Control method for hybrid drive lower limb rehabilitation training system

Abstract

The present disclosure provides a control method for a hybrid drive lower limb rehabilitation training system. The method includes: determining a target trajectory error factor based on the rotation angle of a target joint in a target training part at the current moment; determining a target muscle fatigue factor based on the electromyographic signal of a target muscle in the target training part at the current moment; determining a target interaction force factor based on the human-machine interaction force between an exoskeleton robot and the target training part at the current moment; inputting the target trajectory error factor, the target muscle fatigue factor, and the target interaction force factor into a control model to obtain a target electrical stimulation signal of an electrical stimulation module and a target output torque of a motor module; and controlling the motor module to drive the exoskeleton robot to move based on the target motor output torque to drive the target training part to move, and controlling the electrical stimulation module to send a target electrical stimulation signal to the target muscle to drive the target training part to move.

Description

Technical Field

[0001] The present disclosure relates to the field of exoskeleton robot rehabilitation, and in particular to a control method for a hybrid drive lower limb rehabilitation training system. Background Art

[0002] Doctors and patients can use the lower limb rehabilitation training system to perform lower limb rehabilitation training by using a hybrid drive method of exoskeleton robots and functional electrical stimulation. Driving the patient's lower limb movement with an exoskeleton robot can achieve functional movement of the patient's lower limbs. Driving the patient's lower limb movement with functional electrical stimulation can improve or restore the function of the patient's lower limb muscle groups.

[0003] However, the related control method for the lower limb rehabilitation training system is difficult to adapt to more complex movement situations, and in the process of using the control method for rehabilitation training, there are shortcomings such as low system control accuracy and easy to cause muscle fatigue. Summary of the invention

[0004] In order to at least partially overcome the technical defects of at least one or other inventions mentioned above, at least one embodiment of the present disclosure provides a control method for a hybrid-driven lower limb rehabilitation training system, which can improve the system control accuracy during rehabilitation training and delay the occurrence of muscle fatigue.

[0005] In view of this, an embodiment of the present disclosure provides a control method for a hybrid-driven lower limb rehabilitation training system, the hybrid-driven lower limb rehabilitation training system comprising an exoskeleton robot, a motor module and an electrical stimulation module, characterized in that the method comprises: determining a target trajectory error factor based on the rotation angle of a target joint in a target training part at a current moment; determining a target muscle fatigue factor based on the electromyographic signal of a target muscle in the target training part at a current moment; determining a target interaction force factor based on the human-computer interaction force between the exoskeleton robot and the target training part at a current moment; inputting the target trajectory error factor, the target muscle fatigue factor and the target interaction force factor into a control model to obtain a target electrical stimulation signal of the electrical stimulation module and a target output torque of the motor module; and controlling the motor module to drive the exoskeleton robot to move based on the target motor output torque to drive the target training part to move, and controlling the electrical stimulation module to send the target electrical stimulation signal to the target muscle to drive the target training part to move.

[0006] In some embodiments, the target trajectory error factor, the target muscle fatigue factor and the target interaction force factor are input into a control model to obtain a target electrical stimulation signal of the electrical stimulation module and a target output torque of the motor module, including: solving a numerical solution of the control model based on the target trajectory error factor, the target muscle fatigue factor, the target interaction force factor and the initial value of the control model, wherein the numerical solution includes a first output capacity and a second output capacity; determining the target output torque based on the first output capacity and a first mapping relationship; and determining the target electrical stimulation signal based on the second output capacity and the second mapping relationship.

[0007] In some embodiments, determining the target trajectory error factor based on the rotation angle of the target joint at the current moment includes: when the absolute value of the difference between the rotation angle at the current moment and the target rotation angle is greater than a change threshold, obtaining the target trajectory error factor based on the sum of the value of the current trajectory error factor and a first preset value; and when the absolute value of the difference between the rotation angle at the current moment and the target rotation angle is less than or equal to the change threshold, determining the current trajectory error factor as the target trajectory error factor.

[0008] In some embodiments, determining the target muscle fatigue factor based on the electromyographic signal of the target muscle at the current moment includes: obtaining the average median frequency of the electromyographic signal at the current moment, wherein the average median frequency represents the average value of multiple median frequencies, and the multiple median frequencies include the median frequency of the electromyographic signal at the current moment and the median frequencies of the electromyographic signals at multiple historical moments before the current moment; when the average median frequency is less than the current first baseline value, determining the current muscle fatigue factor as the target muscle fatigue factor; when the average median frequency is greater than the current first baseline value, The median frequency at the current moment is set as the target first baseline value; when the average median frequency is less than the target first baseline value, and the ratio of the absolute value of the difference between the average median frequency and the target first baseline value to the target first baseline value is greater than the second baseline value, the target muscle fatigue factor is obtained based on the sum of the value of the current muscle fatigue factor and the second preset value; when the average median frequency is less than the target first baseline value, and the ratio of the absolute value of the difference between the average median frequency and the target first baseline value to the target first baseline value is less than or equal to the second baseline value, the current muscle fatigue factor is determined to be the target muscle fatigue factor.

