Estimation device, estimation method, estimation program, and learning model generation device

Abstract

To estimate a state of an imparting side for imparting a stimulus to an object using electric characteristics of the object having a conductive flexible material without using a special detection device.SOLUTION: An estimation device (1) includes: a detection unit for detecting electric characteristics between a plurality of detection points (75) predetermined in a flexible material of a grip part (2) having the conductive flexible material (22) whose electric characteristics change according to a change in an imparted stimulus; and an estimation unit (5) for inputting time-series electric characteristics detected by the detection unit to a learning model that is learned so as to output gripping state information with the time-series electric characteristics as input, using the time-series electric characteristics when the stimulus is given to the flexible material and gripping state information indicting a gripping state of the grip part by a person that gives the stimulus to the flexible material as learning data, and estimating the gripping state information indicating the gripping state by the person of the grip part corresponding to the input time-series electric characteristics.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to an estimation device, an estimation method, an estimation program, and a learning model generation device.

Background Art

[0002] Conventionally, it has been practiced to detect a shape change occurring in an object and estimate the state of a person or object that deforms the object using the detection result. In terms of detecting a shape change occurring in an object, it is difficult to detect the deformation without inhibiting the deformation of the object. In addition, since strain sensors used for detecting rigid bodies such as metal deformation are difficult to use for articles, a special detection device is required to detect the deformation of an object. For example, a technique is known in which displacement and vibration of an object are measured by a camera to obtain a deformed image and the amount of deformation is extracted (see, for example, Patent Document 1). Further, a technique is also known in which a pressure distribution applied to a wheelchair, a cushion, a bed, etc. is measured using a sheet-shaped pressure sensor (see, for example, Non-Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Non-Patent Documents

[0004]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in terms of detecting shape changes occurring in an object such as an object, when detecting the amount of deformation such as displacement of the object using a camera and an image analysis method, a system including a camera and image analysis etc. becomes large-scale and causes the apparatus to become large-sized, which is not preferable. Also, with an optical method using a camera, it is impossible to measure hidden portions that are not imaged by the camera. Therefore, there is room for improvement in detecting deformation of an object.

[0006] An object of the present disclosure is to provide an estimation device, an estimation method, an estimation program, and a learning model generation device that can estimate the state of an application side that applies a stimulus to an object by using the electrical characteristics of an object provided with a flexible material having conductivity without using a special detection device.

Means for Solving the Problems

[0007] To achieve the above object, a first aspect is a detection unit that detects the electrical characteristics between a plurality of predetermined detection points in the flexible material of a gripping portion provided with a flexible material having conductivity and whose electrical characteristics change in response to a change in an applied stimulus; using the time-series electrical characteristics when a stimulus is applied to the flexible material and the gripping state information indicating the gripping state by the person of the gripping portion that applies the stimulus to the flexible material as learning data, for a learning model that is learned to take the time-series electrical characteristics as input and output the gripping state information, input the time-series electrical characteristics detected by the detection unit, and estimate the gripping state information indicating the gripping state by the person corresponding to the input time-series electrical characteristics; an estimation unit; and an estimation device including the same.

[0008] A second aspect is the estimation device according to the first aspect, wherein the electrical characteristic is volume resistivity, the gripping state includes a state of applying at least one of a pressure stimulus and a material stimulus by a person to the gripping portion, The learning model is trained to output, as the gripping state information, information indicating a state in which at least one of a pressure stimulus and a material stimulus applied by a person corresponding to the detected electrical characteristics is applied.

[0009] A third aspect is the estimation device according to the second aspect, wherein the pressure stimulus is a pressure stimulus generated as the person grips the gripping part, and the gripping state information is information regarding the movement of gripping the gripping part by the person.

[0010] A fourth aspect is the estimation device according to the third aspect, wherein the gripping state information includes information regarding the position where the person grips the gripping part.

[0011] A fifth aspect is the estimation device according to the second aspect, wherein the material stimulus is a material stimulus generated as water is contained in the gripping part, and the gripping state information is information regarding the water content in the gripping part.

[0012] A sixth aspect is the estimation device according to any one of the first aspect to the fifth aspect, wherein the gripping state information includes the physical state information of the person who grips the gripping part.

[0013] A seventh aspect is the estimation device according to any one of the first aspect to the sixth aspect, further including an output unit that outputs the gripping state estimated by the estimation unit.

[0014] An eighth aspect is the estimation device according to any one of the first aspect to the seventh aspect, wherein the gripping part includes a material in which conductivity is imparted to at least a part of a urethane material having a structure with at least one of a fibrous and a mesh-like skeleton, or a structure in which a plurality of minute air bubbles are dispersed inside.

[0015] A ninth aspect is the estimation device according to any one of the first aspect to the eighth aspect, wherein The gripping part includes at least one of a grip part of a sports equipment and a handrail part of a treatment chair.

[0016] A tenth aspect is the estimation device according to any one of the first aspect to the ninth aspect, The learning model includes a model generated by learning using a network by reservoir computing using the flexible material as a reservoir.

[0017] An eleventh aspect is a computer detecting electrical characteristics between a plurality of predetermined detection points on the flexible material of the gripping part provided with a flexible material having conductivity and whose electrical characteristics change according to a change in a given stimulus; using, as learning data, the time-series electrical characteristics when the flexible material is stimulated and the gripping state information indicating the gripping state of the person of the gripping part who stimulates the flexible material, inputting the time-series electrical characteristics, and outputting the gripping state information, inputting the detected time-series electrical characteristics to a learning model learned to output the gripping state information indicating the gripping state of the person of the gripping part corresponding to the input time-series electrical characteristics, and estimating the gripping state information is an estimation method.

[0018] A twelfth aspect is a computer detecting electrical characteristics between a plurality of predetermined detection points on the flexible material of the gripping part provided with a flexible material having conductivity and whose electrical characteristics change according to a change in a given stimulus; using, as learning data, the time-series electrical characteristics when the flexible material is stimulated and the gripping state information indicating the gripping state of the person of the gripping part who stimulates the flexible material, inputting the time-series electrical characteristics, and outputting the gripping state information, inputting the detected time-series electrical characteristics to a learning model learned to output the gripping state information indicating the gripping state of the person of the gripping part corresponding to the input time-series electrical characteristics, and estimating the gripping state information is an estimation program for causing execution of processing.

