Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Framework for Robust Localization of UUVs and Mapping of Net Pens

David Botta, Luca Ebner, Andrej Studer, Victor Reijgwart, Roland Siegwart, Eleni Kelasidi

Abstract

This paper presents a general framework integrating vision and acoustic sensor data to enhance localization and mapping in highly dynamic and complex underwater environments, with a particular focus on fish farming. The proposed pipeline is suited to obtain both the net-relative pose estimates of an Unmanned Underwater Vehicle (UUV) and the depth map of the net pen purely based on vision data. Furthermore, this paper presents a method to estimate the global pose of an UUV fusing the net-relative pose estimates with acoustic data. The pipeline proposed in this paper showcases results on datasets obtained from industrial-scale fish farms and successfully demonstrates that the vision-based TRU-Depth model, when provided with sparse depth priors from the FFT method and combined with the Wavemap method, can estimate both net-relative and global position of the UUV in real time and generate detailed 3D maps suitable for autonomous navigation and inspection purposes.

Framework for Robust Localization of UUVs and Mapping of Net Pens

Abstract

This paper presents a general framework integrating vision and acoustic sensor data to enhance localization and mapping in highly dynamic and complex underwater environments, with a particular focus on fish farming. The proposed pipeline is suited to obtain both the net-relative pose estimates of an Unmanned Underwater Vehicle (UUV) and the depth map of the net pen purely based on vision data. Furthermore, this paper presents a method to estimate the global pose of an UUV fusing the net-relative pose estimates with acoustic data. The pipeline proposed in this paper showcases results on datasets obtained from industrial-scale fish farms and successfully demonstrates that the vision-based TRU-Depth model, when provided with sparse depth priors from the FFT method and combined with the Wavemap method, can estimate both net-relative and global position of the UUV in real time and generate detailed 3D maps suitable for autonomous navigation and inspection purposes.
Paper Structure (14 sections, 10 figures)

This paper contains 14 sections, 10 figures.

Table of Contents

  1. Introduction
  2. Proposed Framework
  3. Field Trials and Datasets
  4. Net-relative Pose Estimation
  5. Depth Images
  6. Global Pose Estimation
  7. 3D Map Representation
  8. Results
  9. Net-relative Pose Estimation
  10. Depth Images
  11. Global Pose Estimation
  12. 3D Map Representation
  13. Conclusions
  14. Acknowledgement

Figures (10)

  • Figure 1: Overview of the general framework for localization and mapping for UUVs operating in dynamically changing environments
  • Figure 2: ROV with integrated sensors used in the field trials.
  • Figure 3: Net relative distance results.
  • Figure 4: Net relative orientation results.
  • Figure 5: Comparison of depth images. 1: RGB Image; 2: TRU-Depth; 3: Retrained TRU-Depth; 4: DVL Reference.
  • ...and 5 more figures