A method and device for identifying walking speed and a robot walking assistance system

Abstract

The present invention relates to a method for identifying walking speed, which includes: plotting the change trajectory of the center of pressure when the user walks at different preset speeds; fitting the standard trajectory curve equation corresponding to the change trajectory of the center of pressure at different preset speeds; collecting the gait pressure analog quantity of the user's current walking state in real time and calculating the current center of pressure; substituting the abscissa of the current center of pressure into multiple standard trajectory curve equations to obtain multiple standard predicted values; calculating the absolute value of the difference between the ordinate of the current center of pressure and the multiple standard predicted values, and selecting the standard predicted value corresponding to the smallest absolute value of the difference as the target predicted value; selecting the standard trajectory curve equation that outputs the target predicted value as the target trajectory curve equation, and determining the agreed speed of the target trajectory curve equation as the user's current walking speed. The present invention fits the standard trajectory curve equation according to the change trajectory of the center of pressure on the sole of the foot, and identifies the user's current walking speed in real time, and the identification result is accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of robots, and in particular to a method and device for identifying walking speed and a robot walking assistance system. Background Art

[0002] With the evolution of technological intelligence, it is possible to identify and analyze the gait of a wearer during walking, and through the analysis of plantar pressure, the human-machine collaborative control of exoskeletons or intelligent prostheses can be achieved.

[0003] Currently, the collection of plantar pressure relies on array-type thin-film pressure sensors. The collected plantar pressure is mainly used to judge the balance state of human walking, and it is widely used in clinical medical diagnosis, determination of disease degree, evaluation of postoperative curative effect, biomechanics and rehabilitation treatment, sports training research, shoe design and other aspects. However, the use of array-type thin-film pressure sensors to measure the center of pressure (COP) of the plantar surface is less applied in identifying the walking speed of normal people. At present, there are mainly two schemes for using plantar pressure thin-film sensors to judge the walking speed; Scheme 1: Calculate the interval time ΔT between the sensors at the heel or the toes triggered successively by the same foot, and calculate the average walking speed using the ratio of the step length L to the interval time ΔT; Scheme 2: Calculate the interval time ΔT from the heel touchdown to the toe liftoff of the same foot. The walking support time accounts for 60% of the entire gait cycle, and the average walking speed is calculated using the formula V = 2L / (ΔT / 0.6).

[0004] However, both of the above two methods calculate the average walking speed. When a human walks normally, the thighs move forward in a crossed inverted pendulum manner, and the speed is constantly changing. Therefore, these two methods have the disadvantages of inaccurate walking speed discrimination and judgment lag, and are not suitable for the human-machine collaborative control system based on exoskeletons or intelligent prostheses. Summary of the Invention

[0005] Therefore, the technical problem to be solved by the present invention is to overcome the problem of lag and inaccuracy in walking speed judgment in the prior art.

[0006] To solve the above technical problem, the present invention provides a method for identifying walking speed, including:

[0007] Drawing the change trajectory of the center of pressure when the user walks at different preset walking speeds;

[0008] Fitting the standard trajectory curve equation corresponding to the different preset walking speeds according to the change trajectory of the center of pressure under the different preset walking speeds;

[0009] Real-time collecting the gait pressure analog quantity of the user's current walking state, and calculating the coordinates of the corresponding current center of pressure;

[0010] Substitute the abscissa of the current center of pressure into the standard trajectory curve equations at multiple different preset walking speeds to obtain multiple standard predicted values;

[0011] Calculate the absolute values of the differences between the ordinate of the current center of pressure and the multiple standard predicted values respectively, and select the standard predicted value corresponding to the minimum absolute value of the difference as the target predicted value;

[0012] Select the standard trajectory curve equation that outputs the target predicted value as the target trajectory curve equation, and determine that the agreed walking speed of the target trajectory curve equation is the user's current walking speed.

[0013] In an embodiment of the present invention, the drawing of the trajectory of the center of pressure when the user walks at different preset walking speeds includes:

[0014] Collect the gait pressure analog quantity during the walking process when the user walks at a preset walking speed;

[0015] Calculate the coordinates of the center of pressure according to the gait pressure analog quantity;

[0016] Draw the corresponding trajectory of the center of pressure change according to the coordinates of the center of pressure.