[0019] The 13th aspect is an acquisition unit that acquires the electrical characteristics from a detection unit that detects the electrical characteristics between a plurality of predetermined detection points in the flexible material of a gripping part including a flexible material having conductivity and whose electrical characteristics change in response to a change in an applied stimulus, and gripping state information indicating the gripping state by a person of the gripping part that applies a stimulus to the flexible material; a learning model generation unit that generates a learning model that takes, as input, the time-series electrical characteristics when pressure is applied to the flexible material, based on the acquisition result of the acquisition unit, and outputs gripping state information indicating the gripping state by a person of the gripping part that applies a stimulus to the flexible material; and a learning model generation device including the same.

Advantages of the Invention

[0020] According to the present disclosure, there is an effect that the state of the imparting side can be estimated by using the electrical characteristics of an object provided with a flexible material having conductivity without using a special detection device.

Brief Description of the Drawings

[0021]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Mode for Carrying Out the Invention

[0022] Hereinafter, embodiments for realizing the technology of the present disclosure will be described in detail with reference to the drawings. Note that components and processes having the same functions and functions are given the same reference numerals throughout the drawings, and duplicate descriptions may be omitted as appropriate. Further, the present disclosure is not limited to the following embodiments, and can be implemented with appropriate modifications within the scope of the object of the present disclosure.

[0023] In the present disclosure, a person is a concept including at least one of a human body and an object capable of applying a stimulus to an object by a physical quantity. In the following description, without distinguishing between at least one of the human body and the object, the person will be described generically as a concept including a human and an object. That is, each single body of the human body and the object, and a combined body combining the human body and the object are generically referred to as a person.

[0024] First, with reference to FIGS. 1 to 7, a flexible material to which conductivity is applied to which the technology of the present disclosure is applied, and a state estimation process for estimating the state of the application side with respect to the flexible material using the flexible material will be described.

[0025] <Flexible material> In the present disclosure, the "flexible material" is a concept including materials that can be deformed at least in part, such as being bent. It includes soft elastomers such as rubber materials, structures having at least one of fibrous and network-like skeletons, and structures in which a plurality of minute air bubbles are scattered inside. Examples of these structures include polymer materials such as urethane materials. Further, in the present disclosure, a flexible material imparted with conductivity is used. The "flexible material imparted with conductivity" is a concept including materials having conductivity, and includes materials in which a conductive material is imparted to a flexible material to impart conductivity, and materials in which the flexible material has conductivity. Polymer materials such as urethane materials are suitable as flexible materials imparted with conductivity. In the following description, as an example of a flexible material imparted with conductivity, a member formed by blending and infiltrating (also referred to as impregnating) a conductive material into all or part of a urethane material will be described as "conductive urethane". Conductive urethane can be formed by either blending or infiltrating (impregnating) the conductive material, or by combining blending and infiltrating (impregnating) the conductive material. For example, when the conductive urethane formed by infiltration (impregnation) has higher conductivity than the conductive urethane formed by blending, it is preferable to form the conductive urethane by infiltration (impregnation).

[0026] Conductive urethane has a function in which its electrical characteristics change according to a given physical quantity. An example of the physical quantity that causes the function of the electrical characteristics to change is a stimulus value based on a pressure value indicating a pressure stimulus (hereinafter referred to as a pressure stimulus) that deforms the structure such as bending. Note that the pressure stimulus includes pressure application by pressure at a predetermined site and pressure distribution within a predetermined range. Another example of the physical quantity is a stimulus value such as a moisture content indicating a stimulus (hereinafter referred to as a material stimulus) that changes (alters) the properties of the material by the moisture content and moisture application. Conductive urethane changes its electrical characteristics according to a given physical quantity. An example of the physical quantity representing this electrical characteristic is an electrical resistance value. Another example is a voltage value or a current value.

[0027] Conductive urethane imparts conductivity to a flexible material having a predetermined volume, causing electrical characteristics (i.e., changes in electrical resistance values) corresponding to the given physical quantity to appear. The electrical resistance value can be regarded as the volume resistance value of the conductive urethane. In conductive urethane, the electrical paths are intricately coordinated. For example, the electrical paths stretch, contract, expand, or contract in response to deformation. There are also cases where the electrical paths are temporarily disconnected and where connections different from before occur. Therefore, between positions separated by a predetermined distance (e.g., the position of a detection point where an electrode is arranged), conductive urethane exhibits behavior with different electrical characteristics due to deformation and alteration corresponding to the magnitude and distribution of the stimulus (pressure stimulus and material stimulus) by the given physical quantity. For this reason, the electrical characteristics change according to the magnitude and distribution of the stimulus by the physical quantity applied to the conductive urethane.

[0028] Note that by using conductive urethane, it is not necessary to provide detection points such as electrodes at the target locations for deformation and alteration. Detection points such as electrodes may be provided at any at least two locations sandwiching the location where the conductive urethane is stimulated by the physical quantity (e.g., FIG. 1).

[0029] Also, to improve the detection accuracy of the electrical characteristics of the conductive urethane, more detection points than two may be used. Further, the conductive urethane of the present disclosure may be formed as a conductive urethane group formed by arranging a plurality of conductive urethane pieces with the conductive urethane 22 shown in FIG. 1 as one conductive urethane piece. In this case, the electrical characteristics may be detected for each of the plurality of conductive urethane pieces, or the electrical characteristics of the plurality of conductive urethane pieces may be synthesized and detected. When detecting the electrical characteristics for each of the plurality of conductive urethane pieces, electrical characteristics such as electrical resistance values can be detected for each arrangement site (e.g., detection sets #1 to #n). As another example, the detection range on the conductive urethane 22 may be divided, detection points may be provided for each divided detection range, and the electrical characteristics may be detected for each detection range.

[0030] <Estimation device> Next, an example of an estimation device that uses conductive urethane to estimate the state of the application side with respect to the conductive urethane will be described.

[0031] FIG. 1 shows an example of the configuration of an estimation device 1 capable of executing an estimation process for estimating the state of the application side. The estimation device 1 includes an estimation unit 5 and is connected to an object 2 so that the electrical characteristics of the conductive urethane 22 are input. In the estimation device 1, the state of the application side with respect to the conductive urethane 22 included in the object 2 is estimated. The estimation device 1 can be realized by a computer including a CPU as an execution device that executes the processes described later.

