Tactile-based grasping stability prediction based on human grasp demonstration for robot manipulation

Zhao, Zhou; He, Wenhao; Lu, Zhenyu

Abstract

To minimize irrelevant and redundant information in tactile data and harness the dexterity of human hands. In this paper, we introduce a novel binary classification network with normalized differential convolution (NDConv) layers. Our method leverages the recent progress in visual-based tactile sensing to significantly improve the accuracy of grasp stability prediction. First, we collect a dataset from human demonstration by grasping 15 different daily objects. Then, we rethink pixel correlation and design a novel NDConv layer to fully utilize spatio-temporal information. Finally, the classification network not only achieves a real-time temporal sequence prediction but also obtains an average classification accuracy of 92.97%. The experimental results show that the network can hold a high classification accuracy even when facing unseen objects.

• Journal Article Type: Article
• Acceptance Date: Jan 23, 2024
• Online Publication Date: Jan 29, 2024
• Publication Date: Mar 31, 2024
• Deposit Date: Jun 12, 2024
• Publicly Available Date: Jun 12, 2024
• Journal: IEEE Robotics and Automation Letters
• Print ISSN: 2377-3766
• Electronic ISSN: 2377-3766
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 9
• Issue: 3
• Pages: 2646 - 2653
• DOI: https://doi.org/10.1109/lra.2024.3359553
• Keywords: Artificial Intelligence, Control and Optimization, Computer Science Applications, Computer Vision and Pattern Recognition, Mechanical Engineering, Human-Computer Interaction, Biomedical Engineering, Control and Systems Engineering
• Public URL: https://uwe-repository.worktribe.com/output/11680684