Online Stochastic Variational Gaussian Process Mapping for Large-Scale SLAM in Real Time

TL;DR

This paper introduces an online stochastic variational Gaussian process mapping method designed for large-scale, real-time SLAM in underwater environments, addressing the challenges of autonomous underwater vehicle navigation without reliance on external infrastructure.

Contribution

It presents a novel online stochastic variational Gaussian process approach for efficient, real-time large-scale SLAM suitable for autonomous underwater vehicles.

Findings

Enables real-time SLAM in large-scale underwater environments.

Reduces dependence on external infrastructure like GPS or acoustic positioning.

Improves navigation accuracy for deep-sea exploration.

Abstract

Autonomous underwater vehicles (AUVs) are becoming standard tools for underwater exploration and seabed mapping in both scientific and industrial applications \cite{graham2022rapid, stenius2022system}. Their capacity to dive untethered allows them to reach areas inaccessible to surface vessels and to collect data more closely to the seafloor, regardless of the water depth. However, their navigation autonomy remains bounded by the accuracy of their dead reckoning (DR) estimate of their global position, severely limited in the absence of a priori maps of the area and GPS signal. Global localization systems equivalent to the later exists for the underwater domain, such as LBL or USBL. However they involve expensive external infrastructure and their reliability decreases with the distance to the AUV, making them unsuitable for deep sea surveys.