A flexible tactile sensor intelligent sensing method

Abstract

The present invention provides an intelligent sensing method of a flexible tactile sensor, comprising: step 1: reading an object to be sensed and determining the morphological characteristics of the object to be sensed; step 2: performing tactile sensing of the object to be sensed based on the morphological characteristics using a tactile sensor and obtaining sensing data; step 3: processing and reading the sensing data, and outputting a tactile expression of the object to be sensed based on the reading result. The object to be sensed is sensed by combining the morphological characteristics of the object to be sensed with the Hall principle and related technologies, thereby achieving accurate and effective sensing of the object to be sensed, while improving the perceptual sensitivity and comprehensiveness of the flexible tactile sensor and optimizing the working performance of the flexible tactile sensor.

Description

Technical Field

[0001] The present invention relates to the field of sensor technology, and in particular to an intelligent sensing method for a flexible tactile sensor. Background Art

[0002] At present, with the advancement of science and technology, the technology of tactile sensors simulating human tactile perception is becoming more and more advanced. Tactile sensors are a kind of sensor that can sense information such as temperature, humidity, pain, etc. through contact characteristics, and have flexibility similar to human skin, so as to better complete the perception of the external environment;

[0003] However, in the prior art, tactile sensing is mostly performed through capacitive sensors, which are easily interfered by noise, have poor load capacity, and poor flexibility;

[0004] Therefore, the present invention provides an intelligent sensing method for a flexible tactile sensor, which senses the morphological characteristics of the object to be sensed by combining the Hall principle with related technologies, thereby achieving accurate and effective perception of the object to be sensed, while improving the perceptual sensitivity and comprehensiveness of the flexible tactile sensor, and optimizing the working performance of the flexible tactile sensor. Summary of the invention

[0005] The present invention provides an intelligent sensing method for a flexible tactile sensor, which is used to sense the morphological characteristics of the object to be sensed by combining the Hall principle with related technologies, thereby achieving accurate and effective sensing of the object to be sensed, while improving the perceptual sensitivity and comprehensiveness of the flexible tactile sensor, and optimizing the working performance of the flexible tactile sensor.

[0006] The present invention provides an intelligent sensing method of a flexible tactile sensor, comprising:

[0007] Step 1: Read the object to be sensed and determine the morphological characteristics of the object to be sensed;

[0008] Step 2: Performing tactile perception on the object to be perceived based on the morphological features using a tactile sensor, and obtaining perception data;

[0009] Step 3: Process and read the perception data, and output a tactile expression of the object to be perceived according to the reading result.

[0010] Preferably, in a flexible tactile sensor intelligent sensing method, in step 1, reading the object to be sensed includes:

[0011] Reading an image of the object to be sensed based on a preset image acquisition device to determine three views of the object to be sensed, wherein the three views of the object to be sensed include: a front view, a top view, and a side view;

[0012] Reading the three views, respectively determining image pixel information of the three views, and determining contour feature pixel points of the object to be sensed and center pixel points of the three views of the object to be sensed according to the image pixel information;

[0013] Based on the contour feature pixel points of the object to be sensed and the central pixel points of the three-view image of the object to be sensed, the image feature of the object to be sensed is determined, and the reading of the object to be sensed is completed.

[0014] Preferably, a flexible tactile sensor intelligent sensing method, after determining the image features of the object to be sensed, further comprises:

[0015] Determine the pixel point distribution of the three views of the object to be perceived based on the image features of the object to be perceived, and determine the visual perception points of the three views of the object to be perceived respectively based on the pixel point distribution;

[0016] At the same time, based on the three views of the object to be sensed, the scale features of the object to be sensed are read, and based on the scale features, the three views of the object to be sensed are three-dimensionally stitched according to the visual perception points to obtain an initial three-dimensional model;

[0017] Pixel point position information of the initial three-dimensional model and resolution information of the initial three-dimensional model are obtained, and smoothing optimization processing is performed on the initial three-dimensional model according to the pixel point position information and the resolution information of the initial three-dimensional model to obtain the three-dimensional model of the object to be sensed.

[0018] Preferably, in a flexible tactile sensor intelligent sensing method, in step 1, determining the morphological characteristics of the object to be sensed includes:

[0019] Reading the object to be sensed, determining a three-dimensional model of the object to be sensed, and obtaining a model center of gravity of the three-dimensional model;

[0020] Constructing a three-dimensional spatial coordinate system based on the center of the model;

[0021] The convex points, concave points and contour lines of the object to be sensed are determined in the three-dimensional spatial coordinate system, and at the same time, the convex points, concave points and contour lines of the object to be sensed are analyzed to determine the morphological features of the object to be sensed.

[0022] Preferably, in a flexible tactile sensor intelligent sensing method, in step 2, before the tactile sensing of the object to be sensed based on the morphological features by the tactile sensor, the method further includes:

[0023] Acquire a first magnetic field state of the magnetic field where the tactile sensor is located and a second magnetic field state where the object to be sensed is located;

[0024] determining a magnetic field strength sensed by the tactile sensor based on the first magnetic field state and the second magnetic field state;

[0025] Comparing the magnetic field strength with a reference magnetic field strength range to determine whether the tactile sensor can accurately measure the object to be measured;

[0026] When the magnetic field strength is within the reference magnetic field strength range, it is determined that the tactile sensor can accurately measure the object to be measured;

[0027] Otherwise, it is determined that the tactile sensor cannot accurately measure the object to be measured. At the same time, the operating parameters of the Hall element in the tactile sensor are optimized according to a preset algorithm until the magnetic field intensity sensed by the tactile sensor is within the reference magnetic field intensity range.

