Regulation method and device for finger air path of rehabilitation robot

Abstract

According to the adjusting method and device for the finger air path of the rehabilitation robot, a simple linear function is adopted, the finger angle is directly converted into an air pressure target, the calculation process is simplified, the response speed and the control precision of a system are improved, and meanwhile the conversion coefficient and the offset can be conveniently adjusted according to the condition of a patient; the active glove is used for collecting finger postures of a user, the passive glove is responsible for executing corresponding actions, and the passive glove can further monitor the accuracy of action execution through the IMU sensor. The cooperation mechanism of the double gloves effectively improves the effect of rehabilitation training. The posture of the fingers in the active glove and the passive glove is obtained through the IMU sensor, the host control unit can accurately control the flexion and extension action of each finger in the passive glove, and efficient rehabilitation training is achieved. The host control unit can automatically adjust control parameters according to the hand movement ability of the rehabilitative person and dynamically adjust the bending angle and the air pressure of each finger, so that the training process is more personalized and efficient.

Description

Technical Field

[0001] The invention relates to a method and equipment for adjusting finger air paths of a rehabilitation robot. Background Art

[0002] In the prior art, some pneumatic rehabilitation robots can achieve finger flexion and extension through a predetermined control strategy. However, existing products often have the following shortcomings:

[0003] Open-loop control lacks precision: Many traditional rehabilitation devices control air pressure changes based on simple time or force feedback, lacking accurate capture of the actual finger posture, resulting in limited training effects.

[0004] Lack of personalization: Existing equipment usually fails to make adaptive adjustments based on the patient's real-time rehabilitation status. The flexibility of the rehabilitation process is poor, making it difficult to implement personalized rehabilitation plans.

[0005] Large size and inconvenient to wear: Some existing products rely on external equipment for posture capture and airway control. The overall system is relatively bulky, affecting the patient's wearing comfort and autonomous rehabilitation ability. Summary of the invention

[0006] The purpose of the present invention is to provide a method and device for adjusting the finger air path of a rehabilitation robot.

[0007] In order to solve the above problems, the present invention provides a method for adjusting the finger air path of a rehabilitation robot, wherein the rehabilitation robot comprises a passive glove and an active glove, and the method comprises:

[0008] Each finger air cavity is provided in the passive glove, each finger air cavity is connected to an air pump, and a solenoid valve is provided at each air path node between the air pump and each finger air cavity; a host control unit 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;

[0009] IMU sensor data collection and finger posture calculation in active gloves: The IMU sensor in the active gloves collects the posture and bending angle of each finger in real time, and transmits the posture and bending angle of each finger to the host control unit through the communication module;

[0010] The host control unit obtains the target air pressure value of each finger air cavity of the corresponding passive glove based on the posture and bending angle of each finger of the active glove;

[0011] Furthermore, in the above method, the host control unit obtains the target air pressure value of each finger air cavity of the corresponding passive glove based on the posture and bending angle of each finger of the active glove, including:

[0012] The host control unit calculates based on the posture data and bending angle of each finger of the active glove to obtain the angle formed by the fingertip and the palm of each finger of the active glove;

[0013] The host control unit converts the angle formed by the fingertip and palm of each finger of the active glove into the target air pressure value of each finger air cavity of the corresponding passive glove;

[0014] The host control unit controls the solenoid valve and air pump in the passive glove according to the target air pressure value to inflate or deflate the finger air cavity of the passive glove.

[0015] Furthermore, in the above method, the host control unit converts the angle formed by the fingertip and the palm of each finger of the active glove into the target air pressure value of each finger air cavity of the corresponding passive glove, including:

[0016] The host control unit is based on a linear function: air pressure = angle formed by the fingertip and palm of a finger of the active glove × adaptive proportional coefficient + initial air pressure offset, and converts the angle formed by the fingertip and palm of each finger into a target air pressure value of each finger air cavity of the corresponding passive glove.

