Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

DAMM-LOAM: Degeneracy Aware Multi-Metric LiDAR Odometry and Mapping

Nishant Chandna, Akshat Kaushal

TL;DR

DAMM-LOAM tackles degeneracy in LiDAR SLAM by coupling normal-map based semantic feature extraction with a Hessian-based, observability-aware weighting scheme within a multi-metric ICP framework. It classifies points into Ground, Roof, Wall, Edge, and Unknown to enable robust correspondences, and uses per-point weights derived from translational Hessian eigenvalues to downweight poorly observable directions. A Scan Context back-end provides loop closures to enforce global consistency, improving absolute pose accuracy in indoor corridors and degenerate environments. The approach demonstrates robust, LiDAR-only performance in challenging geometries, with practical impact for indoor navigation and reconstructive mapping where features are sparse or repetitive.

Abstract

LiDAR Simultaneous Localization and Mapping (SLAM) systems are essential for enabling precise navigation and environmental reconstruction across various applications. Although current point-to-plane ICP algorithms perform effec- tively in structured, feature-rich environments, they struggle in scenarios with sparse features, repetitive geometric structures, and high-frequency motion. This leads to degeneracy in 6- DOF pose estimation. Most state-of-the-art algorithms address these challenges by incorporating additional sensing modalities, but LiDAR-only solutions continue to face limitations under such conditions. To address these issues, we propose a novel Degeneracy-Aware Multi-Metric LiDAR Odometry and Map- ping (DAMM-LOAM) module. Our system improves mapping accuracy through point cloud classification based on surface normals and neighborhood analysis. Points are classified into ground, walls, roof, edges, and non-planar points, enabling accurate correspondences. A Degeneracy-based weighted least squares-based ICP algorithm is then applied for accurate odom- etry estimation. Additionally, a Scan Context based back-end is implemented to support robust loop closures. DAMM-LOAM demonstrates significant improvements in odometry accuracy, especially in indoor environments such as long corridors

DAMM-LOAM: Degeneracy Aware Multi-Metric LiDAR Odometry and Mapping

TL;DR

DAMM-LOAM tackles degeneracy in LiDAR SLAM by coupling normal-map based semantic feature extraction with a Hessian-based, observability-aware weighting scheme within a multi-metric ICP framework. It classifies points into Ground, Roof, Wall, Edge, and Unknown to enable robust correspondences, and uses per-point weights derived from translational Hessian eigenvalues to downweight poorly observable directions. A Scan Context back-end provides loop closures to enforce global consistency, improving absolute pose accuracy in indoor corridors and degenerate environments. The approach demonstrates robust, LiDAR-only performance in challenging geometries, with practical impact for indoor navigation and reconstructive mapping where features are sparse or repetitive.

Abstract

LiDAR Simultaneous Localization and Mapping (SLAM) systems are essential for enabling precise navigation and environmental reconstruction across various applications. Although current point-to-plane ICP algorithms perform effec- tively in structured, feature-rich environments, they struggle in scenarios with sparse features, repetitive geometric structures, and high-frequency motion. This leads to degeneracy in 6- DOF pose estimation. Most state-of-the-art algorithms address these challenges by incorporating additional sensing modalities, but LiDAR-only solutions continue to face limitations under such conditions. To address these issues, we propose a novel Degeneracy-Aware Multi-Metric LiDAR Odometry and Map- ping (DAMM-LOAM) module. Our system improves mapping accuracy through point cloud classification based on surface normals and neighborhood analysis. Points are classified into ground, walls, roof, edges, and non-planar points, enabling accurate correspondences. A Degeneracy-based weighted least squares-based ICP algorithm is then applied for accurate odom- etry estimation. Additionally, a Scan Context based back-end is implemented to support robust loop closures. DAMM-LOAM demonstrates significant improvements in odometry accuracy, especially in indoor environments such as long corridors
Paper Structure (14 sections, 13 equations, 3 figures, 3 tables)

This paper contains 14 sections, 13 equations, 3 figures, 3 tables.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORK
  3. LiDAR Odometry
  4. Feature Extraction
  5. Degeneracy Awareness
  6. SYSTEM OVERVIEW
  7. Geometric Feature Extraction
  8. Spherical Projection
  9. Surface Normal Estimation
  10. Normal-Based Geometric Classification (Proposed)
  11. Degeneracy Aware Weighting
  12. Scan-Context Back-end
  13. Results
  14. CONCLUSIONS

Figures (3)

  • Figure 1: The image demonstrates feature classification and mapping accuracy of DAMM-LOAM on Ground Challenge Corridor 1 Dataset
  • Figure 2: The pipeline extracts surface normals from LiDAR point cloud, classifies points into structural elements, and performs robust, degeneracy-aware odometry and mapping with loop closure using Scan Context for global consistency.
  • Figure 3: Overview of the geometric classification pipeline: The raw LiDAR point cloud is projected into a spherical range image, surface normals are computed using local neighborhoods, and each point is subsequently categorized into geometric classes.