[0028] Preferably, a flexible tactile sensor intelligent sensing method comprises:

[0029] When the tactile sensor can accurately measure the object to be measured, obtaining a working reference parameter of the tactile sensor;

[0030] Determining a start condition of the tactile sensor based on the working operation reference parameter, and generating a first control sub-instruction based on the start condition;

[0031] Reading the morphological features of the object to be sensed, and generating a second control sub-instruction based on the morphological features of the object to be sensed;

[0032] A comprehensive control instruction is generated based on the first control sub-instruction and the second control sub-instruction, and the tactile sensor is controlled to perform tactile perception on the object to be perceived according to the comprehensive control instruction.

[0033] Preferably, in a flexible tactile sensor intelligent sensing method, in step 2, the tactile sensor performs tactile sensing on the object to be sensed according to the morphological features and obtains sensing data, and the specific process includes:

[0034] Reading the morphological features of the object to be sensed, determining the sensing point for sensing the object to be sensed, and obtaining the target position of the sensing point;

[0035] Based on the target position of the sensing point, the object to be sensed is sensed according to the tactile sensor, and sensing signals at the sensing point are respectively obtained;

[0036] Acquire a signal type corresponding to the sensing signal of the sensing point, and match a corresponding signal calibration code in a preset signal database based on the signal type corresponding to the sensing signal;

[0037] Calibrate the sensing signal of the sensing point based on the signal calibration code, and output a standard sensing signal of the sensing point;

[0038] Converting the standard sensing signal into a digital signal according to a digital-to-analog conversion method, and determining a digital output of the standard sensing signal based on the digital signal to obtain sensing signal data corresponding to the sensing point;

[0039] Acquire a tactile sensing type, and classify the sensing signal data corresponding to each sensing point based on the tactile sensing type to determine sub-sensing signal data corresponding to each sensing point;

[0040] Determining a data fluctuation range, a data fluctuation amplitude, and a data fluctuation frequency of the sub-sensing signal data;

[0041] Determine the tactile perception degree corresponding to each tactile type according to the data fluctuation range of the sub-sensing signal data, and determine the tactile perception intensity of the sub-sensing signal data according to the data fluctuation amplitude and data fluctuation frequency of the sub-sensing signal data;

[0042] Quantifying the tactile perception degree and the tactile perception intensity, and obtaining sub-perception data corresponding to each sensing point based on the processing result;

[0043] The sub-perception data corresponding to each sensing point are subjected to a first synthesis, and the first perception data corresponding to each sensing point is determined based on the first synthesis result. At the same time, the first perception data corresponding to each sensing point is subjected to a second synthesis, and the perception data is determined based on the second synthesis result.

[0044] Preferably, in a flexible tactile sensor intelligent sensing method, in step 3, the sensing data is processed and read, and a tactile expression of the object to be sensed is output according to the reading result, including:

[0045] Acquire perception data, and preprocess the perception data to determine feature items of the perception data, wherein the feature item is at least one;

[0046] Determine the attribute values ​​of the feature items, and use the attribute values ​​as initial cluster centers respectively;

[0047] Determining target distances between each perception data and different initial cluster centers, and determining a target probability that the attribute value can serve as a cluster center of the perception data based on the target distances;

[0048] Taking the attribute value whose target probability is greater than or equal to the preset probability as the target cluster center, and determining the classification label of the perception data based on the target cluster center;

[0049] Building a data classification model based on the classification label and the neural network, and inputting the sensed data into the data classification model to obtain a target category of the sensed data;

[0050] Extracting feature items of the perception data in each target category, and converting the format of the feature items to obtain target feature vectors corresponding to the feature items;

[0051] Determining a tactile expression purpose of the sensed data in each target category based on the target feature vector, and controlling the flexible tactile sensor to output a tactile expression of the object to be sensed based on the tactile expression purpose, and acquiring a working parameter of the flexible tactile sensor in the tactile expression;

[0052] Determining an evaluation index corresponding to the perception data in each target category based on the tactile expression purpose of the perception data in each target category, and quantifying the evaluation index to obtain a weight corresponding to each evaluation index;

[0053] Based on the evaluation index and the corresponding weight, the working parameters of the flexible tactile sensor in the tactile expression are evaluated to obtain the overall performance value of the tactile expression of the perception data by the flexible tactile sensor;

[0054] comparing the overall performance value with a preset threshold;

[0055] If the overall performance value is greater than or equal to the preset threshold, it is determined that the tactile expression of the sensed data by the flexible tactile sensor is qualified;

[0056] Otherwise, determining that the tactile expression of the sensed data by the flexible tactile sensor is unqualified, and determining a characteristic matrix of working parameters of the flexible tactile sensor in the tactile expression;

[0057] Determining specific values ​​of working parameters corresponding to the evaluation index of the flexible tactile sensor based on the characteristic matrix, and determining optimization directions and optimization parameters of the flexible tactile sensor based on the specific values;

[0058] The flexible tactile sensor is optimized based on the optimization direction and the optimization parameters.

[0059] Preferably, a flexible tactile sensor intelligent perception method, obtaining an overall performance value of the tactile expression of the flexible tactile sensor to the perception data, comprises:

[0060] Acquiring initial performance parameters of each component in the flexible tactile sensor, wherein the initial performance parameters are obtained by performing multiple tests on the flexible tactile sensor;

[0061] At the same time, obtaining working parameters of the flexible tactile sensor in tactile expression, and determining an average degradation rate of performance parameters of each device in the flexible tactile sensor based on the working parameters and the initial performance parameters;

[0062] Constructing a reliability evaluation model, and inputting the average degradation rate of the performance parameters of each device in the flexible tactile sensor and the initial performance parameters into the reliability evaluation model to obtain the reliability of the current performance of each device in the flexible tactile sensor;

[0063] The reliability is transmitted to the management terminal for reminder and recording.

