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

2025-07-24

AI Summary

Existing robotic dressing systems assume garments are pre-unfolded, yet in clinical settings medical gowns and aprons are typically stored folded—posing a significant challenge for autonomous deployment. Method: This paper introduces the “pre-dressing” paradigm, focusing on autonomous unfolding of folded medical garments. We (1) formally define and implement the pre-dressing step; (2) construct a library of high- and low-acceleration manipulation primitives via imitation learning; and (3) integrate a vision-based classifier to dynamically recognize closed, semi-open, and fully open garment states, enabling closed-loop, adaptive action sequencing. Results: Our adaptive composition strategy significantly improves unfolding success rate and efficiency compared to monolithic high-dynamic actions, effectively addressing the difficulty of unfolding newly unpacked, stiff garments. This work establishes a critical foundation for robot-assisted dressing in real-world healthcare environments.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Reasoning under Uncertainty: Sequential Decision Making

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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.

Problem

• Robotic unfolding of folded medical garments
• Learning manipulation primitives via imitation
• Classifying garment states for assisted dressing

Innovation

• Imitation learning for garment manipulation primitives
• Visual classifier for garment state categorization
• Combination of motions enhances unfolding efficiency