Multi-layer fabric type sensing glove based on carbon black-silica gel system, method of preparation and gesture reconstruction device

Abstract

The present application relates to the field of flexible wearable sensing device, and is a multi-layer fabric type sensing glove based on carbon black-silica gel system, a preparation method and a gesture reconstruction device. The sensing glove comprises a fabric substrate printed with carbon black-silica gel composite material and sewn together, and is equipped with silver fiber wire and button electrode on the fabric substrate; the fabric substrate comprises an upper fabric substrate and a lower fabric substrate; the carbon black-silica gel composite material is printed on the fabric substrate to form a printing layer and serve as a sensing layer and a conductive layer; the printing layer comprises an upper layer outer printing layer, an upper layer inner printing layer and a lower layer outer printing layer; the upper layer outer printing layer and the upper layer inner printing layer are connected through a via, and the upper layer outer printing layer and the lower layer outer printing layer are connected through silver fiber wire; the sensing layer is arranged on the upper layer outer printing layer to form a plurality of strain sensors. The present application reduces the number of rigid electronic components, improves the integration, stability and wearing comfort of the sensing glove.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of flexible wearable sensing devices, in particular to a multi-layer fabric type sensing glove based on a carbon black-silica gel system, a preparation method and a gesture reconstruction device. BACKGROUND

[0002] With the progress of technology in the fields of material science, medicine and electronics, intelligent wearable devices are gradually changing people's way of life and work. Among them, the hand, as the most frequently used part of the body, plays an important role in daily life and needs to reconstruct and track the posture of the whole hand in virtual reality, medical rehabilitation and other fields. These application scenarios pose the following challenges to wearable sensing gloves: (1) the posture reconstruction angle of the hand must be accurate enough; (2) the motion of the hand must be acquired and tracked in real time; (3) it must have certain reliability and stability; (4) the glove must be worn in a non-invasive manner and cannot affect the normal activities and work of the wearer; (5) it must be mass-produced in a simple and low-cost manner.

[0003] Currently, there are mainly three technical solutions for hand gesture reconstruction: (1) hand gesture reconstruction based on computer vision: this method captures hand images through a depth camera and then uses computer vision technology to calculate the position of the hand skeleton or the angle of the joint, thereby reconstructing the hand posture. The computer vision-based scheme usually has problems such as being susceptible to occlusion, light and background interference, and needs multiple cameras or optical markers, which limits its scope of application. (2) hand gesture reconstruction based on inertial measurement unit (IMU) sensing gloves: this method calculates the posture angle through the IMU fixed on the glove, solves the rotation matrix between the coordinate systems, and finally obtains the relative position relationship, thereby solving the hand posture. Due to the zero drift problem of IMU, the IMU-based sensing glove has the problem of reduced accuracy after long-term use. In addition, the IMU coordinate system is not aligned with the body or joint coordinate system, and a calibration program needs to be performed in advance. The rigidity and bulky size of the IMU make the sensing glove have a complicated appearance and are not conducive to wearing. (3) hand gesture reconstruction based on strain sensor gloves: this method calculates the strain generated on the back of the finger when the finger joint bends through flexible strain sensors to calculate the bending angle of the finger, thereby reconstructing the hand posture. In the manufacturing method of flexible strain sensor-based sensing gloves, most of them manufacture the sensor separately and then fix it on the glove or clothing through various processes. This method will cause instability of the glove structure and discomfort of wearing. A few methods directly integrate the sensor into the glove fabric, but the performance improvement often comes at the cost of complex manufacturing processes and high metal material costs. SUMMARY

[0004] In order to solve the problems existing in the prior art, the application provides a multi-layer fabric type sensing glove based on a carbon black-silica gel system, a preparation method and a gesture reconstruction device, a strain sensor array is integrated on a glove with a double-layer fabric substrate, the process is simple, the cost is low, and the obtained fabric type sensing glove can complete accurate hand posture reconstruction while ensuring the comfort of the wearer.

[0005] In the embodiment of the application, a multi-layer fabric type sensing glove based on a carbon black-silica gel system comprises fabric substrates printed with carbon black-silica gel composite materials and sewn together, and silver fiber wires and button electrodes are assembled on the fabric substrates.

