Flexible Tactile Sensor Array Research Articles

Identification of fruit using a flexible tactile sensor array

This article aims to address the issue of low recognition accuracy in existing sorting robots caused by lighting, occlusion, and environmental factors. A fruit recognition method based on a flexible tactile sensor array is described. This method enables the robot to directly perceive the attributes of the objects and identify fruits using a flexible gripper, facilitating intelligent sorting. A novel flexible tactile sensor array is utilized to construct a flexible hand tactile information acquisition platform, which collects tactile time series data for the fruits. Principal component analysis is then employed for dimensionality reduction, followed by the development of an improved particle swarm optimization for the support vector machine model. Through an experimental study, the optimized model is compared with four other models, demonstrating better classification performance. The optimized model achieves an average tactile classification accuracy of up to 98.10% for the five types of fruits. A comparison between the improved optimization algorithm, genetic algorithm, and grid search algorithm reveals the superior optimization performance of the new approach. In the future, this method is expected to be implemented in industrial sorting robots for intelligent sorting on automatic production lines. Furthermore, the algorithm will be further refined to enhance the classification accuracy and efficiency.

A Learning‐Based Sensor Array for Untethered Soft Prosthetic Hand Aiming at Restoring Tactile Sensation

Endowing tactile feedback for prosthetic hands is profound for upper‐limb amputees. However, existing prosthetic hands are generally not in possession of the embedded sensory feedback. Herein, a flexible tactile sensor array which can be integrated into an untethered soft prosthetic hand to achieve static and dynamic discrimination tasks is presented. The flexible piezoresistive sensory arrays with 25 sensor units which can be arranged on five fingers of the soft prosthetic hand are fabricated. According to the collected large‐scale tactile dataset (including pressure distribution and pressure magnitude) during different grasping tasks, a learning‐based classification model that can reveal the correspondences between tactile information and object attributes while interacting with touched objects is developed. To transfer tactile information extracted from tactile sensor arrays, a wearable vibrotactile feedback band with a spatial coding feedback strategy is implemented by selectively activating vibrotactile motors located on the skin of the upper arm. In a set of tests performed by an individual with transradial amputation and eight able‐bodied subjects, the soft prosthetic hand integrated with tactile sensor arrays can help the users regain finger tactile sensation, discriminate grasped objects, and achieve real‐time dynamic rolling detection.

Development of flexible tactile sensing arrays for hardness recognition

Hardness sensation is an essential function of human skin, which is significant for enhancing the objects perception ability of intelligent manipulators in various scenarios. Although progress has been made in mimicking this function of human hands, the hardness identification still remains a great challenge. In this study, inspired by the Hertz model and the static pressure response of Merkel cells (SA-I) mechanoreceptors, we develop a membrane-like piezoresistive flexible tactile sensor array (PFTSA) that consists of a flexible electrode array layer and a sensitive material layer with a micropyramidal structure, which can effectively identify the hardness values of different objects. The sensor can be a part of the manipulator’s system due to its conformal ability and large deformation, which shows high pressure response sensitivity (4.432 mA/N in the 0–1 N pressure range) and good cycling stability (2100 cycles at 5 N), enabling the consistent and precise detection of external information. As a proof-of-concept illustration, we integrate the PFTSA on a finger of the manipulator to discriminate six objects with different hardness values. The results demonstrate the great potential of PFTSA in the application of human-machine interactions, paving the way for the development of robotic diagnostics, mechanical sorting operations and virtual reality technology.

3: A Machine Haptic System based on a Flexible Tactile Sensor Array Enabling Material Classification and Texture Recognition

Human haptic systems such as hand and skin are capable of material classification and texture recognition with a slight training effort where the mechanoreceptor first collects the tactile information, secondly, the nerves and neurons deliver the message and finally, the somatosensory cortex in the brain computes and makes a decision. In this work, we attempt to build a machine haptic system to mimic functions of skin and nervous system for material classification and recognition.

