Lower limb rehabilitation walking aid system

Abstract

The embodiment of the application discloses a lower limb rehabilitation walking aid system. The system comprises a lower limb rehabilitation walking aid; wherein the lower limb rehabilitation walking aid comprises a movable device, a first adjusting device, a second adjusting device, a human body fixing device and a master control device; wherein the master control device comprises a pressure acquisition module, which is used for acquiring the pressure applied on the human body fixing device by a target object through wearing the human body fixing device for lower limb rehabilitation training through a force feedback motor; a target weight loss obtaining module, which is used for obtaining the target weight loss of the target object; a motor output adjusting parameter obtaining module, which is used for performing proportional integral differential control according to the error between the pressure and the target weight loss to obtain the motor output adjusting parameter; and a torque motor output adjusting module, which is used for adjusting the output of the first torque motor and / or the second torque motor according to the motor output adjusting parameter. The technical scheme of the embodiment of the application can accurately reduce the weight during the lower limb rehabilitation training.

Description

TECHNICAL FIELD

[0001] The embodiment of the present application relates to the technical field of physiotherapy, in particular to a lower limb rehabilitation walking aid system. BACKGROUND

[0002] Stroke or cerebral apoplexy patients, post-traumatic rehabilitation patients, neuromuscular disease patients and the elderly need to improve the motor ability through rehabilitation training due to muscle strength change or trauma.

[0003] According to muscle strength classification, the Medical Research Council (MRC) score standard is usually used, which can be divided into 0 to 5 levels, wherein 0 level represents complete muscle contraction; 1 level represents slight muscle contraction, but cannot produce joint activity; 2 level can produce joint activity against gravity; 3 level can complete joint activity against gravity, but cannot resist external force; 4 level can produce joint activity against certain external force; and 5 level represents normal muscle strength. 0 to 3 levels have weak action ability and poor resistance to external intervention force, so the external force is needed to assist movement.

[0004] In particular, for lower limb rehabilitation training (which requires autonomous joint activity) tasks, 2 level patients are the main objects of the weight reduction technology, because these patients cannot stand autonomously or resist gravity, and weight reduction can help them to start movement and rehabilitation training again. Although 3 to 4 level muscle strength patients can resist gravity, they are still limited in the recovery process, and weight reduction can help them to enhance muscle strength and improve movement quality.

[0005] However, precise weight reduction cannot be performed in the lower limb rehabilitation training process at present, and it is urgent to solve the problem. SUMMARY

[0006] The embodiment of the present application provides a lower limb rehabilitation walking aid system, which solves the problem that precise weight reduction cannot be performed in the lower limb rehabilitation training process.

[0007] According to an aspect of the present application, a lower limb rehabilitation walking aid system can include: a lower limb rehabilitation walking aid; wherein,

[0008] The lower limb rehabilitation walking aid includes a movable device that can move on the ground, a first adjusting device, a second adjusting device, a human body fixing device and a main control device, one end of the movable device is connected with the first adjusting device in a V-shaped rotation mode and the other end is connected with the second adjusting device in a V-shaped rotation mode, the first adjusting device is connected with the second adjusting device in an X-shaped rotation mode, the first adjusting device is provided with a first torque motor and a force feedback motor, the force feedback motor is rigidly connected with the human body fixing device, and the second adjusting device is provided with a second torque motor.

[0009] The master control device comprises a pressure acquisition module, a target weight loss obtaining module, a motor output adjustment parameter obtaining module and a torque motor output adjustment module.

[0010] The pressure acquisition module is configured to acquire, through the force feedback motor, the pressure applied on the human body fixing device by a target object performing lower limb rehabilitation training through the human body fixing device.

[0011] The target weight loss obtaining module is configured to obtain the target weight loss of the target object.

[0012] The motor output adjustment parameter obtaining module is configured to perform proportional integral derivative control according to the error between the pressure and the target weight loss to obtain the motor output adjustment parameter.

[0013] The torque motor output adjustment module is configured to adjust the output of the first torque motor and / or the second torque motor according to the motor output adjustment parameter to adjust the opening and closing angle between the first adjustment device and the second adjustment device, wherein the opening and closing angle is negatively correlated with the supporting force provided to the target object through the human body fixing device, and the supporting force is used to resist the gravity of the target object.

