Evaluating the Pre-Dressing Step: Unfolding Medical Garments Via Imitation Learning

TL;DR

This paper introduces a method for robotic unfolding of medical garments using imitation learning, addressing the gap in prior work which assumes garments are already unfolded, and demonstrates effective manipulation strategies.

Contribution

It proposes a novel pre-dressing step for unfolding garments with imitation learning and a visual classifier for garment state recognition, advancing robotic dressing assistance.

Findings

Dynamic motions are ineffective for unfolding garments.

Combining manipulation primitives improves opening configurations.

Empirical evaluation confirms the effectiveness of the approach.

Abstract

Robotic-assisted dressing has the potential to significantly aid both patients as well as healthcare personnel, reducing the workload and improving the efficiency in clinical settings. While substantial progress has been made in robotic dressing assistance, prior works typically assume that garments are already unfolded and ready for use. However, in medical applications gowns and aprons are often stored in a folded configuration, requiring an additional unfolding step. In this paper, we introduce the pre-dressing step, the process of unfolding garments prior to assisted dressing. We leverage imitation learning for learning three manipulation primitives, including both high and low acceleration motions. In addition, we employ a visual classifier to categorise the garment state as closed, partly opened, and fully opened. We conduct an empirical evaluation of the learned manipulation primitives as well as their combinations. Our results show that highly dynamic motions are not effective for unfolding freshly unpacked garments, where the combination of motions can efficiently enhance the opening configuration.