[0009] In some embodiments, determining the target interaction force factor based on the human-computer interaction force between the exoskeleton robot and or the patient at the current moment includes: when the human-computer interaction force is greater than the interaction force threshold, obtaining the target interaction force factor based on the sum of the value of the current interaction force factor and a third preset value; and when the human-computer interaction force is less than or equal to the interaction force threshold, determining the current interaction force factor as the target interaction force factor.

[0010] In some embodiments, when the patient is in the swing phase, the target muscles include the tibialis anterior of the ankle joint; when the patient is in the stance phase, the target muscles include the gastrocnemius; when the patient is in the swing phase, the target muscles include the biceps femoris; and when the patient is in the late swing phase and mid-stance phase, the target muscles include the quadriceps femoris.

[0011] The present disclosure also provides a hybrid-driven lower limb rehabilitation training system, comprising: an exoskeleton robot configured to support a patient to be trained; a motor module connected to the exoskeleton robot, the motor module configured to drive the exoskeleton robot to move, so as to drive the target training part of the patient to move; an electrical stimulation module arranged on the exoskeleton robot, the electrical stimulation module configured to electrically stimulate target muscles to drive the target training part to move; a detection module arranged on the exoskeleton robot, the detection module configured to detect the human-computer interaction force between the exoskeleton robot and the patient; and a control unit connected to the motor module, the detection module and the electrical stimulation module, the control unit configured to respectively control the motor module and the electrical stimulation module to drive the target training part to move using the method described above.

[0012] In some embodiments, the control unit includes a control model, which includes: a motor output sub-model and a motor inhibition sub-model, wherein the motor output sub-model is characterized by the relationship between the first output capacity and the target trajectory error factor, and the motor inhibition sub-model is characterized by the relationship between the first inhibition capacity and the target muscle fatigue factor; and an electrical stimulation output sub-model and an electrical stimulation inhibition sub-model, wherein the electrical stimulation output sub-model is characterized by the relationship between the second output capacity and the target trajectory error factor, and the electrical stimulation inhibition sub-model is characterized by the relationship between the second inhibition capacity and the human-computer interaction force.

[0013] In some embodiments, the control model is represented as follows:

[0014]

[0015]

[0016]

[0017]

[0018] Among them, S E and S I represents the sigmod function, E represents the first output capability, I represents the first inhibition capability, E1 represents the second output capability, I1 represents the second inhibition capability, P represents the target trajectory error factor, Q1 represents the target muscle fatigue factor, Q2 represents the human-computer interaction force factor, τ represents the calculation rate, t represents time, k1, k2, k3, k4, k`1, k`2, k`3, k`4, k5, k6, k7, k8, k`5, k`6, k`7 and k`8 represent connection coefficients.

[0019] In some embodiments, it also includes: a collection device, which is arranged on the target muscle, and the collection device is configured to collect the electromyographic signal generated by the target muscle while the electrical stimulation module electrically stimulates the target muscle.

[0020] According to the embodiments of the present disclosure, based on the target trajectory error factor, the target muscle fatigue factor and the target interaction force factor, the target electrical stimulation signal of the electrical stimulation module and the target output torque of the motor module can be determined by using a trained control model, and the calculation cost is low, which can reduce the training cost. The human-computer interaction force can be adjusted by determining the target electrical stimulation signal and the target output torque based on the target interaction force factor. The movement posture of the patient's lower limbs can be adjusted based on the target trajectory error factor to ensure that the patient's lower limbs move along the target trajectory line. The target electrical stimulation signal and the target output torque are determined based on the target muscle fatigue factor, which can reduce the fatigue degree of the target muscle, thereby ensuring the effect of rehabilitation training and avoiding secondary injuries. Since the target trajectory error factor, the target interaction force factor and the target muscle fatigue factor at the current moment are determined, the target electrical stimulation signal and the target output torque can be adjusted in real time, so that the output of the electrical stimulation module and the motor module can be controlled more accurately, thereby improving the control efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 An exemplary system architecture that can be applied to a control method for a hybrid-driven lower limb rehabilitation training system according to an embodiment of the present disclosure is schematically shown.

[0022] Figure 2 A flow chart of a control method for a hybrid-driven lower limb rehabilitation training system according to an embodiment of the present disclosure is schematically shown.

