Towards Spiking Control for Dielectric Elastomer Actuators

Dielectric Elastomer Actuators (DEAs) can be seen as flexible capacitors, where an incompressible elastomer is sandwiched between two compliant electrodes. From the elastomer non-linear and time-dependent phenomena arise during the activation of the actuator. This results in the need for appropriate control methods, especially when they are used in the field of soft robots. Therefore, this paper presents a feedforward controller which is based on Spiking Neural Networks (SNNs). To the best of our knowledge this is the first time DEAs and SNNs are combined to make a step towards true soft robots. It was demonstrated that it is necessary to include feedback into the control scheme. Also, it was found that in the context of a SpiNN-3 development board as a neuromorphic hardware platform, neuron encoding is the most promising encoding method. This also implies that a classification approach is preferable to a regression approach.