Target Classification Method of Tactile Perception Data with Deep Learning
Open Access
Abstract
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.Keywords
Funding Information
- the National Important Project (2020YFB1713300, 2018AAA0101803)
- Guizhou Province Higher Education Project ([2020]005,[2020]009)
This publication has 33 references indexed in Scilit:
- Deep Self-Paced Residual Network for Multispectral Images Classification Based on Feature-Level FusionIEEE Geoscience and Remote Sensing Letters, 2018
- LDS-FCM: A Linear Dynamical System Based Fuzzy C-Means Method for Tactile RecognitionIEEE Transactions on Fuzzy Systems, 2018
- More Than a Feeling: Learning to Grasp and Regrasp Using Vision and TouchIEEE Robotics and Automation Letters, 2018
- Generalizing Pooling Functions in CNNs: Mixed, Gated, and TreeIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Tactile texture classification using magnetic tactile sensorInternational Journal of Applied Electromagnetics and Mechanics, 2016
- Object Classification and Grasp Planning Using Visual and Tactile SensingIEEE Transactions on Systems, Man, and Cybernetics: Systems, 2016
- Novel Tactile-SIFT Descriptor for Object Shape RecognitionIEEE Sensors Journal, 2015
- ST-HMP: Unsupervised Spatio-Temporal feature learning for tactile data2014
- Efficient $k$ -Means++ Approximation with MapReduceIEEE Transactions on Parallel and Distributed Systems, 2014
- Tactile-Data Classification of Contact Materials Using Computational IntelligenceIEEE Transactions on Robotics, 2011