Recent Work
Representing clothing items for robotics tasks
Marco Moletta, Michael C. Welle, Alexander Kravchenko, Anastasia Varava and Danica Kragic
Abstract—
We study the problem of clothing item representation and build upon our recent work to perform a comparative study of the most commonly used representations of clothing items. We focus on visual and graph representations, both extracted from images. Visual representations follow the current trend of learning general representations rather than tailoring specific features relevant for the task. Our hypothesis is that graph representations may be more suitable for robotics tasks employing task and motion planning, while keeping the general properties and accuracy of visual representations. We rely on a subset of DeepFashion2 dataset and study performance of developed representations in an unsupervised, contrastive learning framework using a downstream classification task. We demonstrate the performance of graph representations in folding and flattening of different clothing items in a real robotic setup with a Baxter robot.
Dedicated website for Representing clothing items
Elastic Context: Encoding Elasticity in Data-driven Models of Textiles
for Robotic Manipulation
Alberta Longhini, Marco Moletta, Alfredo Reichlin, Michael C. Welle, Alexander Kravchenko, Yufei Wang, David Held, Zackory Erickson, and Danica Kragic
Abstract—
Learning dynamic properties of elastic deformable objects such as textiles is relevant for applications such as assistive dressing, textile recycling, and automation of household tasks. Ongoing research in robotic manipulation has begun to explore interactions with textiles, where the textile properties are held constant or known a priori. We present an Elastic Context (EC) for data-driven models of textiles to leverage elastic-related information during robotic manipulation tasks. The definition of EC relies on force/displacement curves commonly used in textile engineering, which we reformulated for robotic applications. We evaluate EC using Graph Neural-Networks (GNN) to learn generalized elastic behaviours of textiles. In relation to the employed models, we discuss limitations of current robotic simulators in terms of learning data-driven elastic models for manipulation tasks.