Gait training method, electronic equipment and storage medium

Abstract

The invention discloses a gait training method, electronic equipment and a storage medium. The method comprises the steps of obtaining leg data of a target object and determining a current training mode of the target object; obtaining a reference gait track of the target object based on the leg data; based on the reference gait track and the current training mode, force control parameters of the exoskeleton system are adjusted, so that the walking gait track of the target object is adjusted, and an actual gait track is obtained. According to the scheme, the rehabilitation training effect can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of exoskeleton systems, and in particular to a gait training method, electronic equipment, and storage medium. Background Art

[0002] The existing method of conducting rehabilitation training for the target subject's lower limbs is mainly based on passive gait training. This solution makes it impossible for the target subject to actively participate in the rehabilitation training process, and it is easy for the target subject to have a hostile attitude towards exoskeleton rehabilitation training. For example, when the target subject is conducted rehabilitation training using the passive gait training method, in the early stage of rehabilitation training, because the target subject's healthy lower limb strength is strong, and the antagonism with the preset gait trajectory of the exoskeleton machine is also strong, the target subject is tired of using the exoskeleton machine, which greatly reduces the willingness to use the exoskeleton machine, resulting in the abandonment of rehabilitation training or the termination of the entire training treatment; in the later stage of rehabilitation training, the target subject's affected lower limb strength gradually recovers, and the gait also begins to gradually change, but in this stage, the preset gait trajectory of the passive gait training method has not changed, and the exoskeleton machine is still used to completely drag the target subject's lower limbs for training, resulting in the target subject's legs being unable to actively participate in the rehabilitation training process, thereby reducing the training effect.

[0003] Therefore, there is an urgent need for a rehabilitation training program on the market to solve the above problems. Summary of the invention

[0004] The present application at least provides a gait training method, electronic equipment, and storage medium, which can improve the effect of rehabilitation training.

[0005] A first aspect of the present application provides a gait training method, which includes: acquiring leg data of a target object and determining a current training mode of the target object; obtaining a reference gait trajectory of the target object based on the leg data; and adjusting force control parameters of an exoskeleton system based on the reference gait trajectory and the current training mode to adjust the walking gait trajectory of the target object to obtain an actual gait trajectory.

[0006] Among them, based on the leg data, a reference gait trajectory of the target object is obtained, including: using the leg data to generate an initial gait trajectory of the target object; and, based on the leg data, obtaining gait trajectories corresponding to several reference objects from a pre-stored trajectory set; using the gait trajectories corresponding to the several reference objects to interpolate the initial gait trajectory to obtain a reference gait trajectory.

[0007] Among them, based on the leg data, gait trajectories corresponding to several reference objects are obtained from a pre-stored trajectory set, including: based on the leg data and the preset value, a search range is determined, wherein the sum of the leg data and the preset value is used as the maximum value in the search range, and the difference between the leg data and the preset value is used as the minimum value in the search range; in response to the preset leg data of the preset object in the pre-stored trajectory set satisfying the search range, the preset object is used as the reference object, and the preset gait trajectory corresponding to the preset object is used as the gait trajectory corresponding to the reference object.

[0008] Among them, the preset object is an object with normal gait; and / or, the method for generating a preset gait trajectory corresponding to the preset object includes: recording the walking gait of the preset object to obtain an original gait trajectory; and smoothing the original gait trajectory to obtain a preset gait trajectory.

[0009] The leg data includes thigh length data and calf length data; the preset values ​​include a first preset value and a second preset value; based on the leg data and the preset values, determining a search range includes: based on the thigh length data and the first preset value, determining a first search range, wherein the sum of the thigh length data and the first preset value is used as the maximum value in the first search range, and the difference between the thigh length data and the first preset value is used as the minimum value in the first search range; and, using the sum of the calf length data and the second preset value as the second search range, wherein the sum of the calf length data and the second preset value is used as the maximum value in the second search range, and the difference between the calf length data and the second preset value is used as the minimum value in the second search range; in response to the preset leg data of the preset object in the pre-stored trajectory set satisfying the search range, taking the preset object as a reference object, and taking the preset gait trajectory corresponding to the preset object as the gait trajectory corresponding to the reference object, including: in response to the preset thigh length data of the preset object in the pre-stored trajectory set satisfying the first search range, and the preset calf length data satisfying the second search range, taking the preset object as a reference object, and taking the preset gait trajectory corresponding to the preset object as the gait trajectory corresponding to the reference object.