A triboelectric nanogenerator-based tactile sensor array system for monitoring pressure distribution inside prosthetic limb

In the prosthetic field, quantifying interfacial pressure distribution between the amputee's residual limb and the socket’s internal environment is imperative for developing new technologies. However, the commercially available pressure sensors have several disadvantages, namely external power supply requirements, low stability, high cost, and complexities related to integrating the sensor system into prosthetic devices. Herein, we propose a self-powered triboelectric nanogenerator (TENG) based flexible tactile sensor array system to monitor prosthetic socket internal pressure distribution in real-time. The proposed sensor consists of biocompatible polydimethylsiloxane (PDMS) polymer and polycaprolactone (PCL) nanofiber membranes as triboelectric materials. The biodegradable PCL nanofiber membrane, fabricated via a scalable and cost-effective electrospinning process, possesses a high surface area-to-volume ratio, facilitating enhanced charge generation during triboelectrification. The as-fabricated TENG-based tactile sensor is highly stable up to 10,000 cycles. Furthermore, the voltage of the tactile sensor is independent of different temperature and humidity values, demonstrating the stability of the sensor under various environmental conditions. Finally, we successfully integrated the tactile sensor array within a prosthetic device to monitor real-time pressure distribution inside the prosthetic socket during gait simulation. We believe that the proposed novel design provides a new dimension for the rapid development of self-powered, low-cost, and highly stable pressure monitoring systems with considerable potential for commercialization.

Hardness-and-Type Recognition of Different Objects Based on a Novel Porous Graphene Flexible Tactile Sensor Array.

Accurately recognizing the hardness and type of different objects by tactile sensors is of great significance in human-machine interaction. In this paper, a novel porous graphene flexible tactile sensor array with great performance is designed and fabricated, and it is mounted on a two-finger mechanical actuator. This is used to detect various tactile sequence features from different objects by slightly squeezing them by 2 mm. A Residual Network (ResNet) model, with excellent adaptivity and feature extraction ability, is constructed to realize the recognition of 4 hardness categories and 12 object types, based on the tactile time sequence signals collected by the novel sensor array; the average accuracies of hardness and type recognition are 100% and 99.7%, respectively. To further verify the classification ability of the ResNet model for the tactile feature information detected by the sensor array, the Multilayer Perceptron (MLP), LeNet, Multi-Channel Deep Convolutional Neural Network (MCDCNN), and ENCODER models are built based on the same dataset used for the ResNet model. The average recognition accuracies of the 4hardness categories, based on those four models, are 93.6%, 98.3%, 93.3%, and 98.1%. Meanwhile, the average recognition accuracies of the 12 object types, based on the four models, are 94.7%, 98.9%, 85.0%, and 96.4%. All of the results demonstrate that the novel porous graphene tactile sensor array has excellent perceptual performance and the ResNet model can very effectively and precisely complete the hardness and type recognition of objects for the flexible tactile sensor array.

Large-Scale Integrated Flexible Tactile Sensor Array for Sensitive Smart Robotic Touch.

In the long pursuit of smart robotics, it has been envisioned to empower robots with human-like senses, especially vision and touch. While tremendous progress has been made in image sensors and computer vision over the past decades, tactile sense abilities are lagging behind due to the lack of large-scale flexible tactile sensor array with high sensitivity, high spatial resolution, and fast response. In this work, we have demonstrated a 64 × 64 flexible tactile sensor array with a record-high spatial resolution of 0.9 mm (equivalently 28.2 pixels per inch) by integrating a high-performance piezoresistive film (PRF) with a large-area active matrix of carbon nanotube thin-film transistors. PRF with self-formed microstructures exhibited high pressure-sensitivity of ∼385 kPa-1 for multi-walled carbon nanotubes concentration of 6%, while the 14% one exhibited fast response time of ∼3 ms, good linearity, broad detection range beyond 1400 kPa, and excellent cyclability over 3000 cycles. Using this fully integrated tactile sensor array, the footprint maps of an artificial honeybee were clearly identified. Furthermore, we hardware-implemented a smart tactile system by integrating the PRF-based sensor array with a memristor-based computing-in-memory chip to record and recognize handwritten digits and Chinese calligraphy, achieving high classification accuracies of 98.8% and 97.3% in hardware, respectively. The integration of sensor networks with deep learning hardware may enable edge or near-sensor computing with significantly reduced power consumption and latency. Our work could empower the building of large-scale intelligent sensor networks for next-generation smart robotics.

