FEM-Based N-Net Control of a Flexible Dexterous Finger

Abstract Owing to their light weight, compactness, and good adaptability, soft robots are promising for applications with safe human-machine interactions. Compared traditional rigid robots, the distributed actuation of bodies leads complex nonlinear deformation, making it challenging model its dynamics. In this paper, a Finite Element Method (FEM)-based fast neural network open-loop control method is presented flexible dexterous hands in task-space using finite element method. The main idea use simple find mapping between end-effector values displacement. way, structures can be simplified. This especially suitable complicated braking that cannot accurately sensed. Finally, effectiveness proposed verified by experiments, results convincing.