Finger air path control method and device for rehabilitation robot

Abstract

The invention provides a finger air path control method and equipment of a rehabilitation robot, which are used for accurately controlling the air pressure of each finger based on a microprocessor, an air pump, an electromagnetic valve, an air cavity and other components so as to realize accurate flexion and extension actions in a rehabilitation training process. A simple linear function is adopted, the finger angle is directly converted into the air pressure target, the calculation process is simplified, the response speed and the control precision of the system are improved, and meanwhile the conversion coefficient and the offset can be conveniently adjusted according to the condition of a patient. According to the method, the proportionality coefficient kadaptive (t) can be dynamically adjusted based on the air pressure, fed back by the air pressure sensor, of the current air cavity, so that the target air pressure value gradually approaches the optimal pressure range meeting the requirements of a patient.

Description

Technical Field

[0001] The present invention relates to the field of hand function rehabilitation, and in particular to a finger air path control method and device of a rehabilitation robot. Background Art

[0002] Most existing products use complex algorithms or empirical rules to convert the posture of the rehabilitation robot's fingers, and the response speed and control accuracy of the rehabilitation robot's fingers cannot meet the requirements. Summary of the invention

[0003] The purpose of the present invention is to provide a finger air path control method and device for a rehabilitation robot.

[0004] In order to solve the above problems, the present invention provides a finger air path control method of a rehabilitation robot, wherein the rehabilitation robot comprises a passive glove and an active glove, and the method comprises:

[0005] Each finger air cavity is provided in the passive glove of the rehabilitation robot, each finger air cavity is connected to an air pump, and an electromagnetic valve is provided at each air path node between the air pump and each finger air cavity; a microprocessor is connected to the air pump and the electromagnetic valve respectively;

[0006] The IMU sensor in the active glove collects the finger angles to be executed and sends them to the microprocessor;

[0007] The microprocessor converts the finger angle to be executed into the target air pressure value P(t) of each finger air cavity in the corresponding passive glove at the current moment through an algorithm model; wherein the algorithm model of the target air pressure value P(t) of the finger air cavity at the current moment is as follows:

[0008] P(t)=k adaptive (t)·θ(t-β)+b+α·(P(t-Δt)-P feedback (t-Δt)),

[0009] Where t represents the current time, t-Δt represents the previous time; P(t) represents the target pressure value at the current time; k adaptive (t) is the adaptive proportional coefficient adjusted based on the pressure sensor feedback; β is the hysteresis compensation factor, θ(t+β) is the finger angle to be executed, where θ(t+β) represents the finger angle to be executed after the hysteresis compensation coefficient is introduced; b is the initial pressure offset; P(t-Δt) represents the target pressure value at the previous moment t-Δt, P feedback (t-Δt) is the actual feedback pressure value at the previous moment t-Δt; α is the feedback correction factor, which is used to calculate the pressure according to the deviation, that is, P(t-Δt)-P feedback (t-Δt) to adjust the air pressure target, the deviation refers to P(t-Δt)-Pfeedback (t-Δt);

[0010] The microprocessor converts the current target air pressure value P(t) of each finger air cavity into an adjustment instruction for the air pump and the solenoid valve, and controls the opening or closing of the air pump and the solenoid valve based on the adjustment instruction.

[0011] Furthermore, in the above method, each finger air cavity is provided in the passive glove of the rehabilitation robot, including:

[0012] Each finger air cavity can be respectively arranged in 5 finger sleeves of a glove body, each finger sleeve is provided with a frame and a finger air cavity, the frame is arranged outside the finger air cavity and is used to limit the radial expansion of the finger air cavity.

[0013] Furthermore, in the above method, the IMU sensor in the active glove collects the finger angle to be executed and sends it to the microprocessor, including:

[0014] The IMU sensor in the active glove is set at the palm and fingertips of the active glove. The IMU sensor integrates a three-axis accelerometer, a three-axis gyroscope and a three-axis magnetometer, wherein the three-axis accelerometer is used to obtain acceleration, the three-axis gyroscope is used to obtain angular velocity, and the three-axis magnetometer is used to obtain magnetic field strength; the obtained acceleration, angular velocity and magnetic field strength are filtered and subjected to data fusion algorithm to obtain the bending angle of the five fingers, that is, the angle formed by the fingertips and palm of each finger of the active glove.