[0010] Among them, determining the current training mode of the target object includes: determining the current training mode of the target object based on the rehabilitation process of the target object; the force control parameter is the stiffness coefficient of the controller of the exoskeleton system, and based on the reference gait trajectory and the current training mode, the force control parameter of the exoskeleton system is adjusted to adjust the walking gait trajectory of the target object to obtain the actual gait trajectory, including: determining the stiffness coefficient based on the current training mode; when the exoskeleton system controls the target object to walk based on the reference gait trajectory, using the stiffness coefficient to adjust the force of the exoskeleton system on the target object's legs to obtain the actual gait trajectory of the target object.

[0011] Wherein, when the current training mode is the first gait training mode, based on the current training mode, the stiffness coefficient of the controller of the exoskeleton system is determined, including: at the starting position of the swing phase of the target object, the stiffness coefficient of the controller is set to a first value; at the end position of the swing phase of the target object, the stiffness coefficient of the controller is set to a second value; wherein the first value is less than the second value; or, when the current training mode is the second gait training mode, based on the current training mode, the stiffness coefficient of the controller of the exoskeleton system is determined, including: at the starting position of the swing phase of the target object, the stiffness coefficient of the controller is set to a third value; at the end position of the swing phase of the target object, the stiffness coefficient of the controller is set to a fourth value; wherein the third value is greater than the fourth value.

[0012] The first gait training mode corresponds to the first period of the rehabilitation process of the target object; the second gait training mode corresponds to the second period of the rehabilitation process of the target object, and the second period is located after the first period.

[0013] A second aspect of the present application provides an electronic device, comprising a memory and a processor coupled to each other, wherein the processor is used to execute program instructions stored in the memory to implement the gait training method in the first aspect.

[0014] A third aspect of the present application provides a computer-readable storage medium having program instructions stored thereon, and when the program instructions are executed by a processor, the gait training method in the first aspect is implemented.

[0015] The above scheme generates a reference gait trajectory of the target object through the leg data of the target object, and adjusts the force control parameters of the exoskeleton system in real time according to the reference trajectory and the current training mode of the target object, so that when constraining the walking gait trajectory of the target object, the target object is given a certain range of autonomous motion, thereby reducing the target object's resistance to the exoskeleton machine and achieving better training effects.

[0016] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.

[0018] Figure 1 It is a flow chart of an embodiment of the gait training method of the present application;

[0019] Figure 2 It is a schematic diagram of a framework of an embodiment of a gait trajectory of the present application;

[0020] Figure 3 is a flow chart of another embodiment of the gait training method of the present application;

[0021] Figure 4 It is a schematic diagram of the framework of an embodiment of the electronic device of the present application;

[0022] Figure 5 It is a schematic diagram of a framework of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0023] The scheme of the embodiment of the present application is described in detail below in conjunction with the drawings of the specification.

[0024] In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.

[0025] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the previously associated objects are in an "or" relationship. In addition, "many" in this article means two or more than two. In addition, the term "at least one" in this article means any combination of at least two of any one or more of a plurality of, for example, including at least one of A, B, and C, can mean including any one or more elements selected from the set consisting of A, B and C.

[0026] See also Figure 1 , Figure 1 It is a flow chart of an embodiment of the gait training method of the present application.

[0027] Specifically, the following steps may be included:

[0028] Step S110: Acquire the leg data of the target object and determine the current training mode of the target object.

[0029] This application is implemented based on an exoskeleton system. The target subjects in this application can be people with weak lower limbs or paralysis and inability to move. In order to enable the lower limbs of the target subjects to reach a normal state, this method is combined with an exoskeleton system, and different training modes are selected according to the different rehabilitation processes of the target subjects, so as to improve the training effect and reduce the confrontational emotions of the target subjects.

[0030] In some embodiments, the leg data of the target object can be obtained by measuring. For example, the leg data of the target object can be measured using a ruler. The leg data of the target object mentioned here includes thigh data and calf data. In addition, in addition to thigh data and calf data, the leg data of the target object can also include sole data, or the ratio between thigh data and calf data.