[0017] In an embodiment of the present invention, the calculation of the coordinates of the center of pressure according to the gait pressure analog quantity is expressed as:

[0018]

[0019] Among them, X and Y respectively represent the abscissa and ordinate of the center of pressure; n represents the total number of array-type thin-film pressure sensors; x i 、y i respectively represent the abscissa and ordinate of the i-th array-type thin-film pressure sensor; p i represents the pressure value detected by the i-th array-type thin-film pressure sensor.

[0020] In an embodiment of the present invention, the trajectory of the center of pressure change is fitted into a standard trajectory curve equation by using a polynomial fitting algorithm.

[0021] In an embodiment of the present invention, the standard trajectory curve equations corresponding to different preset walking speeds include:

[0022] When the preset walking speed is greater than or equal to 1 km / h and less than 2 km / h, the first standard trajectory curve equation is:

[0023] f 1 (X)=-2.696e-7*X 4 +0.0001357*X 3 -0.02548*X 2+2.144*X - 59.39;

[0024] The conventional walking speed of the first standard trajectory curve equation is 1.5 km / h;

[0025] When the preset walking speed is greater than or equal to 2 km / h and less than 3 km / h, the second standard trajectory curve equation is:

[0026] f 2 (X) = -2.119e - 7*X 4 +0.0001165*X 3 -0.02433*X 2 +2.283*X - 71.28;

[0027] The conventional walking speed of the second standard trajectory curve equation is 2.5 km / h;

[0028] When the preset walking speed is greater than or equal to 3 km / h and less than or equal to 4 km / h, the third standard trajectory curve equation is:

[0029] f 3 (X) = -3.699e - 7*X 4 +0.0001957*X 3 -0.03782*X 2 +3.121*X - 86.07;

[0030] The conventional walking speed of the third standard trajectory curve equation is 3.5 km / h;

[0031] Wherein, X represents the abscissa of the center of pressure.

[0032] In an embodiment of the present invention, determining that the conventional walking speed of the target trajectory curve equation is the user's current walking speed includes:

[0033] Inputting the abscissa X of the current center of pressure into multiple standard trajectory curve equations to obtain multiple standard predicted values f 1 (X), f 2 (X) and f 3 (X);

[0034] Respectively calculating the absolute values of the differences between the ordinate Y of the current center of pressure and the f 1 (X), f 2 (X) and f 3 (X): |Y - f 1 (X)|, |Y - f 2 (X)|, |Y - f 3 (X)|;

[0035] Select the standard predicted value corresponding to the smallest absolute value of the difference as the target predicted value, and use the standard trajectory curve equation for obtaining the target predicted value as the target trajectory curve equation;

[0036] Obtain the agreed walking speed of the target trajectory equation as the current walking speed of the user.

[0037] The present invention also provides a walking speed recognition device for implementing the above-mentioned walking speed recognition method, including:

[0038] A sampling module, configured to obtain gait pressure analog quantities at different preset walking speeds;

[0039] A data processing module, communicatively connected to the sampling module, configured to obtain corresponding centers of pressure according to the gait pressure analog quantities at different preset walking speeds, draw the change trajectories of the centers of pressure, and fit multiple standard trajectory curve equations at different preset walking speeds according to the change trajectories of the centers of pressure;

[0040] An identification module, communicatively connected to the data processing module, configured to select a target trajectory curve equation from multiple standard trajectory curve equations according to the currently obtained center of pressure in real time, and obtain the agreed walking speed of the target trajectory curve equation as the current walking speed of the user;

[0041] A communication module, configured to implement communication between the sampling module and the data processing module, and between the data processing module and the identification module;

[0042] A power supply module, configured to supply power to the sampling module, the data processing module, the identification module, and the communication module.

[0043] In an embodiment of the present invention, the sampling module includes:

[0044] A flexible circuit board, which is provided with different sizes to adapt to the user's sole and is fixed between the insole and the outsole during use;

[0045] Thin film pressure sensors, which are arranged in an array on the flexible circuit board and are used to collect the gait pressure analog quantities of the user.

[0046] In an embodiment of the present invention, the flexible circuit board is connected to the data processing module through a connector.

[0047] The present invention also provides a robot walking assistance system, including:

[0048] The walking speed recognition device as described above, configured to obtain the current walking speed of the user according to the gait pressure analog quantity during the user's walking process;

[0049] A control module, communicatively connected to the walking speed recognition device, to obtain the current walking speed;

[0050] A wearable robot, connected to the control module, so that the control module drives the wearable robot to provide walking assistance to the user according to the current walking speed.

