Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

FR-SLAM: A SLAM Improvement Method Based on Floor Plan Registration

Jiantao Feng, Xinde Li, HyunCheol Park, Juan Liu, Zhentong Zhang

TL;DR

Indoor SLAM often suffers from slow map composition and localization drift. FR-SLAM addresses this by registering partial LiDAR-derived occupancy with 2D floor plans through morphology-based transformations and by employing a real-time update loop to refine alignment, enabling rapid motion-map generation and planning. The approach achieves high floor-plan registration accuracy (IoU-based; $IoU_a$ > 0.85 and up to 0.94 with complete LiDAR data) and reduces rescue-task times in simulated scenarios (up to 6.7% faster than competitive methods). While effective in 2D, extending to 3D point-cloud information is planned to enhance registration fidelity and navigation in complex indoor environments.

Abstract

Simultaneous Localization and Mapping (SLAM) technology enables the construction of environmental maps and localization, serving as a key technique for indoor autonomous navigation of mobile robots. Traditional SLAM methods typically require exhaustive traversal of all rooms during indoor navigation to obtain a complete map, resulting in lengthy path planning times and prolonged time to reach target points. Moreover, cumulative errors during motion lead to inaccurate robot localization, impacting navigation efficiency.This paper proposes an improved SLAM method, FR-SLAM, based on floor plan registration, utilizing a morphology-based floor plan registration algorithm to align and transform original floor plans. This approach facilitates the rapid acquisition of comprehensive motion maps and efficient path planning, enabling swift navigation to target positions within a shorter timeframe. To enhance registration and robot motion localization accuracy, a real-time update strategy is employed, comparing the current position's building structure with the map and dynamically updating floor plan registration results for precise localization. Comparative tests conducted on real and simulated datasets demonstrate that, compared to other benchmark algorithms, this method achieves higher floor plan registration accuracy and shorter time consumption to reach target positions.

FR-SLAM: A SLAM Improvement Method Based on Floor Plan Registration

TL;DR

Indoor SLAM often suffers from slow map composition and localization drift. FR-SLAM addresses this by registering partial LiDAR-derived occupancy with 2D floor plans through morphology-based transformations and by employing a real-time update loop to refine alignment, enabling rapid motion-map generation and planning. The approach achieves high floor-plan registration accuracy (IoU-based; > 0.85 and up to 0.94 with complete LiDAR data) and reduces rescue-task times in simulated scenarios (up to 6.7% faster than competitive methods). While effective in 2D, extending to 3D point-cloud information is planned to enhance registration fidelity and navigation in complex indoor environments.

Abstract

Simultaneous Localization and Mapping (SLAM) technology enables the construction of environmental maps and localization, serving as a key technique for indoor autonomous navigation of mobile robots. Traditional SLAM methods typically require exhaustive traversal of all rooms during indoor navigation to obtain a complete map, resulting in lengthy path planning times and prolonged time to reach target points. Moreover, cumulative errors during motion lead to inaccurate robot localization, impacting navigation efficiency.This paper proposes an improved SLAM method, FR-SLAM, based on floor plan registration, utilizing a morphology-based floor plan registration algorithm to align and transform original floor plans. This approach facilitates the rapid acquisition of comprehensive motion maps and efficient path planning, enabling swift navigation to target positions within a shorter timeframe. To enhance registration and robot motion localization accuracy, a real-time update strategy is employed, comparing the current position's building structure with the map and dynamically updating floor plan registration results for precise localization. Comparative tests conducted on real and simulated datasets demonstrate that, compared to other benchmark algorithms, this method achieves higher floor plan registration accuracy and shorter time consumption to reach target positions.
Paper Structure (12 sections, 9 equations, 6 figures, 2 tables, 3 algorithms)

This paper contains 12 sections, 9 equations, 6 figures, 2 tables, 3 algorithms.

Table of Contents

  1. Introduction
  2. RELATED WORK
  3. METHOD
  4. Floor Plan Registration
  5. Image Preprocessing
  6. Image Registration
  7. Real-time updating strategy
  8. EXPERIMENTS
  9. Dataset Construction
  10. Comparison of registration
  11. Simulated Rescue Scenario Testing
  12. CONCLUSIONS

Figures (6)

  • Figure 1: Schematic diagram of FR-SLAM algorithm
  • Figure 2: The overall workflow of FR-SLAM based on floor plans registration, including LiDAR map generation, original floor plans registration, and map update strategy.
  • Figure 3: (a) The LiDAR map obtained by the robot running in the actual environment (b) Simulation environment generating LiDAR map
  • Figure 4: (a) Annotate the floor plan obtained from the network (b) Annotate the manually drawn floor plan
  • Figure 5: The folding accuracy, rotation accuracy, and $IoU_a$ are evaluated for different degrees of completeness in the LiDAR map
  • ...and 1 more figures