Associating Grasp Configurations with Hierarchical Features in Convolutional Neural Networks

In this work, we provide a solution for posturing the anthropomorphic Robonaut-2 hand and arm for grasping based on visual information. A mapping between visual features extracted from a convolutional neural network (CNN) to grasp points is learned. We demonstrate that a pre-trained CNN for image classification can be applied to a grasping task based on a small set of grasping examples. Our approach takes advantage of the hierarchical nature of the CNN and identifies the 3D positions of features that capture the hierarchical support relations between filters in different CNN layers by tracing the activation of higher level features in the CNN backward. When this backward trace terminates in the RGB-D image, important manipulable structures comprising the objects are, thus, localized. These features located in different layers of the CNN are then associated to controllers belonging to different hierarchies of the robot morphology for grasping. A Grasping Dataset is collected using demonstrated hand/object relationships for Robonaut-2 to evaluate the proposed approach in terms of the precision of the resulting preshape postures. We demonstrate that this approach outperforms base-line approaches in cluttered scenarios on the Grasping Dataset and a point cloud based approach on a grasping task using Robonaut-2.