[0051] The above technical solution of the present invention has the following advantages compared with the prior art:

[0052] In the walking speed recognition method of the present invention, by fitting the change trajectory curve of the center of pressure during the walking process of the user at different walking speeds, multiple standard trajectory curve equations are obtained; the gait pressure analog quantity during the current walking process of the user is collected in real time and converted into the current center of pressure, and the abscissa of the current center of pressure is substituted into multiple standard trajectory curve equations to obtain multiple standard predicted values; according to the absolute value of the difference between the standard predicted value and the ordinate of the current center of pressure, the target trajectory curve equation is selected, and the agreed walking speed of the target trajectory curve equation is used as the recognized current walking speed of the user. Through the research on the change range of the sole pressure center trajectory at different walking speeds, the present invention fits the standard trajectory curve equation, predicts the current center of pressure through the standard trajectory curve equation, and identifies the current walking speed of the user in real time, and the identification result is accurate. Description of the Drawings

[0053] In order to make the content of the present invention easier to be clearly understood, the following further details the present invention according to the specific embodiments of the present invention in conjunction with the drawings, where

[0054] Figure 1 is a schematic diagram of establishing a coordinate system provided by an embodiment of the present invention;

[0055] Figure 2 is a sole pressure center trajectory diagram at different walking speeds provided by an embodiment of the present invention;

[0056] Figure 3 is a step diagram of the walking speed recognition method provided by an embodiment of the present invention;

[0057] Figure 4 is a schematic structural diagram of a walking speed recognition device provided by an embodiment of the present invention;

[0058] Figure 5 is a schematic structural diagram of another walking speed recognition device provided by an embodiment of the present invention.

[0059] Explanation of the reference numerals in the drawings: 1. Thin film pressure sensor; 2. Flexible circuit board; 3. Lower computer; 4. Upper computer. Detailed Embodiments

[0060] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, so that those skilled in the art can better understand the present invention and be able to implement it, but the embodiments cited do not limit the present invention.

[0061] Referring to Figure 1 as shown, a coordinate system with the sole width and length as the X-axis and Y-axis is established. Referring to Figure 2 as shown, it is the moving trajectory diagram of the center of plantar pressure at different walking speeds; the change range of the center of pressure trajectory curve in the Y-axis direction is between 60 mm and 190 mm. According to the three center of pressure moving trajectory curves, the faster the walking speed, the faster the moving rate of the center of pressure in the Y-axis direction, and the smaller the time taken for the movement; in the X-axis direction, the faster the walking speed, the smaller the negative value range of the center of pressure change, the closer it is to a straight line, the smaller the time required for the center of pressure to move, and the faster the moving rate.

[0062] Based on the above principle, according to the current situation that the change range and change rate of the center of pressure trajectory are different at different walking speeds, the present invention collects experimental data in the form of multiple people and multiple groups. Multiple experimental personnel walk at walking speeds greater than or equal to 1 km / h and less than 2 km / h, greater than or equal to 2 km / h and less than 3 km / h, and greater than or equal to 3 km / h and less than or equal to 4 km / h respectively, and collect the gait pressure analog quantity during walking. According to the collected gait pressure analog quantity, the corresponding center of pressure change trajectory is drawn, and multiple standard trajectory curves are fitted as the basis for walking speed recognition.

[0063] Referring to Figure 3 as shown, the walking speed recognition method provided by the embodiment of the present invention includes:

[0064] S1: Draw the change trajectory of the center of pressure when the user walks at different preset walking speeds;

[0065] S11: Collect the gait pressure analog quantity during the walking process when the user walks at the preset walking speed;

[0066] S12: Calculate the coordinates of the center of pressure according to the gait pressure analog quantity;

[0067]

[0068] wherein, X and Y respectively represent the abscissa and ordinate of the center of pressure; n represents the total number of array-type thin-film pressure sensors; x i , y i respectively represent the abscissa and ordinate of the i-th array-type thin-film pressure sensor; p i represents the pressure value detected by the i-th array-type thin-film pressure sensor;

[0069] S13: Plot the corresponding pressure center change trajectory based on the pressure center coordinates.

[0070] S2: Fit the standard trajectory curve equations corresponding to the different preset walking speeds according to the pressure center change trajectories at the different preset walking speeds;

[0071] S21: Based on the polyfit function of MATLAB, input the pressure center coordinates and the order to be fitted, and fit the pressure center into the standard trajectory curve equation.