Fine Texture Detection Based on a Solid-Liquid Composite Flexible Tactile Sensor Array.

Surface texture information plays an important role in the cognition and manipulation of an object. Vision and touch are the two main methods for extracting an object’s surface texture information. However, vision is often limited since the viewing angle is uncertain during manipulation. In this article, we propose a fine surface texture detection method based on a stochastic resonance algorithm through a novel solid–liquid composite flexible tactile sensor array. A thin flexible layer and solid–liquid composite conduction structure on the sensor effectively reduce the attenuation of the contact force and enhance the sensitivity of the sensor. A series of ridge texture samples with different heights (0.9, 4, 10 μm), different widths (0.3, 0.5, 0.7, 1 mm), but the same spatial period (2 mm) of ridges were used in the experiment. The experimental results prove that the stochastic resonance algorithm can significantly improve the signal characteristic of the output signal of the sensor. The sensor has the capability to detect fine ridge texture information. The mean relative error of the estimation for the spatial period was 1.085%, and the ridge width and ridge height, respectively, have a monotonic mapping relationship with the corresponding model output parameters. The sensing capability to sense a fine texture of tactile senor surpasses the limit of human fingers.

An improved BP neural network‐based calibration method for the capacitive flexible three‐axis tactile sensor array

Flexible tactile sensing based on capacitive sensing has become a research hotspot in recent years because of its low energy consumption, high performance and wide application prospects. However, the axis error caused by the coupling deformation of the dielectric will seriously affect the accuracy of the sensor. In this paper, a capacitive flexible three-axis tactile sensor array is modelled and simulated, and a neural network-based calibrator for the three-axis sensor array is proposed, which can be used to calibrate the simulated measurement data. The simulation results show that even though the correlation coefficient of linear regression for each axis is very close to 1, the effect of dielectric nonlinear coupling distortion cannot be eliminated. The calibration method based on the neural network can effectively suppress the nonlinear coupling distortion of the dielectric, and reduce the measurement coupling rate of the sensor model from 26% to 1%. At the same time, in order to ensure the measurement accuracy and robustness of different units in the sensor array, the input layer of the calibrator is expanded, and the data set containing capacitance information and two-dimensional location information is used for training. The experimental results show that the proposed calibration method combining two-dimensional position information training accurately calibrates the capacitive flexible three-dimensional tactile sensor array.

A Flexible Tactile Sensor Array for Dynamic Triaxial Force Measurement Based on Aligned Piezoresistive Nanofibers

This paper proposes a novel flexible tactile sensor array for dynamic triaxial force measurement. Piezoresistive nanofibers, which are fabricated via the electrospinning method and are composed of multi-wall carbon nanotubes (MWCNTs) and thermoplastic polyurethane (TPU), are selected as the sensing material. The sensitive piezoresistive layer, which has micron-scale thickness, is wrapped in polydimethylsiloxane (PDMS) with a bumped surface. This structure not only detects triaxial forces of different magnitudes and frequencies, but also can recognize the shape, size, and curvature of external objects using multiple measuring points of the sensor. When the sensor is subjected to normal forces at different frequencies, the measuring voltage shows good responses with variations of less than 1.21 %. When the sensor is subjected to shear forces, the coefficient of variation is less than 2.05%. In addition, when the sensor is stressed at multiple measuring points, the voltage response errors between the different points are less than 5.29%. The sensor shows high sensitivity (with a resistance change that can reach four orders of magnitude) and high response-speeds (response within 62 ms) in validation experiments. The proposed flexible sensor is efficient in triaxial force detection and has the potential for application to prosthetic hands and wearable devices.

