An extremely simple macroscale electronic skin realized by deep machine learning

Sohn, Kee‐Sun; Chung, Ji-Young; Cho, Min-Young; Timilsina, Suman; Park, Woon Bae; Pyo, Myungho; Shin, Namsoo; Sohn, Keemin; Kim, Ji Sik

doi:10.1038/s41598-017-11663-6

Cited by 44 publications

(50 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another important direction of in the development human-machine interaction devices is methods based on deep learning. Recently, the deep learning technique was used to realize an extremely simple macroscale electronic skin without macro-, nano-, and micropatterns [105]. e deep learning network (DNN) architecture that has been used is shown in Figure 8.…”

Section: Human-machine Interfacementioning

confidence: 99%

“…e results show that the proposed e-skin based on deep learning obtained a 97.22% level of test accuracy for position recognition and had a reliable pressure estimation with a 3.12% RMSE and therefore approximated the capability of human skin. Furthermore, DNN-based e-skin showed high performance in pressure sensitivity and high spatial resolution (0.78 ± 0.44 mm) for position recognition [105].…”

Section: Human-machine Interfacementioning

confidence: 99%

“…e great potential of this revolutionary concept could open a new era for many fields, not only for e-skin application but also high-end applications such flexible keyboard, sign language interpreting, touch panels, and diagnosis motility [105].…”

Section: Human-machine Interfacementioning

confidence: 99%

See 2 more Smart Citations

A Survey of Tactile‐Sensing Systems and Their Applications in Biomedical Engineering

Al-Handarish

Omisore

Igbe

et al. 2020

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

Over the past few decades, tactile sensors have become an emerging field of research in both academia and industry. Recent advances have demonstrated application of tactile sensors in the area of biomedical engineering and opened up new opportunities for building multifunctional electronic skin (e-skin) which is capable of imitating the human sense-of-touch for medical purposes. Analyses have shown that current smart tactile sensing technology has the advantages of high performance, low-cost, time efficiency, and ease-of-fabrication. Tactile sensing systems have thus sufficiently matured for integration into several fields related to biomedical engineering. Furthermore, artificial intelligence has the potential for being applied in human-machine interfacing, for instance, in medical robotic manipulation, especially during minimally invasive robotic surgery, where tactile sensing is usually a problem. In this survey, we present a comprehensive review of the state of the art of tactile sensors. We focus on the technical details of transduction mechanisms such as piezoresistivity, capacitance, piezoelectricity, and triboelectric and highlight the role of novel and commonly used materials in tactile sensing. In addition, we discuss contributions that have been reported in the field of biomedical engineering, which includes its present and future applications in building multifunctional e-skins, human-machine interfaces, and minimally invasive surgical robots. Finally, some challenges and notable improvements that have been made in the technical aspects of tactile sensing systems are reported.

show abstract

Section: Human-machine Interfacementioning

confidence: 99%

Section: Human-machine Interfacementioning

confidence: 99%

See 1 more Smart Citation

A Survey of Tactile‐Sensing Systems and Their Applications in Biomedical Engineering

Al-Handarish

Omisore

Igbe

et al. 2020

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

show abstract

“…A hybrid deep learning structure with a CNN and a recurrent neural network were designed to process sequential tactile information online and solve the tactile emotion recognition problem in the human-robot interaction process [82]. Sohn et al [83] applied deep learning to large-scale electronic skin tactile perception. By using various contact forces, the obtained tactile spatio-temporal sequence information was integrated and a 3D CNN was designed to realize object recognition [42].…”

Section: Tactile Feature Learning and Classificationmentioning

confidence: 99%

Embodied tactile perception and learning

Liu

Guo

Sun

et al. 2020

Brain Science Advances

View full text Add to dashboard Cite

Various living creatures exhibit embodiment intelligence, which is reflected by a collaborative interaction of the brain, body, and environment. The actual behavior of embodiment intelligence is generated by a continuous and dynamic interaction between a subject and the environment through information perception and physical manipulation. The physical interaction between a robot and the environment is the basis for realizing embodied perception and learning. Tactile information plays a critical role in this physical interaction process. It can be used to ensure safety, stability, and compliance, and can provide unique information that is difficult to capture using other perception modalities. However, due to the limitations of existing sensors and perception and learning methods, the development of robotic tactile research lags significantly behind other sensing modalities, such as vision and hearing, thereby seriously restricting the development of robotic embodiment intelligence. This paper presents the current challenges related to robotic tactile embodiment intelligence and reviews the theory and methods of robotic embodied tactile intelligence. Tactile perception and learning methods for embodiment intelligence can be designed based on the development of new large‐scale tactile array sensing devices, with the aim to make breakthroughs in the neuromorphic computing technology of tactile intelligence.

show abstract

“…Below it there is a submerged top electrode. The third layer is CNT (carbon nano-tube) dispersed PDMS layer having piezo-resistivity [8,9,10,11]. The third layer is contacted downward with the bottom 16-electrode layer for generating 16 plantar pressure signals.…”

Section: Insole Fabricationmentioning

confidence: 99%

Characterization of Elastic Polymer-Based Smart Insole and a Simple Foot Plantar Pressure Visualization Method Using 16 Electrodes

Lee

2018

Sensors

View full text Add to dashboard Cite

In this paper, we propose a smart insole for inexpensive plantar pressure sensing and a simple visualizing scheme. The insole is composed of two elastomeric layers and two electrode layers where the common top electrode is submerged in the insole. The upper elastomeric layer is non-conductive poly-dimethyl-siloxane (PDMS) and supports plantar pressure buffering and the lower layer is carbon nano-tube (CNT)-dispersed PDMS for pressure sensing through piezo-resistivity. Under the lower sensing layer are 16 bottom electrodes for pressure distribution sensing without cell-to-cell interference. Since no soldering or sewing is needed the smart insole manufacturing processes is simple and cost-effective. The pressure sensitivity and time response of the material was measured and based on the 16 sensing data of the smart insole, we virtually extended the frame size for continuous and smoothed pressure distribution image with the help of a simple pseudo interpolation scheme.

show abstract

An extremely simple macroscale electronic skin realized by deep machine learning

Cited by 44 publications

References 25 publications

A Survey of Tactile‐Sensing Systems and Their Applications in Biomedical Engineering

A Survey of Tactile‐Sensing Systems and Their Applications in Biomedical Engineering

Embodied tactile perception and learning

Characterization of Elastic Polymer-Based Smart Insole and a Simple Foot Plantar Pressure Visualization Method Using 16 Electrodes

Contact Info

Product

Resources

About