[0072] S22: Change the preset walking speed to obtain multiple standard trajectory curve equations at different preset walking speeds;

[0073] When the preset walking speed is greater than or equal to 1 km / h and less than 2 km / h, the first standard trajectory curve equation is:

[0074] f 1 (X) = -2.696e-7*X 4 +0.0001357*X 3 -0.02548*X 2 +2.144*X - 59.39;

[0075] The agreed walking speed of the first standard trajectory curve equation is 1.5 km / h;

[0076] When the preset walking speed is greater than or equal to 2 km / h and less than 3 km / h, the second standard trajectory curve equation is:

[0077] f 2 (X) = -2.119e-7*X 4 +0.0001165*X 3 -0.02433*X 2 +2.283*X - 71.28;

[0078] The agreed walking speed of the second standard trajectory curve equation is 2.5 km / h;

[0079] When the preset walking speed is greater than or equal to 3 km / h and less than or equal to 4 km / h, the third standard trajectory curve equation is:

[0080] f 3 (X) = -3.699e-7*X 4 +0.0001957*X 3 -0.03782*X 2 +3.121*X - 86.07;

[0081] The agreed walking speed of the third standard trajectory curve equation is 3.5 km / h;

[0082] Among them, X represents the abscissa of the center of pressure;

[0083] The above standard trajectory curve equation is a standard curve fitted from the trajectory of the change of the center of pressure obtained from the gait pressure analog quantity collected in the experiment. Different experimental data can fit different standard trajectory curve equations.

[0084] S3: Real-time collect the gait pressure analog quantity of the user's current walking state, and calculate the coordinates of the corresponding current center of pressure;

[0085] S4: Substitute the abscissa of the current center of pressure into the standard trajectory curve equations under multiple different preset walking speeds to obtain multiple standard predicted values; respectively calculate the absolute values of the differences between the ordinate of the current center of pressure and the multiple standard predicted values, and select the standard predicted value corresponding to the smallest absolute value of the difference as the target predicted value; select the standard trajectory curve equation for obtaining the target predicted value as the target trajectory curve equation, and determine the agreed walking speed of the target trajectory curve equation as the user's current walking speed.

[0086] S41: Input the abscissa X of the current center of pressure into the first standard trajectory curve equation, the second standard trajectory curve equation and the third standard trajectory curve equation respectively to obtain the first standard predicted value f 1 (X), the second standard predicted value f 2 (X) and the third standard predicted value f 3 (X);

[0087] S42: Respectively calculate the absolute values of the differences between the ordinate Y of the current center of pressure and the first standard predicted value f 1 (X), the second standard predicted value f 2 (X), the third standard predicted value f 3 (X): |Y - f 1 (X)|, |Y - f 2 (X)|, |Y - f 3 (X)|;

[0088] S43: Select the standard predicted value corresponding to the smallest absolute value of the difference as the target predicted value, and use the standard trajectory curve equation for obtaining the target predicted value as the target trajectory curve equation;

[0089] S44: Obtain the agreed walking speed of the target trajectory curve equation as the recognized user's current walking speed.

[0090] In the embodiments of the present invention, multiple standard trajectory curve equations at different walking speeds are obtained by fitting experimental data collected by multiple experimenters walking at different walking speeds; the change trajectories of the plantar pressure centers of the user's left and right feet are symmetric about the X-axis. The corresponding standard trajectory curve equations can be respectively fitted according to the change trajectories of the plantar pressure centers of the left and right feet, so as to identify the current walking speeds of the user's left and right feet according to the above steps. During the walking speed identification process, weight coefficients can be added to different standard trajectory curve equations to obtain the target trajectory curve equation, and further determine the current walking speed of the user.

[0091] Referring to Figure 4 As shown, the embodiments of the present invention also provide a walking speed identification device, including:

[0092] A sampling module, configured to obtain gait pressure analog quantities at different preset walking speeds;

[0093] A data processing module, communicatively connected to the sampling module, configured to obtain the corresponding pressure centers according to the gait pressure analog quantities at different preset walking speeds, draw the change trajectories of the pressure centers, and fit multiple standard trajectory curve equations at different preset walking speeds according to the change trajectories of the pressure centers;

[0094] An identification module, communicatively connected to the data processing module, configured to select a target trajectory curve equation from multiple standard trajectory curve equations according to the currently obtained pressure center in real time, and obtain the agreed walking speed of the target trajectory curve equation as the current walking speed of the user;

[0095] A communication module, configured to implement communication between the sampling module and the data processing module, and between the data processing module and the identification module;

[0096] A power supply module, configured to supply power to the sampling module, the data processing module, the identification module, and the communication module.

