2026-04-13T13:36:30Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/3311822025-07-22T22:20:51Zcom_2072_1033col_2072_452951

00925njm 22002777a 4500 dc Sánchez Molina, David author 2020-06-30 Fish generate propulsion through body and caudal (tail) fin undulation. The undulation kinematics, suchas the amplitude and the frequency, determines the generated hydrodynamic force, associated accelera-tion, and therefore the fish velocity.In this study, we will investigate how a fish can rush to a target in the shortest time using the com-bination of high fidelity computational fluid dynamics (CFD) and deep reinforcement learning. Thehydrodynamics force experienced by fish will be computed from CFD solver. Reinforcement learningwill be used to find out the optimized kinematics fish can use to approach the target most swiftly. Àrees temàtiques de la UPC::Física Reinforcement learning Fishes - Morphology Hydrodynamics Computational fluid dynamics Genetic algorithms Machine Learning Reinforcement Learning fish acceleration Genetic Algorithm simulation CFD Fluid Dynamics zebrafish efficiency vorticity Aprenentatge per reforç Peixos -- Morfologia Hidrodinàmica Dinàmica de fluids computacional Algorismes genètics How could fish win a race through Reinforcement Learning Study: How could fish win a race through Reinforcement Learning