Long-term Mapping Techniques for Ship Hull Inspection and Surveillance using an Autonomous Underwater Vehicle
Long-term Mapping Techniques for Ship Hull Inspection and Surveillance using an Autonomous Underwater Vehicle
复制标题
DOI：
10.1002/rob.21582
复制
发表时间：
2016-05-01
影响因子：
8.3
通讯作者：
Eustice, Ryan M.
中科院分区：
文献类型：
--
作者：
Ozog, Paul;Carlevaris-Bianco, Nicholas;Eustice, Ryan M.
本文报道了一种用于自主水下航行器的系统，该系统使用长期同时定位和映射（SLAM）来执行原位、多会话船体检查。我们的方法假设很少的先验知识，并且不需要声学信标的帮助来进行导航，这是此类应用中的典型导航模式。我们的系统结合了水下显着性视觉 SLAM 的最新技术和将船体表面表示为许多局部平面表面特征的集合的方法。这种方法可以生成准确的地图，可以在消费级计算硬件上实时构建。单会话 SLAM 结果最初用作后续会话的先前地图，其中机器人自动将多个测量合并到公共的相对于船体的参考系中。为了执行重新定位步骤，我们使用粒子滤波器，该滤波器利用船体表面的局部平面表示和快速视觉描述符匹配算法。最后，我们应用最近开发的图稀疏工具（通用线性约束）作为机器人在多个会话中积累信息时管理 SLAM 系统计算复杂性的方法。我们展示了两艘大型船只在几天、几个月甚至长达三年的时间里进行 20 次 SLAM 会话的结果，总路径长度约为 10.2 公里。
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 it does not require the aid of acoustic beacons for navigation, which is a typical mode of navigation in this type of application. 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 initially used as a prior map for later sessions, where the robot automatically merges the multiple surveys into a common hull-relative reference frame. To perform the relocalization 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, 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 approximately 10.2 km.