Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

NV-LIO: LiDAR-Inertial Odometry using Normal Vectors Towards Robust SLAM in Multifloor Environments

Dongha Chung, Jinwhan Kim

Abstract

Over the last few decades, numerous LiDAR-inertial odometry (LIO) algorithms have been developed, demonstrating satisfactory performance across diverse environments. Most of these algorithms have predominantly been validated in open outdoor environments, however they often encounter challenges in confined indoor settings. In such indoor environments, reliable point cloud registration becomes problematic due to the rapid changes in LiDAR scans and repetitive structural features like walls and stairs, particularly in multifloor buildings. In this paper, we present NV-LIO, a normal vector based LIO framework, designed for simultaneous localization and mapping (SLAM) in indoor environments with multifloor structures. Our approach extracts the normal vectors from the LiDAR scans and utilizes them for correspondence search to enhance the point cloud registration performance. To ensure robust registration, the distribution of the normal vector directions is analyzed, and situations of degeneracy are examined to adjust the matching uncertainty. Additionally, a viewpoint based loop closure module is implemented to avoid wrong correspondences that are blocked by the walls. The propsed method is validated through public datasets and our own dataset. To contribute to the community, the code will be made public on https://github.com/dhchung/nv_lio.

NV-LIO: LiDAR-Inertial Odometry using Normal Vectors Towards Robust SLAM in Multifloor Environments

Abstract

Over the last few decades, numerous LiDAR-inertial odometry (LIO) algorithms have been developed, demonstrating satisfactory performance across diverse environments. Most of these algorithms have predominantly been validated in open outdoor environments, however they often encounter challenges in confined indoor settings. In such indoor environments, reliable point cloud registration becomes problematic due to the rapid changes in LiDAR scans and repetitive structural features like walls and stairs, particularly in multifloor buildings. In this paper, we present NV-LIO, a normal vector based LIO framework, designed for simultaneous localization and mapping (SLAM) in indoor environments with multifloor structures. Our approach extracts the normal vectors from the LiDAR scans and utilizes them for correspondence search to enhance the point cloud registration performance. To ensure robust registration, the distribution of the normal vector directions is analyzed, and situations of degeneracy are examined to adjust the matching uncertainty. Additionally, a viewpoint based loop closure module is implemented to avoid wrong correspondences that are blocked by the walls. The propsed method is validated through public datasets and our own dataset. To contribute to the community, the code will be made public on https://github.com/dhchung/nv_lio.
Paper Structure (17 sections, 10 equations, 9 figures, 2 tables)

This paper contains 17 sections, 10 equations, 9 figures, 2 tables.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORK
  3. METHOD
  4. System Overview
  5. Preprocessing
  6. Spherical Projection & Normal Extraction
  7. Normal Cloud Registration
  8. Loop Closure Detection
  9. Degeneracy Detection
  10. Pose-Graph SLAM Framework
  11. Implementation Details
  12. EXPERIMENTAL VALIDATION
  13. Results
  14. SubT-MRS Multifloor Dataset
  15. Newer College Dataset
  16. ...and 2 more sections

Figures (9)

  • Figure 1: Mapping result of the KI building, a five-story building at KAIST, using NV-LIO. (a) shows the overall mapping result and LiDAR trajectory. (b) shows the comparison of photography taken indoors of the building with the mapping result.
  • Figure 2: The framework of the proposed algorithm
  • Figure 3: Normal extraction process
  • Figure 4: Inter-floor loop closure detection example using viewpoint based loop detection
  • Figure 5: Degenerate cases in the stairwell and in the long corridor environment
  • ...and 4 more figures