A cyber-physical system for clothes detection, manipulation and washing machine loading

In this paper, a cyber-physical system for the detection and manipulation of clothes and its application to the problem of their robotized insertion in a washing machine drum is presented. Starting with the clothes randomly placed inside a bin next to the appliance, the method describes the approach used for the laundry bin picking together with a recovery picking from the drum door region in case some large cloth remains partially out from the washing machine. The same pointcloud-based perception algorithm is utilized for both tasks: the approaches are different only for what concerns the segmentation of the pointcloud for the extraction of the cloth-related points. The main algorithm exploits a wrinkledness measure to identify wrinkles in the cloth surface, to robustly assign spline curves to the detected wrinkle-like structure and to estimate grasping frames. In addition, a pointcloud registration technique is applied in the washing machine recovery task for the segmentation stage. The planning of the robot operations to execute the cloth grasping is also presented. The approach has been validated extensively by performing 100 trials grasps for both tasks.