CloSE: A Geometric Shape-Agnostic Cloth State Representation
Jay Kamat, Julia Borras Sol, Carme Torras
AI summary
Problem
Robotic cloth manipulation is hindered by the infinite-dimensional configuration space and the lack of a simplified, generalizable representation that works across varying cloth shapes and sizes.
Approach
The method computes a directional derivative of the Gauss Linking Integral for all cloth border segments, maps these values onto a circular grid (dGLI disk), and extracts corner and fold features into a continuous circle-based descriptor called CloSE.
Key results
- Novel dGLI disk arrangement revealing consistent geometric patterns across diverse cloth shapes
- Accurate prediction of fold locations and orientations across multiple simulation datasets
- Compact, continuous, and fully analytical encoding of the cloth configuration space
- Demonstrated utility in automatic semantic labeling and manipulation sequence planning
Why it matters
Provides a generalizable, low-dimensional state encoding that can streamline learning-based and planning approaches for robotic cloth manipulation across different garments.
Abstract
Cloth manipulation is a difficult problem mainly because of the non-rigid nature of cloth, which makes a good representation of deformation essential. We present a new representation for the deformation-state of clothes. First, we propose the dGLI disk representation based on topological indices computed for edge segments of the cloth border that are arranged on a circular grid. The heat-map of the dGLI disk uncovers patterns that correspond to features of the cloth state that are consistent for different shapes, sizes or orientation of the cloth. We then abstract these important features from the dGLI disk into a circle, calling it the Cloth StatE representation (CloSE). This representation is compact, continuous, and general for different shapes. We show that this representation is able to accurately predict the fold locations for several simulation clothing datasets. Finally, we also show the strengths of this representation in two relevant appli- cations: semantic labeling and high- and low-level planning. The code and the dataset can be accessed from: https: //close-representation.github.io/