4D printing soft robots guided by machine learning and finite element models

This paper presents a method for four-dimensional (4D) printing of soft pneumatic actuator robot (SPA)s, using nonlinear machine learning (ML) and finite element model (FEM). A FEM is developed to accurately simulate experimental actuation obtain training data the ML modeling. More than thousand samples from hyperelastic material generated use as model, which was predict geometrical requirements 4D-printed SPA realize bending required specific tasks. The predicted proved be viable solution 4D robots dynamic structures. work helps understand how develop robots’ designs problems FEM.