[0023] Figure 3 The steady-state curve diagram of the control model according to the embodiment of the present disclosure is schematically shown.

[0024] Figure 4 A block diagram of a hybrid-driven lower limb rehabilitation training system according to an embodiment of the present disclosure is schematically shown, wherein a patient is shown.

[0025] Figure 5 The principle diagram of the control model according to the embodiment of the present disclosure is schematically shown.

[0026] Figure 6 A block diagram of an electronic device for a control method of a hybrid-driven lower limb rehabilitation training system according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0027] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0028] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0029] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0030] In the case of using expressions such as "at least one of A, B, and C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.). In the case of using expressions such as "at least one of A, B, or C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, or C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0031] Figure 1An exemplary system architecture that can be applied to a control method for a hybrid-driven lower limb rehabilitation training system according to an embodiment of the present disclosure is schematically shown.

[0032] It should be noted that Figure 1 The examples shown are only examples of system architectures to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios. For example, in another embodiment, an exemplary system architecture that can be applied to a control method for a hybrid-driven lower limb rehabilitation training system may include a terminal device, but the terminal device may not need to interact with a server to implement the control method for a hybrid-driven lower limb rehabilitation training system provided by the embodiments of the present disclosure.

[0033] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a hybrid-driven lower limb rehabilitation training system 101, a terminal device 102, a network 103, and a server 104. The network 103 is used to provide a medium for a communication link between the hybrid-driven lower limb rehabilitation training system 101, the terminal device 102, and the server 104. The network 103 may include various connection types, such as wired and / or wireless communication links, etc.

[0034] The user can use the hybrid drive lower limb rehabilitation training system 101 and the terminal device 102 to interact with the server 104 through the network 103 to receive or send messages, etc. The hybrid drive lower limb rehabilitation training system 101 can be a device for driving the patient to move, etc. (only for example). Various communication client applications can be installed on the terminal device 102, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients and / or social platform software, etc. (only for example).

[0035] The terminal device 102 may be any electronic device having a display screen and supporting web browsing, including but not limited to a television, a tablet computer, a laptop computer, a desktop computer, and the like.

[0036] Server 104 can be any type of server that provides various services. For example, server 104 can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services (Virtual Private Server). Server 104 can also be a server of a distributed system, or a server combined with a blockchain.

[0037] It should be noted that the control method for the hybrid-driven lower limb rehabilitation training system provided in the embodiment of the present disclosure can generally be executed by the hybrid-driven lower limb rehabilitation training system 101 or the terminal device 102 .

[0038] Alternatively, the control method for the hybrid drive lower limb rehabilitation training system provided in the embodiment of the present disclosure may also be generally executed by the server 104. The control method for the hybrid drive lower limb rehabilitation training system provided in the embodiment of the present disclosure may also be executed by a server or server cluster that is different from the server 104 and can communicate with the hybrid drive lower limb rehabilitation training system 101, the terminal device 102 and / or the server 104. It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of image acquisition devices, terminal devices, networks and servers may be provided according to the implementation requirements.

[0039] It should be noted that the sequence numbers of the operations in the following method are only used as representations of the operations for the purpose of description, and should not be regarded as representing the execution order of the operations. Unless explicitly stated, the method does not need to be executed completely in the order shown.

[0040] Figure 2 A flow chart of a control method for a hybrid-driven lower limb rehabilitation training system according to an embodiment of the present disclosure is schematically shown.

[0041] like Figure 2 As shown, an embodiment of the present disclosure provides a control method for a hybrid drive lower limb rehabilitation training system. The hybrid drive lower limb rehabilitation training system includes an exoskeleton robot, a motor module and an electrical stimulation module. The method 200 includes performing operations S210 to S250.

[0042] In operation S210 , a target trajectory error factor is determined based on a rotation angle of a target joint in a target training part at a current moment.

[0043] In operation S220, a target muscle fatigue factor is determined based on the myoelectric signal of the target muscle in the target training part at the current moment.

[0044] In operation S230, a target interaction force factor is determined based on the human-machine interaction force between the exoskeleton robot and the target training part at the current moment.

[0045] In operation S240, the target trajectory error factor, the target muscle fatigue factor, and the target interaction force factor are input into the control model to obtain the target electrical stimulation signal of the electrical stimulation module and the target output torque of the motor module.

[0046] In operation S250, the motor module is controlled to drive the exoskeleton robot to move based on the target motor output torque to drive the target training part to move, and the electrical stimulation module is controlled to send a target electrical stimulation signal to the target muscle to drive the target training part to move.

[0047] According to an embodiment of the present disclosure, the target training part may be a lower limb part of the patient. For example, the target training part may include the patient's thigh, calf, hip joint, knee joint and ankle joint.

