Grasp stability assessment through the fusion of proprioception and tactile signals using convolutional neural networks

Grasp stability assessment through the fusion of proprioception and tactile signals using convolutional neural networks

Kwiatkowski, Jennifer and Cockburn, Deen and Duchaine, Vincent

IEEE International Conference on Intelligent Robots and Systems 2017

Abstract : The growing demand in industry for robots capable of performing a variety of tasks requires an increased capability in robotic grasping. Humans are adept at interacting with novel objects, a skill attributed primarily to tactile feedback in the form of exteroception and proprioception. This paper presents a novel way to incorporate exteroception and proprioception into grasp stability assessment: by using convolutional neural networks. This method improves upon the results of a unsupervised feature learning approach that used similar tactile feedback. 1000 different grasps on 100 objects were used to train and test the network. The network achieved an overall accuracy of 88.4% while predicting the failure class with an accuracy of 92.7%.