Motion modeling and neural networks based yaw control of a biomimetic robotic fish

This paper focuses on the modeling of undulation propulsion and a neural network (NN) yaw controller based on this model. First, because of the importance of the first link’s oscillation in yaw control, a motion model of free swimming was built based on the Lagrangian function, and the coupled dynamic and kinematic functions were calculated based on the relation between the generalized force and the fluid force. Second, a neural network was trained through the data generated from this model to obtain a predictive yaw controller that could control the orientation by the different offsets of each link. Finally, simulations were conducted to demonstrate the performance of the controller.