Surface Texture Recognition by Deep Learning‐Enhanced Tactile Sensing

Yan, Youcan; Hu, Zhe; Shen, Yajing; Pan, Jia

doi:10.1002/aisy.202100076

Cited by 31 publications

(14 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[ 156 ] Minerals and fabrics have similar appearance categories: texture, color, hardness, and microstructure. [ 157 ] We believe that tactile features of minerals/rocks as auxiliary information, combined with appearance, spectral and microscopic images, can provide more comprehensive identification. It is also in line with the development trend of multimodal mineral identification.…”

Section: Discussionmentioning

confidence: 99%

Application of Image Sensing System in Mineral/Rock Identification: Sensing Mode and Information Process

Zhang,

Yang,

Sun

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

Artificial intelligence promotes the development of mineral/rock automatic recognition technology to reduce labor costs and reliance on personal experience. With instrument digitization, image recognition has played an increasingly important role. This review focuses on the image sensing system applied to mineral/rock identification and redivides this system into a sensing module, an imaging module, and an information processing module. The sensing and imaging mechanisms are summarized via technologies of sensing, imaging, and display. The information processing is classified into single‐modal or multimodal recognition. This review analyzes the limitations of single‐modal recognition and discusses the advantages and significance of multimodal recognition. The challenges of current mineral/rock identification are concluded, such as public database, multimodal learning, and portable sensing system. The interdisciplinary sensing technologies are discussed, and application feasibility is explored. This review aims to provide a reference for the research community in automatic mineral/rock identification and sensing system optimization.

show abstract

Section: Discussionmentioning

confidence: 99%

Application of Image Sensing System in Mineral/Rock Identification: Sensing Mode and Information Process

Zhang,

Yang,

Sun

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…This challenge can be overcome by optimizing the structure and classification by machine learning. [144,145]…”

Section: Discussionmentioning

confidence: 99%

Review on Microscale Sensors with 3D Engineered Structures: Fabrication and Applications

Zhang

et al. 2022

Small Methods

View full text Add to dashboard Cite

they can only perceive portion, along one or two axes, of a stimulus which is normally full of 3D space surrounding the sensors. [10,11] Another limitation is the deficient interface between the 2D sensors and target objects. For instance, health monitoring could be realized by attaching or implanting biomedical sensors to target organs or tissues of the human body. [12] However, it is difficult for traditional 2D sensors to collect accurate vital signals because they cannot conform to the 3D structure of organs or tissues. [13,14] Although this problem can be partially relieved by using flexible 2D sensors, [15] passive adaptation to target objects inevitably results in gaps. [16] Sensors with 3D structures have been developed to overcome these limitations. A 3D cubic sensor generated by selffolding has the ability to gain concentration as well as spatial information (i.e., direction and orientation) of target analytes surrounding the device. [17][18][19] Moreover, a 3D strain sensor fabricated by in situ 3D printing was observed to be compliant with the surface of a breathing porcine lung for continuous mapping of respiration-induced deformation with high 3D spatial resolution. [20] Besides full-space sensing and conformity to targets, compared to 2D counterparts, 3D sensors also possess advantages such as high sensitivity, [21] large specific surface area, [22] multimodal sensing, [23] and so forth.Despite their superiority to 2D sensors, it is challenging to fabricate a sensor with a delicate 3D configuration on a small scale because current micro-nano fabrication technologies are typically performed on planar silicon wafers. [35] Considerable efforts have been made to develop new fabrication methods for 3D sensors, which will be reviewed in this paper. According to the criterion of material quantity change, [36] these fabrication methods are divided into four categories: bulk chemical etching (subtractive manufacturing), 3D printing (additive manufacturing), molding (formative manufacturing), and stress-induced assembly (formative manufacturing), as shown in Figure 1. Basic applications or sensing functions (e.g., light, force, electricity, and chemical/gas), advanced applications (e.g., robotics, HMI, health monitoring, and tissue engineering), and strengths over 2D counterparts (high spatial resolution, multimodality, conformity, and high sensitivity) are illustrated for relevant 3D sensors. The fabrication methods and their pros and cons in generating 3D structures for various applications are summarized in Table 1. The discussions are concluded by outlining current challenges and future opportunities for 3D sensors.The intelligence of modern technologies relies on perceptual systems based on microscale sensors. However, because of the traditional top-down fabrication approaches performed on planar silicon wafers, a large proportion of existing microscale sensors have 2D structures, which severely restricts their sensing capabilities. To overcome these restrictions, over the past few decades, increasing e...

show abstract

“…[54] Copyright 2022, The Authors, published by Springer Nature; middle, Reproduced under the terms of the CC-BY Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/). [179] Copyright 2022, The Authors, published by Wiley-VCH; right, Reproduced with permission. [111] Copyright 2022, AAAS.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning for Tactile Perception: Advancements, Challenges, and Opportunities

Lin

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

The past decades have seen the rapid development of tactile sensors in material, fabrication, and mechanical structure design. The advancement of tactile sensors has heightened the expectation of sensor functions, and thus put forward a higher demand for data processing. However, conventional analysis techniques have not kept pace with the tactile sensor development and still suffer from some severe drawbacks, like cumbersome models, poor efficiency, and expensive costs. Machine learning, with its prominent ability for big data analysis and fast processing speed, can offer many possibilities for tactile data analysis. Herein, the machine learning techniques employed for processing tactile signals are reviewed. Supervised learning and unsupervised learning for analog signals are covered, and processing spike signals with machine learning are summarized. Furthermore, the applications in robotic tactile perception and human activity monitoring are presented. Finally, the current challenges and future prospects in sensors, data, algorithms, and benchmarks are discussed.

show abstract

Surface Texture Recognition by Deep Learning‐Enhanced Tactile Sensing

Cited by 31 publications

References 27 publications

Application of Image Sensing System in Mineral/Rock Identification: Sensing Mode and Information Process

Application of Image Sensing System in Mineral/Rock Identification: Sensing Mode and Information Process

Review on Microscale Sensors with 3D Engineered Structures: Fabrication and Applications

Machine Learning for Tactile Perception: Advancements, Challenges, and Opportunities

Contact Info

Product

Resources

About