Textile Taxonomy and Classification Using Pulling and Twisting

Abstract

Identification of textile properties is an important milestone toward advanced robotic manipulation tasks that consider interaction with clothing items such as assisted dressing, laundry folding, automated sewing, textile recycling and reusing. Despite the abundance of work considering this class of deformable objects, many open problems remain. These relate to the choice and modelling of the sensory feedback as well as the control and planning of the interaction and manipulation strategies. Most importantly, there is no structured approach for studying and assessing different approaches that may bridge the gap between the robotics community and textile production industry. To this end, we outline a textile taxonomy considering fiber types and production methods, commonly used in textile industry. We devise datasets according to the taxonomy, and study how robotic actions, such as pulling and twisting of the textile samples, can be used for the classification. We also provide important insights from the perspective of visualization and interpretability of the gathered data.

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

“…Differently from the simulated data, the ground truth elastic properties of the textile are not easily accessible as their estimation would require specific tensile tests as discussed in Section II. To overcome this challenge, we fixed K according a proxy categorization of textile properties represented by the taxonomy proposed in [13]. We chose 40 different combinations of yarn material to maximize the variance of the elastic responses, while keeping the construction technique fixed to knitted as the one leading to more elastic behaviors.…”

“…Our previous work introduced a taxonomy considering the yarn material and the fabric construction technique to understand textile properties [13]. To meet this goal, it relied on physical interactions (pulling and twisting) and forcetorque measurements.…”

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

“…Differently from the simulated data, the ground truth elastic properties of the textile are not easily accessible as their estimation would require specific tensile tests as discussed in Section II. To overcome this challenge, we fixed K according to a proxy categorization of textile properties represented by the taxonomy proposed in [13]. We chose 40 different combinations of yarn material to maximize the variance of the elastic responses, while keeping the construction technique fixed to knitted as the one leading to more elastic behaviors.…”

“…In our previous work we introduced a taxonomy regarding the role of yarn material and construction techniques [13], and we studied these properties through physical interactions 1 The authors are with the Robotics, Perception and Learning Lab, EECS, at KTH Royal Institute of Technology, Stockholm, Sweden albertal, moletta, alfrei, mwelle, okr, dani@kth.se 2 The authors are with are with Carnegie Mellon University, Pittsburgh, USA yufeiw2, dheld, zerickso@andrew.cmu.edu such as pulling and twisting using force-torque measurements. We build upon these ideas and propose a way to encode elastic behaviors of textiles, named Elastic Context (EC).…”

“…In modern textiles, these raw materials are blended with elastomers, such as elastane, making the yarn more flexible [17]. The construction technique (woven or knitted) determines how the yarn threads are interlaced or interloped; see our taxonomy in [13]. Woven textiles, such as jeans, are produced with two sets of tightly interlaced yarns that make the textile rather rigid.…”