[0015] Furthermore, in the above method, the target air pressure value P(t) at the current moment of each finger air cavity in the corresponding passive glove is converted into the target air pressure value P(t) through the algorithm model, including:

[0016] In the real-time control process, based on the feedback pressure P feedback The difference between (t-Δt) and the target pressure P(t) is k adaptive (t) Dynamic adjustment; wherein, an incremental adjustment algorithm is used, when the feedback pressure P feedback When (t-Δt) is less than the target pressure P(t), gradually increase k adaptive (t) to increase the air pressure; otherwise, k is gradually reduced adaptive (t).

[0017] Furthermore, in the above method, the target air pressure value P(t) at the current moment of each finger air cavity in the corresponding passive glove is converted into the target air pressure value P(t) through the algorithm model, including:

[0018] Determine β through experiments, set the target air pressure value P(t), start to inflate the air cavities of each finger according to the target air pressure value P(t), start timing after the inflation is completed, and stop timing after observing that the finger air cavity stops deforming. The difference time between starting timing and stopping timing is determined as the hysteresis compensation factor β.

[0019] Furthermore, in the above method, the target air pressure value P(t) at the current moment of each finger air cavity in the corresponding passive glove is converted into the target air pressure value P(t) through the algorithm model, including:

[0020] In the experimental stage, the target pressure value P(t) of the air cavity under different bending angles is measured, and the target pressure value P(t) is imported into MATLAB for curve fitting to obtain a suitable initial k adaptive (t) value and b value.

[0021] Furthermore, in the above method, the target air pressure value P(t) at the current moment of each finger air cavity in the corresponding passive glove is converted into the target air pressure value P(t) through the algorithm model, including:

[0022] During the experimental stage, the actual feedback pressure value P under the delayed condition of air cavity inflation and deflation under different target pressure values ​​P(t-Δt) can be measured. feedback (t-Δt), the deviation data is P(t-Δt)-P feedback (t-Δt), input the gradient descent optimization algorithm to adjust the α value, wherein the actual feedback pressure value P at the previous moment t-Δt is obtained through the air pressure sensor installed in the connecting air path between the solenoid valve and the finger air cavity feedback (t-Δt).

[0023] Furthermore, in the above method, the microprocessor converts the current target air pressure value P(t) of each finger air cavity into an adjustment instruction of the air pump and the solenoid valve, and controls the opening or closing of the air pump and the solenoid valve based on the adjustment instruction, including:

[0024] The microprocessor MCU controls the electromagnetic valve of the corresponding finger air cavity to open based on the adjustment instruction, wherein each electromagnetic valve corresponds to a channel connected to a finger air cavity;

[0025] The microprocessor controls the air pump to increase or decrease pressure based on the adjustment instruction, so as to achieve the effect of inflating or deflating the air cavity of the finger;

[0026] The microprocessor detects the inflation or deflation of the finger air cavity through the air pressure sensor installed in the connecting air path between the solenoid valve and the finger air cavity. After the air pressure reaches the target value P(t), the microprocessor MCU controls the air pump to stop and close the corresponding solenoid valve.

[0027] According to another aspect of the present invention, there is further provided a computer-readable storage medium having computer-executable instructions stored thereon, wherein when the computer-executable instructions are executed by a processor, the processor is enabled to: perform any of the methods described above.

[0028] According to another aspect of the present invention, there is also provided a computer device, comprising:

[0029] Processor; and

[0030] A memory arranged to store computer executable instructions which, when executed, cause the processor to: a method as described in any one of the above.

[0031] Compared with the prior art, the present invention is used in the field of hand function rehabilitation, and aims to help patients perform functional movement training such as finger flexion and extension through a soft rehabilitation robot. The present invention is based on components such as a microprocessor, an air pump, a solenoid valve, and an air cavity, and is used to accurately control the air pressure of each finger to achieve precise flexion and extension movements during rehabilitation training. The present invention uses a simple linear function to directly convert the finger angle into an air pressure target, which simplifies the calculation process, improves the response speed and control accuracy of the system, and facilitates the adjustment of the conversion coefficient and offset according to the patient's condition. The present invention can dynamically adjust the proportional coefficient k based on the current air pressure of the air cavity fed back by the air pressure sensor. adaptive (t), so that the target air pressure value gradually approaches the optimal pressure range that meets the patient's needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a flow chart of a finger air path control method of a rehabilitation robot according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0034] In a typical configuration of the present application, the terminal, the device of the service network and the trusted party all include one or more processors (CPU), input / output interfaces, network interfaces and memories.