[0017] Furthermore, in the above method, the linear function: air pressure = angle × adaptive proportional coefficient + offset is the following linear conversion formula:

[0018] P(t)=k adaptive (t)·θ(t-β)+b+α·(P(t-Δt)-P feedback (t-Δt)),

[0019] 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 feedback of the air pressure sensor; β is the hysteresis compensation factor, θ(t+β) is the angle between the fingertip and the palm of a finger of the active glove, where θ(t+β) represents the finger angle to be executed after the hysteresis compensation coefficient is introduced; b is the initial air pressure offset; P(t-Δt) represents the target air 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).

[0020] Furthermore, in the above method, the host control unit converts the angle formed by the fingertip and the palm of each finger of the active glove into the target air pressure value of each finger air cavity of the corresponding passive glove, including:

[0021] Obtain patient assessment results, including: rehabilitation stage, rehabilitation goals and individual needs;

[0022] The host control unit sets the angle range formed by the air cavity of each finger and the palm of the passive glove based on the evaluation result, and sets the adaptive proportional coefficient and initial air pressure offset of the linear conversion formula based on the angle range;

[0023] The host control unit obtains the target air pressure value of each finger air cavity of the passive glove based on the adaptive proportional coefficient of the set linear conversion formula and the initial air pressure offset.

[0024] Furthermore, in the above method, after the host control unit controls the solenoid valve and the air pump in the passive glove according to the target air pressure value to inflate or deflate the finger air cavity of the passive glove, the method further includes:

[0025] During the training process, the host control unit can collect the activity of each finger air cavity of the passive glove worn by the patient in real time, monitor the movement performance of each finger, and further adjust the adaptive proportional coefficient and initial air pressure offset of the linear conversion formula based on the activity of each finger air cavity, including:

[0026] The host control unit obtains the angle formed by the fingertip and the palm of each finger air cavity, i.e., the bending angle, through the IMU sensor of the passive glove; obtains the actual feedback air pressure value through the air pressure sensor of the passive glove; and analyzes the smoothness of the movement of each finger air cavity through the IMU sensor of the passive glove, including the analysis of the angle range and movement speed;

[0027] The host control unit further adjusts the adaptive proportional coefficient and the initial air pressure offset of the linear conversion formula based on the bending angle, the actual feedback air pressure value and the smoothness;

[0028] The host control unit obtains a new target air pressure value of each finger air cavity of the passive glove based on the adaptive proportional coefficient of the adjusted linear conversion formula and the initial air pressure offset.

[0029] Furthermore, in the above method, after the host control unit controls the solenoid valve and the air pump in the passive glove according to the target air pressure value to inflate or deflate the finger air cavity of the passive glove, the method further includes:

[0030] The host control unit controls the air cavity of the finger of the passive glove to inflate or deflate. At the same time, the air pressure sensor of the passive glove monitors the actual feedback air pressure value of the finger air cavity in real time. The host control unit performs real-time closed-loop adjustment of the target air pressure value based on the linear conversion formula and the actual feedback air pressure value.

[0031] The host control unit detects the real-time bending angle and movement state of the passive glove through the IMU sensor carried in the passive glove, and further adjusts the target air pressure value of each finger air cavity of the passive glove based on the real-time bending angle and movement state of the passive glove.

[0032] Furthermore, in the above method, after the host control unit controls the solenoid valve and the air pump in the passive glove according to the target air pressure value to inflate or deflate the finger air cavity of the passive glove, the method further includes:

[0033] The host control unit detects the actual bending angle of each air cavity of the passive glove in real time through the IMU sensor carried in the passive glove. If the error value between the actual bending angle and the target bending angle is greater than the preset threshold, the host control unit dynamically adjusts the target air pressure value based on the Kalman filter fusion result of the IMU data of the passive glove and the air pressure sensor data.

[0034] 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 caused to: execute any of the methods described above.

[0035] According to another aspect of the present invention, there is also provided a computer device, comprising:

[0036] Processor; and

[0037] A memory arranged to store computer executable instructions, which when executed cause the processor to: perform any of the methods described above.