[0064] Preferably, in a flexible tactile sensor intelligent sensing method, in step 3, outputting a tactile expression of the object to be sensed includes:

[0065] determining a neural stimulation signal relative to a tactile expression of the subject based on a data type of the sensory data;

[0066] Establishing an association hub between the neural stimulation signal and the perception type of the perception data, and constructing a tactile perception simulation model based on the association hub;

[0067] The perception data is input into the tactile perception model for simulation analysis, and a tactile expression of the object to be perceived is output based on the analysis result.

[0068] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0069] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0071] Figure 1 This is a flow chart of an intelligent sensing method of a flexible tactile sensor in an embodiment of the present invention;

[0072] Figure 2 This is a flow chart of step 1 in a flexible tactile sensor intelligent sensing method in an embodiment of the present invention;

[0073] Figure 3This is a flow chart of step 2 in a flexible tactile sensor intelligent sensing method in an embodiment of the present invention. DETAILED DESCRIPTION

[0074] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0075] Embodiment 1:

[0076] This embodiment provides a flexible tactile sensor intelligent sensing method, such as Figure 1 As shown, including:

[0077] Step 1: Read the object to be sensed and determine the morphological characteristics of the object to be sensed;

[0078] Step 2: Performing tactile perception on the object to be perceived based on the morphological features using a tactile sensor, and obtaining perception data;

[0079] Step 3: Process and read the perception data, and output a tactile expression of the object to be perceived according to the reading result.

[0080] In this embodiment, the tactile sensor may be based on the Hall principle of a Hall sensor and may be combined with a temperature sensor, a position sensor, etc. to form a tactile sensor to sense an object to be sensed.

[0081] In this embodiment, the tactile expression includes: the perception degree of the object to be perceived, that is, including shape, temperature, humidity, temperature, pain, and touch, and the tactile expression is to express the perception degree of the object to be perceived through data and generate a text file.

[0082] In this embodiment, the object to be sensed may be an object that the flexible tactile sensor needs to sense.

[0083] In this embodiment, the morphological feature may be the appearance, volume, surface smoothness or concavity of the object to be sensed.

[0084] In this embodiment, the perception data may be a corresponding perception situation obtained after the flexible tactile sensor perceives the object to be perceived.

[0085] The beneficial effect of the above technical solution is: the morphological characteristics of the object to be sensed are combined with the Hall principle and related technologies to sense the object to be sensed, thereby achieving accurate and effective perception of the object to be sensed, while improving the sensory sensitivity and comprehensiveness of the flexible tactile sensor, and optimizing the working performance of the flexible tactile sensor.

[0086] Embodiment 2:

[0087] Based on Example 1, this embodiment provides an intelligent sensing method for a flexible tactile sensor, such as Figure 2 As shown, in step 1, the object to be sensed is read, including:

[0088] S101: Reading an image of the object to be sensed based on a preset image acquisition device to determine three views of the object to be sensed, wherein the three views of the object to be sensed include: a front view, a top view, and a side view;

[0089] S102: reading the three views, respectively determining image pixel information of the three views, and determining contour feature pixel points of the object to be sensed and center pixel points of the three views of the object to be sensed according to the image pixel information;

[0090] S103: Based on the contour feature pixel points of the object to be sensed and the central pixel points of the three-view image of the object to be sensed, the image feature of the object to be sensed is determined, and the reading of the object to be sensed is completed.

[0091] In this embodiment, the preset image acquisition device is set in advance and is used to acquire image data of the object to be sensed.

[0092] In this embodiment, the contour feature pixel points may be pixel points located at the edge of the image in the image corresponding to the object to be sensed.

[0093] In this embodiment, the central pixel point may be a pixel point located at the center of the image in the three-view image.

[0094] In this embodiment, the image feature may be the shape, surface concavity, etc. of the object to be sensed recorded in the image data.

[0095] The beneficial effect of the above technical solution is that by acquiring the three-view image data of the object to be sensed, the morphological features of the object to be sensed can be accurately read, thereby providing convenience and guarantee for the flexible tactile sensor to accurately sense the object to be sensed.

[0096] Embodiment 3:

[0097] On the basis of Example 2, this embodiment provides an intelligent sensing method of a flexible tactile sensor, which, after determining the image features of the object to be sensed, further includes:

[0098] Determine the pixel point distribution of the three views of the object to be perceived based on the image features of the object to be perceived, and determine the visual perception points of the three views of the object to be perceived respectively based on the pixel point distribution;

[0099] At the same time, based on the three views of the object to be sensed, the scale features of the object to be sensed are read, and based on the scale features, the three views of the object to be sensed are three-dimensionally stitched according to the visual perception points to obtain an initial three-dimensional model;

[0100] Pixel point position information of the initial three-dimensional model and resolution information of the initial three-dimensional model are obtained, and smoothing optimization processing is performed on the initial three-dimensional model according to the pixel point position information and the resolution information of the initial three-dimensional model to obtain the three-dimensional model of the object to be sensed.

[0101] In this embodiment, the visual perception points may be all observation points of the object to be perceived that can be visually seen.

[0102] In this embodiment, the scale feature may be the size information of the object to be sensed.

[0103] In this embodiment, the initial three-dimensional model may be a stereoscopic model obtained by three-dimensionally stitching three views of the object to be sensed.

[0104] In this embodiment, the smoothing optimization process may be to optimize the joint seams of the spliced ​​models to ensure that the ultimately obtained three-dimensional model is reliable and effective.

[0105] The beneficial effect of the above technical solution is: by analyzing and splicing the three views of the object to be perceived, the initial three-dimensional stereo model of the object to be perceived is accurately obtained, and the initial three-dimensional stereo model is smoothed and optimized, thereby ultimately ensuring that the obtained three-dimensional model of the object to be perceived is accurate and reliable, providing a guarantee for accurately obtaining the perception data of the object to be perceived.

