SIS: Seam-Informed Strategy for T-shirt Unfolding

TL;DR

This paper introduces SIS, a seam-informed strategy for robotic T-shirt unfolding that leverages seam features and a decision matrix updated through human demonstrations and robot execution, trained on real data.

Contribution

The paper presents a novel seam feature extraction and decision-making method for garment handling, trained on real data without simulation, improving robot grasping and unfolding.

Findings

Effective seam-based grasping point detection

Decision matrix improves with robot execution feedback

Successful real-world T-shirt unfolding experiments

Abstract

Seams are information-rich components of garments. The presence of different types of seams and their combinations helps to select grasping points for garment handling. In this paper, we propose a new Seam-Informed Strategy (SIS) for finding actions for handling a garment, such as grasping and unfolding a T-shirt. Candidates for a pair of grasping points for a dual-arm manipulator system are extracted using the proposed Seam Feature Extraction Method (SFEM). A pair of grasping points for the robot system is selected by the proposed Decision Matrix Iteration Method (DMIM). The decision matrix is first computed by multiple human demonstrations and updated by the robot execution results to improve the grasping and unfolding performance of the robot. Note that the proposed scheme is trained on real data without relying on simulation. Experimental results demonstrate the effectiveness of the proposed strategy. The project video is available at https://github.com/lancexz/sis