[0032] The above-described deformation and alteration of the conductive urethane occur due to physical quantities given to the conductive urethane in time series. The physical quantities given in this time series depend on the state of the application side. Therefore, the electrical characteristics of the conductive urethane that change over time correspond to the state of the application side of the physical quantities given to the conductive urethane. For example, when a pressure stimulus that deforms the conductive urethane or a material stimulus that alters the conductive urethane is applied, the electrical characteristics of the conductive urethane that change over time correspond to the state of the application side indicating the position, distribution, and magnitude of the pressure stimulus. Therefore, it is possible to estimate the state of the application side with respect to the conductive urethane from the electrical characteristics of the conductive urethane that change over time.

[0033] In the estimation device 1, an unknown state of the application side is estimated and output using a learned learning model 51 by the estimation process described later. As a result, it becomes possible to identify the state of the application side with respect to the object 2 without using a special device or a large device or directly measuring the deformation and alteration of the conductive urethane 22 included in the object 2. The learning model 51 is learned with the state of the application side with respect to the object 2 and the electrical characteristics of the object 2 (that is, the electrical characteristics such as the electrical resistance value of the conductive urethane 22 disposed on the object 2) as inputs. The learning of the learning model 51 will be described later.

[0034] Note that the conductive urethane 22 can be arranged on the flexible member 21 to form the object 2 (Fig. 2). The object 2 composed of the member 21 on which the conductive urethane 22 is arranged includes an electrical property detection unit 76. The conductive urethane 22 may be arranged on at least a part of the member 21, and may be arranged inside or outside. Further, the conductive urethane may be arranged so as to be able to estimate the state on the application side to the conductive urethane. For example, it may be arranged so as to be directly or indirectly, or both, in contact with a person.

[0035] Fig. 2 shows an example of the arrangement of the conductive urethane 22 in the object 2. As shown by taking the A-A cross section of the object 2 as the object cross section 2-1, the conductive urethane 22 may be formed so as to fill the entire inside of the member 21. Further, as shown in the object cross section 2-2, the conductive urethane 22 may be formed on one side (surface side) inside the member 21, and as shown in the object cross section 2-3, the conductive urethane 22 may be formed on the other side (back side) inside the member 21. Further, as shown in the object cross section 2-4, the conductive urethane 22 may be formed on a part of the inside of the member 21. Also, as shown in the object cross section 2-5, the conductive urethane 22 may be separately arranged outside the surface side of the member 21, and as shown in the object cross section 2-6, it may be arranged outside the other side (back side). When the conductive urethane 22 is arranged outside the member 21, the conductive urethane 22 and the member 21 may only be laminated, or the conductive urethane 22 and the member 21 may be integrated by adhesion or the like. Note that even when the conductive urethane 22 is arranged outside the member 21, since the conductive urethane 22 is a urethane member having conductivity, the flexibility of the member 21 is not impaired.

[0036] As shown in FIG. 1, the conductive urethane 22 detects the electrical characteristics (i.e., the volume resistivity which is the electrical resistance value) of the conductive urethane 22 based on signals from at least two detection points 75 arranged at a distance. In the example of FIG. 1, a detection set #1 is shown which detects the electrical characteristics (time-series electrical resistance values) based on signals from two detection points 75 arranged at diagonal positions on the conductive urethane 22. Note that the number and arrangement of the detection points 75 are not limited to the positions shown in FIG. 1, and may be three or more in number and at any position as long as they can detect the electrical characteristics of the conductive urethane 22. Note that for the electrical characteristics of the conductive urethane 22, an electrical characteristic detection unit 76 that detects the electrical characteristics (for example, the volume resistivity which is the electrical resistance value) may be connected to the detection point 75 and its output may be used.

[0037] In the present embodiment, since the conductive urethane 22 is used as the sensor, for example, when a person is intervening, the sense of discomfort given to the person is extremely small compared to conventional sensors. Therefore, it is possible to simultaneously perform measurement and estimation of the state of the application side without harming the state of the application side regarding the person during measurement. This is an advantage compared to conventional sensors that separately perform measurement and estimation of the state of the application side, and particularly in the estimation by long-term measurement evaluation that follows time-series changes, the merit is great.

[0038] The estimation unit 5 is a functional unit that is connected to the object 2 and estimates the state on the application side using the learning model 51 based on the electrical characteristics that change according to at least one of the deformation and alteration of the conductive urethane 22. Specifically, time-series input data 4 representing the magnitude of the electrical resistance (such as the electrical resistance value) in the conductive urethane 22 is input to the estimation unit 5. The input data 4 corresponds to state data 3 indicating the state on the application side with respect to the object 2, for example, the state related to the behavior of a person such as the posture and movement of the person who has come into contact with the object 2. For example, when a person comes into contact with the object 2, they come into contact in a predetermined state such as a posture, and in response to this state, a stimulus (at least one of a pressure stimulus and a material stimulus) is given as a physical quantity to the conductive urethane 22 that constitutes the object 2, and the electrical characteristics of the conductive urethane 22 change. Therefore, the electrical characteristics of the conductive urethane 22 that change in time series as indicated by the input data 4 correspond to the object 2, that is, the state on the application side with respect to the conductive urethane 22. Further, the estimation unit 5 outputs output data 6 representing the state on the application side corresponding to the electrical characteristics of the conductive urethane 22 that change in time series as an estimation result using the learned learning model 51.

[0039] The learning model 51 is a model that has completed learning to derive output data 6 representing the state on the application side from the electrical resistance (input data 4) of the conductive urethane 22 that changes due to stimuli (pressure stimulus and material stimulus) given as physical quantities. The learning model 51 is, for example, a model that defines a learned neural network and is expressed as a set of information on the weights (intensities) of the connections between the nodes (neurons) that make up the neural network.

[0040] <Learning process> Next, the learning process for generating the learning model 51 will be described. FIG. 3 shows the conceptual configuration of a learning model generation device that generates the learning model 51. The learning model generation device includes a learning processing unit 52. The learning model generation device can be configured to include a computer equipped with a CPU (not shown), and the learning model 51 is generated by being executed as the learning processing unit 52 by the learning data collection process and the learning model generation process executed by the CPU.

[0041] <Learning data collection process> In the learning data collection process, the learning processing unit 52 collects, as learning data, a large amount of input data 4 obtained by measuring, in time series, the electrical characteristics (e.g., electrical resistance value) of the conductive urethane 22 using the state data 3 representing the state of the applying side as a label. Therefore, the learning data includes a large number of sets of the input data 4 indicating the electrical characteristics and the state data 3 indicating the state of the applying side corresponding to the input data 4.