[0106] Embodiment 4:

[0107] On the basis of Example 1, this embodiment provides an intelligent sensing method of a flexible tactile sensor. In step 1, determining the morphological features of the object to be sensed includes:

[0108] Reading the object to be sensed, determining a three-dimensional model of the object to be sensed, and obtaining a model center of gravity of the three-dimensional model;

[0109] Constructing a three-dimensional spatial coordinate system based on the center of the model;

[0110] The convex points, concave points and contour lines of the object to be sensed are determined in the three-dimensional spatial coordinate system, and at the same time, the convex points, concave points and contour lines of the object to be sensed are analyzed to determine the morphological features of the object to be sensed.

[0111] In this embodiment, the contour line may be the contour shape of the object to be sensed.

[0112] The beneficial effect of the above technical solution is: by constructing a three-dimensional coordinate system and determining the concave and convex points and contour lines of the object to be perceived based on the three-dimensional coordinate system, the morphological characteristics of the object to be perceived can be accurately and effectively acquired, which provides convenience for accurate perception of the object to be perceived.

[0113] Embodiment 5:

[0114] Based on Example 1, this embodiment provides an intelligent sensing method for a flexible tactile sensor, such as Figure 3 As shown, in step 2, before the tactile perception of the object to be perceived based on the morphological features by the tactile sensor, it also includes:

[0115] S201: Acquire a first magnetic field state of a magnetic field where the tactile sensor is located and a second magnetic field state where the object to be sensed is located;

[0116] S202: determining the magnetic field strength sensed by the tactile sensor based on the first magnetic field state and the second magnetic field state;

[0117] S203: comparing the magnetic field strength with a reference magnetic field strength range to determine whether the tactile sensor can accurately measure the object to be measured;

[0118] S204: When the magnetic field strength is within the reference magnetic field strength range, it is determined that the tactile sensor can accurately measure the object to be measured;

[0119] S205: Otherwise, it is determined that the tactile sensor cannot accurately measure the object to be measured. At the same time, the operating parameters of the Hall element in the tactile sensor are optimized according to a preset algorithm until the magnetic field intensity sensed by the tactile sensor is within the reference magnetic field intensity range.

[0120] In this embodiment, the preset algorithm may be to perform differential subtraction operation on the Hall elements in the same direction.

[0121] In this embodiment, the first magnetic field state may be a magnetic field state generated by the tactile sensor through the Hall effect, including: magnetic field intensity, etc., and the second magnetic field state may be a magnetic field state of the external environment.

[0122] In this embodiment, the tactile sensor has good linearity within a certain range of magnetic field strength. When the magnetic field strength is too small, the signal changes little, the sensitivity of the tactile sensor is reduced, and it is not easy to measure. When the magnetic field strength exceeds the reference magnetic field strength range, it affects the measurement accuracy and measurement range of the tactile sensor. Therefore, the reference magnetic field strength range is based on the magnetic field strength corresponding to the linear relationship of the tactile sensor as the reference magnetic field strength range.

[0123] The beneficial effect of the above technical solution is: by acquiring the magnetic field strength in the tactile sensor and comparing it with the reference magnetic field strength range, it is helpful to ensure the sensing sensitivity of the tactile sensor, thereby improving the sensing efficiency and sensing accuracy of the tactile sensor.

[0124] Embodiment 6:

[0125] Based on Example 5, this embodiment provides an intelligent sensing method for a flexible tactile sensor, which is characterized by comprising:

[0126] When the tactile sensor can accurately measure the object to be measured, obtaining a working reference parameter of the tactile sensor;

[0127] Determining a start condition of the tactile sensor based on the working operation reference parameter, and generating a first control sub-instruction based on the start condition;

[0128] Reading the morphological features of the object to be sensed, and generating a second control sub-instruction based on the morphological features of the object to be sensed;

[0129] A comprehensive control instruction is generated based on the first control sub-instruction and the second control sub-instruction, and the tactile sensor is controlled to perform tactile perception on the object to be perceived according to the comprehensive control instruction.

[0130] In this embodiment, the operating reference parameters of the tactile sensor may be parameters such as linearity, hysteresis, zero drift, resolution, and bandwidth of the tactile sensor.

[0131] In this embodiment, the start condition can be used to determine the optimal working state of the tactile sensor based on the working operation benchmark parameters of the tactile sensor, thereby determining the start condition of the tactile sensor, and the start condition is a condition for protecting the working operation benchmark parameters of the tactile sensor from being destroyed, which is conducive to ensuring the normal operation of the tactile sensor.

[0132] In this embodiment, the first control sub-instruction is to activate the tactile sensor.

[0133] In this embodiment, the second control sub-instruction may be determined by the morphological features of the object to be sensed.

[0134] The beneficial effect of the above technical solution is: by respectively determining the first control sub-instruction and the second control sub-instruction to determine the comprehensive control instruction, it is beneficial to achieve accurate activation of the tactile sensor and accurate measurement of the tactile sensor.