[0035] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0036] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include non-transitory media such as modulated data signals and carrier waves.

[0037] like Figure 1 As shown, the present invention provides a finger air path control method of a rehabilitation robot, wherein the rehabilitation robot comprises a passive glove and an active glove, and the method comprises: steps S1 to S4.

[0038] Step S1, setting each finger air cavity in the passive glove of the rehabilitation robot, connecting each finger air cavity to an air pump, setting a solenoid valve at each air path node between the air pump and each finger air cavity; connecting a microprocessor to the air pump and the solenoid valve respectively;

[0039] Here, in the present invention, the active glove is used to collect the finger gestures demonstrated by the user, and the passive glove is responsible for executing the actions corresponding to the demonstrated finger gestures;

[0040] Preferably, each finger air cavity can be respectively arranged in 5 finger sleeves of a glove body, each finger sleeve is provided with a frame and a finger air cavity, the frame is arranged outside the finger air cavity and is used to limit the radial expansion of the finger air cavity;

[0041] Here, the microprocessor can control the switching of the air pump and each solenoid valve to control the overall air system.

[0042] Air pump: provides a stable air source for the system.

[0043] Solenoid valve: It is an air path node between the air pump and each finger air cavity. It can control the on and off of the air flow by controlling the switch of the solenoid valve to ensure independent control of each finger air cavity.

[0044] Finger air cavity: The air cavity structure of each finger can deform under different air pressures to achieve bending and stretching, so movement can be achieved through changes in air pressure.

[0045] Step S2, the IMU sensor in the active glove collects the finger angle to be executed and sends it to the microprocessor;

[0046] Preferably, the IMU sensors in the active glove are arranged at the palm and fingertips of the five fingers of the active glove, and the IMU sensor integrates a three-axis accelerometer, a three-axis gyroscope and a three-axis magnetometer, wherein the three-axis accelerometer is used to obtain acceleration, the three-axis gyroscope is used to obtain angular velocity, and the three-axis magnetometer is used to obtain magnetic field strength; the obtained acceleration, angular velocity and magnetic field strength are filtered and subjected to a data fusion algorithm to obtain the bending angles of the five fingers, that is, the angles formed by the fingertips and palm of each finger of the active glove, that is, the finger angles to be executed.

[0047] Step S3, the microprocessor converts the target air pressure value P(t) of each finger air cavity in the corresponding passive glove at the current moment through an algorithm model according to the finger angle to be executed; wherein the algorithm model of the target air pressure value P(t) of the finger air cavity at the current moment is as follows:

[0048] P(t)=k adaptive (t)·θ(t-β)+b+α·(P(t-Δt)-P feedback (t-Δt)),

[0049] Among them, t represents the current moment, and t-Δt represents the previous moment;

[0050] P(t) represents the target air pressure value at the current moment;

[0051] k adaptive (t) is an adaptive proportional coefficient adjusted based on the feedback of the air pressure sensor; preferably, an air pressure sensor is installed in the connecting air path between the solenoid valve and the finger air cavity; preferably, k adaptive (t) is dynamically updated in every Δt cycle, and each Δt is a cycle. In the real-time control process, based on the feedback pressure P feedback The difference between (t-Δt) and the target pressure P(t) is k adaptive (t) Dynamic adjustment; wherein, an incremental adjustment algorithm is used, when the feedback pressure P feedback When (t-Δt) is less than the target pressure P(t), gradually increase k adaptive (t) to increase the air pressure; otherwise, k is gradually reduced adaptive (t). Here, k adaptive (t) is the adaptive proportional coefficient adjusted based on the pressure sensor feedback, so that the target pressure gradually approaches the optimal pressure range that meets the patient's needs.

