Dataset for “Combined model‑based and data‑driven approach for the control of a soft robotic neck”

The study investigates a hybrid control strategy that combines an analytical model of a soft robotic neck with a multilayer perceptron (MLP) neural network trained on experimental data. The goal is to minimize position errors while maintaining a hybrid solution that includes models trained using deep learning techniques, without discarding the purely analytical model of inverse kinematics for the soft robotic neck.

The repository contains processed data used for training the models. The models used have been exported along with the necessary scripts to reproduce the experiments and results.