Elastic Context: Encoding Elasticity for Data-driven Models of Textiles

Alberta Longhini, Marco Moletta, Alfredo Reichlin, Michael C. Welle, Alexander Kravberg, Yufei Wang, David Held, Zackory Erickson, Danica Kragic

Keywords: Deformable Objects, Elastic Properties, Contact Dynamics

TL;DR: In this work we address the problem of encoding elastic properties of textiles from robotic force sensors, to learn data-driven models of interaction dynamics between rigid objects and deformable objects with different elastic properties.

Abstract: Physical interaction with textiles, such as assistive dressing or household tasks, requires advanced dexterous skills. The complexity of textile behavior during contact interactions is influenced by the material properties of the yarn and by the textile's construction technique, which are often unknown in real-world settings. Moreover, identification of physical properties of textiles through sensing commonly available on robotic platforms remains an open problem. To address this, we introduce Elastic Context (EC), a method to encode the elasticity of textiles using stress-strain curves adapted from textile engineering for robotic applications. We employ EC to learn a data-driven model of textiles that captures the variations of elastic force responses of textiles in contact-rich scenarios. Moreover, we examine the effect of EC dimension on accurate force modeling of real-world non-linear elastic responses during contact interactions.

Confirmation: I am a student and I would like to be considered for the funding award.