Download PDFOpen PDF in browserAutonomous Clothes Folding: a Complete Pipeline from Perception to ActionEasyChair Preprint 117687 pages•Date: January 14, 2024AbstractThis research presents a comprehensive pipeline for autonomous clothes folding, encompassing various stages from perception to action. Leveraging advanced robotic technologies, computer vision, and machine learning, the proposed system achieves a high degree of autonomy in the intricate task of folding clothes. The pipeline begins with the perception phase, where a combination of sensors, including RGB-D cameras, captures detailed information about the clothes' spatial configuration. Subsequently, a sophisticated computer vision system processes this data to create a precise representation of the clothing articles. The core of the system relies on machine learning techniques, specifically tailored for garment manipulation, enabling the robot to understand and adapt to diverse clothing types and shapes. Keyphrases: action, perception, pipeline
|