[0135] Embodiment 7:

[0136] On the basis of Example 1, this embodiment provides an intelligent sensing method of a flexible tactile sensor. In step 2, the tactile sensor performs tactile sensing on the object to be sensed according to the morphological features and obtains sensing data. The specific process includes:

[0137] Reading the morphological features of the object to be sensed, determining the sensing point for sensing the object to be sensed, and obtaining the target position of the sensing point;

[0138] Based on the target position of the sensing point, the object to be sensed is sensed according to the tactile sensor, and sensing signals at the sensing point are respectively obtained;

[0139] Acquire a signal type corresponding to the sensing signal of the sensing point, and match a corresponding signal calibration code in a preset signal database based on the signal type corresponding to the sensing signal;

[0140] Calibrate the sensing signal of the sensing point based on the signal calibration code, and output a standard sensing signal of the sensing point;

[0141] Converting the standard sensing signal into a digital signal according to a digital-to-analog conversion method, and determining a digital output of the standard sensing signal based on the digital signal to obtain sensing signal data corresponding to the sensing point;

[0142] Acquire a tactile sensing type, and classify the sensing signal data corresponding to each sensing point based on the tactile sensing type to determine sub-sensing signal data corresponding to each sensing point;

[0143] Determining a data fluctuation range, a data fluctuation amplitude, and a data fluctuation frequency of the sub-sensing signal data;

[0144] Determine the tactile perception degree corresponding to each tactile type according to the data fluctuation range of the sub-sensing signal data, and determine the tactile perception intensity of the sub-sensing signal data according to the data fluctuation amplitude and data fluctuation frequency of the sub-sensing signal data;

[0145] Quantifying the tactile perception degree and the tactile perception intensity, and obtaining sub-perception data corresponding to each sensing point based on the processing result;

[0146] The sub-perception data corresponding to each sensing point are subjected to a first synthesis, and the first perception data corresponding to each sensing point is determined based on the first synthesis result. At the same time, the first perception data corresponding to each sensing point is subjected to a second synthesis, and the perception data is determined based on the second synthesis result.

[0147] In this embodiment, the sensing point may be a sensing position when the flexible tactile sensor senses the object to be sensed.

[0148] In this embodiment, the target position may be the location of the sensing point on the object to be sensed.

[0149] In this embodiment, the signal type may be the tactile condition sensed by the tactile sensor, for example, it may be temperature perception, and the signal type is temperature. Temperature processing requires corresponding signal calibration coding. Different types have different calibration codes, and the calibration results of the signal are also different, in order to obtain a more accurate signal.

[0150] In this embodiment, the preset signal database is set in advance and is used to store signal calibration codes corresponding to different sensing signals.

[0151] In this embodiment, the standard sensing signal may be a sensing signal obtained by calibrating the sensing signal through signal calibration coding.

[0152] In this embodiment, the sub-sensing signal data may be the sensing signals corresponding to each category after the sensing signals are classified.

[0153] In this embodiment, the tactile types include: temperature, humidity, pain, touch, etc.

[0154] In this embodiment, the tactile perception degree may be the perception data corresponding to each type of execution, specifically: when the perception type is temperature, the perceived temperature; when the perception type is smoothness, it includes perceived roughness or perceived smoothness.

[0155] In this embodiment, the tactile perception intensity may be the speed at which the sensing signal changes, such as the intensity of the vibration when vibration is sensed, or the speed at which the temperature changes when temperature is sensed.

[0156] In this embodiment, the quantization process may be a tactile

[0157] In this embodiment, the first synthesis may be to summarize the corresponding perception types in all sub-perception data and the data values ​​corresponding to the perception types.

[0158] In this embodiment, the first perception data may be data obtained by summarizing the sub-perception data corresponding to each sensing point.

[0159] In this embodiment, the second synthesis may be to aggregate the first sensing data of all sensing points on the object to be sensed.

[0160] The beneficial effect of the above technical solution is: by analyzing the object to be perceived, the perception points on the object to be perceived are determined, so that the object to be perceived is quantified into multiple perception points, and the perception type of each perception point and the perception data corresponding to the perception type are summarized and analyzed, so as to achieve accurate and effective acquisition of the perception data of the object to be perceived, thereby improving the accuracy of acquiring the perception data of the object to be perceived, and at the same time, it also ensures accurate and effective perception expression based on the perception data of the object to be perceived.

[0161] Embodiment 8:

[0162] Based on Example 1, this embodiment provides an intelligent sensing method of a flexible tactile sensor. In step 3, the sensing data is processed and read, and a tactile expression of the object to be sensed is output according to the reading result, including:

[0163] Acquire perception data, and preprocess the perception data to determine feature items of the perception data, wherein the feature item is at least one;

[0164] Determine the attribute values ​​of the feature items, and use the attribute values ​​as initial cluster centers respectively;

[0165] Determining target distances between each perception data and different initial cluster centers, and determining a target probability that the attribute value can serve as a cluster center of the perception data based on the target distances;

[0166] Taking the attribute value whose target probability is greater than or equal to the preset probability as the target cluster center, and determining the classification label of the perception data based on the target cluster center;

[0167] Building a data classification model based on the classification label and the neural network, and inputting the sensed data into the data classification model to obtain a target category of the sensed data;

[0168] Extracting feature items of the perception data in each target category, and converting the format of the feature items to obtain target feature vectors corresponding to the feature items;

[0169] Determining a tactile expression purpose of the sensed data in each target category based on the target feature vector, and controlling the flexible tactile sensor to output a tactile expression of the object to be sensed based on the tactile expression purpose, and acquiring a working parameter of the flexible tactile sensor in the tactile expression;

[0170] Determining an evaluation index corresponding to the perception data in each target category based on the tactile expression purpose of the perception data in each target category, and quantifying the evaluation index to obtain a weight corresponding to each evaluation index;

[0171] Based on the evaluation index and the corresponding weight, the working parameters of the flexible tactile sensor in the tactile expression are evaluated to obtain the overall performance value of the tactile expression of the perception data by the flexible tactile sensor;

[0172] comparing the overall performance value with a preset threshold;

[0173] If the overall performance value is greater than or equal to the preset threshold, it is determined that the tactile expression of the sensed data by the flexible tactile sensor is qualified;

[0174] Otherwise, determining that the tactile expression of the sensed data by the flexible tactile sensor is unqualified, and determining a characteristic matrix of working parameters of the flexible tactile sensor in the tactile expression;

[0175] Determining specific values ​​of working parameters corresponding to the evaluation index of the flexible tactile sensor based on the characteristic matrix, and determining optimization directions and optimization parameters of the flexible tactile sensor based on the specific values;

[0176] The flexible tactile sensor is optimized based on the optimization direction and the optimization parameters.

