Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Real-Time Interpolation for Enhanced AUV Deep Sea Mapping

Devanshu Saxena

TL;DR

The paper tackles the challenge of real-time bathymetric interpolation onboard AUVs by proposing an edge-computing architecture that leverages GPU acceleration to reduce data transfer to surface assets. It systematically compares three interpolation methods—Bilinear, Catmull-Rom Cubic Spline, and Ordinary Kriging—across CPU and GPU implementations in Grid A (synthetic) and Grid B (GEBCO-based) trials, revealing substantial speedups on GPUs and superior accuracy of kriging, especially under sparse data conditions. The findings demonstrate that even low-end GPUs can deliver meaningful performance gains, enabling capable onboard processing that enhances mapping quality while extending mission duration. The work highlights practical implications for deep-sea exploration, including data-driven decisions about interpolation method choice and the viability of onboard real-time processing to alleviate bandwidth and comms limitations in underwater environments.

Abstract

Approximately seventy-one percent of the Earth is covered in water. Of that area, ninety-five percent of the ocean has never been explored or mapped. There are several engineering challenges that have prevented the exploration of the deep ocean through human or autonomous means. These challenges include but are not limited to high pressure, cold temperatures, little natural light, corrosion of materials, and communication. Ongoing research has been focused on trying to find optimal and low-cost solutions to effective communication between autonomous underwater vehicles (AUVs), and the surface or air. In this paper, an architecture is introduced that utilizes an edge computing approach to establish computation nearer to the source of data, allowing further exploration of the deep ocean. Taking the most common interpolation techniques used today in the field of bathymetry, the data are tested and analyzed to find the feasibility of switching from CPU to GPU computation. Specifically, the focus is on writing efficient interpolation algorithms that can be run on low-level GPUs, which can be carried onboard AUVs as payload.

Towards Real-Time Interpolation for Enhanced AUV Deep Sea Mapping

TL;DR

The paper tackles the challenge of real-time bathymetric interpolation onboard AUVs by proposing an edge-computing architecture that leverages GPU acceleration to reduce data transfer to surface assets. It systematically compares three interpolation methods—Bilinear, Catmull-Rom Cubic Spline, and Ordinary Kriging—across CPU and GPU implementations in Grid A (synthetic) and Grid B (GEBCO-based) trials, revealing substantial speedups on GPUs and superior accuracy of kriging, especially under sparse data conditions. The findings demonstrate that even low-end GPUs can deliver meaningful performance gains, enabling capable onboard processing that enhances mapping quality while extending mission duration. The work highlights practical implications for deep-sea exploration, including data-driven decisions about interpolation method choice and the viability of onboard real-time processing to alleviate bandwidth and comms limitations in underwater environments.

Abstract

Approximately seventy-one percent of the Earth is covered in water. Of that area, ninety-five percent of the ocean has never been explored or mapped. There are several engineering challenges that have prevented the exploration of the deep ocean through human or autonomous means. These challenges include but are not limited to high pressure, cold temperatures, little natural light, corrosion of materials, and communication. Ongoing research has been focused on trying to find optimal and low-cost solutions to effective communication between autonomous underwater vehicles (AUVs), and the surface or air. In this paper, an architecture is introduced that utilizes an edge computing approach to establish computation nearer to the source of data, allowing further exploration of the deep ocean. Taking the most common interpolation techniques used today in the field of bathymetry, the data are tested and analyzed to find the feasibility of switching from CPU to GPU computation. Specifically, the focus is on writing efficient interpolation algorithms that can be run on low-level GPUs, which can be carried onboard AUVs as payload.

Paper Structure

This paper contains 24 sections, 7 equations, 10 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Temperature and Pressure
  3. Corrosion and Darkness
  4. Sonar Mapping and Communication
  5. Proposed Solution
  6. Related Work
  7. GFOE Deep Discover
  8. Opensea IQ Edge
  9. Interpolation Methods
  10. Bilinear Interpolation
  11. Cubic Spline Interpolation (Catmull-Rom)
  12. Ordinary Kriging
  13. Additional Considerations
  14. Computational Design
  15. Experimental Findings
  16. ...and 9 more sections

Figures (10)

  • Figure 1: Example of data transfer architecture upon implementation of real time interpolation on an AUV
  • Figure 2: Zoomed-in view of a single interpolated value inside a larger grid. The red square represents the interpolated value
  • Figure 3: Specifications of the CPU device used in this study
  • Figure 4: Specifications of the GPU device used in this study
  • Figure 5: Original grid elevation map for Grid A testing.
  • ...and 5 more figures