[0038] Compared with the prior art, the present invention adopts 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 is convenient for adjusting the conversion coefficient and offset according to the patient's condition. The active gloves of the present invention are used to collect the user's finger posture, and the passive gloves are responsible for performing the corresponding actions, and the passive gloves can further monitor the accuracy of the executed actions through the IMU sensor. This double-glove synergy mechanism effectively improves the effect of rehabilitation training. The present invention obtains the posture of the fingers in the active and passive gloves through the IMU sensor, and the host control unit can accurately control the flexion and extension of each finger in the passive glove to achieve efficient rehabilitation training. The host control unit can automatically adjust the control parameters according to the hand activity ability of the rehabilitator, and dynamically adjust the bending angle and air pressure of each finger, making the training process more personalized and efficient.

[0039] In addition, the host control unit can combine the air pressure sensor with the IMU data to achieve precise air pressure regulation and finger posture control, thereby improving the safety and stability of rehabilitation training. Through dual feedback from the air pressure sensor and the IMU sensor, the system can adjust the air path control strategy in real time according to the actual posture and air pressure of the finger, ensuring that the finger flexion and extension movements are accurately matched with the patient's intentions, avoiding instability problems in the open-loop system. The present invention is flexible in design, and can adjust the range of motion and strength according to the rehabilitation needs of different patients. It can be adaptively adjusted through software algorithms, and can be widely used in rehabilitation training after hand injuries. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a flow chart of a method for adjusting the finger air path of a rehabilitation robot according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] like Figure 1 As shown, the present invention provides a method for adjusting the finger air path of a rehabilitation robot, wherein the rehabilitation robot includes a passive glove and an active glove, and the method includes:

[0046] Step S1, setting each finger air cavity in the passive glove, 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 the host control unit to the air pump and the solenoid valve respectively; installing an air pressure sensor in the connecting air path between the solenoid valve and the finger air cavity;

[0047] 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;

[0048] 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;

[0049] Here, the host control unit can control the switch of the air pump and each solenoid valve to control the overall air system.

[0050] Air pump: provides a stable air source for the system.

[0051] 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.

[0052] 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.

[0053] Step S2, IMU sensor data collection and finger posture calculation in the active glove: The IMU sensor in the active glove collects the posture and bending angle of each finger in real time, and transmits the posture and bending angle of each finger to the host control unit through the communication module;

[0054] Here, the patient's intention input can be realized through the IMU sensor of the active glove, and the host control unit will track the angle of each finger of the healthy hand; the host control unit will then detect the angle change of the active glove in real time, and compare it with the current air pressure of the passive glove to decide whether to control inflation or deflation;

[0055] 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.

[0056] Step S3: The host control unit obtains the target air pressure value of each finger air cavity of the corresponding passive glove based on the posture and bending angle of each finger of the active glove:

[0057] Step S31, the host control unit performs calculation based on the posture data and bending angle of each finger of the active glove to obtain the angle formed by the fingertip and the palm of each finger of the active glove;

[0058] Step S32, the host control unit converts the angle formed by the fingertip and the palm of each finger of the active glove into a target air pressure value of each finger air cavity of the corresponding passive glove, so as to subsequently determine the inflation and deflation volume of each finger air cavity of the passive glove based on the target air pressure value;

[0059] Preferably, the host control unit converts the angle formed by the fingertip and palm of each finger into a target air pressure value of each finger air cavity of the corresponding passive glove based on a linear function air pressure = angle formed by the fingertip and palm of a finger of the active glove × adaptive proportional coefficient + initial air pressure offset.

[0060] A better linear function is: air pressure = angle × adaptive proportional coefficient + offset, which is the following linear conversion formula:

[0061] P(t)=k adaptive (t)·θ(t-β)+b+α·(P(t-Δt)-Pfeedback (t-Δt)),

[0062] 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 feedback of the air pressure sensor; β is the hysteresis compensation factor, θ(t+β) is the angle between the fingertip and the palm of a finger of the active glove, where θ(t+β) represents the finger angle to be executed after the hysteresis compensation coefficient is introduced; b is the initial air pressure offset; P(t-Δt) represents the target air 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).