[0177] In this embodiment, preprocessing may include cleaning, screening, and other operations on the perception data.

[0178] In this embodiment, the feature item may be data with obvious category features or obvious numerical change features in the perception data.

[0179] In this embodiment, the attribute value of the feature item may be the category of the feature item and the corresponding specific data value.

[0180] In this embodiment, the initial cluster center may be a category feature point of a type of data set for determining the data category of the perception data. The data belonging to this category shares the cluster center and has a short distance from the cluster center.

[0181] In this embodiment, the target distance may be used to characterize the byte distance between different perception data and the initial cluster center. The farther the distance is, the less the data belongs to the cluster center.

[0182] In this embodiment, the target probability may be used to characterize the possibility that the attribute of the feature item can represent the type of perception data. The larger the probability, the more it can represent the center of the type of data.

[0183] In this embodiment, the preset probability is set in advance and can be adjusted.

[0184] In this embodiment, the target cluster center may be an attribute value that is determined to be a feature item of the data center when the probability is greater than or equal to a preset probability.

[0185] In this embodiment, the target category refers to the data category obtained after the perception data is classified.

[0186] In this embodiment, the target feature vector may be a binary number corresponding to the feature item.

[0187] In this embodiment, the tactile expression purpose may be the final function that each type of perception data wants to achieve.

[0188] In this embodiment, the overall performance value may be used to characterize the reliability and accuracy of the tactile expression of the sensed data by the tactile sensor.

[0189] In this embodiment, the preset threshold is set in advance and is used to measure whether the flexible tactile sensor can achieve the purpose of accurate expression, and can be adjusted.

[0190] In this embodiment, the characteristic matrix may be obtained by converting the working parameters of the flexible tactile sensor in the tactile expression into a corresponding matrix form, so as to facilitate accurate acquisition of the working defects or working failures of the flexible tactile sensor.

[0191] In this embodiment, the optimization direction and optimization parameters may be the components of the flexible tactile sensor that need to be optimized and the specific degree of optimization of each component.

[0192] The beneficial effects of the above technical scheme are: by processing and classifying the perception data, the perception purpose of each type of perception data can be accurately obtained, and at the same time, the working parameters of the flexible tactile sensor when perceiving and expressing the perception data are obtained, and the tactile expression performance of the flexible tactile sensor is accurately evaluated based on the working parameters, and timely optimized when the performance does not meet the requirements, thereby improving the tactile expression effect and tactile expression ability of the flexible tactile sensor, and at the same time improving the sensory sensitivity and perception comprehensiveness of the flexible tactile sensor, and optimizing the working performance of the flexible tactile sensor.

[0193] Embodiment 9:

[0194] On the basis of Example 8, this embodiment provides an intelligent perception method of a flexible tactile sensor, which obtains an overall performance value of the tactile expression of the flexible tactile sensor to the perception data, including:

[0195] Acquiring initial performance parameters of each component in the flexible tactile sensor, wherein the initial performance parameters are obtained by performing multiple tests on the flexible tactile sensor;

[0196] At the same time, obtaining working parameters of the flexible tactile sensor in tactile expression, and determining an average degradation rate of performance parameters of each device in the flexible tactile sensor based on the working parameters and the initial performance parameters;

[0197] Constructing a reliability evaluation model, and inputting the average degradation rate of the performance parameters of each device in the flexible tactile sensor and the initial performance parameters into the reliability evaluation model to obtain the reliability of the current performance of each device in the flexible tactile sensor;

[0198] The reliability is transmitted to the management terminal for reminder and recording.

[0199] In this embodiment, the initial performance parameters may be the working parameters of each component in the flexible tactile sensor when it leaves the factory.

[0200] In this embodiment, the average degradation rate may be the degree to which the performance of each component in the flexible tactile sensor degrades sequentially over time.

[0201] The beneficial effect of the above technical solution is: by effectively analyzing the average degradation rate of the working performance of each device in the flexible tactile sensor, the current reliability of each device in the flexible tactile sensor can be accurately obtained, ensuring that the flexible tactile sensor can accurately and effectively perceive the object to be perceived, thereby improving the tactile perception expression effect.

[0202] Embodiment 10:

[0203] Based on Example 1, this example provides an intelligent sensing method for a flexible tactile sensor. In step 3, outputting a tactile expression of the object to be sensed includes:

[0204] determining a neural stimulation signal relative to a tactile expression of the subject based on a data type of the sensory data;

[0205] Establishing an association hub between the neural stimulation signal and the perception type of the perception data, and constructing a tactile perception simulation model based on the association hub;

[0206] The perception data is input into the tactile perception model for simulation analysis, and a tactile expression of the object to be perceived is output based on the analysis result.

[0207] In this embodiment, the data types include temperature data, humidity data, etc. in the sensed data.

[0208] In this embodiment, the neural stimulation signal is a simulated signal determined based on human senses.

[0209] In this embodiment, the tactile perception simulation model may be a model used to simulate the feeling of a subject (human).

[0210] The beneficial effect of the above technical solution is: by establishing a tactile perception model to simulate perception data in real time, the tactile perception effect of tactile expression is improved.