Robot Grasping System and Grasp Stability Prediction Based on Flexible Tactile Sensor Array

As an essential perceptual device, the tactile sensor can efficiently improve robot intelligence by providing contact force perception to develop algorithms based on contact force feedback. However, current tactile grasping technology lacks high-performance sensors and high-precision grasping prediction models, which limits its broad application. Herein, an intelligent robot grasping system that combines a highly sensitive tactile sensor array was constructed. A dataset that can reflect the grasping contact force of various objects was set up by multiple grasping operation feedback from a tactile sensor array. The stability state of each grasping operation was also recorded. On this basis, grasp stability prediction models with good performance in grasp state judgment were proposed. By feeding training data into different machine learning algorithms and comparing the judgment results, the best grasp prediction model for different scenes can be obtained. The model was validated to be efficient, and the judgment accuracy was over 98% in grasp stability prediction with limited training data. Further, experiments prove that the real-time contact force input based on the feedback of the tactile sensor array can periodically control robots to realize stable grasping according to the real-time grasping state of the prediction model.

Three-Dimensional Force Prediction of a Flexible Tactile Sensor Based on Radial Basis Function Neural Networks

A flexible tactile sensor array with 6 × 6 N-type sensitive elements made of conductive rubber is presented in this paper. The property and principle of the tactile sensor are analyzed in detail. Based on the piezoresistivity of conductive rubber, this paper takes full advantage of the nonlinear approximation ability of the radial basis function neural network (RBFNN) method to approach the high-dimensional mapping relation between the resistance values of the N-type sensitive element and the three-dimensional (3D) force and to accomplish the accurate prediction of the magnitude of 3D force loaded on the sensor. In the prediction process, the k -means algorithm and recursive least square (RLS) method are used to optimize the RBFNN, and the k -fold cross-validation method is conducted to build the training set and testing set to improve the prediction precision of the 3D force. The optimized RBFNN with different spreads is used to verify its influence on the performance of 3D force prediction, and the results indicate that the spread value plays a very important role in the prediction process. Then, sliding window technology is introduced to build the RBFNN model. Experimental results show that setting the size of the sliding window appropriately can effectively reduce the prediction error of the 3D force exerted on the sensor and improve the performance of the RBFNN predictor, which means that the sliding window technology is very feasible and valid in 3D force prediction for the flexible tactile sensor. All of the results indicate that the optimized RBFNN with high robustness can be well applied to the 3D force prediction research of the flexible tactile sensor.

Large-Area, Crosstalk-Free, Flexible Tactile Sensor Matrix Pixelated by Mesh Layers.

Tactile sensor arrays have attracted considerable attention for their use in diverse applications, such as advanced robotics and interactive human-machine interfaces. However, conventional tactile sensor arrays suffer from electrical crosstalk caused by current leakages between the tactile cells. The approaches that have been proposed thus far to overcome this issue require complex rectifier circuits or a serial fabrication process. This article reports a flexible tactile sensor array fabricated through a batch process using a mesh. A carbon nanotube-polydimethylsiloxane composite is used to form an array of sensing cells in the mesh through a simple "dip-coating" process and is cured into a concave shape. The contact area between the electrode and the composite changes significantly under pressure, resulting in an excellent sensitivity (5.61 kPa-1) over a wide range of pressure up to 600 kPa. The mesh separates the composite into the arranged sensing cells to prevent the electrical connection between adjacent cells and simultaneously connects each cell mechanically. Additionally, the sensor shows superior durability compared with previously reported tactile sensors because the mesh acts as a support beam. Furthermore, the tactile sensor array is successfully utilized as a Braille reader via information processing based on machine learning.