[0042] Specifically, in the learning data collection process, electrical characteristics (e.g., electrical resistance value) that change due to stimuli (pressure stimulus and material stimulus) corresponding to the state of the applying side when the state in the object 2 (i.e., the state of the applying side with respect to the conductive urethane 22) is formed are acquired in time series. Next, the state data 3 is assigned as a label to the acquired time-series electrical characteristics (input data 4), and the process is repeated until the set of the state data 3 and the input data 4 reaches a predetermined number or a predetermined time. The set of the state data 3 indicating these states of the applying side and the time-series electrical characteristics (input data 4) of the conductive urethane 22 acquired for each state of the applying side becomes the learning data. Note that the state data 3 in the learning data is stored in a memory (not shown) so as to be treated as output data 6 indicating the state of the applying side where the estimation result is correct in the learning process described later.

[0043] Note that time-series information may be associated with the learning data by assigning information indicating the measurement time to each of the electrical resistance values (input data 4) of the conductive urethane 22. In this case, for the period determined as the state of the applying side, information indicating the measurement time may be assigned to the set of time-series electrical resistance values in the conductive urethane 22 to associate the time-series information.

[0044] An example of the above-described learning data is shown in the following table. Table 1 is an example of a data set in which time-series electrical resistance value data (r) and state data (R) indicating the state of the applying side are associated as learning data regarding the state of the applying side with respect to the conductive urethane 22.

[0045]

Table 1

[0046] Note that the electrical characteristics detected by the conductive urethane 22 (time characteristics based on time-series electrical resistance value data) can be regarded as a characteristic pattern related to the state of the application side with respect to the conductive urethane 22. That is, different stimuli are applied to the conductive urethane 22 in time series depending on the state of the application side with respect to the conductive urethane 22. Therefore, it is considered that the time-series electrical characteristics within a predetermined time appear as electrical characteristics characteristic of the application side state. Thus, the pattern shown by the electrical characteristics detected by the conductive urethane 22 (time characteristics based on time-series electrical resistance value data) (for example, the distribution shape of the time-series electrical resistance values in the electrical characteristics) corresponds to the state of the application side and functions effectively in the learning process described later.

[0047] <Learning model generation process> Next, the learning model generation process will be described. The learning model generation device shown in FIG. 3 generates a learning model 51 using the above-described learning data through the learning model generation process in the learning processing unit 52.

[0048] FIG. 4 is a diagram showing the functional configuration of the learning processing unit 52, that is, the functional configuration of a CPU (not shown) related to the learning model generation process executed by the learning processing unit 52. The CPU (not shown) of the learning processing unit 52 operates as functional units of a generator 54 and an arithmetic unit 56. The generator 54 has a function of generating an output in consideration of the context of the electrical resistance values acquired in the input time series.

[0049] The learning processing unit 52 holds a large number of sets of the above-described input data 4 (for example, electrical resistance values) and output data 6 which is state data 3 indicating the state of the application side that has stimulated the conductive urethane 22 in a memory (not shown) as learning data.

[0050] The generator 54 includes an input layer 540, an intermediate layer 542, and an output layer 544 to constitute a known neural network (NN). Since the neural network itself is a known technology, a detailed description thereof will be omitted. However, the intermediate layer 542 includes a large number of node groups (neuron groups) having inter-node connections and feedback connections. Data from the input layer 540 is input to the intermediate layer 542, and the data of the calculation result of the intermediate layer 542 is output to the output layer 544.

[0051] The generator 54 is a neural network that generates generated output data 6A as data representing the state on the application side or data close to the state on the application side from the input input data 4 (for example, electrical resistance value). The generated output data 6A is data obtained by estimating the state on the application side where the conductive urethane 22 is stimulated from the input data 4. The generator 54 generates generated output data indicating a state close to the state on the application side from the input data 4 input in time series. The generator 54 can generate generated output data 6A close to the state on the application side of the object 2, that is, a person or the like to whom the conductive urethane 22 is stimulated, by learning using a large number of input data 4. In another aspect, by capturing the electrical characteristics, which are the input data 4 input in time series, as a pattern and learning the pattern, generated output data 6A close to the state on the application side of the object 2, that is, a person or the like to whom the conductive urethane 22 is stimulated, can be generated.

[0052] The calculator 56 is a calculator that compares the generated output data 6A with the output data 6 of the learning data and calculates the error of the comparison result. The learning processing unit 52 inputs the generated output data 6A and the output data 6 of the learning data to the calculator 56. In response to this, the calculator 56 calculates the error between the generated output data 6A and the output data 6 of the learning data, and outputs a signal indicating the calculation result.

[0053] The learning processing unit 52 performs learning of the generator 54 to tune the weight parameters of the connections between nodes based on the error calculated by the arithmetic unit 56. Specifically, the weight parameters of the connections between the nodes of the input layer 540 and the intermediate layer 542, the weight parameters of the connections between the nodes within the intermediate layer 542, and the weight parameters of the connections between the intermediate layer 542 and the output layer 544 in the generator 54 are each fed back to the generator 54 using a method such as the gradient descent method or the error backpropagation method. That is, with the output data 6 of the learning data as the target, the connections between all the nodes are optimized so as to minimize the error between the generated output data 6A and the output data 6 of the learning data.

[0054] Note that the generator 54 may use a recurrent neural network having a function of generating an output in consideration of the temporal input relationship, or other methods may be used.

[0055] The learning processing unit 52 generates a learning model 51 using the above-described learning data by learning model generation processing. The learning model 51 is expressed as a set of information on the weight parameters (weights or strengths) of the connections between the nodes of the learning result, and is stored in a memory (not shown).

[0056] Specifically, the learning processing unit 52 executes the learning model generation processing according to the following procedure. In the first learning process, input data 4 (electrical characteristics) with information indicating the state of the giving side, which is learning data of the results measured in time series, is acquired as a label. In the second learning process, the learning model 51 is generated using the learning data of the results measured in time series. That is, a set of information on the weight parameters (weights or strengths) of the connections between the nodes of the learning result obtained by learning using a large number of learning data as described above is obtained. Then, in the third learning process, the data expressed as a set of information on the weight parameters (weights or strengths) of the connections between the nodes of the learning result is stored as the learning model 51.