[0063] Preferably, an air pressure sensor can be installed in the air path connecting 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.

[0064] 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 host control unit 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 degassing 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 host control unit can fine-tune the air pressure before the attitude changes, reducing the error caused by lag.

[0065] 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.

[0066] 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;

[0067] 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.

[0068] Here, the parameters of the linear conversion formula can be flexibly adjusted according to the patient's rehabilitation needs to ensure that the air cavity pressure is consistent with the target posture of the finger.

[0069] Specifically, it can be achieved by flexibly adjusting the adaptive proportional coefficient of the linear conversion formula and the initial air pressure offset according to the patient's specific conditions, such as the degree of hand function recovery, rehabilitation training plan, etc.

[0070] Step S321, obtaining the patient's assessment results, including: rehabilitation stage, rehabilitation goals and personalized needs;

[0071] Here, before the patient wears the passive gloves and starts training, the patient's hand function can be evaluated, the patient's rehabilitation stage (such as mild, moderate, and severe impairment) and rehabilitation goals (such as enhancing finger flexion and extension movements, improving grip strength, etc.) can be understood, and the patient's personalized needs can be collected, such as the maximum range of motion of the fingers, rehabilitation progress, etc.

[0072] Step S322, the host control unit sets the angle range formed by the air cavity hand and the palm of each finger of the passive glove based on the evaluation result, and sets the adaptive proportional coefficient and the initial air pressure offset of the linear conversion formula based on the angle range, so that the passive glove can generate an appropriate air pressure target value. For example, if the patient is in the early stage of rehabilitation, a smaller angle range and a lower adaptive ratio are set; in the late stage of rehabilitation, a larger angle range and a higher adaptive ratio can be set. More preferably, for some special cases, such as in the early stage of rehabilitation or for some patients (such as arthritis patients), excessive flexion and extension may cause discomfort or injury. The maximum air pressure limit and the maximum angle limit can also be set to ensure that the fingers do not exceed the safety range during training.

[0073] Here, different rehabilitation modes can be selected according to the patient's specific rehabilitation goals, such as restoring flexion and extension movements (focusing on flexion and extension movements, setting the air pressure range), and enhancing grip strength (improving grip ability by increasing the coordinated movement of the thumb and other fingers).

[0074] Step S323, the host control unit obtains the target air pressure value of each finger air cavity of the passive glove based on the set adaptive proportional coefficient of the linear conversion formula and the initial air pressure offset;

[0075] Step S4, air circuit closed-loop control and regulation: the host control unit controls the solenoid valve and air pump in the passive glove according to the target air pressure value, and inflates or deflates the finger air cavity of the passive glove to drive the flexion and extension movement of the finger.

[0076] Preferably, step S4 includes:

[0077] Step S41, the host control unit controls the corresponding solenoid valve of the finger air cavity to open based on the target air pressure value, wherein each solenoid valve corresponds to a channel connected to a finger air cavity;

[0078] Step S42, the host control unit controls the air pump to pressurize or depressurize based on the target air pressure value, so as to achieve the effect of inflating or deflating the finger air cavity;

[0079] Step S43, the host control unit detects that the finger air cavity is inflated or deflated to reach the target air pressure value through the air pressure sensor installed in the connecting air path between the solenoid valve and the finger air cavity, and then controls the air pump to stop and close the corresponding solenoid valve.

[0080] Preferably, after step S4, the following steps may also be included:

[0081] Step S5, during the training process, the host control unit can collect the activity of each finger air cavity of the passive glove worn by the patient in real time, monitor the movement performance of each finger, and further adjust the adaptive proportional coefficient and initial air pressure offset of the linear conversion formula based on the activity of each finger air cavity, including:

[0082] Step S51, the host control unit obtains the angle formed by the fingertip and the palm of each finger air cavity, i.e., the bending angle, through the IMU sensor of the passive glove; obtains the actual feedback air pressure value through the air pressure sensor of the passive glove; and analyzes the smoothness of the movement of each finger air cavity through the IMU sensor of the passive glove, including analyzing the angle range and movement speed;

[0083] Step S52, the host control unit further adjusts the adaptive proportional coefficient of the linear conversion formula and the initial air pressure offset based on the bending angle, the actual feedback air pressure value and the smoothness;

[0084] Step S53: the host control unit obtains a new target air pressure value of each finger air cavity of the passive glove based on the adaptive proportional coefficient of the adjusted linear conversion formula and the initial air pressure offset.