Scalable Batch Fabrication of Flexible, Transparent and Self-triggered Tactile Sensor Array Based on Triboelectric Effect

In this study, a facile and scalable fabrication process of the flexible and transparent tactile sensor array where its operation is based on the triboelectric effect is proposed. The overall process is assisted by the solution based screen printing method, which is well-known as advantageous in the batch fabrication of the electronic devices. The introduction of the batch fabrication process to the tactile sensor array enables the realization of high functionality such as transparency and flexibility. The performance of the fabricated tactile sensor array is systematically investigated through the parametric studies and the discernibility to multiple external physical stimuli such as vertical contact and horizontal sliding is verified. It is confirmed that although the present self-triggered tactile sensor array could be easily fabricated and scaled-up without cumbersome processes, the functionalities such as sensitivity, resolution, transparency, flexibility and even peak power density, are comparable to previously developed tactile sensors. Consequently, the scalable and design-flexible fabrication methodology with cost-effect and high production speed in this study effectively broadens the applicability of the sensor array. As proof-of-concept demonstration of potential applications, a stand-alone sensory lighting system as well as a wearable transparent code generator are developed and their performances are investigated.

A master–slave hand operation cooperative perception system for grasping object via information fusion of flexible strain sensors

The cooperative perception technology of master–slave hand operation provides intelligent and convenient support for people engaged in various risky and arduous tasks. This study presents a master–slave hand operation cooperative perception method for grasping objects through multi-information fusion of flexible strain sensors. A data glove and a strain sensor array are designed on stretchable strain sensors for accurate detection of master–slave hand ontology gestures. Meanwhile, a flexible tactile sensor array is proposed for dexterous hand interactive tactile perception. Furthermore, the master–slave hand gesture coordination method is presented. A method of perceiving dexterous hand grasping operation states is proposed on the basis of tactile perception arrays and clustering analysis of tactile perception sequences. Experimental results show that the proposed data glove and tactile sensor arrays exhibit good performance of master–slave hand ontology gesture perception and coordination as well as dexterous hand interactive tactile perception. The error measurements of the joint angle of master-slave hand during gesture coordination process were less than two degrees.

A metal-electrode-free, fully integrated, soft triboelectric sensor array for self-powered tactile sensing

The dramatic advances in flexible/wearable electronics have garnered great attention for touch sensors for practical applications in human health monitoring and human–machine interfaces. Self-powered triboelectric tactile sensors with high sensitivity, reduced crosstalk, and simple processing routes are highly desirable. Herein, we introduce a facile and low-cost fabrication approach for a metal-electrode free, fully integrated, flexible, and self-powered triboelectric tactile sensor array with 8-by-8 sensor units. Through the height difference between the sensor units and interconnect electrodes, the crosstalk derived from the electrodes has been successfully suppressed with no additional shielding layers. The tactile sensor array shows a remarkable sensitivity of 0.063 V kPa–1 with a linear range from 5 to 50 kPa, which covers a broad range of testing objects. Furthermore, due to the advanced mechanical design, the flexible sensor array exhibits great capability of pressure sensing even under a curved state. The voltage responses from the pattern mapping by finger touching demonstrate the uniformity of the sensor array. Finally, real-time tactile sensing associated with light-emitting diode (LED) array lighting demonstrates the potential application of the sensor array in position tracking, self-powered touch screens, human–machine interfaces and many others.

A Paper-Based Flexible Tactile Sensor Array for Low-Cost Wearable Human Health Monitoring

This paper presents the design, fabrication, and characterization results of a paper-based, low-cost, easy-to-use, comfortable and wearable tactile sensor array for human health monitoring applications. Paper substrate and spray-deposited metallic electrodes and traces are employed to achieve a low fabrication cost. Capacitive sensing scheme employing a deformable triangular PDMS sensing membrane is chosen due to its high sensitivity and zero DC power dissipation. Trade-offs among different sensor array designs are investigated to achieve an optimal design, which consists of a $1\times 5$ sensor array occupying an area of 10 mm $\times10$ mm. Each sensor in the array achieves a nominal capacitance value and sensitivity of approximately 1 pF and 30 fF/mmHg, respectively. Fabricated sensor array can be comfortably attached to an individual's temporal region and ankle area to monitor real-time blood pressure (BP) pulse waveform with high fidelity, from which heart rate and heart rate variability information can be accurately obtained. In addition, the prototype sensor array demonstrates its capability of detecting atrial fibrillation (AFib) from BP pulse waveform measured from an AFib patient. [2020-0179]