[0048] According to an embodiment of the present disclosure, the target joints may be joints of the patient's lower limbs. For example, the target joints may include the patient's hip joint, knee joint, and ankle joint.

[0049] According to an embodiment of the present disclosure, the target muscles may be the patient's lower limb muscles. For example, the target muscles may include the patient's ankle joint tibialis anterior, gastrocnemius, biceps femoris and quadriceps femoris.

[0050] According to the embodiment of the present disclosure, the electromyographic signal can be characterized as a physiological electrical signal generated by the target muscle.

[0051] According to the embodiment of the present disclosure, the human-machine interaction force is generated when the motor module drives the exoskeleton robot to drive the target training part to move. The human-machine interaction force can be characterized as the interaction force between the exoskeleton robot and the target training part.

[0052] According to the embodiments of the present disclosure, based on the target trajectory error factor, the target muscle fatigue factor and the target interaction force factor, the target electrical stimulation signal of the electrical stimulation module and the target output torque of the motor module can be determined using a trained control model, and the calculation cost is low, which can reduce the training cost. The human-computer interaction force can be adjusted by determining the target electrical stimulation signal and the target output torque based on the target interaction force factor. The movement posture of the patient's lower limbs can be adjusted based on the target trajectory error factor to ensure that the patient's lower limbs move along the target trajectory line. The target electrical stimulation signal and the target output torque are determined based on the target muscle fatigue factor, which can reduce the fatigue level of the target muscle, thereby ensuring the effect of rehabilitation training and avoiding secondary injuries. Since the target trajectory error factor, the target interaction force factor and the target muscle fatigue factor at the current moment are determined, the target electrical stimulation signal and the target output torque can be adjusted in real time, so that the output of the electrical stimulation module and the motor module can be controlled more accurately, thereby improving the control efficiency.

[0053] In some embodiments, the target trajectory error factor, the target muscle fatigue factor, and the target interaction force factor are input into the control model to obtain the target electrical stimulation signal of the electrical stimulation module and the target output torque of the motor module, including: based on the target trajectory error factor, the target muscle fatigue factor, the target interaction force factor, and the initial value of the control model, the numerical solution of the control model at the current moment can be solved. The numerical solution may include a first output capacity, a second output capacity, a first inhibition capacity, and a second inhibition capacity. The initial value of the control model may include the first output capacity and the second output capacity of the control model at the previous moment. Based on the first output capacity and the first mapping relationship, the target output torque can be determined. Based on the second output capacity and the second mapping relationship, the target electrical stimulation signal can be determined.

[0054] Figure 3 The steady-state curve diagram of the control model according to the embodiment of the present disclosure is schematically shown.

[0055] like Figure 3 As shown, according to an embodiment of the present disclosure, after the target trajectory error factor, the target muscle fatigue factor and the target interaction force factor are input into the control model, when the values ​​of the first output capacity and the second output capacity are in a steady state, it can be determined that the first output capacity and the second output capacity are the numerical solutions of the control model at the current moment.

[0056] The first mapping relationship can be expressed as the relationship between the first output capacity and the output torque of the motor module. The second mapping relationship can be expressed as the relationship between the second output capacity and the electrical stimulation signal of the electrical stimulation module. Based on the first mapping relationship, the output torque corresponding to the first output capacity at the current moment can be determined as the target output torque. Based on the second mapping relationship, the electrical stimulation signal corresponding to the second output capacity at the current moment can be determined as the target electrical stimulation signal.

[0057] The first output capacity and the second output capacity may be normalized values. The first output capacity may be greater than or equal to 0 and less than or equal to 1. The second output capacity may be greater than or equal to 0 and less than or equal to 1. For example, the amplitude of the electrical stimulation signal ranges from [10,24]mA. When the second output capacity is 0.5, the target electrical stimulation signal is 10+0.5*(24-10)mA, that is, the target electrical stimulation signal is 17mA. For example, the output torque ranges from [0,0.6]Nm*W. When the first output capacity is 0.5, the target electrical stimulation signal is 0+0.5*0.6Nm*W, that is, the target electrical stimulation signal is 0.3Nm*W.

