Autonomous Quilt Spreading for Caregiving Robots

A well trained deep network model can help to discern This work investigates the application of skeletal detection crucial grasping regions on fabric such as edges and wrinkles and segmentation techniques, combined with a deep learning [12]. By collecting extensive deformation data of various model, to efficiently spread a quilt over an infant, addressing fabric types within simulators, neural networks can discern challenges posed by limb interference. While robots and perform tasks across different fabric colors, shapes, excel at manipulating rigid objects, handling flexible materials--crucial textures, and sizes [13]. Compared to RGB images, tactile in textiles [1], [2] and medicine [3]--remains a sensors can directly capture fabric morphology when they are challenge. The primary objective of this work is to devise an fixed to the fingertips. Training a classifier in conjunction manipulation actions to ensure infants, especially when their with these sensors can determine if a robot has grasped a limbs are laid on a quilt during sleep, remain adequately specific number of fabric layers [14].