[0031] In some embodiments, to determine the current training mode of the target object, it can be determined by the current rehabilitation process of the target object. Specifically, based on the rehabilitation process of the target object, the current training mode of the target object is determined. For example, when the target object is in the early stage of the rehabilitation process, a tougher training mode is adopted; when the target object is in the middle stage of the rehabilitation process, a more moderate training mode is adopted; when the target object is in the late stage of the rehabilitation process, a more comfortable training mode is adopted. In addition, the current training mode of the target object can be set by a professional operator, wherein the professional operator can be a doctor, a software engineer, etc.

[0032] Step S120: obtaining a reference gait trajectory of the target object based on the leg data.

[0033] In some embodiments, after obtaining the leg data of the target object, the leg data can be input into a deep neural network model, and the deep neural network model generates a corresponding reference trajectory according to the input leg data. The deep neural network model is a trained model with the expected training effect, and the training method of the deep neural network model is a prior art, so it will not be described in detail here.

[0034] In other embodiments, an exoskeleton system may be used to generate an initial gait trajectory of a target object using leg data. The initial gait trajectory generated by the exoskeleton system usually has noise or an uneven trajectory. Therefore, in order to improve the accuracy of the gait trajectory generated by the exoskeleton system, the gait trajectories corresponding to several reference objects may be obtained from a pre-stored trajectory set based on the leg data, and then the gait trajectories corresponding to the several reference objects may be used to interpolate the initial gait trajectory to obtain a reference gait trajectory.

[0035] Furthermore, in order to avoid obtaining several reference objects from the pre-stored trajectory set that have low correlation with the target object, so as to affect the final output result of the gait trajectory of the exoskeleton system. Specifically, the search range can be determined based on the leg data and the preset value, wherein the sum of the leg data and the preset value is used as the maximum value in the search range, and the difference between the leg data and the preset value is used as the minimum value in the search range. If the preset leg data of the preset object in the pre-stored trajectory set meets the search range, the preset object is used as the reference object, and the preset gait trajectory corresponding to the preset object is used as the gait trajectory corresponding to the reference object. Among them, the preset object is an object with normal gait.

[0036] For example, the leg data may include thigh length data and calf length data. Based on the thigh length data and a first preset value, a first search range is determined, wherein the sum of the thigh length data and the first preset value is used as the maximum value in the first search range, and the difference between the thigh length data and the first preset value is used as the minimum value in the first search range; and, the sum of the calf length data and the second preset value is used as the second search range, wherein the sum of the calf length data and the second preset value is used as the maximum value in the second search range, and the difference between the calf length data and the second preset value is used as the minimum value in the second search range; if the preset thigh length data of the preset object in the pre-stored trajectory set satisfies the first search range, and the preset calf length data satisfies the second search range, the preset object is used as a reference object, and the preset gait trajectory corresponding to the preset object is used as the gait trajectory corresponding to the reference object.

[0037] In some embodiments, the method for generating a preset gait trajectory corresponding to a preset object may be: using motion capture technology to record the walking gait of the preset object to obtain an original gait trajectory, and then smoothing the original gait trajectory to obtain a preset gait trajectory.

[0038] In addition, a manual editing method may also be used to obtain the preset gait trajectory of the preset object. Therefore, the method for obtaining the preset gait trajectory of the preset object is not specifically limited here.

[0039] Step S130: Based on the reference gait trajectory and the current training mode, the force control parameters of the exoskeleton system are adjusted to adjust the walking gait trajectory of the target object to obtain an actual gait trajectory.

[0040] In some embodiments, in order to make each step of the target subject's walking training smooth during the rehabilitation process and considering that the target subject's performance is different in different rehabilitation processes, a force control algorithm is introduced in this embodiment to improve the wearing comfort of the target subject and the training effect:

[0041]

[0042] Among them, q represents the angle of the target object's leg joint when walking, represents the angular velocity of the target object's leg joints when walking, represents the angular acceleration of the target object's leg joints when walking, M(q) represents the generalized mass matrix, represents the generalized Coriolis force matrix, G(q) represents the generalized gravity matrix, τ represents the motor torque in the exoskeleton system, τ h Represents the interaction torque between the target object and the exoskeleton system.