[0085] For example, in the early stages of rehabilitation, if the patient's finger range of motion is small and the flexion and extension ability is weak, when the bending angle is detected to be insufficient and the speed is slow, the target air pressure can be lowered and a smaller air pressure range can be set. The system will reduce the coefficient and offset in the conversion formula to prevent the patient from feeling uncomfortable due to excessive training intensity. If in the later stages of rehabilitation, the patient's finger function is close to normal, when the system detects a large angle range and normal speed, it will automatically increase the air pressure target to increase the intensity of the finger flexion and extension exercise, ensuring that the maximum flexion and extension ability of the finger is restored.

[0086] After step S4, the following steps may also be included:

[0087] In step S6, the host control unit controls the finger air cavity of the passive glove to inflate or deflate. At the same time, the actual feedback air pressure value of the finger air cavity is monitored in real time through the air pressure sensor of the passive glove. The host control unit performs real-time closed-loop adjustment on the target air pressure value based on the linear conversion formula and the actual feedback air pressure value to ensure the accurate movement of the finger air cavity of the passive glove.

[0088] Here, the air pressure sensor of the passive glove can detect the air pressure in the finger air cavity in real time. After receiving the angle data of the active glove, the host control unit can convert it into the target air pressure and compare it with the current air pressure output by the air pressure sensor to decide whether to inflate or deflate. During the inflation or deflation process, the air pressure sensor is also in real-time detection. Once the target air pressure is reached, the air pump and solenoid valve are turned off.

[0089] After step S4, the method further includes:

[0090] Step S7, auxiliary posture monitoring of passive gloves: the host control unit detects the real-time bending angle and movement state of the passive gloves through the IMU sensor carried in the passive gloves, and further adjusts the target air pressure value of each finger air cavity of the passive gloves based on the real-time bending angle and movement state of the passive gloves.

[0091] Here, the IMU sensor carried in the passive glove can be used as an auxiliary monitoring device to verify the actual movement of the fingers, which can further improve the control accuracy.

[0092] The IMU sensor in the glove can detect the specific bending angle and motion state of the passive glove in real time. Due to the influence of factors such as the software structure and airflow delay, the actual air pressure may deviate from the target air pressure. The angle information provided by the IMU sensor can be used as a control accuracy compensation near the target air pressure. For example, if the target angle is 120° and the actual angle is 130°, the host control unit can correct the error by adjusting the target air pressure.

[0093] Preferably, the IMU sensor in the passive glove is arranged at the palm and fingertips of the five fingers of the passive 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 angle of the five fingers, that is, the angle formed by the fingertips and the palm of the air cavity of each finger of the passive glove, that is, the finger angle to be executed.

[0094] After step S4, the following steps may also be included:

[0095] In step S8, the host control unit detects the actual bending angle of each air cavity of the passive glove in real time through the IMU sensor carried in the passive glove. If the error value between the actual bending angle and the target bending angle is greater than a preset threshold, the host control unit dynamically adjusts the target air pressure value based on the Kalman filter fusion result of the IMU data of the passive glove and the air pressure sensor data.

[0096] Here, during the training process, if the error value between the actual bending angle of the passive glove and the target bending angle is greater than the preset threshold after reaching the target air pressure, the system will trigger the air pressure adjustment process. The host control unit dynamically adjusts the air pressure target based on the Kalman filter fusion results of the IMU data of the passive glove and the air pressure sensor data. The host control unit makes the movement of the finger reach a precise bending angle through repeated adjustments and corrections. The air pressure sensor and IMU sensor ensure the refinement of control through continuous feedback compensation. At the end of the training, the host control unit ensures that the finger is in a safe posture position through feedback from the air pressure sensor and IMU sensor, such as the finger air cavity is completely deflated and the finger is in a naturally bent position.

