Fully Automatic Visual Servoing Control for Underwater Vehicle Manipulator Systems Based on a Heuristic Inverse Kinematics

Abstract The use of underwater vehicle manipulator systems (UVMS) equipped with cameras has gained significant attention due to their capacity perform tasks autonomously. However, controlling both the and remotely operated (ROV) based on vision system information is not an easy task, especially in situations where cannot be parked/held stationary. Most existing approaches work complex matrix calculations for inverse kinematics (IK), which can lead high computational costs need deal singularity problems. A problem arises when amount time needed calculate UVMS configuration result reduced frequency target pose estimation, beyond point moved out camera field view. Therefore, this paper proposes autonomous visual servoing approach UVMS, including extension a heuristic technique named M-FABRIK (Mobile - Forward Backward Reaching IK) simple fast way. This aims control ROV position order allow intervention solution allows positioned according additional criteria, besides avoiding inversion being robust singularities. Trials have been performed mounted work-class monitoring task results demonstrate approach, able set as well applications real-time, such monitoring, tracking underwater.