[0097] Specifically, the sampling module includes a flexible circuit board and a thin-film pressure sensor arranged in an array on the flexible circuit board. To be applicable to different users, the flexible circuit board has different sizes and is fixed between the insole and the sole worn by the user during use. When the user walks, the thin-film pressure sensor arranged on its upper surface senses the pressure change, collects the gait pressure analog quantity, and uploads it to the data processing module through the flexible circuit board; the flexible circuit board is connected to the data processing module through a connector; the thin-film pressure sensor is simple to use and easy to carry, and is arranged on the flexible circuit board without interfering with the normal walking of the user, providing a more accurate gait pressure analog quantity.

[0098] Referring to Figure 5As shown in the figure, in another embodiment provided by the present invention, the walking speed recognition device includes a lower computer and an upper computer; the lower computer is connected to the flexible circuit board through a connector, and includes: a sampling module, a data processing module and a communication module; the upper computer includes: a communication module and an identification module. The sampling module collects the gait pressure analog quantity by using a thin-film pressure sensor and uploads it through the flexible circuit board; the data processing module is used to obtain the gait pressure analog quantity uploaded by the flexible circuit board, convert the gait pressure analog quantity into a center of pressure, and fit a standard trajectory curve equation based on the center of pressure according to the center of pressure; the lower computer communication module transmits the center of pressure and the standard trajectory curve equation to the upper computer; the upper computer communication module obtains the signal transmitted by the lower computer communication module; the identification module uses the above-mentioned walking speed recognition method to recognize the current walking speed of the user according to the center of pressure and the standard trajectory curve equation. In an embodiment provided by the present invention, the sampling module, the data processing module and the identification module can be integrated on the same device, or can be separately arranged in the lower computer and the upper computer, and the signal transmission is realized by using the communication between the upper computer and the lower computer, and further the walking speed recognition is realized.

[0099] The embodiment of the present invention also provides a robot walking assistance system, including the walking speed recognition device as described above, which is used to obtain the current walking speed of the user according to the gait pressure analog quantity during the user's walking; a control module, which is communicatively connected to the walking speed recognition device to obtain the current walking speed; a wearable robot, which is connected to the control module, so that the control module drives the wearable robot to give the user walking assistance according to the current walking speed. The embodiment of the present invention realizes the non-sensing interaction of human-machine cooperation by collecting the gait pressure analog quantity during the user's walking in real time, predicting the user's current walking speed, and sending it to the control module, so that the control module drives the robot to give the user the assistance to move forward at the current walking speed, giving the robot sufficient reaction time.

[0100] In an embodiment of the present invention, the wearable robot is a wearable assistance device for the user, including an exoskeleton and a smart prosthetic limb. The user wears the assistance device, and the walking speed recognized by the walking speed recognition device drives the assistance device to assist the user to walk.

[0101] A walking speed recognition method provided by the present invention obtains a plurality of standard trajectory curve equations by fitting the change trajectory curve of the center of pressure during the user's walking at different speeds; real-time collects the gait pressure analog quantity during the user's current walking process and converts it into the current center of pressure, substitutes the abscissa of the current center of pressure into the plurality of standard trajectory curve equations to obtain a plurality of standard predicted values; selects the target trajectory curve equation according to the absolute value of the difference between the standard predicted value and the ordinate of the current center of pressure, and takes the agreed speed of the target trajectory curve equation as the recognized current walking speed of the user. The present invention studies the change range of the sole pressure center trajectory at different walking speeds, fits the standard trajectory curve equation, predicts the current center of pressure through the standard trajectory curve equation, identifies the current walking speed of the user, and provides a more real-time and accurate walking speed identification result. Based on the above walking speed identification result, the control module is used to drive the exoskeleton or intelligent prosthetics to give the user walking assistance, realizing non-intrusive human-computer interaction.

[0102] Obviously, the above embodiments are only examples given for clear illustration and are not limitations on the implementation manners. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to enumerate all the implementation manners here. And the obvious changes or modifications derived therefrom are still within the protection scope of the present invention.

