SVIn2: Sonar Visual-Inertial SLAM with Loop Closure for Underwater Navigation
This paper presents a novel tightly-coupled keyframe based Simultaneous Localization and Mapping (SLAM) system with loop-closing and relocalization capabilities targeted to the underwater domain. The state-of-the-art visual-inertial state estimation package OKVIS has been significantly augmented to accommodate acoustic data from sonar and depth measurements from pressure sensor, along with visual and inertial data in a non-linear optimization-based framework. The main contributions of this paper are: a robust initialization method to refine scale using depth measurements and a real-time loop-closing and relocalization method. An additional contribution is the tightly-coupled optimization formulation using acoustic, visual, inertial, and depth data. Experimental results on datasets collected with a custom-made underwater sensor suite and an autonomous underwater vehicle from challenging underwater environments with poor visibility demonstrate the performance of our approach.
READ FULL TEXT