This dataset was used to learn visually interpretable oscillator networks in "Learning Visually Interpretable Oscillator Networks for Soft Continuum Robots from Video" (DOI: https://doi.org/10.48550/arXiv.2511.18322). Please cite this paper when using the dataset. The implementation of the visually interpretable oscillator networks and their training is published as a GitHub repository (https://github.com/UThenrik/visual_oscillators_for_SCR). The dataset includes: Pressure and video raw data of a soft pneumatic robot during dynamic planar movements based on step and oscillatory inputs Data processing script for data loading, synchronization, subsampling and cropping Processed data used for training of networks in the paper