🐢TURTLMap: Real-time Localization and Dense Mapping of Low-texture Underwater Environments with a Low-cost Unmanned Underwater Vehicle

Jingyu Song1*, Onur Bagoren1*, Razan Andigani1 Advaith Sethuraman1 Katherine A. Skinner1
*Equal Contribution 1University of Michigan
Paper arXiv Video Code (coming soon)

We present TURTLMap, a novel solution that focuses on Textureless Underwater environments through a Real-Time Localization and Mapping method.

TURTLMap

Abstract

Significant work has been done on advancing localization and mapping in underwater environments. Still, state-of-the-art methods are challenged by low-texture environments, which is common for underwater settings. This makes it difficult to use existing methods in diverse, real-world scenes. In this paper, we present TURTLMap, a novel solution that focuses on Textureless Underwater environments through a Real-Time Localization and Mapping method. We show that this method is low-cost, and capable of tracking the robot accurately, while constructing a dense map of a low-textured environment in real-time. We evaluate the proposed method using real-world data collected in an indoor water tank with a motion capture system and ground truth map reference. Qualitative and quantitative results validate the proposed system achieves accurate and robust localization and precise dense mapping, even when subject to wave conditions.

Overview

We propose a pose graph-based DVL-inertial-barometer localization package that achieves improved localization accuracy in low-texture regions.

With the proposed localization package and a real-time volumetric mapping package, we demonstrate real-time and accurate dense mapping on an onboard embedded computer on a low-cost UUV with a downward-facing stereo camera in a low-texture underwater environment.

We provide extensive quantitative and qualitative evaluation on localization and mapping performance with ground truth localization provided by an underwater motion capture system and reference mapping provided by a 3D CAD model of the experimental site with and without wave conditions. Our contribution include detailed description of integrated hardware and we provide open-source software supporting future implementation and extension for the research community.

TURTLMap Overview

BibTeX

@article{song2024turtlmap,
      title={TURTLMap: Real-time Localization and Dense Mapping of Low-texture Underwater Environments with a Low-cost Unmanned Underwater Vehicle},
      author={Song, Jingyu and Bagoren, Onur and Andigani, Razan and Sethuraman, Advaith Venkatramanan and Skinner, Katherine},
      journal={arXiv preprint arXiv:2408.01569},
      year={2024},
}