[0057] Then, in the above-described estimation device 1, a learned generator 54 (that is, data expressed as a set of information on the coupling weight parameters between nodes of the learning result) is used as the learning model 51. If the sufficiently learned learning model 51 is used, it is not impossible to identify the state on the application side from the time-series electrical characteristics of the object 2, that is, the conductive urethane 22 (for example, the characteristics of the electrical resistance value that changes over time).

[0058] <prc> Incidentally, as described above, the conductive urethane 22 shows behavior according to changes (deformations) such as the complex cooperation of electrical paths, the expansion and contraction, temporary disconnection, and new connection of electrical paths, as well as changes (alterations) in the properties of the material. As a result, the conductive urethane 22 shows behavior of having different electrical characteristics according to a given stimulus (e.g., a pressure stimulus). This means that the conductive urethane 22 can be treated as a reservoir for storing data related to the deformation of the conductive urethane 22. That is, the estimation device 1 can apply the conductive urethane 22 to a network model called physical reservoir computing (PRC) (hereinafter referred to as PRCN). Since PRC and PRCN themselves are known technologies, detailed descriptions are omitted, but PRC and PRCN are suitable for estimating information related to the deformation and alteration of the conductive urethane 22.

[0059] FIG. 5 shows an example of the functional configuration of the learning processing unit 52 to which PRCN is applied. The learning processing unit 52 to which PRCN is applied includes an input reservoir layer 541 and an estimation layer 545. The input reservoir layer 541 corresponds to the conductive urethane 22 included in the object 2. That is, in the learning processing unit 52 to which PRCN is applied, the object 2 including the conductive urethane 22 is treated as a reservoir for storing data related to the deformation and alteration of the object 2 including the conductive urethane 22 and is learned. The conductive urethane 22 becomes an electrical characteristic (electrical resistance value) corresponding to each of various stimuli, functions as an input layer for inputting the electrical resistance value, and also functions as a reservoir layer for storing data related to the deformation and alteration of the conductive urethane 22. Since the conductive urethane 22 outputs different electrical characteristics (input data 4) according to the stimulus given by the state of the applying side such as a person, it is possible to estimate the unknown state of the applying side from the electrical resistance value of the given conductive urethane 22 in the estimation layer 545. Therefore, in the learning processing in the learning processing unit 52 to which PRCN is applied, it is only necessary to learn the estimation layer 545.

[0060] <Configuration of the Estimation Device> Next, an example of the specific configuration of the above-described estimation device 1 will be further described. FIG. 6 shows an example of the electrical configuration of the estimation device 1. The estimation device 1 shown in FIG. 6 is configured to include a computer as an execution device that executes processes for realizing the various functions described above. The above-described estimation device 1 can be realized by causing a computer to execute a program representing each of the above functions.

[0061] The computer that functions as the estimation device 1 includes a computer main body 100. The computer main body 100 includes a CPU 102, a RAM 104 such as a volatile memory, a ROM 106, an auxiliary storage device 108 such as a hard disk drive (HDD), and an input / output interface (I / O) 110. These CPU 102, RAM 104, ROM 106, auxiliary storage device 108, and input / output I / O 110 are configured to be connected via a bus 112 so as to be able to exchange data and commands with each other. Further, connected to the input / output I / O 110 are a communication unit 114 for communicating with an external device, an operation display unit 116 such as a display and a keyboard, and a detection unit 118. The detection unit 118 has a function of acquiring input data 4 (electrical characteristics such as a time-series electrical resistance value) from the object 2 including the conductive urethane 22. That is, the detection unit 118 includes the object 2 in which the conductive urethane 22 is disposed, and can acquire the input data 4 from an electrical characteristic detection unit 76 connected to the detection point 75 in the conductive urethane 22. Note that the detection unit 118 may be connected via the communication unit 114.

[0062] Stored in the auxiliary storage device 108 is a control program 108P for causing the computer main body 100 to function as the estimation device 1 as an example of the estimation device of the present disclosure. The CPU 102 reads the control program 108P from the auxiliary storage device 108 and expands it in the RAM 104 to execute the process. Thereby, the computer main body 100 that has executed the control program 108P operates as the estimation device 1.

[0063] Note that the auxiliary storage device 108 stores a learning model 108M including the learning model 51 and data 108D including various types of data. The control program 108P may be provided by a recording medium such as a CD-ROM.

[0064] <Estimation Process> Next, the estimation process in the estimation device 1 implemented by a computer will be further described. FIG. 7 shows an example of the flow of the estimation process by the control program 108P executed by the computer main body 100. The estimation process shown in FIG. 7 is executed by the CPU 102 when the power of the computer main body 100 is turned on. The CPU 102 reads the control program 108P from the auxiliary storage device 108, expands it in the RAM 104, and executes the process.

[0065] First, the CPU 102 reads the learning model 51 from the learning model 108M of the auxiliary storage device 108 and expands it in the RAM 104 to obtain the learning model 51 (step S200). Specifically, a network model (see FIGS. 4 and 5) that is the connection between nodes by the weight parameters expressed as the learning model 51 is expanded in the RAM 104, thereby constructing the learning model 51 in which the connection between nodes by the weight parameters is realized.

[0066] Next, the CPU 102 acquires, in time series, unknown input data 4 (electrical characteristics) that is the target for estimating the state on the application side due to the stimulus applied to the conductive urethane 22 via the detection unit 118 (step S202). Next, the CPU 102 estimates output data 6 (unknown state on the application side) corresponding to the acquired input data 4 using the learning model 51 (step S204). Then, the CPU 102 outputs the output data 6 (state on the application side) of the estimation result via the communication unit 114 (step S206) and ends this processing routine.

[0067] In this way, according to the estimation device 1, it is possible to estimate the state of the unknown application side from the electrical resistance value of the conductive urethane 22. Specifically, in the estimation device 1, it is possible to estimate the state of the application side such as a person from the input data 4 (electrical characteristics) that changes according to the stimulus applied to the conductive urethane 22 depending on the state of the application side. That is, it is possible to estimate the state of the application side such as a person without using a special device or a large device or directly measuring the deformation of the flexible member.

[0068] <Estimation of gripping state> If such a conductive urethane 22 is applied to the gripping portion, a pressure stimulus such as partial compression of the gripping portion occurs according to the movement of gripping the gripping portion by a person. Therefore, the estimation device 1 can estimate the movement of gripping the gripping portion by a person from the time-series electrical resistance value of the conductive urethane 22. For convenience of explanation, hereinafter, the person who grips the gripping portion will simply be referred to as "person". Here, the "movement of gripping the gripping portion by a person" includes whether the person is gripping the gripping portion (presence or absence of gripping), with what force the person is gripping the gripping portion (strength of the gripping force), at what position the person is gripping the gripping portion (position of gripping), with which finger the person is applying force to grip the gripping portion (way of gripping), and the like.