[0006] The fabric substrate comprises an upper fabric substrate and a lower fabric substrate; the carbon black-silica gel composite material is printed on the fabric substrate to form a printing layer, and the printing layer serves as a sensing layer and a conductive layer.

[0007] The printing layer comprises an upper layer outer printing layer, an upper layer inner printing layer and a lower layer outer printing layer; the upper layer outer printing layer and the upper layer inner printing layer are connected through a via, and the upper layer outer printing layer and the lower layer outer printing layer are connected through a silver fiber wire; the sensing layer is arranged on the upper layer outer printing layer to form a plurality of strain sensors, and the sensors are strained and the resistance is increased with the bending of fingers.

[0008] In the embodiment of the application, a method for preparing the above multi-layer fabric type sensing glove specifically comprises the following steps.

[0009] S1, carbon black is used as a conductive medium to prepare carbon black-silica gel conductive composite paste, and the paste-like composite paste is printed on both sides of one fabric substrate and one side of another fabric substrate through a designed screen printing mold.

[0010] S2, holes are punched at via positions and button electrode positions; the via positions are the center of column electrodes of the first row of sensors and the center of column electrodes of the third row of sensors.

[0011] S3, the composite paste is applied on both sides of the via and solidified, and the composite paste is in full contact with the printing layer to form stable electrical connection.

[0012] S4, the silver fiber wire is sewn on the protruding area of the upper layer outer printing layer and the lower layer outer printing layer, electrical connection is realized through the contact between the silver fiber wire and the printing layer, and finally the two fabric substrates are sewn together with a knitting line to form a complete glove.

[0013] In the embodiment of the application, a gesture reconstruction device of a fabric type sensing glove comprises:

[0014] The above multi-layer fabric type sensing glove is used to obtain finger joint bending angle information, and the finger joint bending angle information is mapped into a resistance change signal.

[0015] A signal acquisition and transmission circuit is configured to read a voltage signal caused by a resistance change of the strain sensor on the fabric type sensing glove and send the read voltage signal to the hand posture solving module.

[0016] The hand posture solving module is configured to receive the voltage signal sent by the signal acquisition and transmission circuit and solve the resistance value of each sensor in the strain sensor in real time, estimate the finger bending angle according to the resistance value, and predict the bending angle of each joint of the finger through a deep learning network to reconstruct the hand posture.

[0017] From the above technical solutions, the present application avoids the instability problem caused by the traditional mechanical connection mode of the sensor and the glove, reduces the number of rigid electronic components, improves the integration, stability and wearing comfort of the sensing glove, and has important reference value for the perception of human motion in the field of wearable sensing devices.

[0018] Compared with the prior art, the present application has the following beneficial effects:

[0019] 1. The sensing glove of the present application does not contain any rigid electronic components, has a non-invasive full-textile form, does not affect the normal activities of the wearer, and has good wearing comfort.

[0020] 2. The sensing glove of the present application adopts a printed integrated scheme, has high stability and integration, is not easy to cause the sensor to fall off in long-term use, and has a lighter and thinner volume.

[0021] 3. The present application provides an efficient scheme for integrating a strain sensor array of a carbon black-silica gel system into a fabric glove, reducing the number of additional connecting components and interface electrodes, and optimizing the manufacturing process.

[0022] 4. The fabric type sensing glove of the present application can generate a stable response signal according to the hand movement, and can solve the hand posture through a deep learning algorithm. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 is a structural diagram of the fabric type sensing glove in the embodiments of the present application;

[0024] Figure 2 is a distribution diagram of three rows of strain sensors of the upper outer printed layer;

[0025] Figure 3 is a row and column electrode connection mode of the strain sensor array in the upper outer printed layer and the upper inner printed layer and the corresponding button electrode position, wherein A, B, C, D and E are the positions of the button electrodes of the column electrodes, and F, G and H are the positions of the button electrodes of the row electrodes;

[0026] Figure 4 Equivalent circuit diagram of strain sensor array;

[0027] Figure 5 Screen printing pattern of 3-layer printing layer;

[0028] Figure 6 Absolute resistance change rate test results of resistance of each block with strain;

[0029] Figure 7 Change curve of sensor resistance with hand movement. DETAILED DESCRIPTION