[0058] According to an embodiment of the present disclosure, a trained control model can be obtained by inputting a plurality of second output capabilities corresponding to a plurality of electrical stimulation signals of the electrical stimulation module, a plurality of first output capabilities corresponding to a plurality of output torques of the motor module, a plurality of first inhibition capabilities, a plurality of second inhibition capabilities, a plurality of trajectory error factors, a plurality of muscle fatigue factors, and a plurality of interactive force factors into a model to be trained for target training and weight adjustment. The first output capability, the second output capability, the first inhibition capability, the second inhibition capability, the trajectory error factor, the muscle fatigue factor, and the interactive force factor can be obtained through previously recorded data. Furthermore, by inputting a target trajectory error factor corresponding to the trajectory error factor, a target muscle fatigue factor corresponding to the muscle fatigue factor, and a target interactive force factor corresponding to the interactive force factor into the control model, a target electrical stimulation signal of the electrical stimulation module and a target output torque of the motor module can be obtained.

[0059] In some embodiments, based on the rotation angle of the target joint at the current moment, determining the target trajectory error factor includes: when the absolute value of the difference between the rotation angle at the current moment and the target rotation angle is greater than the change threshold, based on the sum of the value of the current trajectory error factor and the first preset value, obtaining the target trajectory error factor. When the absolute value of the difference between the rotation angle at the current moment and the target rotation angle is less than or equal to the change threshold, determining the current trajectory error factor as the target trajectory error factor.

[0060] According to an embodiment of the present disclosure, a hybrid drive lower limb rehabilitation training system may include a target trajectory line at a fixed gait speed. The target trajectory line may be characterized as the rotation angle of the target joint of the exoskeleton robot from the beginning of the heel strike event in the current gait to the end of the heel strike event in the next gait. Marking points representing different control information may be set during the movement process. The target trajectory line may be stretched and scaled according to the set gait speed, and adapted to different gait speeds based on the changes in the marking points, so as to adapt to more complex movement conditions. The rotation angle corresponding to the current moment in the target trajectory line is the target rotation angle of the target joint at the current moment. The change rate threshold and the first preset value may be set by a doctor or patient according to the patient's physical condition. When the absolute value of the difference between the rotation angle at the current moment and the target rotation angle is greater than the change threshold, the target trajectory error factor may be the sum of the value of the current trajectory error factor and the first preset value.

[0061] According to the embodiment of the present disclosure, the difference D between the rotation angle of the current trajectory error factor at the current moment and the target rotation angle i (n) can be expressed as follows:

[0062] D i (n) = X i (n)-x i(n) (1).

[0063] Among them, X i (n) represents the target rotation angle, x i (n) represents the rotation angle at the current moment, n represents the nth gait cycle, and i represents the i-th moment in the gait cycle.

[0064] According to the embodiment of the present disclosure, the target trajectory error factor P i (n) can be expressed as follows:

[0065]

[0066] Among them, P i-1 (n) represents the current trajectory error factor, L p represents the first preset value, and D represents the change threshold.

[0067] In some embodiments, based on the electromyographic signal of the target muscle at the current moment, determining the target muscle fatigue factor includes: obtaining the average median frequency of the electromyographic signal at the current moment. The average median frequency can represent the average value of multiple median frequencies. The multiple median frequencies can include the median frequency of the electromyographic signal at the current moment and the median frequencies of the electromyographic signals at multiple historical moments before the current moment.

[0068] In the case where the average median frequency is less than the current first baseline value, the current muscle fatigue factor is determined to be the target muscle fatigue factor. In the case where the average median frequency is greater than the current first baseline value, the median frequency at the current moment is set as the target first baseline value. In the case where the average median frequency is less than the target first baseline value, and the ratio of the absolute value of the difference between the average median frequency and the target first baseline value to the target first baseline value is greater than the second baseline value, the target muscle fatigue factor is obtained based on the sum of the value of the current muscle fatigue factor and the second preset value. In the case where the average median frequency is less than the target first baseline value, and the ratio of the absolute value of the difference between the average median frequency and the target first baseline value to the target first baseline value is greater than the second baseline value, the target muscle fatigue factor is the sum of the value of the current muscle fatigue factor and the second preset value. In the case where the average median frequency is less than the target first baseline value, and the ratio of the absolute value of the difference between the average median frequency and the target first baseline value to the target first baseline value is less than or equal to the second baseline value, the current muscle fatigue factor is determined to be the target muscle fatigue factor.

[0069] The current first baseline value may be a changing value. The target first baseline value at the current moment may be the current first baseline value at the next moment. The initial value of the current first baseline value and the initial value of the second baseline value may be set by a doctor or a patient according to the patient's physical condition. The target muscle fatigue factor may be a value updated in real time. The second baseline value may be 0.05. The target muscle fatigue factor at the current moment may be the current muscle fatigue factor at the next moment. The initial value of the current muscle fatigue factor may be zero.

[0070] According to the embodiment of the present disclosure, the median frequency can characterize the patient's muscle fatigue level, and the median frequency MF can be expressed as the following formula (3).

