LEARNING SOFT ROBOT AND SOFT ACTUATOR DYNAMICS USING DEEP NEURAL NETWORK

Inspired by living organisms and being the forefront of robotics evolution, the research in soft robotics has been growing exponentially. Due to the flexibility of these robots that is made from soft materials such as silicone or even a fabric allows them to manoeuvre on secluded environments through crevice openings which bring many advantages comparing to the rigidcomponent robots which proves much more delicate interaction with humans and environments. In this paper, modelling of the soft robot using finite element modelling will be discussed in conjunction with deep neural network for the bending and control of the end effector.