[0030] The technical solutions of the present application will be described in detail below in combination with the drawings and specific embodiments, but the embodiments of the present application are not limited thereto. EMBODIMENT

[0031] Due to the particularity of the structure of the human hand, a general double-layer sensor array based on a resistance matrix cannot be directly deployed on a fabric sensing glove, because the sensors of each finger can only be connected at the proximal end, and direct connection at the middle and distal ends will affect the normal activity of the fingers. Therefore, the present embodiment provides a printed multi-layer fabric type sensing glove based on a carbon black-silica gel system, which sets the sensors at the finger joint positions to sense the bending changes of the fingers, thereby detecting hand posture signals. The process is simple and the cost is low. Specifically, a 3x5 strain sensor array is integrated on a double-layer fabric base glove, reducing the number of rigid electronic components and additional connection components. The fabric type sensing glove can complete accurate hand gesture reconstruction while ensuring the comfort of the wearer.

[0032] Referring to Figure 1 The fabric type sensing glove of the present embodiment has a multi-layer sensing-conducting integrated fabric structure, specifically including two layers of knitted fabric printed with carbon black-silica gel composite material, which are sewn together, and a male buckle of silver fiber wire and conductive button electrode (such as metal button electrode) is assembled on the knitted fabric. Among them, the knitted fabric serves as a fabric base, including an upper layer (back of hand layer) fabric base and a lower layer (palm layer) fabric base; carbon black-silica gel composite material is printed on the fabric base to form a printing layer, which serves as a sensing layer and a conductive layer. The present embodiment prints three layers of printing layers on the two layers of fabric base, which are the upper layer outer printing layer, the upper layer inner printing layer and the lower layer outer printing layer; the upper layer outer printing layer and the upper layer inner printing layer are electrically connected by vias, and the upper layer outer printing layer and the lower layer outer printing layer are electrically connected by silver fiber wire.

[0033] The embodiment designs an adaptive printing pattern according to the shape and structure of a human hand, and the printing pattern includes a connecting part and a sensing part. The sensing part is designed in a snake shape to increase the resistance. The connecting part is designed in a strip shape according to the space condition. The sensing part is arranged on the upper outer printing layer to form a plurality of strain sensors. With the bending of the fingers, the sensors are strained, and the resistance is increased.

[0034] In combination Figure 2 , 15 strain sensors are printed on the upper outer printing layer, and 3 strain sensors are printed on each finger. Specifically, the first row of sensors is arranged at the position of the distal phalanx, the second row of sensors is arranged at the position of the middle phalanx, and the third row of sensors is arranged at the position of the proximal phalanx. The two poles of each sensor are a row electrode and a column electrode. The distal end of the first row of sensors is the row electrode, and the proximal end is the column electrode. The distal end of the second row of sensors and the third row of sensors is the column electrode, and the proximal end is the row electrode.

[0035] The row electrodes of the first row of sensors are electrically connected to the lower outer printing layer through silver fiber wires, and the interconnection between the row electrodes of the first row of sensors is realized. The column electrodes of the first row of sensors and the second row of sensors are directly connected through the same connecting part, and the first row of sensors and the second row of sensors constitute a symmetrical arrangement with opposite electrodes. The column electrodes of the first and second rows of sensors are electrically connected to the column electrodes of the third row of sensors through vias and the upper inner printing layer. The row electrodes and the column electrodes of all the sensors are concentrated to the electrode lead-out area on the back of the hand through the connecting part of the printing layer, and are directly connected to the flexible circuit board through the button electrode, without the need to install additional connecting wires.

[0036] The embodiment is provided with a protruding area on the upper outer printing layer and the lower outer printing layer for sewing silver fiber wires. That is, the silver fiber wires are sewn in the protruding area of the upper outer printing layer and the lower outer printing layer, to realize the electrical connection between the upper outer printing layer and the lower outer printing layer, and to realize the electrical connection between the row electrodes of the first row of sensors. The protruding area is located at the fingertips of the fingers and the flexor / extensor tendons of the little finger, as shown in Figure 1 The upper outer printing layer and the upper inner printing layer are electrically connected through the vias shown in Figure 1 , and the electrical connection between the column electrodes of the second row of sensors and the third row of sensors is realized. The vias are filled with the same paste as the printing layer (i.e. the same carbon black-silica composite paste), and the paste needs to fill the entire via and fully contact the coating of the column electrode. The male buckle of the metal button electrode is installed in the electrode lead-out area designed on the printing layer, which can be directly connected to the female buckle on the flexible circuit board.