[0071]

[0072] Where, M = 1024, P j By acquiring multiple electromyographic signals of the patient, a frequency curve of the electromyographic signal can be obtained, and the amplitude of the frequency curve can be represented as the amplitude of the frequency spectrum.

[0073] According to the embodiment of the present disclosure, by setting the electromyographic signal sliding window, obtaining the median frequency of the preset length, calculating the average value of the median frequency of the preset length, when the average value is greater than the current first baseline, the average value can be the current first baseline value, that is, the updated first baseline value. For example, a 1000ms electromyographic signal sliding window is set, the overlap width can be 0ms, and after obtaining 5 median frequencies, the average value of the 5 median frequencies is calculated. When the average value is greater than the current first baseline, the average value can be the current first baseline value.

[0074] In some embodiments, based on the human-machine interaction force between the exoskeleton robot and or the patient at the current moment, determining the target interaction force factor includes: when the human-machine interaction force is greater than the interaction force threshold, obtaining the target interaction force factor based on the sum of the value of the current interaction force factor and the third preset value. When the human-machine interaction force is less than or equal to the interaction force threshold, determining the current interaction force factor as the target interaction force factor.

[0075] According to an embodiment of the present disclosure, the interaction force threshold and the third preset value can be set by a doctor or a patient according to the patient's physical condition. When it is detected that the human-computer interaction force is greater than the interaction force threshold, the target interaction force factor can be determined as the sum of the current interaction force factor and the third preset value. That is, the target interaction force factor can be a value updated in real time. The target interaction force factor at the current moment can be the current interaction force factor at the next moment. The initial value of the current interaction force factor can be zero. The third preset value can be 0.1. The interaction force threshold can be a variable value and can be updated according to the patient's motion state.

[0076] In some embodiments, when the patient is in the swing phase, the target muscle may include the tibialis anterior of the ankle joint. When the patient is in the stance phase, the target muscle may include the gastrocnemius. When the patient is in the swing phase, the target muscle may include the biceps femoris. When the patient is in the late swing phase and the middle stance phase, the target muscle may include the quadriceps femoris. Further, during the period when the patient is controlled to enter the swing phase, only the tibialis anterior of the ankle joint may be electrically stimulated. During the period when the patient is controlled to enter the stance phase, only the gastrocnemius may be electrically stimulated. During the period when the patient is controlled to enter the swing phase, only the biceps femoris may be electrically stimulated. During the period when the patient is controlled to enter the swing phase, only the quadriceps femoris may be electrically stimulated. Through the above-mentioned electrical stimulation method, the target muscle can be electrically stimulated more accurately, avoiding the muscle from being in an activated state all the time, thereby reducing muscle fatigue, and avoiding unnecessary electrical stimulation from interfering with the lower limb movement, causing deviations between the actual movement trajectory and the target trajectory line.

[0077] Figure 4 A block diagram of a hybrid-driven lower limb rehabilitation training system according to an embodiment of the present disclosure is schematically shown, wherein a patient is shown.

[0078] like Figure 4 As shown, the embodiment of the present disclosure also provides a hybrid drive lower limb rehabilitation training system 400. The hybrid drive lower limb rehabilitation training system 400 may include an exoskeleton robot 410, a motor module 420, an electrical stimulation module 430, a detection module 440 and a control unit 450. The exoskeleton robot 410 can be used to support the patient to be trained. The motor module 420 is connected to the exoskeleton robot 410. The motor module 420 can be used to drive the exoskeleton robot 410 to move, so as to drive the target training part of the patient to move. The electrical stimulation module 430 is arranged on the exoskeleton robot 410. The electrical stimulation module 430 can be used to electrically stimulate the target muscle to drive the target training part to move. The detection module 440 can be arranged on the exoskeleton robot 410. The detection module 440 can be used to detect the human-machine interaction force between the exoskeleton robot 410 and the patient. The interaction force threshold can be determined according to the position where the detection module 440 is set on the patient's leg. For example, the interaction force threshold value when the detection module 440 is close to the hip joint is less than the value when it is far away from the hip joint. The control unit 450 is connected to the motor module 420, the detection module 440 and the electrical stimulation module 430. The control unit 450 can be used to control the motor module 420 and the electrical stimulation module 430 to drive the target training part to move using the above method. Specifically, the control unit 450 can control the motor module 420 to drive the exoskeleton robot 410 to move based on the target motor output torque obtained by the above method to drive the target training part to move. The control unit 450 can control the electrical stimulation module 430 to send a target electrical stimulation signal to the target muscle to electrically stimulate the target muscle, thereby driving the target training part to move.

[0079] In some embodiments, the hybrid drive lower limb rehabilitation training system further includes: a collection device. The collection device can be arranged on the target muscle. The collection device can be used to collect the electromyographic signal generated by the target muscle while the electrical stimulation module 430 electrically stimulates the target muscle.

