Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Jan 18;11(1):103.
doi: 10.3390/mi11010103.

Smart Tactile Sensing Systems Based on Embedded CNN Implementations

Mohamad Alameh  1 , Yahya Abbass  1 , Ali Ibrahim  1   2 , Maurizio Valle  1
Affiliations

Smart Tactile Sensing Systems Based on Embedded CNN Implementations

Mohamad Alameh et al. Micromachines (Basel). .

Abstract

Embedding machine learning methods into the data decoding units may enable the extraction of complex information making the tactile sensing systems intelligent. This paper presents and compares the implementations of a convolutional neural network model for tactile data decoding on various hardware platforms. Experimental results show comparable classification accuracy of 90.88% for Model 3, overcoming similar state-of-the-art solutions in terms of time inference. The proposed implementation achieves a time inference of 1.2 ms while consuming around 900 μ J. Such an embedded implementation of intelligent tactile data decoding algorithms enables tactile sensing systems in different application domains such as robotics and prosthetic devices.

Keywords: convolutional neural network; embedding intelligence; tactile sensing systems.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Block diagram of the tactile sensing system.
Figure 2
Figure 2
Examples of visual (top) vs. pressure (middle) vs. tactile images (bottom) of common objects.
Figure 3
Figure 3
Architecture of the tested model. BaN, Batch Normalization.
Figure 4
Figure 4
Visual representation of the training, test, and validation split using cross-validation.
Figure 5
Figure 5
Example of an image resized for the sticky tape object; the red canvas is shown for illustration, which signifies the original image size (28 × 50).
Figure 6
Figure 6
Learning accuracy for the 3 configurations of the TactNet4model: (a) training; (b) validation.
Figure 7
Figure 7
Comparison of the performance, number of trainable parameters, and FLOPS in the convolutional layers.
Figure 8
Figure 8
Implementation flow.
See this image and copyright information in PMC

References

    1. Ibrahim A., Pinna L., Seminara L., Valle M. Material-Integrated Intelligent Systems-Technology and Applications. John Wiley & Sons, Ltd.; WeinHeim, Germany: Dec 1, 2017. Achievements and Open Issues Toward Embedding Tactile Sensing and Interpretation into Electronic Skin Systems; pp. 571–594. Chapter 23. - DOI
    1. Saleh M., Abbass Y., Ibrahim A., Valle M. Experimental assessment of the interface electronic system for PVDF-based piezoelectric tactile sensors. Sensors. 2019;19:4437. doi: 10.3390/s19204437. - DOI - PMC - PubMed
    1. Alameh M., Ibrahim A., Valle M., Moser G. DCNN for Tactile Sensory Data Classification based on Transfer Learning; Proceedings of the 2019 15th Conference on Ph.D Research in Microelectronics and Electronics (PRIME); Lausanne, Switzerland. 15–18 July 2019; pp. 237–240. - DOI
    1. Luo S., Bimbo J., Dahiya R., Liu H. Robotic tactile perception of object properties: A review. Mechatronics. 2017;48:54–67. doi: 10.1016/j.mechatronics.2017.11.002. - DOI
    1. Gandarias J.M., Garcia-Cerezo A.J., Gomez-de Gabriel J.M. CNN-Based Methods for Object Recognition With High-Resolution Tactile Sensors. IEEE Sens. J. 2019;19:6872–6882. doi: 10.1109/JSEN.2019.2912968. - DOI