[0037] In combination Figure 3 and Figure 4, the row and column electrode connection mode of the strain sensor array of the upper layer outer side printing layer and the upper layer inner side printing layer, and the corresponding button electrode position and equivalent circuit are shown, the three printing layers, the via and the silver fiber wire constitute a 3x5 row and column shared resistance matrix, and the via and the silver fiber wire only need 10 and 6 groups respectively. The column electrode of the third row sensor is designed as a circle with a diameter of 4 mm to reduce the occupation of the space of the row electrode connection part of the second row sensor.

[0038] A button electrode is led out in each row and column of the row and column shared resistance matrix, and 3 rows of button electrodes and 5 columns of button electrodes are obtained. Among the 8 button electrodes, 4 button electrodes are in contact with the upper layer outer side printing layer, and the other 4 button electrodes are in contact with the upper layer inner side printing layer, so as to avoid conflict between different electrode connection areas. The column electrode buttons of the index finger, the middle finger, the ring finger and the little finger are in contact with the upper layer inner side printing layer to realize electrical connection, and all the row electrode buttons and the column electrode button of the thumb are in contact with the upper layer outer side printing layer to realize electrical connection.

[0039] In an embodiment, the design pattern of the printing layer is as shown in Figure 5 , wherein the width of the sensing area is not higher than 1 mm, and the length is not less than 73 mm; the minimum width of the connection area is not less than 8 mm, and the maximum length is not higher than 16 mm. The pattern design rules of the sensing area and the connection area follow the size effect theory, and the effective aspect ratio of each part of the connection area is related to the shape and current path. Among them, the upper layer inner side printing layer and the lower layer outer side printing layer are both used as the connection area, and the upper layer outer side printing layer is provided with the sensing area and the connection area.

[0040] That is to say, the upper layer outer side printing layer in the embodiment mirrors and flips the first row of sensors, with the distal end as the row electrode and the proximal end as the column electrode. The row electrode of the first row of sensors is interconnected with the lower layer outer side printing layer through the silver fiber wire and led out to the button electrode position, the column electrode of the first row of sensors and the column electrode of the second row of sensors are directly connected and connected with the upper layer inner side printing layer and the column electrode of the third row of sensors through the via. The row electrodes and the column electrodes of all the sensors are led to the electrode leading-out area on the back of the hand through the connection area of the printing layer, and then the plate-to-plate direct connection is realized through the button electrode and the flexible circuit board, without the need of installing additional wires.

[0041] In the embodiment, the preparation method of the fabric type sensing glove mainly includes the following steps:

[0042] S1, carbon black is used as a conductive medium to prepare a carbon black-silica gel conductive composite paste, and the paste-like composite paste is printed on both sides of one fabric substrate and one side of another fabric substrate through a designed screen printing mold; a rectangular frame line is designed around the pattern of the screen printing mold to realize the alignment of different printing layers.

[0043] Specifically, carbon black (3 grams), silica gel (30.3 grams), and silicone oil (45 grams) are mixed, 1.8 grams of curing agent is added, and the mixture is stirred for 30 minutes with a blender. The blended paste is poured onto a customized screen printing mold, and the paste is printed on a fabric base, which is a composite knitted fabric of polyester and spandex, using a rubber brush plate. The printed fabric is placed in a vacuum drying oven for 1 hour for curing. Two-layer fabrics printed with three layers of printing layers are prepared by the above method, respectively, wherein the two printing layers on the upper fabric need to be aligned by designing a rectangular frame as a marker on the screen printing mold.

[0044] S2, use an electric puncher to punch round holes at the designed via hole positions and button electrode positions, which are the center of the column electrodes (square) of the first row of sensors and the center of the column electrodes (circle) of the third row of sensors.