[0069] FIG. 8 is a diagram showing an example in which the conductive urethane 22 is applied to a grip portion T of a sports equipment, for example, a tennis racket R. That is, the object 2 to which the stimulus is applied is the grip portion of the sports equipment.

[0070] In the example shown in FIG. 8(A), a person grips the grip portion T including the conductive urethane 22 with the hand H. That the grip portion T includes the conductive urethane 22 means that the arrangement example of the conductive urethane 22 and the member 21 constituting the grip portion T of the tennis racket R, more specifically, the member 21 wound around the grip portion T (in this case, cotton or chemical fiber), satisfies any of the arrangement examples of the conductive urethane 22 and the member 21 shown in FIG. 2.

[0071] Then, as shown in FIG. 8(A), when the electrical property detection unit 76 is attached to the grip part T and wireless communication is used, it is possible to connect the electrical property detection unit 76 to the estimation device 1 via the communication unit 114 without disturbing the movement of the person gripping the grip part T. Note that the electrical property detection unit 76 and the estimation device 1 may be connected by wire according to the situation.

[0072] In the example shown in FIG. 8(A), the electrical property detection unit 76 is attached to the grip part T, and the electrical property detection unit 76 attached to the grip part T detects the electrical resistance value of the conductive urethane 22 included in the grip part T.

[0073] Note that the gripping part in the present embodiment is not limited in type as long as it can be gripped by a person. For example, it may be the grip part of the above-described sports equipment, the handrail part of a treatment chair, or the handrail part provided on the seat of a roller coaster. Here, the grip part T of the sports equipment may be the grip part T of the above-described tennis racket R, or may be the grip part of a golf club, the grip part of a baseball bat, or the like. Further, the handrail part of the treatment chair includes the handrail part that a patient being treated while sitting on a dental chair grips.

[0074] As described above, since the movement of gripping the gripping part by a person affects the gripping state of the gripping part, the information regarding the movement of gripping the gripping part by a person is an example of the gripping state information indicating the gripping state by the person.

[0075] Next, a learning process for generating a learning model 51 for estimating the movement of gripping the gripping part by a person will be described.

[0076] In the learning data collection process, the learning processing unit 52 of the learning model generation device shown in FIG. 3 collects, as learning data, a large amount of input data 4 in which the electrical resistance value in the conductive urethane 22 is measured in time series using the state data 3 representing the movement of gripping the gripping part by a person as a label.

[0077] Specifically, in the learning data collection process, the electrical characteristics (e.g., electrical resistance value) of the conductive urethane 22 included in the gripping part, which changes due to the movement of a person gripping the gripping part, are acquired in time series from the electrical characteristic detection unit 76 attached to the gripping part. Next, state data 3 is used as a label for the acquired time-series electrical characteristics, i.e., input data 4, and a plurality of learning data combining the state data 3 and the input data 4 is prepared.

[0078] Also, the learning data instructs a person to move to grip the gripping part, detects the electrical resistance value at that time, and collects the movement of the person gripping the gripping part (see Table 2). The person who makes the movement of gripping the gripping part of such learning data may be a specific person, for example, a professional tennis player, or may be a plurality of various persons.

[0079] Hereinafter, although the electrical resistance value is used as an example of the electrical characteristics of the conductive urethane 22 included in the gripping part, it has been described above that a current value or a voltage value may be used as the electrical characteristics of the conductive urethane 22.

[0080] Table 2 is an example of a data set in which the time-series electrical resistance value data obtained from the gripping part, that is, the input data 4, and the state data 3 (R1 to Rk) indicating the movement of a person gripping the gripping part are associated with each other as learning data used for estimating the movement of a person gripping the gripping part.

[0081]

Table 2

[0082] Here, the gripping state information is, for example, information on how strongly the gripping part is gripped (the strength of the gripping force). The strength of the gripping force is collected by giving an instruction to apply a gripping force to the gripping part in various scenarios according to the type of the gripping part to a person who makes a movement of gripping the gripping part in the training data. For example, when the gripping part is the grip part T of a tennis racket, the electrical resistance value when serving (R1), the electrical resistance value when hitting a ball with a stroke (R2), the electrical resistance value when hitting a ball with a volley (R3), etc. are collected. That is, for example, it is known that the way of gripping the grip part T differs between a skilled tennis player and a beginner. Therefore, by collecting the training data of the skilled player, generating the learning model 51, and from the pressure stimulus of gripping the input gripping part to the generated learning model 51, the estimation unit 5 can estimate the current gripping state of the person. Then, the estimation result is output to a terminal device such as a smartphone. From the output estimation result, it is also possible to aim for improvement in technology to approach a skilled player by practicing the way of gripping the grip part T of the tennis racket so that the person corrects the difference from the training data.

[0083] Also, when the gripping part is the handrail part of a treatment chair, the electrical resistance value when gripping during the normal state (R1), the electrical resistance value when gripping during treatment with pain (R2), etc. are collected. That is, for example, it is known that when a person is tense or feeling pain, the gripping part is gripped stronger than in the normal state when not tense or not feeling pain. Therefore, by collecting the training data, generating the learning model 51, and from the pressure stimulus of gripping the input gripping part to the generated learning model 51, the estimation unit 5 can estimate the current physical state of the person. Then, the estimation result is output to a terminal device such as a smartphone. When the output estimation result is gripping state information indicating that the person during treatment is feeling pain, it is also possible to take measures such as interrupting the treatment. In this way, the gripping state information includes physical state information such as the tension state and the pain state.

