigating odometry drift and further enhancing ATE accuracy. By integrating semantic information into the mapping process, we enable the filtering of specific classes, such as parked vehicles, from the resulting map. This filtering improves relocalization quality by addressing temporal changes, such as vehicles being moved.

Problem

• Improving LiDAR localization accuracy using semantic information
• Enhancing map generation and re-localization in urban environments
• Reducing odometry drift with semantic-aided loop closure detection

Innovation

• Incorporating semantic info into KISS-ICP
• Enhancing Cartographer with semantic filtering
• Improving map accuracy via semantic LiDAR