[0045] S3, apply composite paste on both sides of the via hole and cure it, and the composite paste needs to be in full contact with the printing layer to form a stable electrical connection. The male buckle of the metal button electrode is installed at the button hole.

[0046] This step fills the via hole and the surrounding two printing layers with composite paste and cures it. The male buckle of the button electrode is installed at the button electrode position by engaging two metal sheets, and is attached to the upper layer of the outer printing layer to form a stable electrical connection.

[0047] S4, sew silver fiber threads in the protruding areas of the upper and lower outer printing layers to achieve electrical connection through the contact between the silver fiber threads and the printing layers; finally, the two fabric bases are sewn together with ordinary knitted threads to make a complete glove.

[0048] The embodiment also provides a gesture reconstruction device based on a multi-layer fabric type sensing glove, comprising:

[0049] The fabric type sensing glove is used to obtain the bending angle information of 15 finger joints of 5 fingers, and map the bending angle information of the finger joints to resistance change signals;

[0050] The signal acquisition and transmission circuit is used to read the voltage signals caused by the resistance change of the strain sensors on the fabric type sensing glove, and transmit the read voltage signals to the hand pose solving module in a wireless manner in real time;

[0051] The hand pose solving module is used to receive the voltage signals sent by the signal acquisition and transmission circuit, and solve the resistance values of each sensor in the strain sensor in real time, estimate the bending angle of the finger according to the resistance value, and predict the bending angle of each joint of the finger through a deep learning network to reconstruct the hand pose and control a mechanical hand or a hand model in virtual reality (VR).

[0052] The hand posture solving module can be implemented by a host computer, including a data receiving and gesture reconstruction module and an interactive display module. The data receiving and gesture reconstruction module receives and unpacks the voltage signal (i.e. Bluetooth data) sent by the signal acquisition and transmission circuit, maps the normalized resistance values of 100 frames of strain sensor arrays to 15 joint bending angles through a trained deep learning network, and the interactive display module includes a robot control system and / or a VR hand model control interface, which realizes precise control of the robot and / or the hand model according to the joint bending angles predicted by the deep learning network. The deep learning network is a long short-term memory (LSTM) network.

[0053] The signal acquisition and transmission circuit includes a readout circuit and a Bluetooth data sending module. The readout circuit includes a microcontroller, which uses the resistance matrix method (RMA) to read and calculate the resistance values of the 3x5 strain sensor array. The row line scanning signal is controlled by the IO port of the microcontroller and loaded onto the corresponding button electrode of the row electrode on the circuit board. The voltage on the column electrode is then obtained through the analog-to-digital conversion (ADC) peripheral inside the microcontroller. Finally, the resistance values of the 15 strain sensors are calculated locally in the microcontroller according to the RMA calculation formula. The Bluetooth data sending module communicates with the microcontroller through a serial port and sends the resistance values of the sensors to the host computer at a fixed frequency.

[0054] The signal acquisition and transmission circuit is made of a flexible printed circuit board (FPCB), which is designed with a custom button electrode package consisting of a double-sided rectangular pad and a central circular hole. The row electrodes of each sensor on the fabric-type sensing glove are connected to the IO port of the microcontroller (STM32F103RCT6), and the column electrodes are connected to the ADC channel. The Bluetooth data sending module is connected to the serial port. The electrode is designed according to the size of the metal button electrode, and the PCB package consists of a square double-sided pad and a circular via. After installing the female buckle of the metal button electrode on the PCB and further soldering with solder, a stable electrical connection is achieved. After installing the female buckle of the metal button electrode on the button electrode package, a stable electrical connection is achieved by soldering with solder. After installing the metal electrode button, a stable electrical-mechanical dual connection between the flexible circuit board and the fabric-type sensing glove can be achieved through the electrode button.

[0055] The readout circuit performs dynamic row scanning (each row level is pulled low, and other rows are pulled high), and the voltage of each column is obtained through the ADC channel. The resistance values of each sensor are calculated by the microcontroller according to the resistance matrix method calculation formula, and are sent to the host computer through Bluetooth at a frame rate of 30Hz. The host computer is written in python language, which unpacks and filters the data received by Bluetooth after reading, and draws a curve graph of the resistance of 15 sensors changing with time, and saves the resistance data. All functions of the host computer are realized by real-time running of the program through timing calling.

