Data-Driven Machine Learning Models for a Multi-Objective Flapping Fin Unmanned Underwater Vehicle Control System

Flapping-fin unmanned underwater vehicle (UUV) propulsion systems provide high maneuverability for naval tasks such as surveillance and terrain exploration. Recent work has explored the use of time-series neural network surrogate models to predict thrust from design fin kinematics. We develop a search-based inverse model that leverages kinematics-to-thrust control system design. Our finds set kinematics with multi-objective goal reaching target creating smooth kinematic transition between flapping cycles. demonstrate how integrating this can make online, cycle-to-cycle adjustments prioritize different objectives.