Research on the direction perception of cruising copepods by the fish lateral line using pressure difference matrix and residual neural network regression method

Abstract

Autonomous Underwater Vehicles (AUVs) are high-end marine equipment. In turbid, dimly lit waters that require high concealment, traditional methods struggle to detect targets effectively. Fish, however, can accurately perceive nearby targets using lateral line systems even in harsh environments. This provides inspiration for intelligent detection in AUVs. In this study, the flow field cloud around copepods and visualization of pressure difference matrix are analyzed. A method combining the pressure difference matrix and residual neural network regression is proposed to study how fish lateral lines perceive the direction of cruising copepods. Furthermore, the effects of three key parameters on direction perception are discussed, including perception time scale, initial vertical distance and training angular intervals number. The results indicate that most predicted directions are close to the true directions, with only a small number of misjudgments occurring in the vicinity of the opposite or perpendicular directions to the true direction. Moderate perception time scales (100 ms), shorter vertical distances (2.5 mm), and reasonable training angular intervals number (24 or 36) all lead to lower perception error. This study provides a quantitative analysis of fish lateral line perception mechanism, offering valuable theoretical guidance and technical support for intelligent detection in AUVs.