[0056] In this embodiment, the resistance matrix method calculation formula is:

[0057] ;

[0058] wherein, R ij R is the resistance of each sensor, V ij V is the voltage on the jth column when the ith row is scanned, V rj V is the voltage on the jth column when the reference resistance is scanned, V cc V is the power supply voltage of the microcontroller, R rj R is the reference resistance value.

[0059] Further, in addition to real-time drawing of the resistance-time curve, the host computer also inputs the resistance data sequence to the trained LSTM network, the sequence is composed of 100 frames of 15 resistance data, the LSTM network maps the resistance data sequence to 15 finger joint angles, and then inputs the resistance data sequence to the script in Unity to control the motion of the hand model in the virtual scene; or through Bluetooth to send to the Arduino control board of the mechanical hand to control the mechanical hand to perform corresponding actions. The training data set is composed of sensor data and labels, and the label uses the joint angle data collected by the commercially available gesture reconstruction glove (MANUS) as the gold standard. When collecting data, first wear the fabric type sensing glove in the application, and then wear the MANUS gesture reconstruction glove outside.

[0060] The performance test of the fabric type sensing glove and the gesture reconstruction device of the embodiment is as follows:

[0061] In combination Figure 6 , the fabric printed with conductive material is divided into 41 blocks, each block is stretched to 60% strain by a universal testing machine, the resistance is tested by a Keithley digital multimeter, the resistance-strain relationship diagram is obtained, and the absolute resistance change rate of each block with strain is calculated by derivation; the results show that the resistance change rate of the sensing area is much larger than that of the connecting area, that is, the resistance change of the sensing area under the same strain is much higher than that of the connecting area, proving that the designed printing layer pattern meets the size effect design requirement.

[0062] In combination Figure 7, test the response signal of the gesture reconstruction device based on the fabric type sensing glove with the hand movement, after the user wears the glove and connects the signal acquisition and transmission circuit, each finger performs a single bending action and a combined bending action, and the resistance curve of each sensor with time is recorded by the upper computer. The first letter of the English letter abbreviation in the figure represents the name of the finger: T-the thumb, I-the index finger, M-the middle finger, R-the ring finger, L-the little finger; the latter letter is the abbreviation of the name of the finger joint, CMC-the first metacarpophalangeal joint, MCP-the metacarpophalangeal joint, IP-the interphalangeal joint, PIP-the proximal interphalangeal joint, DIP-the distal interphalangeal joint. When the fingers perform different actions, the calculated resistance signal has a stable and low crosstalk waveform. It should be noted that the slight crosstalk between the ring finger and the little finger is due to the fact that they cannot complete completely independent actions, not the crosstalk between the sensors.

[0063] The above embodiments are the preferred embodiments of the present application, but the embodiments of the present application are not limited by the above embodiments, and any changes, modifications, substitutions, combinations, simplifications made without departing from the spirit and principles of the present application should be equivalent replacement methods, which are all included in the protection scope of the present application.

Claims

1. A multi-layer fabric-based sensing glove based on a carbon black-silica gel system, characterized in that, The fabric substrate printed with the carbon black-silica gel composite material is sutured, and silver fiber wires and button electrodes are arranged on the fabric substrate; The fabric substrate includes an upper fabric substrate and a lower fabric substrate; the carbon black-silica gel composite material is printed on the fabric substrate to form a printed layer, which serves as a sensing layer and a conductive layer; The printed layer includes an upper layer outer printed layer, an upper layer inner printed layer, and a lower layer outer printed layer; the upper layer outer printed layer and the upper layer inner printed layer are connected through vias, and the upper layer outer printed layer and the lower layer outer printed layer are connected through silver fiber wires; the sensing layer is arranged on the upper layer outer printed layer to form a plurality of strain sensors, and as the fingers bend, the sensors are strained, and the resistance is increased; The upper layer outer printed layer prints three strain sensors on each finger, specifically including a first row of sensors arranged at the distal phalanx position, a second row of sensors arranged at the middle phalanx position, and a third row of sensors arranged at the proximal phalanx position; the two poles of each sensor are a row electrode and a column electrode; The distal end of the first row of sensors is the row electrode, and the proximal end is the column electrode; the distal end of the second row of sensors and the third row of sensors is the column electrode, and the proximal end is the row electrode; The row electrodes of the first row of sensors are connected through silver fiber wires and the lower layer outer printed layer to realize the interconnection between the row electrodes of the first row of sensors; the column electrodes of the first row of sensors and the second row of sensors are designed to be directly connected through the same connection part, and the first row of sensors and the second row of sensors are arranged in a symmetrical arrangement with opposite electrodes; the column electrodes of the first and second rows of sensors are connected through vias and the upper layer inner printed layer to the column electrodes of the third row of sensors; the row electrodes and the column electrodes of all the sensors are concentratedly led to the electrode lead-out area on the back of the hand through the connection part of the printed layer.

