A Continuous Robot Vision Approach for Predicting Shapes and Visually Perceived Weights of Garments

We present a continuous perception approach that learns geometric and physical similarities between garments by continuously observing a garment while a robot picks it up from a table. The aim is to capture and encode geometric and physical characteristics of a garment into a manifold where a decision can be carried out, such as predicting the garment's shape class and its visually perceived weight. Our approach features an early stop strategy, which means that a robot does not need to observe a full video sequence of a garment being picked up from a crumpled to a hanging state to make a prediction, taking 8 seconds in average to classify garment shapes. In our experiments, we find that our approach achieves prediction accuracies of 93% for shape classification and 98.5% for predicting weights and advances state-of-art approaches in similar robotic perception tasks by 22%for shape classification.