[0080] In some embodiments, the control unit 450 may include a control model. The control model may include: a motor output sub-model, a motor inhibition sub-model, an electrical stimulation output sub-model, and an electrical stimulation inhibition sub-model. The motor output sub-model may be characterized as a relationship between a first output capability and a target trajectory error factor. The motor inhibition sub-model may be characterized as a relationship between a first inhibition capability and a target muscle fatigue factor. The electrical stimulation output sub-model may be characterized as a relationship between a second output capability and a target trajectory error factor. The electrical stimulation inhibition sub-model may be characterized as a relationship between a second inhibition capability and a human-computer interaction force.

[0081] Figure 5 The principle diagram of the control model according to the embodiment of the present disclosure is schematically shown.

[0082] like Figure 5 As shown, in some embodiments, the control model is expressed as follows:

[0083]

[0084]

[0085]

[0086]

[0087] Among them, S E and S I represents the sigmod function, sigmod(x)=(1+e -x ) -1, the upper and lower limits of the sigmod function are (0, 1). E represents the first output capability. I represents the first inhibition capability. E1 represents the second output capability. I1 represents the second inhibition capability. P represents the target trajectory error factor. Q1 represents the target muscle fatigue factor. Q2 represents the human-computer interaction force factor. τ represents the calculation rate. t represents time. k1, k2, k3, k4, k5, k6, k7, k8, k`1, k`2, k`3, k`4, k`5, k`5, k`6, k`7 and k`8 represent connection coefficients. Formula (4) can be expressed as a motor output submodel. Formula (5) can be expressed as a motor inhibition submodel. Formula (6) can be expressed as an electrical stimulation output submodel. Formula (7) can be expressed as an electrical stimulation inhibition submodel. The control model can be obtained by optimizing and training the Wilson-Cowan model.

[0088] Figure 6 A block diagram of an electronic device for a control method of a hybrid-driven lower limb rehabilitation training system according to an embodiment of the present disclosure is schematically shown. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0089] like Figure 6 As shown, the electronic device 600 according to an embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include an onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0090] In RAM 603, various programs and data required for the operation of electronic device 600 are stored. Processor 601, ROM 602 and RAM 603 are connected to each other through bus 604. Processor 601 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 602 and / or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in one or more memories.

[0091] According to an embodiment of the present disclosure, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to the bus 604. The system 600 may further include one or more of the following components connected to the I / O interface 605: an input portion 606 including a keyboard, a mouse, etc. An output portion 607 including a speaker, etc., such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc. A storage portion 608 including a hard disk, etc. A communication portion 609 including a network interface card, such as a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network, such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that the computer program read therefrom is installed into the storage portion 608 as needed.

[0092] According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0093] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments. It may also exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0094] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include, but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0095] For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 602 and / or the RAM 603 described above and / or one or more memories other than the ROM 602 and the RAM 603 .

[0096] The embodiments of the present disclosure also include a computer program product, which includes a computer program, and the computer program contains program code for executing the method provided by the embodiments of the present disclosure. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the above method provided by the embodiments of the present disclosure.

[0097] When the computer program is executed by the processor 601, the above functions defined in the system / device of the embodiment of the present disclosure are executed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0098] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 609, and / or installed from a removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0099] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level procedures and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, Python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0100] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It can be understood by those skilled in the art that the features recorded in the various embodiments and / or claims of the present disclosure can be combined and / or combined in a variety of ways, even if such a combination or combination is not explicitly recorded in the present disclosure. In particular, without departing from the spirit and teaching of the present disclosure, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0101] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A hybrid drive lower limb rehabilitation training system, comprising: an exoskeleton robot configured to support a patient to be trained; a motor module connected to the exoskeleton robot and configured to drive the exoskeleton robot to move so as to drive the target training part of the patient to move; An electrical stimulation module, disposed on the exoskeleton robot, and configured to electrically stimulate target muscles to drive the target training part to move; A detection module, disposed on the exoskeleton robot, configured to detect a human-machine interaction force between the exoskeleton robot and a patient; as well as A control unit is connected to the motor module, the detection module and the electrical stimulation module, and is configured as follows: Determine the target trajectory error factor based on the difference between the rotation angle of the target joint at the current moment and the target rotation angle; Determine the target muscle fatigue factor based on the average median frequency of the electromyographic signal of the target muscle at the current moment, where the average median frequency represents the average value of multiple median frequencies, and the multiple median frequencies include the median frequency of the electromyographic signal at the current moment and the median frequencies of the electromyographic signals at multiple historical moments before the current moment; Determine the target interaction force factor based on the human-machine interaction force and interaction force threshold between the exoskeleton robot and the target training part at the current moment; The target trajectory error factor, the target muscle fatigue factor and the target interaction force factor are input into a control model to obtain a target electrical stimulation signal of the electrical stimulation module and a target output torque of the motor module, wherein the control model includes a motor output sub-model representing the relationship between a first output capability and a target trajectory error factor, a motor inhibition sub-model representing the relationship between a first inhibition capability and a target muscle fatigue factor, an electrical stimulation output sub-model representing the relationship between a second output capability and a target trajectory error factor, and an electrical stimulation inhibition sub-model representing the relationship between a second inhibition capability and a human-computer interaction force; Based on the target motor output torque, the motor module is controlled to drive the exoskeleton robot to move so as to drive the target training part to move, and the electrical stimulation module is controlled to send the target electrical stimulation signal to the target muscle to drive the target training part to move.