[0084] Also, the gripping state information is, for example, information regarding the water content in the gripping part. When the gripping part containing the conductive urethane 22 contains moisture, a material stimulus occurs, and the electrical characteristics of the conductive urethane 22 change according to the magnitude and distribution of the material stimulus. Therefore, the estimation device 1 can estimate information regarding the water content generated in the gripping part from the time-series electrical resistance values of the conductive urethane 22. Here, the water content in the gripping part is mainly sweat generated from the hand of the person gripping the gripping part. The water content in the gripping part is collected by giving instructions to grip the gripping part in various scenes according to the type of the gripping part to a person who makes a movement to grip the gripping part of the learning data. For example, when the gripping part is the handrail part of the treatment chair, the electrical resistance value based on the water content (R1) in the normal state, the electrical resistance value based on the water content (R2) during the treatment with pain, etc. are collected. That is, for example, it is known that when a person is tense or feels pain, they sweat more on the hand gripping the gripping part than in the normal state when they are not tense or do not feel pain. Therefore, by collecting learning data, generating the learning model 51, and inputting the material stimulus for gripping the gripping part to the generated learning model 51, the estimation unit 5 can estimate the current physical state of the person. Then, the estimation result is output to a terminal device such as a smartphone. When the output estimation result is gripping state information indicating that the person during the treatment feels pain, it is also possible to take measures such as interrupting the treatment. In this way, the gripping state information includes physical state information such as the tension state and the pain state.

[0085] In addition, the gripping state information is, for example, information regarding at what position the gripping part is being gripped (the position where the gripping part is gripped). As shown in FIG. 8(B), from the coordinate positions (x, y) in the state where the member 21 wound around the grip part T of the tennis racket R is deployed, for example, the electrical resistance value when gripping coordinates x1, y1 (R1), the electrical resistance value when gripping coordinates x1, y2 (R2), etc. are collected. That is, for example, it is known that the positions where a skilled tennis player and a beginner grip the grip part T are different. Therefore, by collecting the learning data of the skilled player, generating the learning model 51, and from the pressure stimulus for gripping the gripping part input to the generated learning model 51, the estimation unit 5 can estimate the current gripping state of the person. Then, the estimation result is output to a terminal device such as a smartphone. By practicing the position where the grip part T of the tennis racket R is gripped so as to correct the difference from the learning data based on the output estimation result, it is also possible to approach a skilled player.

[0086] Note that the gripping state information is not limited to the above-described, and may be, for example, the electrical characteristics of the conductive urethane 22 due to the pressure stimulus and material stimulus for each finger of the person.

[0087] The learning processing unit 52 can be configured to include a computer including a CPU (not shown), and executes learning data collection processing and learning processing.

[0088] FIG. 9 is a diagram showing an example of the flow of the learning data collection processing performed by the learning processing unit 52.

[0089] In step S100, the learning processing unit 52 instructs a person to move the gripping part, and in step S102, it acquires, in time series, the electrical resistance value that changes according to the pressure stimulus corresponding to the gripping state accompanied by the movement of the gripping part. In the next step S104, the acquired time-series electrical resistance value is labeled with the gripping state accompanied by the movement and stored (see Table 2). The learning processing unit 52 repeats the above processing until the set of these gripping states and the electrical resistance value of the conductive urethane 22 reaches a predetermined number or a predetermined time (negatively determines until a positive determination is made in step S106). As a result, the learning processing unit 52 can acquire and store the electrical resistance value in the conductive urethane 22 in time series for each gripping state, and the set of the time-series electrical resistance values of the conductive urethane 22 for each stored gripping state becomes learning data.

[0090] The learning model 51 is generated by the learning processing of the learning processing unit 52. The learning model 51 is expressed as a set of information on the coupling weight parameters (weights or intensities) between the nodes of the learning result by the learning processing unit 52.

[0091] FIG. 10 is a diagram showing an example of the flow of the learning process performed by the learning processing unit 52.

[0092] In step S110, the learning processing unit 52 selects any one of the plurality of learning data shown in Table 2. Then, the time-series input data 4 is acquired from the selected learning data. In step S112, the learning processing unit 52 generates the learning model 51 using the learning data of the measured results in time series. That is, a set of information on the coupling weight parameters (weights or intensities) between the nodes of the learning result learned using a large number of learning data as described above is obtained. Then, in step S114, the data expressed as a set of information on the coupling weight parameters (weights or intensities) between the nodes of the learning result is stored as the learning model 51.

[0093] Note that the generator 54 may use a recurrent neural network having a function of generating an output in consideration of the context of the time-series input, or may use other methods.

[0094] Then, in the above-described estimation device 1, the learned generator 54 (i.e., data expressed as a set of information on the connection weight parameters between nodes of the learning result) generated by the method exemplified above is used as the learning model 51. By using the sufficiently learned learning model 51, it is not impossible to identify the gripping state from the time-series electrical resistance values in the gripping part, i.e., the conductive urethane 22.

[0095] Note that the processing by the learning processing unit 52 is executed, for example, by an external learning model generation device (not shown) different from the estimation device 1. The estimation device 1 includes an estimation unit 5. The output data 6, which is information indicating the gripping state, is an example of the gripping state information of the present disclosure.

[0096] Next, the estimation process of the gripping state using the learning model 51 according to the present embodiment will be described.

[0097] FIG. 11 shows an example of the flow of the estimation process of the gripping state by the control program 108P executed by the computer main body 100. The estimation process shown in FIG. 11 is executed by the CPU 102 when the computer main body 100 is powered on.

[0098] First, in step S200, the learned learning model 51 for estimating the gripping state is read from the learning model 108M of the auxiliary storage device 108 and developed in the RAM 104, thereby acquiring the learning model 51 and constructing the learning model 51.

[0099] Next, in step S202, unknown input data 4 (electrical characteristics), which is the target for estimating the gripping state of the gripping part due to the pressure stimulus applied to the gripping part, is acquired in time series via the detection unit 118.

[0100] Next, in step S204, using the learning model 51 obtained in step S200, the output data 6 (grasping state) corresponding to the input data 4 (electrical characteristics) obtained in step S202 is estimated. Then, in the next step S206, the output data 6 (grasping state) of the estimation result is output to the auxiliary storage device 108 or output via the communication unit 114 which is an example of an output unit, and this processing routine is terminated. Here, the estimation result output to a terminal device such as a smartphone via the communication unit 114 may be an image of the grasping state that can show the difference from an expert.

[0101] The estimation process shown in FIG. 11 described above is an example of the process executed by the estimation method of the present disclosure.

[0102] As described above, according to the present disclosure, it is possible to estimate the movement of grasping a person's grasping part from the unknown electrical characteristics of grasping the person's grasping part.

[0103] Therefore, with the estimation device 1, for example, the proficiency and experience level of a person can be understood from the movement of grasping the grasping part, so the estimation device 1 can be applied to the field of sports such as form checking.

[0104] Also, with the estimation device 1, for example, the physical state of a person can be understood from the movement of grasping the grasping part, so the estimation device 1 can be applied to the medical field such as interrupting treatment.

