Study and development of AI-based approaches for cloth manipulation capabilities

According to the World Health Organization forecasts, there are already more than one billion people over the age of 60, with that figure predicted to climb to 1.4 billion by 2030. As a result, there is a growth in the need for caregivers, which may become unsustainable for the future society. In this scenario, as the world population ages, the demand for automated help grows. Service robotics is one area of robotics where robots have shown significant promise in working closely with people. Hospitals, household settings, and elderly homes will need intelligent robotic agents in use that perform daily activities. Cloth manipulation is one such daily activity and represents a challenging area for a robot. This thesis details two main aspects: the cloth image classification and the identification of grasping points for clothing manipulation. Taking into account the cloth classification task, we first enhance state-of-the-art convolutions neural networks, e.g., LeNET, by adding additional image processing features to the network structure. Finally, to further improve the accuracy, we investigated the implementation of multiple convolutional neural networks (MCNN). The proposed networks are trained and tested on the Fashion- MNIST dataset. The second research goal of this thesis focused on finding the grasping points of the highest wrinkle (from a later point of view) of a folded hospital gown. The wrinkle is detected using the Generative Grasping Convolutional Neural Network (GGCNN), while the approach to the cloth by a manipulator is obtained by designing a visual servoing algorithm that considers the input of the GGCNN. In conclusion, the results described in this thesis tend to study by deep some AI-based approaches for cloth manipulation capabilities; in particular, we concentrated on study- ing the cloth image classification with neural networks and the Fashion-MNIST dataset. Moreover, we analysed how to identify the first wrinkle of a cloth by combining the visual servoing approach with a neural network.