Learning to Hang Crumpled Garments with Confidence-Guided Grasping and Active Perception

Shengzeng Huo, He Zhang, Hoi-Yin Lee, Peng ZHOU, David Navarro-Alarcon

Attend In Person: Yes

Keywords: deformable object manipulation

TL;DR: The paper address the task of autonomously hanging a crumpled, collared garment on a rack while imposing only minimal assumptions regarding either the garment’s or the rack’s configuration.

Abstract: In this study, we concentrate on the task of hanging crumpled garments on a rack. This context presents two primary challenges: (1) perceiving and grasping the structural regions of garments that exhibit severe deformations and self-occlusions; (2) adjusting the configuration of garments to fit the supporting components of the rack. We propose a confidence-guided grasping strategy that actively seeks garment collars through handovers between dual robotic arms. The exact grasping pose is determined through depth-aware contour extraction, and its success is evaluated based on a specially designed metric. Furthermore, we formulate the hanging task as one-shot imitation learning with an egocentric view. We propose a two-step hanging strategy that involves coarse approaching followed by fine transformation. We perform comprehensive experiments and show that our framework notably enhances the success rate compared to existing methods.

Submission Number: 11