[0052] β is the hysteresis compensation factor, θ(t+β) is the finger angle to be executed, where θ(t+β) represents the finger angle to be executed after the hysteresis compensation coefficient is introduced; the finger angle θ(t+β) to be executed is offset by β time from the finger angle θ(t) in the active glove at the current time t, that is, the finger angle θ(t+β) to be executed obtained by the microprocessor is the finger angle to be executed β time before the current time t; preferably, β can be determined by experiment, the target air pressure value P(t) is set, and each finger air cavity starts to be inflated according to the target air pressure value P(t), and the timing is started after the inflation is completed, and the timing is stopped after the finger air cavity stops deforming, and the difference time between the start timing and the stop timing is determined as the hysteresis compensation factor β. Here, the present application introduces an advance compensation θ(t-β) to the finger bending angle θ(t) in the active glove, so that the system considers the influence of the hysteresis of air cavity filling and discharging in advance, and reduces the hysteresis error caused by air cavity deformation. β is the hysteresis compensation coefficient, and its value is adjusted based on the characteristics of the air cavity material and the response delay. Through this advance amount β, the microprocessor can fine-tune the air pressure before the attitude changes, reducing the error caused by lag.

[0053] b is the initial air pressure offset. Preferably, in the experimental stage, the target air pressure value P(t) of the air cavity under different bending angles is measured, and the target air pressure value P(t) is imported into MATLAB for curve fitting to obtain a suitable initial k adaptive (t) value and b value.

[0054] P(t-Δt) represents the target pressure value at the previous time t-Δt, P feedback (t-Δt) is the actual feedback pressure value at the previous moment t-Δt;

[0055] α is the feedback correction factor, which is used to adjust the deviation according to P(t-Δt)-P feedback (t-Δt) to adjust the air pressure target, the deviation refers to P(t-Δt)-P feedback (t-Δt); Preferably, in the experimental stage, the actual feedback pressure value P under the delayed condition of the air cavity filling and deflation under different target pressure values ​​P(t-Δt) can be measured. feedback (t-Δt), the deviation data is P(t-Δt)-P feedback (t-Δt), input the gradient descent optimization algorithm to adjust the α value to minimize the actual feedback pressure value P feedback Preferably, the actual feedback pressure value P at the last moment t-Δt can be obtained by installing an air pressure sensor in the air path connecting the solenoid valve and the finger air cavity. feedback (t-Δt). Here, the correction term α·(P(t-Δt)-P feedback(t-Δt)), which compares the target pressure value P(t-Δt) at the previous moment with the actual feedback pressure value P feedback The deviation of (t-Δt) is used to adjust the target pressure value P(t) at the current moment in time. α is the feedback gain coefficient, which controls the response degree of the correction. The larger the α value, the faster the feedback correction, and the system can reach the target pressure more quickly. α is not the larger the better, and a suitable value should be taken, which can be determined through experiments.

[0056] In step S4, the microprocessor converts the current target air pressure value P(t) of each finger air cavity into an adjustment instruction for the air pump and the solenoid valve, and controls the opening or closing of the air pump and the solenoid valve based on the adjustment instruction; thereby achieving independent control of each air cavity to achieve independent bending and extension of the fingers.

[0057] Preferably, step S4 comprises:

[0058] Step S41, the microprocessor MCU controls the electromagnetic valve of the corresponding finger air cavity to open based on the adjustment instruction, wherein each electromagnetic valve corresponds to a channel connected to a finger air cavity;

[0059] Step S42, the microprocessor MCU controls the air pump to pressurize or depressurize based on the adjustment instruction, so as to achieve the effect of inflating or deflating the finger air cavity;

[0060] Step S43, the microprocessor MCU detects the inflation or deflation of the finger air cavity through the air pressure sensor installed in the connecting air path between the solenoid valve and the finger air cavity. After the air pressure reaches the target air pressure value P(t), the microprocessor MCU controls the air pump to stop and close the corresponding solenoid valve.

[0061] According to another aspect of the present invention, there is further provided a computer-readable storage medium having computer-executable instructions stored thereon, wherein when the computer-executable instructions are executed by a processor, the processor is enabled to: perform any of the methods described above.

