Machine-Learning-Enhanced Iontronic Sensor Array for 3-D Tactile Perception
IEEE Transactions on Instrumentation and Measurement · 2026 · 75 · 1-12
DOI: 10.1109/tim.2026.3671911 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Instrumentation and Measurement, 2026. Verfasst von Bowen Li und 5 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Gefördert von: State Key Laboratory of Quantum Functional Materials, Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenz…, Shenzhen Southern University of Science and Technology Education Foundation.
Abstract (Originalsprache)
Tactile interfaces are crucial for enhancing human–machine interactions. However, achieving a precise perception of 3-D force under flexible contact conditions remains challenging due to strong signal coupling, computationally intensive data processing, and limited model interpretability. To overcome these limitations, we designed a flexible iontronic sensor array composed of four-capacitor integrated units to sense human hand grasping interactions. Furthermore, we developed a machine learning framework for 3-D force detection that leverages feature engineering. By integrating physics-inspired features into a lightweight random forest (RF) model through a selective process, our approach facilitates efficient and interpretable force decoupling. Experimental results demonstrate competitive accuracy in flexible-to-flexible interaction scenarios, with a mean squared error (mse) below 0.1 and an R2 value of 0.94. We integrated this approach with our sensor array to create a flexible multidimensional force-tactile sensing system capable of supporting real-time applications, such as virtual 3-D interactive operation. This work not only demonstrates the potential for precise force control in virtual reality (VR) and interactive devices but also provides new insights for developing AI-enhanced sensor technologies.
Förderung
- State Key Laboratory of Quantum Functional Materials, Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenz…
- Shenzhen Southern University of Science and Technology Education Foundation
Zitieren
APA
Li, B., Li, Z., Si, W., Zhang, C., Chen, X., & Wang, T. (2026). Machine-Learning-Enhanced Iontronic Sensor Array for 3-D Tactile Perception. IEEE Transactions on Instrumentation and Measurement, 75, 1-12. https://doi.org/10.1109/tim.2026.3671911
Vancouver
Li B, Li Z, Si W, Zhang C, Chen X, Wang T. Machine-Learning-Enhanced Iontronic Sensor Array for 3-D Tactile Perception. IEEE Transactions on Instrumentation and Measurement. 2026;75:1-12. doi:10.1109/tim.2026.3671911
BibTeX
@article{Li2026,
author = {Li, Bowen and Li, Zhibin and Si, Wenlong and Zhang, Chengbi and Chen, Xingxing and Wang, Taihong},
title = {Machine-Learning-Enhanced Iontronic Sensor Array for 3-D Tactile Perception},
journal = {IEEE Transactions on Instrumentation and Measurement},
year = {2026},
volume = {75},
pages = {1--12},
doi = {10.1109/tim.2026.3671911}
}
EUVIMED