Tracking cloth deformation: a novel dataset for closing the sim-to-real gap for robotic cloth manipulation learning

We present a cloth dataset consisting of 120 high-quality recordings of several textiles during dynamic motions. Using a Motion Capture System, we record the location of key-points on the cloth surface of four types of fabrics (cotton, denim, wool and polyester) of two sizes (A2 and A3) and at different speeds. The scenarios considered are all dynamic and involve rapid shaking and twisting of the textiles, collisions with frictional objects, strong hits with a long rigid object and even self-collisions.

For more information about the dataset, see: Franco Coltraro, Júlia Borràs, Maria Alberich-Carramiñana and Carme Torras. Tracking cloth deformation: a novel dataset for closing the sim-to-real gap for robotic cloth manipulation learning to appear in International Journal of Robotics Research (2025).