[0097] Through dual feedback from the air pressure sensor and IMU sensor, the host control unit can adjust the air path control strategy in real time according to the actual finger posture and air pressure, ensuring that the finger flexion and extension movements accurately match the patient's intentions and avoiding instability problems in the open-loop system.

[0098] During the training process, the host control unit can use the data from the passive glove's IMU sensor and air pressure sensor as real-time feedback, and continuously adjust the target air pressure to accurately control the passive glove's finger posture so that the patient's intentions and actual movements always match.

[0099] In summary, the present invention adopts 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 is convenient for adjusting the conversion coefficient and offset according to the patient's condition. The active gloves of the present invention are used to collect the user's finger posture, and the passive gloves are responsible for performing the corresponding actions, and the passive gloves can further monitor the accuracy of the executed actions through the IMU sensor. This double-glove synergy mechanism effectively improves the effect of rehabilitation training. The present invention obtains the posture of the fingers in the active and passive gloves through the IMU sensor, and the host control unit can accurately control the flexion and extension of each finger in the passive glove to achieve efficient rehabilitation training. The host control unit can automatically adjust the control parameters according to the hand activity ability of the rehabilitator, and dynamically adjust the bending angle and air pressure of each finger, making the training process more personalized and efficient.

[0100] In addition, the host control unit can combine the air pressure sensor with the IMU data to achieve precise air pressure regulation and finger posture control, thereby improving the safety and stability of rehabilitation training. Through dual feedback from the air pressure sensor and the IMU sensor, the system can adjust the air path control strategy in real time according to the actual posture and air pressure of the finger, ensuring that the finger flexion and extension movements are accurately matched with the patient's intentions, avoiding instability problems in the open-loop system. The present invention is flexible in design, and can adjust the range of motion and strength according to the rehabilitation needs of different patients. It can be adaptively adjusted through software algorithms, and can be widely used in rehabilitation training after hand injuries.

[0101] In addition, the present invention applies IMU sensors, uses miniaturized sensors, does not require flexible potentiometers or external optical equipment, has strong resistance to environmental interference, is easy to use in mobile scenarios, and is suitable for rehabilitation robots' requirements for comfort, portability, and low cost.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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 method for adjusting the finger air path of 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 provided in the passive glove, each finger air cavity is connected to an air pump, and a solenoid valve is provided at each air path node between the air pump and each finger air cavity; a host control unit 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; IMU sensor data collection and finger posture calculation in active gloves: The IMU sensor in the active gloves collects the posture and bending angle of each finger in real time, and transmits the posture and bending angle of each finger to the host control unit through the communication module; The host control unit obtains the target air pressure value of each finger air cavity of the corresponding passive glove based on the posture and bending angle of each finger of the active glove.

2. The method for adjusting the finger air path of a rehabilitation robot according to claim 1, characterized in that: The host control unit obtains the target air pressure value of each finger air cavity of the corresponding passive glove based on the posture and bending angle of each finger of the active glove, including: The host control unit performs calculation based on the posture data and bending angle of each finger of the active glove to obtain the angle formed by the fingertip and the palm of each finger of the active glove; The host control unit converts the angle formed by the fingertip and palm of each finger of the active glove into the target air pressure value of each finger air cavity of the corresponding passive glove; The host control unit controls the solenoid valve and air pump in the passive glove according to the target air pressure value to inflate or deflate the finger air cavity of the passive glove.

3. The method for adjusting the finger air path of a rehabilitation robot according to claim 2, characterized in that: The host control unit converts the angle formed by the fingertip and palm of each finger of the active glove into the target air pressure value of each finger air cavity of the corresponding passive glove, including: The host control unit is based on a linear function: air pressure = angle formed by the fingertip and palm of a finger of the active glove × adaptive proportional coefficient + initial air pressure offset, and converts the angle formed by the fingertip and palm of each finger into a target air pressure value of each finger air cavity of the corresponding passive glove.

