No abstract

In this study, the authors developed the dynamic routing algorithm combining an image detection technique to support the optimal route plan of Autonomous Underwater Vehicle (AUV) inspecting an offshore wind farm affected by ocean currents. A modular structure is applied to program design by the graphical language, LabVIEW (Laboratory Virtual Instrument Engineering Workbench). The modular structure is composed of 6-DOF (Six Degrees-of-Freedom) motion module, a self-tuning fuzzy control module, a stereo-vision detection module, and a dynamic routing module. In terms of path planning for inspection, several Pareto frontiers are solved iteratively according to two objectives, namely, cruise time and energy consumption. Performances obtained from MOPSO (Multi-Objective Particle Swarm Optimization) -based dynamic routing algorithm would be in comparison with those from SOPSO (Single-Objective Particle Swarm Optimization) -based dynamic routing algorithm. In addition, selections of fixed weight and dynamic weight of MOPSO-based dynamic routing algorithms would be discussed in the environment with or without ocean currents. Eventually, the image inspection mode is not only beneficial for optimizing feasible routes but it can also identify features of obstacles for positioning.

This study investigated the development of visual recognition and stereoscopic imaging technology, applying them to the construction of an image processing system for Autonomous Underwater Vehicles (AUVs). For the proposed visual recognition technology, an optical flow algorithm was used to detect the linear features and movement speeds of dynamic images; the proposed stereoscopic imaging technique employed a Harris corner detector to estimate the distance of the target. A physical AUV was constructed with a wide-angle lens camera and a binocular vision device mounted on the bow to provide image input. Subsequently, a simulation environment was established in Simscape Multibody and used to control the post-driver system of the stern, which contained horizontal and vertical rudder planes as well as the propeller. Finally, the dynamic testing results were combined with a fuzzy controller to output the real-time responses of the vehicle regarding the angles, rates of the rudder planes, and the propeller revolution speeds at various distances.