The dGLI Cloth Coordinates: A Topological Representation for Semantic Classification of Cloth States
This addresses the challenge of cloth state estimation for robotics, enabling more efficient learning in manipulation tasks, though it appears incremental as it builds on topological representations.
The paper tackles the problem of robotic cloth manipulation by introducing the dGLI Cloth Coordinates, a low-dimensional representation that efficiently distinguishes topological changes in cloth states, resulting in more accurate classification and sensitivity to grasping affordances compared to existing methods.
Robotic manipulation of cloth is a highly complex task because of its infinite-dimensional shape-state space that makes cloth state estimation very difficult. In this paper we introduce the dGLI Cloth Coordinates, a low-dimensional representation of the state of a rectangular piece of cloth that allows to efficiently distinguish key topological changes in a folding sequence, opening the door to efficient learning methods for cloth manipulation planning and control. Our representation is based on a directional derivative of the Gauss Linking Integral and allows us to represent both planar and spatial configurations in a consistent unified way. The proposed dGLI Cloth Coordinates are shown to be more accurate in the classification of cloth states and significantly more sensitive to changes in grasping affordances than other classic shape distance methods. Finally, we apply our representation to real images of a cloth, showing we can identify the different states using a simple distance-based classifier.