[0105] As described above, in the present disclosure, the case where conductive urethane is applied as an example of the flexible member has been described, but it goes without saying that the flexible member is not limited to conductive urethane.

[0106] Also, the technical scope of the present disclosure is not limited to the scope described in the above embodiment. Various changes or improvements can be made to the above embodiment without departing from the gist, and the forms with such changes or improvements are also included in the technical scope of the present disclosure.

[0107] In the above-described embodiment, the estimation process and the learning process have been described in the case where they are realized by a software configuration using a flowchart, but the present invention is not limited thereto. For example, each process may be realized by a hardware configuration.

[0108] Further, a part of the estimation device, for example, a neural network such as a learning model, may be configured as a hardware circuit.

Explanation of Signs

[0109] 1 Estimation device 2 Object 3 State data 4 Input data 5 Estimation unit 6 Output data 6A Generated output data 22 Conductive urethane 51 Learning model 52 Learning processing unit 54 Generator 56 Arithmetic unit 75 Detection point 76 Electrical property detection unit R Tennis racket T Grip part H Hand< / prc>

Claims

1. A detection unit that detects the electrical properties between a plurality of predetermined detection points on the flexible material of a gripping part provided with a flexible material having conductivity and whose electrical properties change in response to a change in the applied stimulus; Using the time-series electrical properties when a stimulus is applied to the flexible material and the gripping state information indicating the gripping state by the person of the gripping part that applies the stimulus to the flexible material as learning data, for a learning model that is trained to take the time-series electrical properties as input and output the gripping state information, the time-series electrical properties detected by the detection unit are input, and a gripping state information indicating the gripping state by the person corresponding to the input time-series electrical properties is estimated. An estimation unit; including The electrical property is volume resistivity. The gripping state includes a state in which at least one of a pressure stimulus and a material stimulus by a person on the gripping part is applied. The learning model is trained to output, as the gripping state information, information indicating a state in which at least one of a pressure stimulus and a material stimulus by a person corresponding to the detected electrical property is applied. The gripping part includes a material in which conductivity is imparted to at least a part of a urethane material having a structure in which a plurality of minute air bubbles are scattered inside, and is an estimation device.

2. The pressure stimulus is a pressure stimulus generated as the person grips the gripping part. The estimation device according to claim 1, wherein the gripping state information is information regarding the movement of the person gripping the gripping part.

3. The estimation device according to claim 2, wherein the gripping state information includes information regarding the position where the person grips the gripping part.

4. The material stimulus is a material stimulus generated as the gripping part becomes hydrated. The estimation device according to claim 1, wherein the gripping state information is information regarding the hydration in the gripping part.

5. The estimation device according to any one of claims 1 to 4, wherein the gripping state information includes information on the physical state of the person gripping the gripping part.

6. The estimation device according to any one of claims 1 to 5, further including an output unit that outputs the gripping state estimated by the estimation unit.

7. The estimation device according to any one of claims 1 to 6, wherein the gripping part includes at least one of a grip part of a sports equipment and a handrail part of a treatment chair.

8. The learning model includes a model generated by training using a network based on reservoir computing that uses the flexible material as a reservoir. The estimation device according to any one of claims 1 to 7.

9. A computer detects the electrical characteristics between a plurality of predetermined detection points on the flexible material of the gripping part provided with a flexible material having conductivity and whose electrical characteristics change according to a change in a given stimulus, using, as learning data, the time-series electrical characteristics when a stimulus is applied to the flexible material and the gripping state information indicating the gripping state of the person of the gripping part who applies the stimulus to the flexible material, inputting the time-series electrical characteristics, and estimating, for a learning model trained to output the gripping state information, the gripping state information indicating the gripping state of the person of the gripping part corresponding to the input time-series electrical characteristics by inputting the detected time-series electrical characteristics, which is an estimation method, The electrical characteristic is volume resistance, The gripping state includes a state in which at least one of a pressure stimulus and a material stimulus applied by a person to the gripping part is applied, The learning model is trained to output, as the gripping state information, information indicating a state in which at least one of a pressure stimulus and a material stimulus applied by a person corresponding to the detected electrical characteristics is applied, The gripping part includes a material in which conductivity is imparted to at least a part of a urethane material having a structure in which a plurality of minute air bubbles are scattered inside, Estimation method.

10. To a computer detects the electrical characteristics between a plurality of predetermined detection points on the flexible material of the gripping part provided with a flexible material having conductivity and whose electrical characteristics change according to a change in a given stimulus, using, as learning data, the time-series electrical characteristics when a stimulus is applied to the flexible material and the gripping state information indicating the gripping state of the person of the gripping part who applies the stimulus to the flexible material, inputting the time-series electrical characteristics, and estimating the gripping state information indicating the gripping state of the person of the gripping part corresponding to the input time-series electrical characteristics for a learning model trained to output the gripping state information An estimation program for causing the execution of processing, The electrical characteristic is volume resistance, The gripping state includes a state in which at least one of a pressure stimulus and a material stimulus applied by a person to the gripping part is applied, The learning model is trained to output, as the gripping state information, information indicating a state in which at least one of a pressure stimulus and a material stimulus by a person corresponding to the detected electrical characteristics is applied. The gripping part includes a material in which conductivity is imparted to at least a part of a urethane material having a structure in which a plurality of minute air bubbles are dispersed inside. Estimation program.

11. The electrical characteristics from a detection unit that detects the electrical characteristics between a plurality of predetermined detection points in the flexible material of a gripping part including a flexible material that has conductivity and whose electrical characteristics change in response to a change in the applied stimulus, and gripping state information indicating the gripping state by a person who applies a stimulus to the flexible material. An acquisition unit that acquires the information; Based on the acquisition result of the acquisition unit, a learning model that takes as input the time-series electrical characteristics when pressure is applied to the flexible material and outputs gripping state information indicating the gripping state by a person who applies a stimulus to the flexible material. A learning model generation unit that generates the model; A learning model generation device including: The electrical characteristic is volume resistance. The gripping state includes a state in which at least one of a pressure stimulus and a material stimulus by a person on the gripping part is applied. The learning model is trained to output, as the gripping state information, information indicating a state in which at least one of a pressure stimulus and a material stimulus by a person corresponding to the detected electrical characteristics is applied. The gripping part includes a material in which conductivity is imparted to at least a part of a urethane material having a structure in which a plurality of minute air bubbles are dispersed inside. Learning model generation device.

Images