4. The method for adjusting the finger air path of a rehabilitation robot according to claim 3, characterized in that: Linear function: Air pressure = angle × adaptive proportional coefficient + offset, which is the following linear conversion formula: 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 feedback of the air pressure sensor; β is the hysteresis compensation factor, θ(t+β) is the angle between the fingertip and the palm of a finger of the active glove, where θ(t+β) represents the finger angle to be executed after the hysteresis compensation coefficient is introduced; b is the initial air pressure offset; P(t-Δt) represents the target air 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).

5. The method for adjusting the finger air path of a rehabilitation robot according to claim 4, characterized in that: The host control unit converts the angle formed by the fingertip and palm of each finger of the active glove into the target air pressure value of each finger air cavity of the corresponding passive glove, including: Obtain patient assessment results, including: rehabilitation stage, rehabilitation goals and individual needs; The host control unit sets the angle range formed by the air cavity of each finger and the palm of the passive glove based on the evaluation result, and sets the adaptive proportional coefficient and initial air pressure offset of the linear conversion formula based on the angle range; The host control unit obtains the target air pressure value of each finger air cavity of the passive glove based on the adaptive proportional coefficient of the set linear conversion formula and the initial air pressure offset.

6. The method for adjusting the finger air path of a rehabilitation robot according to claim 4, characterized in that: The host control unit controls the solenoid valve and the air pump in the passive glove according to the target air pressure value, and after inflating or deflating the finger air cavity of the passive glove, it also includes: During the training process, the host control unit can collect the activity of each finger air cavity of the passive glove worn by the patient in real time, monitor the movement performance of each finger, and further adjust the adaptive proportional coefficient and initial air pressure offset of the linear conversion formula based on the activity of each finger air cavity, including: The host control unit obtains the angle formed by the fingertip and the palm of each finger air cavity, i.e., the bending angle, through the IMU sensor of the passive glove; obtains the actual feedback air pressure value through the air pressure sensor of the passive glove; and analyzes the smoothness of the movement of each finger air cavity through the IMU sensor of the passive glove, including the analysis of the angle range and movement speed; The host control unit further adjusts the adaptive proportional coefficient and the initial air pressure offset of the linear conversion formula based on the bending angle, the actual feedback air pressure value and the smoothness; The host control unit obtains a new target air pressure value of each finger air cavity of the passive glove based on the adaptive proportional coefficient of the adjusted linear conversion formula and the initial air pressure offset.

7. The method for adjusting the finger air path of a rehabilitation robot according to claim 4, characterized in that: The host control unit controls the solenoid valve and the air pump in the passive glove according to the target air pressure value, and after inflating or deflating the finger air cavity of the passive glove, it also includes: The host control unit controls the air cavity of the finger of the passive glove to inflate or deflate. At the same time, the air pressure sensor of the passive glove monitors the actual feedback air pressure value of the finger air cavity in real time. The host control unit performs real-time closed-loop adjustment of the target air pressure value based on the linear conversion formula and the actual feedback air pressure value. The host control unit detects the real-time bending angle and movement state of the passive glove through the IMU sensor carried in the passive glove, and further adjusts the target air pressure value of each finger air cavity of the passive glove based on the real-time bending angle and movement state of the passive glove.

8. The method for adjusting the finger air path of a rehabilitation robot according to claim 1, characterized in that: The host control unit controls the solenoid valve and the air pump in the passive glove according to the target air pressure value, and after inflating or deflating the finger air cavity of the passive glove, it also includes: The host control unit detects the actual bending angle of each finger air cavity of the passive glove in real time through the IMU sensor carried in the passive glove. If the error value between the actual bending angle and the target bending angle is greater than the preset threshold, the host control unit dynamically adjusts the target air pressure value based on the Kalman filter fusion result of the IMU data of the passive glove and the air pressure sensor data.

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 is caused 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: perform a method as claimed in any one of claims 1 to 8.

Images