Detection and Inspection of Local Bottom Objects with the Help of a Group of Special-Purpose AUVs

Abstract

Autonomous Unmanned Underwater Vehicles (AUV) equipped with side-scan sonars (SSS) and photo systems may be used for automatic detection and inspection of local bottom objects. SSS allows efficient identification of bottom objects at a considerable distance, while photo the system is used for detailed registration of object states in the short-range zone. To carry out monitoring, both scenarios assume the use of a single multi-purpose AUV (cycling through the stages of detection and photo survey) and a group of special-purpose AUVs simultaneously performing these missions is possible. Online detection of predetermined objects on acoustic images is carried out with the help of algorithms. They include: gradient field mapping, objects boundaries detection, and detection of the objects themselves by means of clustering procedures. Then the objects meeting preset characteristics shall be chosen and their coordinates determined. The coordinates obtained are used for arrangement of AUV approaching the object detected and carrying out its photo coverage. This paper focuses on model simulation of monitoring tasks, including investigation of object identification algorithms and AUV control in case of a single and group application. The results of experiments that confirmed the possibility for application of the developed algorithms during real operations are discussed.