Bimanual Robot-Assisted Dressing: A Spherical Coordinate-Based Strategy for Tight-Fitting Garments

2025-08-17

AI Summary

Existing robotic dressing research primarily addresses loose-fitting garments, failing to resolve jamming issues caused by narrow sleeves of tight-fitting clothing. Method: This paper proposes a bimanual cooperative dressing framework for tight-fitting garments, introducing a spherical coordinate system to encode dressing trajectories, with azimuth angle serving as the key coordination feature between arms; it integrates Gaussian Mixture Models (GMM) and Gaussian Mixture Regression (GMR) for imitation learning, enabling systematic generation of human-arm-pose-adaptive bimanual policies. Contribution/Results: Experiments demonstrate significant improvements in dressing success rate and motion smoothness for tight-fitting garments, effectively overcoming the jamming bottleneck inherent in unimanual approaches. The framework provides a scalable modeling and learning paradigm for robotic assistance in dressing highly deformable garments.

Technology Category

• Intelligent Robots: Manipulation
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Robot-assisted dressing is a popular but challenging topic in the field of robotic manipulation, offering significant potential to improve the quality of life for individuals with mobility limitations. Currently, the majority of research on robot-assisted dressing focuses on how to put on loose-fitting clothing, with little attention paid to tight garments. For the former, since the armscye is larger, a single robotic arm can usually complete the dressing task successfully. However, for the latter, dressing with a single robotic arm often fails due to the narrower armscye and the property of diminishing rigidity in the armscye, which eventually causes the armscye to get stuck. This paper proposes a bimanual dressing strategy suitable for dressing tight-fitting clothing. To facilitate the encoding of dressing trajectories that adapt to different human arm postures, a spherical coordinate system for dressing is established. We uses the azimuthal angle of the spherical coordinate system as a task-relevant feature for bimanual manipulation. Based on this new coordinate, we employ Gaussian Mixture Model (GMM) and Gaussian Mixture Regression (GMR) for imitation learning of bimanual dressing trajectories, generating dressing strategies that adapt to different human arm postures. The effectiveness of the proposed method is validated through various experiments.

Problem

• Develops bimanual robot strategy for tight-fitting garments dressing
• Establishes spherical coordinate system for adaptive dressing trajectories
• Uses GMM and GMR for posture-adaptive dressing imitation learning

Innovation

• Bimanual robot strategy for tight garments
• Spherical coordinate system for dressing
• GMM and GMR for imitation learning