II-NVM: Enhancing Map Accuracy and Consistency with Normal Vector-Assisted Mapping

2025-04-11

AI Summary

To address the “dual-surface mapping problem” in indoor SLAM—where adjacent planar surfaces are erroneously merged into a single plane—this paper proposes a normal-vector-augmented voxel-based SLAM framework. First, we design an enhanced voxel map structure that jointly encodes point coordinates and surface normals. Second, we introduce a normal-vector consistency constraint to guide neighborhood search and incremental map updates. Third, we propose an adaptive-radius KD-tree search coupled with an LRU-based caching strategy for efficient voxel management. We further construct the first dedicated synthetic and real-world benchmark datasets for this problem and publicly release the source code. Experiments demonstrate that our method significantly suppresses erroneous dual-surface merging, reducing average planar separation error by 62% across diverse indoor scenes, while substantially improving both mapping accuracy and geometric consistency.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Mixed Discrete/Continuous Search
• Planning, Routing, and Scheduling: Replanning and Plan Repair

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
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

SLAM technology plays a crucial role in indoor mapping and localization. A common challenge in indoor environments is the"double-sided mapping issue", where closely positioned walls, doors, and other surfaces are mistakenly identified as a single plane, significantly hindering map accuracy and consistency. To address this issue this paper introduces a SLAM approach that ensures accurate mapping using normal vector consistency. We enhance the voxel map structure to store both point cloud data and normal vector information, enabling the system to evaluate consistency during nearest neighbor searches and map updates. This process distinguishes between the front and back sides of surfaces, preventing incorrect point-to-plane constraints. Moreover, we implement an adaptive radius KD-tree search method that dynamically adjusts the search radius based on the local density of the point cloud, thereby enhancing the accuracy of normal vector calculations. To further improve realtime performance and storage efficiency, we incorporate a Least Recently Used (LRU) cache strategy, which facilitates efficient incremental updates of the voxel map. The code is released as open-source and validated in both simulated environments and real indoor scenarios. Experimental results demonstrate that this approach effectively resolves the"double-sided mapping issue"and significantly improves mapping precision. Additionally, we have developed and open-sourced the first simulation and real world dataset specifically tailored for the"double-sided mapping issue".

Problem

• Resolves double-sided mapping issue in SLAM
• Improves map accuracy with normal vectors
• Enhances realtime performance using LRU cache

Innovation

• Enhances voxel map with normal vector data
• Uses adaptive radius KD-tree search method
• Implements LRU cache for efficient updates