[0043] Since the exoskeleton system supports the target object through the bracket and the bottom wheel, and the running speed of the exoskeleton system is slow during support, the generalized Coriolis force matrix in formula (1) can be ignored, and gravity compensation is used in this embodiment to compensate for the force control deviation of the exoskeleton system. Therefore, the generalized gravity matrix in formula (1) can also be ignored. Therefore, in the force control algorithm of this embodiment, only the generalized mass matrix needs to be considered, that is:

[0044]

[0045] In this implementation, impedance control is introduced on the basis of the force control algorithm, the purpose of which is to limit the abnormal gait of the target object and give the target object a certain degree of freedom of movement. Through impedance control, when the gait trajectory of the target object is different from the reference gait trajectory, the gait of the target object is corrected, thereby achieving the purpose of training. For example, when the gait trajectory of the target object deviates outward from the reference gait trajectory, based on impedance control, the exoskeleton system will generate an inward force; when the gait trajectory of the target object deviates inward from the reference gait trajectory, based on impedance control, the exoskeleton system will generate an outward force.

[0046] In a specific embodiment, the force control parameter may be the stiffness coefficient of the controller of the exoskeleton system. In this case, the exoskeleton system is equivalent to a spring system, and changes in its position easily cause changes in the applied force. The stiffness coefficient of the controller is variable to adapt to different rehabilitation processes and meet the training needs of different target objects.

[0047] Therefore, in this embodiment, the stiffness coefficient can be determined based on the current training mode, wherein the stiffness coefficients may be different for different training modes. Then, when the exoskeleton system controls the target object to walk based on the reference gait trajectory, the stiffness coefficient is used to adjust the force exerted by the exoskeleton system on the target object's legs to obtain the target object's actual gait trajectory, so that the target object's actual gait trajectory is smoother, and the force output by the exoskeleton system is not entirely the force exerted by the target object when walking, so that the target object can also generate a part of the force during the training process to ensure that the target object can actively participate in the training process.

[0048] In some embodiments, the current training mode includes a first gait training mode and a second gait training mode, and the stiffness coefficient of the corresponding controller varies in different gait training modes. Specifically, when the current training mode is the first gait training mode, the stiffness coefficient of the controller is set to a first value at the start position of the swing phase of the target object; and the stiffness coefficient of the controller is set to a second value at the end position of the swing phase of the target object; wherein the first value is less than the second value, for example, when the first value is 3, the second value is 5; when the first value is 2.5, the second value is 8.7, etc. Among them, the swing phase and the support phase can be combined with reference to Figure 2 ,exist Figure 2 The solid line in the figure is the right leg of the target object, and the dotted line is the left leg of the target object. When the right leg of the target object takes a step, the stage when the right leg leaves the ground is the swing phase, and the remaining stages are the support phases. The support phases of the object with normal gait and the object with abnormal gait are basically similar, and only the swing phase is different. Therefore, the swing phase is mainly introduced in this embodiment.

[0049] In the first posture training mode, in the trajectory of the target object taking a step, or in the process of the target object's legs moving from the starting position to the end position of the swing phase, the stiffness coefficient of the exoskeleton system controller changes in real time, and the stiffness coefficient gradually changes from a first value to a second value. The gradual change of the stiffness coefficient from the first value to the second value can be regular, such as a linear change, a gradual increase to the second value, etc.; or it can be an irregular change, such as a nonlinear change, etc. Therefore, the way in which the stiffness coefficient gradually changes from the first value to the second value is not specifically limited here. In the first posture training mode, when the target object takes a step, the change curve of the stiffness coefficient can be the same, different, or partially the same.

[0050] When the current training mode is the second gait training mode, the stiffness coefficient of the controller is set to a third value at the starting position of the swing phase of the target object; and the stiffness coefficient of the controller is set to a fourth value at the ending position of the swing phase of the target object; wherein the third value is greater than the fourth value, for example, when the third value is 10, the fourth value is 4; when the third value is 7.3, the fourth value is 1.8, and so on.

[0051] In the second gait training mode, in the trajectory of the target object taking a step, or in the process of the target object's legs moving from the starting position to the ending position of the swing phase, the stiffness coefficient of the exoskeleton system controller also changes in real time, and the stiffness coefficient changes from the third value to the fourth value. The change of the stiffness coefficient from the third value to the fourth value can be regular, such as linear change, gradual decrease to the fourth value, etc.; or it can be an irregular change, such as nonlinear change, etc. Therefore, the way the stiffness coefficient changes from the third value to the fourth value is not specifically limited here. In the second gait training mode, when the target object takes a step, the change curve of the stiffness coefficient can be the same, different, or partially the same.