[0211] Embodiment 11:

[0212] On the basis of Example 1, step 2 further includes:

[0213] Determining current values ​​at both ends of a Hall element in the tactile sensor when the tactile sensor performs tactile perception on an object to be perceived;

[0214] Calculating the relationship between the Hall potential and the magnetic induction intensity in the tactile sensor based on the current value at both ends of the Hall element in the tactile sensor;

[0215]

[0216] Wherein, U represents the Hall potential in the tactile sensor; φ represents the Hall coefficient; I represents the current value at both ends of the Hall element in the tactile sensor; B represents the magnetic induction intensity; n represents the number of carriers per unit volume of the Hall element in the tactile sensor; a represents the length of the Hall element; b represents the width of the Hall element; θ represents the weight coefficient of the magnetic induction intensity, and its value is (0.98, 0.99);

[0217] Constructing a two-dimensional relationship diagram based on the relationship between the Hall potential and the magnetic induction intensity in the tactile sensor, and determining the best linear section between the Hall potential and the magnetic induction in the two-dimensional relationship diagram;

[0218] Based on the optimal linear section, determining a maximum Hall potential and a minimum Hall potential in the two-dimensional relationship diagram, and setting an optimal working condition of the tactile sensor based on the maximum Hall potential and the minimum Hall potential;

[0219]

[0220] Among them, U B Indicates the Hall potential output when the current magnetic induction intensity is B; U max represents the maximum Hall potential; U min represents the minimum Hall potential; μ represents the optimal working condition of the tactile sensor;

[0221] Determining whether the tactile sensor is in an optimal working state according to the optimal working condition of the tactile sensor;

[0222] Wherein, when the optimal working condition output is 0, it is determined that the tactile sensor is not in the optimal working state, and the target control instruction controls the tactile sensor to stop working;

[0223] When the optimal working condition output is 1, it is determined that the tactile sensor is in the optimal working state.

[0224] In this embodiment, the target control instruction may be an instruction for controlling the tactile sensor to stop working.

[0225] The beneficial effect of the above technical solution is: by determining the relationship between the Hall potential and the magnetic induction intensity in the tactile sensor, the maximum Hall potential and the minimum Hall potential are determined, and then the optimal working conditions are set, and the optimal working conditions are used to measure whether the tactile sensor is in the best working state, thereby improving the perception efficiency.

[0226] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A flexible tactile sensor intelligent sensing method, characterized in that: include: Step 1: Read the object to be sensed and determine the morphological characteristics of the object to be sensed; Step 2: Performing tactile perception on the object to be perceived based on the morphological features using a tactile sensor, and obtaining perception data; Step 3: Processing and reading the sensed data, and outputting a tactile expression of the object to be sensed according to the reading result; In step 2, before performing tactile perception on the object to be perceived based on the morphological features using the tactile sensor, the method further includes: Acquire a first magnetic field state of the magnetic field where the tactile sensor is located and a second magnetic field state where the object to be sensed is located; determining a magnetic field strength sensed by the tactile sensor based on the first magnetic field state and the second magnetic field state; Comparing the magnetic field strength with a reference magnetic field strength range to determine whether the tactile sensor can accurately measure the object to be sensed; When the magnetic field strength is within the reference magnetic field strength range, it is determined that the tactile sensor can accurately measure the object to be sensed; Otherwise, it is determined that the tactile sensor cannot accurately measure the object to be sensed, and at the same time, the operating parameters of the Hall element in the tactile sensor are optimized according to a preset algorithm until the magnetic field intensity sensed by the tactile sensor is within the reference magnetic field intensity range.

2. The intelligent sensing method of a flexible tactile sensor according to claim 1, characterized in that: In step 1, the object to be sensed is read, including: Reading an image of the object to be sensed based on a preset image acquisition device to determine three views of the object to be sensed, wherein the three views of the object to be sensed include: a front view, a top view, and a side view; Reading the three views, respectively determining image pixel information of the three views, and determining contour feature pixel points of the object to be sensed and center pixel points of the three views of the object to be sensed according to the image pixel information; Based on the contour feature pixel points of the object to be sensed and the central pixel points of the three-view image of the object to be sensed, the image feature of the object to be sensed is determined, and the reading of the object to be sensed is completed.

3. The flexible tactile sensor intelligent sensing method according to claim 2, characterized in that: After determining the image features of the object to be sensed, the method further includes: Determine the pixel point distribution of the three views of the object to be perceived based on the image features of the object to be perceived, and determine the visual perception points of the three views of the object to be perceived respectively based on the pixel point distribution; At the same time, based on the three views of the object to be sensed, the scale features of the object to be sensed are read, and based on the scale features, the three views of the object to be sensed are three-dimensionally stitched according to the visual perception points to obtain an initial three-dimensional model; Pixel point position information of the initial three-dimensional model and resolution information of the initial three-dimensional model are obtained, and smoothing optimization processing is performed on the initial three-dimensional model according to the pixel point position information and the resolution information of the initial three-dimensional model to obtain the three-dimensional model of the object to be sensed.

4. The flexible tactile sensor intelligent sensing method according to claim 1, characterized in that: In step 1, determining the morphological characteristics of the object to be sensed includes: Reading the object to be sensed, determining a three-dimensional model of the object to be sensed, and obtaining a model center of gravity of the three-dimensional model; Constructing a three-dimensional spatial coordinate system based on the center of the model; The convex points, concave points and contour lines of the object to be sensed are determined in the three-dimensional spatial coordinate system, and at the same time, the convex points, concave points and contour lines of the object to be sensed are analyzed to determine the morphological features of the object to be sensed.

