Towards three-dimensional underwater mapping without odometry

Abstract

This paper presents a method for the creation of three-dimensional maps of underwater cisterns and wells using a submersible robot equipped with two scanning sonars and a compass. Previous work in this area utilized a particle filter to perform offline simultaneous localization and mapping (SLAM) in two dimensions using a single sonar. This work utilizes scan matching and incorporates an additional sonar that scans in a perpendicular plane. Given a set of overlapping horizontal and vertical sonar scans, an algorithm was implemented to map underwater chambers by matching sets of scans using a weighted iterative closest point (ICP) method. This matching process has been augmented to align the features of the underwater cistern data without robot odometry. Results from a swimming pool and an archeological site trials indicate successful mapping is achieved.