[0052] In addition, the first gait training mode corresponds to the first period of the rehabilitation process of the target object, and the second gait training mode corresponds to the second period of the rehabilitation process of the target object, and the second period is located after the first period. Specifically, the first period can be an early period, and the second period can be a late period.

[0053] Therefore, in the first step training mode, when the target object's legs are in the starting position, the stiffness coefficient of the controller is relatively small. As the target object's legs move to the end position, the stiffness coefficient of the controller gradually increases, and the force provided by the exoskeleton system also gradually increases, thereby forming a trend of gait narrowing. Therefore, at the starting position of the first step training mode, the target object has a large degree of freedom of movement, and for the target object with limited lower limb strength in the initial stage, the foot can be lifted better. At the end position of the first step training mode, the target object has a small degree of freedom of movement, which allows the target object's legs to land better, thereby maintaining the walking gait. In addition, continuous training of the target object in the early stage can effectively improve the leg strength of the target object with lower limb hemiplegia. Due to the existence of the controller, as the target object's strength increases, the force of the exoskeleton system also has a certain redundancy, and there will not be a lot of discomfort and mismatch problems, which reduces the problem of training fatigue of the target object.

[0054] As the rehabilitation process progresses, the target subject's lower limb strength gradually recovers to a certain level of free movement. At this point, the training mode of the exoskeleton system can be switched to the second gait training mode. In this mode, the stiffness coefficient set by the controller at the starting position of the swing phase of the target subject is relatively large, and the stiffness coefficient set at the end position of the swing phase of the target subject is relatively small. As the target subject's legs move in the swing phase, the stiffness coefficient gradually decreases, and the force provided by the exoskeleton system also gradually decreases, thus forming a trend of gait diffusion. In this way, in the early stage of walking gait, the gait of the target subject is further corrected. At the end of the walking gait, the diffuse gait is actually a reduction in the role of the controller, allowing the target subject to better participate in the training, thereby turning passive training into training that the target subject can actively participate in. In this way, the target subject can experience the difference in step length and step height changes in this mode, and gradually train his brain to regain the feeling of walking.

[0055] In the rehabilitation process, the combination of the above two gait training modes can effectively improve the leg strength of the target subjects while reducing the problem of training fatigue and the resistance of the target subjects to rehabilitation training, so that the target subjects can actively participate in the training, thereby improving the effect of rehabilitation training.

[0056] In other embodiments, the current training mode can be determined according to the target object's stage of illness, and a strong training mode, a moderate training mode, and a gentle training mode are set in the exoskeleton system. The force control parameter is the force output by the motor in the exoskeleton system, wherein the strong training mode corresponds to the early stage of illness, the moderate training mode corresponds to the middle stage of illness, and the gentle training mode corresponds to the late stage of illness. If the target object is in the early stage of illness, the strong training mode is selected. In this mode, the force value of the exoskeleton system is set to be larger, and the force of the exoskeleton system is dominant, so that in this mode, almost all the forces required for the target object to walk are provided by the exoskeleton system, so that the target object walks strictly according to the reference gait trajectory. Because this mode corresponds to the early stage of illness of the target object, the force that the target object can provide is limited at this time, and in order to avoid further aggravation of the disease, almost all the forces are provided by the exoskeleton system, and in this mode, it is also easy for the target object to form muscle memory to remember the normal gait.

[0057] If the target subject is in the middle stage of the disease, a moderate training mode is selected. In this mode, the force of the exoskeleton system is set to a normal state, and the force of the target subject is allowed to participate in the training. That is, in this mode, the target subject is allowed to actively join the training process, and the deviation between the actual gait trajectory of the target subject and the reference gait trajectory is within the allowable range.

[0058] If the target subject is in the late stage of the disease, the gentle training mode is selected. In this mode, the force of the exoskeleton system is set to be small. At this time, the force of the target subject is dominant and the force of the exoskeleton system is auxiliary. In this mode, the target subject has a high degree of freedom of movement, and the reference gait trajectory is only used as a "reference". The actual gait trajectory of the target subject does not need to be based on the reference gait trajectory.

