A Coarse-to-Fine Robotic Fabric Alignment System Integrating Visual Servoing and Admittance Control

Jiaming Qi, Liang Lu, Lei Yang, Yan Ding, Pai Zheng, David Navarro-Alarcon, Jia Pan, Peng Zhou

Abstract: Fabric alignment is essential to key production processes such as cutting, sewing, and fusing in garment manufacturing. Traditionally, this task has relied heavily on the dexterity and expertise of skilled human workers. Although automated systems have been introduced, they often lack the flexibility required for complex alignment tasks. In this paper, we present a novel robotic fabric alignment framework that fully automates the process with high precision and adaptability. First, we propose a coarse-to-fine alignment strategy, where an initial imprecise target position is roughly computed based on a basic perception module and eye-to-hand calibration. This is followed by a sliding mode control (SMC)-based visual servoing approach (in an eye-in-hand configuration) to ensure a close-up view of feedback features for the fine alignment process. Additionally, we consider system disturbances estimated by a fuzzy logic system (FLS) and combine it with the controller to further enhance the system’s robustness. Finally, we developed an advanced end-effector equipped with force/torque (F/T) sensors and air-powered needle grippers for gentle fabric manipulation using admittance control. We validate our framework through a series of experiments that demonstrate its effectiveness in fabric alignment tasks. Note to Practitioners—Fabric alignment in garment production is a labor-intensive task that heavily relies on skilled human workers. Existing automated fabric alignment machines are typically limited to specific fabric shapes, patterns, and materials. Furthermore, transitioning between different fabric types requires extensive testing and adjustments, resulting in a lack of adaptability and flexibility. In this work, we propose a robotic fabric alignment system based on a coarse-to-fine alignment strategy. The initial target pose is roughly estimated using a basic perception module and eye-to-hand calibration, followed by fine adjustments through a visual servoing controller in an eye-in-hand configuration. Additionally, to ensure gentle handling, the contact force between the end-effector and the platform surface is optimized using admittance control. The proposed system offers practitioners a comprehensive solution for automating fabric alignment with high precision, while maintaining flexibility and adaptability across various fabric types and initial environmental conditions.