A framework for the automated design and modelling of soft robotic systems

The introduction of collaborative robots is expected to have a positive impact on industrial assembly. In this respect, new generations of robots that can deform and yield in a collision, thus being less harmful, seem a promising supplement to traditional rigid-link robots. Recently, these so-called soft robots have received significant attention and are now beginning to unfold their potential in industrial automation. This paper presents a framework for a soft robot design and modelling tool that effectively combines finite element analysis, continuum robot modelling, and machine learning. To validate the proposed method, a soft actuator is designed, modelled, and tested.