Claims

1. A method for identifying walking speed, characterized in that, it includes: Drawing the trajectory of the center of pressure change when the user walks at different preset speeds; Fitting the standard trajectory curve equations corresponding to the different preset speeds according to the trajectories of the center of pressure change at the different preset speeds, including: When the preset pace is greater than or equal to 1 and less than 2 , the first standard trajectory curve equation is: ; The agreed pace of the first standard trajectory curve equation is 1.5 ; When the preset walking speed is greater than or equal to 2 and less than 3 , the second standard trajectory curve equation is: ; The agreed walking speed of the second standard trajectory curve equation is 2.5 ; When the preset pace is greater than or equal to 3 and less than or equal to 4 , the third standard trajectory curve equation is: ; The agreed pace of the third standard trajectory curve equation is 3.5 ; Among them, represents the abscissa of the center of pressure; Real-time collecting the gait pressure analog quantity of the user's current walking state, and calculating the coordinates of the corresponding current center of pressure; Substituting the abscissa of the current center of pressure into the standard trajectory curve equations at multiple different preset speeds to obtain multiple standard predicted values; Calculating the absolute values of the differences between the ordinate of the current center of pressure and the multiple standard predicted values respectively, and selecting the standard predicted value corresponding to the smallest absolute value of the difference as the target predicted value; Selecting and outputting the standard trajectory curve equation of the target predicted value as the target trajectory curve equation, and determining the agreed speed of the target trajectory curve equation as the user's current walking speed.

2. The walking speed identification method according to claim 1, characterized in that, The drawing of the trajectory of the center of pressure change when the user walks at different preset speeds includes: Collecting the gait pressure analog quantity during the walking process when the user walks at a preset speed; Calculating the coordinates of the center of pressure according to the gait pressure analog quantity; Drawing the corresponding trajectory of the center of pressure change according to the coordinates of the center of pressure.

3. The walking speed identification method according to claim 2, characterized in that, The calculation of the coordinates of the center of pressure according to the gait pressure analog quantity is expressed as: ， ； Among them, and represent the abscissa and ordinate of the pressure center respectively; represents the total number of thin-film pressure sensors; and represent the abscissa and ordinate of the th thin-film pressure sensor respectively; represents the pressure value detected by the th thin-film pressure sensor.

4. The walking speed identification method according to claim 1, characterized in that, Using the polynomial fitting algorithm to fit the trajectory of the center of pressure change into the standard trajectory curve equation.

5. The walking speed identification method according to claim 1, characterized in that, The determination that the agreed speed of the target trajectory curve equation is the user's current walking speed includes: The abscissa of the current pressure center is input into multiple standard trajectory curve equations to obtain multiple standard predicted values 、 and ; Calculate the ordinate of the current pressure center respectively With the said , And The absolute value of the difference: , , ; Selecting the standard predicted value corresponding to the smallest absolute value of the difference as the target predicted value, and taking the standard trajectory curve equation for obtaining the target predicted value as the target trajectory curve equation; Obtaining the agreed speed of the target trajectory curve equation as the user's current walking speed.

6. A walking speed identification device for implementing the walking speed identification method according to any one of claims 1 to 5, characterized in that, it includes: A sampling module for obtaining the gait pressure analog quantity at different preset speeds; A data processing module, communicatively connected to the sampling module, for obtaining the corresponding center of pressure according to the gait pressure analog quantity at the different preset speeds, drawing the trajectory of the center of pressure change, and fitting multiple standard trajectory curve equations at different preset speeds according to the trajectory of the center of pressure change; An identification module, communicatively connected to the data processing module, for selecting the target trajectory curve equation from multiple standard trajectory curve equations according to the currently obtained center of pressure, and obtaining the agreed speed of the target trajectory curve equation as the user's current walking speed; A communication module for realizing the communication between the sampling module and the data processing module, and between the data processing module and the identification module; A power supply module for supplying power to the sampling module, the data processing module, the recognition module and the communication module.

7. The walking speed recognition device according to claim 6, characterized in that the sampling module includes: A flexible circuit board, which is provided in different sizes to fit the user's sole and is fixed between the insole and the sole when in use; Thin film pressure sensors, which are arranged in an array on the flexible circuit board and are used to collect the gait pressure analog quantity of the user.

8. The walking speed recognition device according to claim 7, characterized in that The flexible circuit board is connected to the data processing module through a connector.

9. A robot walking assistance system, characterized in that it includes: The walking speed recognition device according to claim 6, which is used to obtain the current walking speed of the user according to the gait pressure analog quantity during the user's walking; A control module, which is communicatively connected to the walking speed recognition device to obtain the current walking speed; A wearable robot, which is connected to the control module so that the control module can drive the wearable robot to give the user walking assistance according to the current walking speed.

Images