5. The intelligent sensing method of a flexible tactile sensor according to claim 1, characterized in that: include: When the tactile sensor can accurately measure the object to be sensed, obtaining a working reference parameter of the tactile sensor; Determining a start condition of the tactile sensor based on the working operation reference parameter, and generating a first control sub-instruction based on the start condition; Reading the morphological features of the object to be sensed, and generating a second control sub-instruction based on the morphological features of the object to be sensed; A comprehensive control instruction is generated based on the first control sub-instruction and the second control sub-instruction, and the tactile sensor is controlled to perform tactile perception on the object to be perceived according to the comprehensive control instruction.

6. The intelligent sensing method of a flexible tactile sensor according to claim 1, characterized in that: In step 2, the tactile sensor performs tactile perception on the object to be perceived according to the morphological features and obtains perception data. The specific process includes: Reading the morphological features of the object to be sensed, determining the sensing point for sensing the object to be sensed, and obtaining the target position of the sensing point; Based on the target position of the sensing point, the object to be sensed is sensed according to the tactile sensor, and sensing signals at the sensing point are respectively obtained; Acquire a signal type corresponding to the sensing signal of the sensing point, and match a corresponding signal calibration code in a preset signal database based on the signal type corresponding to the sensing signal; Calibrate the sensing signal of the sensing point based on the signal calibration code, and output a standard sensing signal of the sensing point; Converting the standard sensing signal into a digital signal according to a digital-to-analog conversion method, and determining a digital output of the standard sensing signal based on the digital signal to obtain sensing signal data corresponding to the sensing point; Acquire a tactile sensing type, and classify the sensing signal data corresponding to each sensing point based on the tactile sensing type to determine sub-sensing signal data corresponding to each sensing point; Determine a data fluctuation range, a data fluctuation amplitude, and a data fluctuation frequency of the sub-sensing signal data; Determine the tactile perception degree corresponding to each tactile type according to the data fluctuation range of the sub-sensing signal data, and determine the tactile perception intensity of the sub-sensing signal data according to the data fluctuation amplitude and data fluctuation frequency of the sub-sensing signal data; Quantifying the tactile perception degree and the tactile perception intensity, and obtaining sub-perception data corresponding to each sensing point based on the processing result; The sub-perception data corresponding to each sensing point are subjected to a first synthesis, and the first perception data corresponding to each sensing point is determined based on the first synthesis result. At the same time, the first perception data corresponding to each sensing point is subjected to a second synthesis, and the perception data is determined based on the second synthesis result.

7. The intelligent sensing method of a flexible tactile sensor according to claim 1, characterized in that: In step 3, the sensed data is processed and read, and a tactile expression of the object to be sensed is output according to the reading result, including: Acquire perception data, and preprocess the perception data to determine feature items of the perception data, wherein the feature item is at least one; Determine the attribute values ​​of the feature items, and use the attribute values ​​as initial cluster centers respectively; Determining target distances between each perception data and different initial cluster centers, and determining a target probability that the attribute value can serve as a cluster center of the perception data based on the target distances; Taking the attribute value whose target probability is greater than or equal to the preset probability as the target cluster center, and determining the classification label of the perception data based on the target cluster center; Building a data classification model based on the classification label and the neural network, and inputting the sensed data into the data classification model to obtain a target category of the sensed data; Extracting feature items of the perception data in each target category, and converting the format of the feature items to obtain target feature vectors corresponding to the feature items; Determining a tactile expression purpose of the sensed data in each target category based on the target feature vector, and controlling the flexible tactile sensor to output a tactile expression of the object to be sensed based on the tactile expression purpose, and acquiring a working parameter of the flexible tactile sensor in the tactile expression; Determining an evaluation index corresponding to the perception data in each target category based on the tactile expression purpose of the perception data in each target category, and quantifying the evaluation index to obtain a weight corresponding to each evaluation index; Based on the evaluation index and the corresponding weight, the working parameters of the flexible tactile sensor in the tactile expression are evaluated to obtain the overall performance value of the tactile expression of the perception data by the flexible tactile sensor; comparing the overall performance value with a preset threshold; If the overall performance value is greater than or equal to the preset threshold, it is determined that the tactile expression of the sensed data by the flexible tactile sensor is qualified; Otherwise, determining that the tactile expression of the sensed data by the flexible tactile sensor is unqualified, and determining a characteristic matrix of working parameters of the flexible tactile sensor in the tactile expression; Determining specific values ​​of working parameters corresponding to the evaluation index of the flexible tactile sensor based on the characteristic matrix, and determining optimization directions and optimization parameters of the flexible tactile sensor based on the specific values; The flexible tactile sensor is optimized based on the optimization direction and the optimization parameters.

8. The intelligent sensing method of a flexible tactile sensor according to claim 7, characterized in that: Obtaining an overall performance value of the tactile expression of the flexible tactile sensor to the sensed data, including: Acquiring initial performance parameters of each component in the flexible tactile sensor, wherein the initial performance parameters are obtained by performing multiple tests on the flexible tactile sensor; At the same time, obtaining working parameters of the flexible tactile sensor in tactile expression, and determining an average degradation rate of performance parameters of each device in the flexible tactile sensor based on the working parameters and the initial performance parameters; Constructing a reliability evaluation model, and inputting the average degradation rate of the performance parameters of each device in the flexible tactile sensor and the initial performance parameters into the reliability evaluation model to obtain the reliability of the current performance of each device in the flexible tactile sensor; The reliability is transmitted to the management terminal for reminder and recording.

9. The intelligent sensing method of a flexible tactile sensor according to claim 1, characterized in that: In step 3, outputting the tactile expression of the object to be sensed includes: determining a neural stimulation signal relative to the subject's tactile expression based on a data type of the sensory data; Establishing an association hub between the neural stimulation signal and the perception type of the perception data, and constructing a tactile perception simulation model based on the association hub; The perception data is input into the tactile perception model for simulation analysis, and a tactile expression of the object to be perceived is output based on the analysis result.

Images