Target Classification Method of Tactile Perception Data with Deep Learning

• Published in: Entropy (Basel, Switzerland) Vol. 23; no. 11; p. 1537
• Main Authors: Zhang, Xingxing, Li, Shaobo, Yang, Jing, Bai, Qiang, Wang, Yang, Shen, Mingming, Pu, Ruiqiang, Song, Qisong
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 18.11.2021; MDPI
• Subjects: Accuracy; Algorithms; Artificial neural networks; Classification; Cluster analysis; Clustering; Deep learning; Machine learning; Neural networks; Perception; ResNet; Robots; Sensors; Tactile discrimination; tactile perception data; tactile sensor; Tactile sensors (robotics); target classification; Target recognition; Vector quantization
• ISSN: 1099-4300; 1099-4300
• DOI: 10.3390/e23111537

In order to improve the accuracy of manipulator operation, it is necessary to install a tactile sensor on the manipulator to obtain tactile information and accurately classify a target. However, with the increase in the uncertainty and complexity of tactile sensing data characteristics, and the continuous development of tactile sensors, typical machine-learning algorithms often cannot solve the problem of target classification of pure tactile data. Here, we propose a new model by combining a convolutional neural network and a residual network, named ResNet10-v1. We optimized the convolutional kernel, hyperparameters, and loss function of the model, and further improved the accuracy of target classification through the K-means clustering method. We verified the feasibility and effectiveness of the proposed method through a large number of experiments. We expect to further improve the generalization ability of this method and provide an important reference for the research in the field of tactile perception classification.