A high-resolution flexible sensor array based on PZT nanofibers

Flexible tactile sensor array has drawn great attention due to its ability to mimic human skin for sensing weak pressure and distinguishing pressure distribution, but the deficiency of sensitivity, the low resolution, and the complex and costly fabrication process seriously limit its development. Hence, it is urgent to explore a fully flexible sensor array with high sensitivity and high resolution as an electronic-skin. Here, the flexible piezoelectric tactile sensor array based on the composite film of PZT nanowires and polydimethylsiloxane (PDMS) was fabricated by the simple fabrication process (electrospinning process and mixture process). The electrospun PZT nanofibers have high aspect ratio and could enhance the generation and accumulation of the piezoelectric charges in the two electrodes of the composite film. By virtue of the inherently high piezoelectric coefficient of PZT material and high aspect ratio of PZT nanofibers, the composite film (75 wt% PZT nanofibers) presents high force-electric conversion capability and high sensitivity. Owing to the bottom electrode sheet shared by all sensor units and the supporting layer with relatively high elastic modulus, the sensor array shows high resolution to qualitatively sense the distribution and size of the impact in real time. Moreover, the sensor array also shows great durability, repeatability, and large working range. Based on these excellent characteristics, the sensor array has wide potential applications in the field of bionics science, robotics science and human–machine interaction.

Integrated Piezoelectric AlN Thin Film with SU-8/PDMS Supporting Layer for Flexible Sensor Array.

This research focuses on the development of a flexible tactile sensor array consisting of aluminum nitride (AlN) based on micro-electro-mechanical system (MEMS) technology. A total of 2304 tactile sensors were integrated into a small area of 2.5 × 2.5 cm2. Five hundred nm thick AlN film with strong c-axis texture was sputtered on Cr/Au/Cr (50/50/5 nm) layers as the sacrificial layer coated on a Si wafer. To achieve device flexibility, polydimethylsiloxane (PDMS) polymer and SU-8 photoresist layer were used as the supporting layers after etching away a release layer. Twenty-five mM (3-mercaptopropyl) trimethoxysilane (MPTMS) improves the adhesion between metal and polymers due to formation of a self-assembled monolayer (SAM) on the surface of the top electrode. The flexible tactile sensor has 8 × 8 channels and each channel has 36 sensor elements with nine SU-8 bump blocks. The tactile sensor array was demonstrated to be flexible by bending 90 degrees. The tactile sensor array was demonstrated to show clear spatial resolution through detecting the distinct electrical response of each channel under local mechanical stimulus.

Unconstrained Detection of the Respiratory Motions of Chest and Abdomen in Different Lying Positions Using a Flexible Tactile Sensor Array

Respiratory Inductance Plethysmography (RIP) is commonly used to detect the respiratory motions of chest and abdomen during sleep. However, this method is not suitable for daily use due to its strong constraints. Many unconstrained methods have been developed, but they have a common problem with distinguishing the chest and abdominal motions, which are required for understanding the type of sleep apnea. In this paper, we proposed an unconstrained method to distinguish chest and abdominal motions by measuring the pressure fluctuations from the chest and abdomen acting on a mattress. We then investigated the feasibility of detecting respiratory motions by using a flexible tactile sensor array, which was laid on a bed like a bed sheet. Ten healthy subjects (five males and five females) were tested and the results were compared with those measured by the RIP band sensors. It was confirmed that the sensor array could measure the motions of the chest and abdomen and obtain the respiratory rate at a high accuracy. However, the phase of the pressure fluctuations measured by the sensor array might disagree with the outputs of the RIP band sensors, depending on the gender and lying position of the subject. The reason was discussed with a dynamic model, which showed that the disagreement might have been related to the coupling of the chest and abdomen. In addition, the influence of the stiffness of the mattress on the pressure fluctuations was investigated. The results showed that mattress stiffness had little effect on the measurement.