Robotic Fabric Flattening with Wrinkle Direction Detection

Abstract

Deformable Object Manipulation (DOM) is an important field of research as it contributes to practical tasks such as automatic cloth handling, cable routing, surgical operation, etc. Perception is considered one of the major challenges in DOM due to the complex dynamics and high degree of freedom of deformable objects. In this paper, we develop a novel image-processing algorithm based on Gabor filters to extract useful features from cloth, and based on this, devise a strategy for cloth flattening tasks. We evaluate the overall framework experimentally, and compare it with three human operators. The results show that our algorithm can determine the direction of wrinkles on the cloth accurately in the simulation as well as the real robot experiments. Besides, the robot executing the flattening tasks using the dewrinkling strategy given by our algorithm achieves satisfying performance compared to other baseline methods. The experiment video is available on https://sites.google.com/view/robotic-fabric-flattening/home

Robotic perception of object properties using tactile sensing

“…Deformable object manipulation has been a growing research area with various applications, such as assembling cables in factories [23]- [26], assisted dressing and laundry folding [27]- [30] and food production [31], [32]. These tasks mainly rely on visual perception [23], [28], [32]- [34]. However, the specific challenge of manipulating thin and flexible objects remains relatively unexplored.…”

Textile Taxonomy and Classification Using Pulling and Twisting

“…Nevertheless, in situations where clothes significantly self-occlude, point cloud representations become ambiguous as different layers of the cloth cannot be distinguished based solely on the observable set of points. While classical computer vision approaches such as a Harris Corner Detector [22] or a wrinkle-detector [23] can be used for detecting cloth features, they are typically not robust to variations of texture, lightning conditions, and non-static observations. This study tackles these perception challenges by integrating semantic descriptors, derived from RGB observations through pre-trained VLMs, with point cloud representations.…”