2. The multi-layer fabric-based sensing glove of claim 1, wherein, The upper layer outer printed layer and the lower layer outer printed layer are provided with protruding areas for sewing silver fiber wires; the protruding areas are located at the fingertips of the fingers and the flexor tendon of the little finger.

3. The multi-layer fabric-based sensing glove of claim 1, wherein, The vias are filled with the same carbon black-silica gel composite material as the printed layer.

4. A method of making the multi-layer fabric sensor glove of any one of claims 1-3, wherein, The method includes the following steps: S1. Carbon black is used as a conductive medium to prepare a carbon black-silica gel conductive composite paste, and the paste is printed on both sides of one fabric substrate and one side of another fabric substrate through a designed screen printing mold; S2. Holes are punched at the via positions and the button electrode positions; the via positions are the centers of the column electrodes of the first row of sensors and the centers of the column electrodes of the third row of sensors; S3. The composite paste is applied on both sides of the vias and solidified, and the composite paste is in full contact with the printed layer to form stable electrical connection; S4. Silver fiber wires are sewn in the protruding areas of the upper layer outer printed layer and the lower layer outer printed layer, and electrical connection is achieved through the contact between the silver fiber wires and the printed layer; finally, the two fabric substrates are sutured with knitting lines to make a complete glove.

5. A gesture reconstruction apparatus for a fabric type sensing glove, characterized by, The method includes: The multi-layer fabric type sensing glove according to any one of claims 1-3 is used to obtain the bending angle information of the finger joints, and the bending angle information of the finger joints is mapped into a resistance change signal; A signal acquisition and transmission circuit is used to read the voltage signal caused by the resistance change of the strain sensor on the fabric type sensing glove, and send the read voltage signal to a hand posture solving module. The hand posture solving module is configured to receive the voltage signal sent by the signal acquisition and transmission circuit, and to solve the resistance value of each sensor in the strain sensor in real time, estimate the finger bending angle according to the resistance value, and predict the bending angle of each joint of the finger through a deep learning network to reconstruct the hand posture.

6. The gesture reconstruction apparatus of claim 5, wherein, The hand posture solving module comprises a data receiving and gesture reconstruction module and an interactive display module; the data receiving and gesture reconstruction module receives and unpacks the voltage signal sent by the signal acquisition and transmission circuit, and maps the resistance value of the strain sensor to the bending angle of the knuckle through the trained deep learning network; the interactive display module comprises a mechanical hand control system and / or a VR hand model control interface, and realizes precise control of the mechanical hand and / or the hand model according to the bending angle of the joint predicted by the deep learning network.

7. The gesture reconstruction apparatus of claim 5, wherein, The signal acquisition and transmission circuit comprises a readout circuit and a Bluetooth data sending module; the readout circuit comprises a microcontroller, uses the resistance matrix method to read and calculate the resistance value of the sensor array of the strain sensor, controls the row line scanning signal by the IO port of the microcontroller, loads the high and low levels to the button electrode corresponding to the row electrode, acquires the voltage on the column electrode through the analog-to-digital conversion peripheral device inside the microcontroller, and finally calculates the resistance value of the sensor according to the resistance matrix method calculation formula; the Bluetooth data sending module communicates with the microcontroller through the serial port, and sends the resistance value of the sensor to the hand posture solving module at a fixed frequency.

8. The gesture reconstruction apparatus of claim 7, wherein, The signal acquisition and transmission circuit is made of a flexible circuit board.

Images