Long-term mapping techniques for ship hull inspection and surveillance using an autonomous underwater vehicle

This paper reports on a system for an autonomous underwater vehicle to perform in-situ, multiple session, hull inspection using long-term simultaneous localization and mapping (SLAM). Our method assumes very little a-priori knowledge, and does not require the aid of acoustic beacons for navigation, which is a typical mode of navigation in this type of ap-plication. Our system combines recent techniques in underwater saliency-informed visual SLAM and a method for representing the ship hull surface as a collection of many locally planar surface features. This methodology produces accurate maps that can be constructed in real-time on consumer-grade computing hardware. A single-session SLAM result is ini-tially used as a prior map for later sessions, where the robot automatically merges the mul-tiple surveys into a common hull-relative reference frame. To perform the re-localization step, we use a particle filter that leverages the locally planar representation of the ship hull surface, and a fast visual descriptor matching algorithm. Finally, we apply the recently-developed graph sparsification tool, generic linear constraints (GLC), as a way to manage the computational complexity of the SLAM system as the robot accumulates information across multiple sessions. We show results for 20 SLAM sessions for two large vessels over the course of days, months, and even up to three years, with a total path length of approx-imately 10.2 km.