Grasp type understanding — classification, localization and clustering

Abstract

Prehensile analysis is a research field attracting multi-disciplinary interests, including computer science, mechanology and neuroscience. For robot, grasp type recognition provides critical information for human-robot interaction and robot self-learning. One of the research direction is to discover the common modes of human hand use with first-person point-of-view wearable cameras. In contrast to previous methods based on handcraft features and multi-stage pipeline, we use a convolutional neural network to learn discriminative features of grasp types automatically, which can also achieve grasp type localization and classification simultaneously in a single-stage pipeline. Furthermore, a clustering method is also proposed to find the hierarchical relationships between different grasp types. Experiments are conducted on UT Grasp dataset and Yale human grasping dataset. The proposed method shows better accuracy and higher efficiency than traditional methods.