[0059] It is understandable that no specific limitation is made here regarding the current training mode and the setting of force control parameters.

[0060] See also Figure 3 , Figure 3 It is a flow chart of an embodiment of the gait training method of the present application.

[0061] Specifically, the following steps may be included:

[0062] Step S310: Acquire the leg data of the target object and determine the current training mode of the target object.

[0063] This step is the same as the above step S110 and will not be described again here.

[0064] Step S320: Match the leg data with the preset leg data of the preset object in the pre-stored trajectory set to obtain a matching result.

[0065] In some embodiments, the leg data includes thigh length data and calf length data, and the thigh length data and calf length data of the target object are matched with the preset thigh length data and calf length data of each preset object to obtain a matching result.

[0066] Step S330: In response to the matching result that the leg data does not match all preset leg data, prediction is performed based on the leg data to obtain a reference gait trajectory of the target object.

[0067] In some embodiments, if the matching result is that the leg data does not match all the preset leg data, it indicates that the leg data of the target object does not match the preset leg data of each preset object in the pre-stored trajectory set. Therefore, in order to obtain the reference gait trajectory of the target object, the exoskeleton system can be used to generate the initial gait trajectory of the target object according to the leg data, and then the sum of the leg data and the preset value is used as the maximum value in the search range, and the difference between the leg data and the preset value is used as the minimum value in the search range to determine the search range. Then, the preset leg data of the preset object in the pre-stored trajectory set that meets the search range is used to interpolate the initial gait trajectory to obtain the reference gait trajectory of the target object.

[0068] In addition, if the matching result obtained is that the leg data of the target object matches the preset leg data of a preset object, the preset gait trajectory corresponding to the preset object can be directly used as the reference gait trajectory of the target object, thereby avoiding waste of resources.

[0069] Step S340: Based on the reference gait trajectory and the current training mode, the force control parameters of the exoskeleton system are adjusted to adjust the walking gait trajectory of the target object to obtain an actual gait trajectory.

[0070] This step is the same as the above step S130, so it will not be described again here.

[0071] On the basis of passive gait, this application adds kinematics-based gait adjustment based on gait statistical information, so that the gait can be more adapted to the physiological parameters of the target object. At the same time, when controlling the target object for training, variable force control is introduced to dynamically adjust the gait trajectory in real time to make the gait smoother and more natural. And according to the training situation, the force control parameters can be adjusted to make the training more in line with the gait of the target object, so as to improve the effect of rehabilitation training. Specifically, two gait modes are introduced to meet the gait of the target object: gait narrowing mode, that is, the first gait training mode; gait diffusion mode, that is, the second gait training mode.

[0072] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0073] See also Figure 4 , Figure 4 4 is a schematic diagram of a framework of an embodiment of an electronic device 40 of the present application. The electronic device 40 includes a memory 41 and a processor 42 coupled to each other, and the processor 42 is used to execute program instructions stored in the memory 41 to implement the steps in any of the above-mentioned step training method embodiments. In a specific implementation scenario, the electronic device 40 may include but is not limited to: a microcomputer, a server, and in addition, the electronic device 40 may also include a mobile device such as a laptop computer and a tablet computer, which is not limited here.

[0074] Specifically, the processor 42 is used to control itself and the memory 41 to implement the steps in any of the above-mentioned step training method embodiments. The processor 42 can also be called a CPU (Central Processing Unit). The processor 42 may be an integrated circuit chip with signal processing capabilities. The processor 42 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 42 can be implemented by an integrated circuit chip.

[0075] See also Figure 5 , Figure 5 1 is a schematic diagram of a framework of an embodiment of a computer-readable storage medium 50 of the present application. The computer-readable storage medium 50 stores program instructions 501 that can be executed by a processor, and the program instructions 501 are used to implement the steps in any of the above-mentioned gait training method embodiments.

[0076] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0077] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0078] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0079] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0080] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

Claims

1. A gait training method, characterized in that: include: Acquiring leg data of a target object and determining a current training mode of the target object; Based on the leg data, obtaining a reference gait trajectory of the target object; Based on the reference gait trajectory and the current training mode, the force control parameters of the exoskeleton system are adjusted to adjust the walking gait trajectory of the target object to obtain an actual gait trajectory.