[0062] According to another aspect of the present invention, there is also provided a computer device, comprising:

[0063] Processor; and

[0064] A memory arranged to store computer executable instructions which, when executed, cause the processor to: a method as described in any one of the above.

[0065] In summary, the present invention is used in the field of hand function rehabilitation, and aims to help patients perform functional movement training such as finger flexion and extension through a soft rehabilitation robot. The present invention can be based on components such as a microprocessor, an air pump, a solenoid valve, an air cavity, etc., to accurately control the air pressure of each finger to achieve precise flexion and extension movements during rehabilitation training. The present invention uses a simple linear function to directly convert the finger angle into an air pressure target, which simplifies the calculation process, improves the response speed and control accuracy of the system, and facilitates the adjustment of the conversion coefficient and offset according to the patient's condition. The present invention can dynamically adjust the proportional coefficient k based on the current air pressure of the air cavity fed back by the air pressure sensor. adaptive (t), so that the target air pressure value gradually approaches the optimal pressure range that meets the patient's needs.

[0066] The detailed contents of the device embodiments of the present invention can be found in the corresponding parts of the method embodiments, which will not be described in detail here.

[0067] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0068] It should be noted that the present invention can be implemented in software and / or a combination of software and hardware, for example, can be implemented using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present invention can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present invention (including related data structures) can be stored in a computer readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and the like. In addition, some steps or functions of the present invention can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0069] In addition, a part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. The program instruction for calling the method of the present invention may be stored in a fixed or removable recording medium, and / or transmitted through a data stream in a broadcast or other signal-bearing medium, and / or stored in a working memory of a computer device that runs according to the program instruction. Here, according to an embodiment of the present invention, a device is included, the device including a memory for storing computer program instructions and a processor for executing program instructions, wherein, when the computer program instruction is executed by the processor, the device is triggered to run the method and / or technical solution based on the aforementioned multiple embodiments of the present invention.

[0070] It is obvious to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A finger air path control method for a rehabilitation robot, characterized in that: The rehabilitation robot comprises a passive glove and an active glove, and the method comprises: Each finger air cavity is set in the passive glove of the rehabilitation robot, each finger air cavity is connected to an air pump, and a solenoid valve is set at each air path node between the air pump and each finger air cavity; a microprocessor is connected to the air pump and the solenoid valve respectively; and an air pressure sensor is installed in the connecting air path between the solenoid valve and the finger air cavity; The IMU sensor in the active glove collects the finger angles to be executed and sends them to the microprocessor; The microprocessor converts the finger angle to be executed into the target air pressure value P(t) of each finger air cavity in the corresponding passive glove at the current moment through an algorithm model; wherein the algorithm model of the target air pressure value P(t) of the finger air cavity at the current moment is as follows: P(t)=k adaptive (t)·θ(t-β)+b+α·(P(t-Δt)-P feedback (t-Δt)), Where t represents the current time, t-Δt represents the previous time; P(t) represents the target pressure value at the current time; k adaptive (t) is the adaptive proportional coefficient adjusted based on the pressure sensor feedback; β is the hysteresis compensation factor, θ(t+β) is the finger angle to be executed, where θ(t+β) represents the finger angle to be executed after the hysteresis compensation coefficient is introduced; b is the initial pressure offset; P(t-Δt) represents the target pressure value at the previous moment t-Δt, P feedback (t-Δt) is the actual feedback pressure value at the previous moment t-Δt; α is the feedback correction factor, which is used to calculate the pressure according to the deviation, that is, P(t-Δt)-P feedback (t-Δt) to adjust the air pressure target, the deviation refers to P(t-Δt)-P feedback (t-Δt); The microprocessor converts the current target air pressure value P(t) of each finger air cavity into an adjustment instruction for the air pump and the solenoid valve, and controls the opening or closing of the air pump and the solenoid valve based on the adjustment instruction.

2. The finger air path control method of the rehabilitation robot according to claim 1, characterized in that: Each finger air cavity is set in the passive glove of the rehabilitation robot, including: Each finger air cavity can be respectively arranged in 5 finger sleeves of a glove body, each finger sleeve is provided with a frame and a finger air cavity, the frame is arranged outside the finger air cavity and is used to limit the radial expansion of the finger air cavity.