2. The hybrid drive lower limb rehabilitation training system according to claim 1, characterized in that: The step of inputting the target trajectory error factor, the target muscle fatigue factor, and the target interaction force factor into a control model to obtain a target electrical stimulation signal of the electrical stimulation module and a target output torque of the motor module comprises: Based on the target trajectory error factor, the target muscle fatigue factor, the target interaction force factor and the initial value of the control model, solving a numerical solution of the control model, wherein the numerical solution includes a first output capacity and a second output capacity; determining the target output torque based on the first output capacity and a first mapping relationship; and Based on the second output capacity and the second mapping relationship, the target electrical stimulation signal is determined.

3. The hybrid drive lower limb rehabilitation training system according to claim 1, characterized in that: Determining the target trajectory error factor based on the difference between the rotation angle of the target joint at the current moment and the target rotation angle includes: When the absolute value of the difference between the rotation angle at the current moment and the target rotation angle is greater than the change threshold, the target trajectory error factor is obtained based on the sum of the value of the current trajectory error factor and the first preset value; and When the absolute value of the difference between the rotation angle at the current moment and the target rotation angle is less than or equal to the change threshold, the current trajectory error factor is determined to be the target trajectory error factor.

4. The hybrid drive lower limb rehabilitation training system according to claim 1, characterized in that: Determining the target muscle fatigue factor based on the average median frequency of the electromyographic signal of the target muscle at the current moment includes: When the average median frequency is less than the current first baseline value, determining the current muscle fatigue factor as the target muscle fatigue factor; When the average median frequency is greater than the current first baseline value, the median frequency at the current moment is set as the target first baseline value; When the average median frequency is less than the target first baseline value, and the ratio of the absolute value of the difference between the average median frequency and the target first baseline value to the target first baseline value is greater than the second baseline value, the target muscle fatigue factor is obtained based on the sum of the value of the current muscle fatigue factor and the second preset value; When the average median frequency is less than the target first baseline value, and the ratio of the absolute value of the difference between the average median frequency and the target first baseline value to the target first baseline value is less than or equal to the second baseline value, the current muscle fatigue factor is determined to be the target muscle fatigue factor.

5. The hybrid drive lower limb rehabilitation training system according to claim 1, characterized in that: The determining of the target interaction force factor based on the human-machine interaction force and interaction force threshold between the exoskeleton robot and the patient at the current moment includes: When the human-computer interaction force is greater than the interaction force threshold, obtaining the target interaction force factor based on the sum of the value of the current interaction force factor and the third preset value; and When the human-computer interaction force is less than or equal to the interaction force threshold, the current interaction force factor is determined as the target interaction force factor.

6. The hybrid drive lower limb rehabilitation training system according to claim 1, characterized in that: With the patient in the swing phase, target muscles include the tibialis anterior at the ankle; With the patient in the stance phase, target muscles include the gastrocnemius; With the patient in the swing phase, target muscles include the biceps femoris; as well as With the patient in late swing phase and mid stance phase, target muscles include the quadriceps.

7. The hybrid drive lower limb rehabilitation training system according to claim 1, characterized in that: The control model is expressed as follows: ； ； ； ； in, and express function, represents the first output capability, Indicates the first inhibition ability, Indicates the second output capability, Indicates the second inhibitory ability, represents the target trajectory error factor, Indicates the target muscle fatigue factor, represents the human-computer interaction factor, represents the calculation rate, Indicates time, , , , , , , , , , , , , , , Represents the connection coefficient.

8. The hybrid drive lower limb rehabilitation training system according to claim 1, characterized in that: Also includes: The acquisition device is arranged on the target muscle, and is configured to acquire the electromyographic signal generated by the target muscle while the electrical stimulation module electrically stimulates the target muscle.

Images