2. The method according to claim 1, characterized in that The obtaining a reference gait trajectory of the target object based on the leg data includes: generating an initial gait trajectory of the target object using the leg data; and, Based on the leg data, obtaining gait trajectories corresponding to a plurality of reference objects from a pre-stored trajectory set; The initial gait trajectory is interpolated using the gait trajectories corresponding to the plurality of reference objects to obtain the reference gait trajectory.

3. The method according to claim 2, characterized in that The acquiring, based on the leg data, gait trajectories corresponding to a plurality of reference objects from a pre-stored trajectory set comprises: Based on the leg data and the preset value, a search range is determined, wherein the sum of the leg data and the preset value is used as the maximum value in the search range, and the difference between the leg data and the preset value is used as the minimum value in the search range; In response to the preset leg data of the preset object in the pre-stored trajectory set satisfying the search range, the preset object is used as the reference object, and the preset gait trajectory corresponding to the preset object is used as the gait trajectory corresponding to the reference object.

4. The method according to claim 3, characterized in that The preset object is an object with normal gait; And / or, the method for generating a preset gait trajectory corresponding to the preset object includes: Recording the walking gait of the preset object to obtain an original gait trajectory; The original gait trajectory is smoothed to obtain the preset gait trajectory.

5. The method according to claim 3, characterized in that: The leg data includes thigh length data and calf length data; the preset value includes a first preset value and a second preset value; and determining the search range based on the leg data and the preset value includes: Based on the thigh length data and the first preset value, a first search range is determined, wherein the sum of the thigh length data and the first preset value is used as the maximum value in the first search range, and the difference between the thigh length data and the first preset value is used as the minimum value in the first search range; and, Based on the calf length data and the second preset value, a second search range is determined, wherein the sum of the calf length data and the second preset value is used as the maximum value in the second search range, and the difference between the calf length data and the second preset value is used as the minimum value in the second search range; In response to the preset leg data of the preset object in the pre-stored trajectory set satisfying the search range, taking the preset object as the reference object, and taking the preset gait trajectory corresponding to the preset object as the gait trajectory corresponding to the reference object, comprising: In response to the preset thigh length data of the preset object in the pre-stored trajectory set satisfying the first search range, and the preset calf length data satisfying the second search range, the preset object is used as the reference object, and the preset gait trajectory corresponding to the preset object is used as the gait trajectory corresponding to the reference object.

6. The method according to claim 1, characterized in that The determining the current training mode of the target object comprises: Based on the rehabilitation process of the target object, determining the current training mode of the target object; the force control parameter is the stiffness coefficient of the controller of the exoskeleton system; based on the reference gait trajectory and the current training mode, adjusting the force control parameter of the exoskeleton system to adjust the walking gait trajectory of the target object to obtain an actual gait trajectory, including: Based on the current training mode, determining the stiffness coefficient; When the exoskeleton system controls the target object to walk based on the reference gait trajectory, the stiffness coefficient is used to adjust the force applied by the exoskeleton system to the legs of the target object to obtain the actual gait trajectory of the target object.

7. The method according to claim 6, characterized in that When the current training mode is the first posture training mode, determining the stiffness coefficient of the controller of the exoskeleton system based on the current training mode includes: At the start position of the swing phase of the target object, the stiffness coefficient of the controller is set to a first value; at the end position of the swing phase of the target object, the stiffness coefficient of the controller is set to a second value; wherein the first value is smaller than the second value; Alternatively, when the current training mode is the second gait training mode, determining the stiffness coefficient of the controller of the exoskeleton system based on the current training mode includes: At the starting position of the swing phase of the target object, the stiffness coefficient of the controller is set to a third value; at the ending position of the swing phase of the target object, the stiffness coefficient of the controller is set to a fourth value; wherein the third value is greater than the fourth value.

8. The method according to claim 7, characterized in that The first step training mode corresponds to the first period of the rehabilitation process of the target subject; The second gait training pattern corresponds to a second period of the rehabilitation process of the target subject, and the second period is located after the first period.

9. An electronic device, characterized in that: It comprises a memory and a processor coupled to each other, wherein the processor is used to execute program instructions stored in the memory to implement the gait training method according to any one of claims 1 to 8.

10. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the gait training method according to any one of claims 1 to 8 is implemented.

Images