3. The finger air path control method of the rehabilitation robot according to claim 1, characterized in that: The IMU sensor in the active glove collects the finger angles to be executed and sends them to the microprocessor, including: The IMU sensor in the active glove is set at the palm and fingertips of the active glove. The IMU sensor integrates a three-axis accelerometer, a three-axis gyroscope and a three-axis magnetometer, wherein the three-axis accelerometer is used to obtain acceleration, the three-axis gyroscope is used to obtain angular velocity, and the three-axis magnetometer is used to obtain magnetic field strength; the obtained acceleration, angular velocity and magnetic field strength are filtered and subjected to data fusion algorithm to obtain the bending angle of the five fingers, that is, the angle formed by the fingertips and palm of each finger of the active glove.

4. The finger air path control method of the rehabilitation robot according to claim 1, characterized in that: The target air pressure value P(t) of each finger air cavity in the corresponding passive glove at the current moment is converted into the algorithm model, including: In the real-time control process, based on the feedback pressure P feedback The difference between (t-Δt) and the target pressure P(t) is k adaptive (t) Dynamic adjustment; wherein, an incremental adjustment algorithm is used, when the feedback pressure P feedback When (t-Δt) is less than the target pressure P(t), gradually increase k adaptive (t) to increase the air pressure; otherwise, k is gradually reduced adaptive (t).

5. The finger air path control method of the rehabilitation robot according to claim 1, characterized in that: The target air pressure value P(t) of each finger air cavity in the corresponding passive glove at the current moment is converted into the algorithm model, including: Determine β through experiments, set the target air pressure value P(t), start to inflate the air cavities of each finger according to the target air pressure value P(t), start timing after the inflation is completed, and stop timing after observing that the finger air cavity stops deforming. The difference time between starting timing and stopping timing is determined as the hysteresis compensation factor β.

6. The finger air path control method of the rehabilitation robot according to claim 1, characterized in that: The target air pressure value P(t) of each finger air cavity in the corresponding passive glove at the current moment is converted into the algorithm model, including: In the experimental stage, the target pressure value P(t) of the air cavity under different bending angles is measured, and the target pressure value P(t) is imported into MATLAB for curve fitting to obtain a suitable initial k adaptive (t) value and b value.

7. The finger air path control method of the rehabilitation robot according to claim 1, characterized in that: The target air pressure value P(t) of each finger air cavity in the corresponding passive glove at the current moment is converted into the algorithm model, including: During the experimental stage, the actual feedback pressure value P under the delayed condition of air cavity inflation and deflation under different target pressure values ​​P(t-Δt) can be measured. feedback (t-Δt), the deviation data is P(t-Δt)-P feedback (t-Δt), input the gradient descent optimization algorithm to adjust the α value, wherein the actual feedback pressure value P at the previous moment t-Δt is obtained through the air pressure sensor installed in the connecting air path between the solenoid valve and the finger air cavity feedback (t-Δt).

8. The finger air path control method of a rehabilitation robot as claimed in claim 1, characterized in that: The microprocessor converts the current target air pressure value P(t) of each finger air cavity into an adjustment instruction for the air pump and the solenoid valve, and controls the opening or closing of the air pump and the solenoid valve based on the adjustment instruction, including: The microprocessor MCU controls the electromagnetic valve of the corresponding finger air cavity to open based on the adjustment instruction, wherein each electromagnetic valve corresponds to a channel connected to a finger air cavity; The microprocessor controls the air pump to increase or decrease pressure based on the adjustment instruction, so as to achieve the effect of inflating or deflating the air cavity of the finger; The microprocessor detects the inflation or deflation of the finger air cavity through the air pressure sensor installed in the connecting air path between the solenoid valve and the finger air cavity. After the air pressure reaches the target value P(t), the microprocessor MCU controls the air pump to stop and close the corresponding solenoid valve.

9. A computer-readable storage medium having computer-executable instructions stored thereon, wherein: When the computer executable instructions are executed by a processor, the processor causes the processor to: perform the method according to any one of claims 1 to 8.

10. A computer device, wherein: include: processor; as well as A memory arranged to store computer executable instructions which, when executed, cause the processor to: a method as claimed in any one of claims 1 to 8.

Images