[0014] The lower limb rehabilitation walker described in the embodiment of the present application performs PID control on the error between the target weight loss and the actual supporting force provided to the target object, adjusts the output of the torque motor, and thus ensures the accuracy of the torque motor output, and further realizes the effect of precise weight loss in the lower limb rehabilitation training process.

[0015] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0017] Figure 1 is a structural block diagram of a lower limb rehabilitation walking system according to an embodiment of the present application;

[0018] Figure 2 is a schematic diagram of a lower limb rehabilitation walker in a lower limb rehabilitation walking system according to an embodiment of the present application;

[0019] Figure 3 is a structural block diagram of another lower limb rehabilitation walking system according to an embodiment of the present application;

[0020] Figure 4 is a structural block diagram of still another lower limb rehabilitation walking aid system according to an embodiment of the present application;

[0021] Figure 5a is a schematic diagram of an IMU sensor C and sEMG acquisition module in still another lower limb rehabilitation walking aid system according to an embodiment of the present application;

[0022] Figure 5b is a schematic diagram of a plantar pressure measurement module in still another lower limb rehabilitation walking aid system according to an embodiment of the present application;

[0023] Figure 6a is a schematic diagram of multi-modal data acquisition in still another lower limb rehabilitation walking aid system according to an embodiment of the present application;

[0024] Figure 6b is a structural block diagram of a corresponding sEMG acquisition module in still another lower limb rehabilitation walking aid system according to an embodiment of the present application; Figure 6a

[0025] Figure 6c is a structural block diagram of a corresponding IMU acquisition module in still another lower limb rehabilitation walking aid system according to an embodiment of the present application; Figure 6a

[0026] Figure 6d is a structural block diagram of a corresponding plantar pressure measurement module in still another lower limb rehabilitation walking aid system according to an embodiment of the present application; Figure 6a

[0027] Figure 7 is a structural block diagram of still another lower limb rehabilitation walking aid system according to an embodiment of the present application;

[0028] Figure 8 is a work flow diagram of still another lower limb rehabilitation walking aid system according to an embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to make the personnel in the art better understand the present application scheme, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0030] ​​​It should be noted that the terms "first", "second", and the like in the description and in the claims of the present application and above-described accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular sequential or chronological order. It should be understood that the data thus used can be interchanged, where appropriate, so that the embodiments of the application described herein can be carried out in other than the order shown or described herein. The case of "target", "original" and the like is similar, and will not be repeated here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0031] Figure 1 Figure 1 is a structural block diagram of a lower limb rehabilitation walking aid system provided by an embodiment of the present application. The present embodiment can be applied to the case of weight reduction during lower limb rehabilitation training.

[0032] Referring to Figure 1 The lower limb rehabilitation walking aid system described in the present embodiment comprises a lower limb rehabilitation walking aid A, wherein,

[0033] The lower limb rehabilitation walking aid A comprises a movable device A1 that can move on the ground, a first adjusting device A2, a second adjusting device A3, a human body fixing device A4 and a master control device A5. One end of the movable device A1 is connected to the first adjusting device A2 in a V-shaped rotation and the other end is connected to the second adjusting device A3 in a V-shaped rotation. The first adjusting device A2 is connected to the second adjusting device A3 in an X-shaped rotation. The first adjusting device A2 is provided with a first torque motor and a force feedback motor. The force feedback motor is rigidly connected to the human body fixing device A4. The second adjusting device A3 is provided with a second torque motor.

[0034] The master control device A5 comprises a pressure acquisition module A51, a target weight reduction obtaining module A52, a motor output adjustment parameter obtaining module A53 and a torque motor output adjustment module A54.

[0035] The pressure acquisition module A51 is configured to acquire, through the force feedback motor, the pressure applied to the human body fixing device A4 by a target object performing lower limb rehabilitation training by wearing the human body fixing device A4.

[0036] The target weight reduction obtaining module A52 is configured to obtain the target weight reduction of the target object.

[0037] The motor output adjustment parameter obtaining module A53 is configured to perform proportional integral derivative control according to the error between the pressure and the target weight reduction to obtain the motor output adjustment parameter.

[0038] The torque motor output adjustment module A54 is configured to adjust the output of the first torque motor and / or the second torque motor according to the motor output adjustment parameter, so as to adjust the opening and closing angle between the first adjustment device A2 and the second adjustment device A3, wherein the opening and closing angle is negatively correlated with the supporting force provided by the human body fixing device A4 to the target object, and the supporting force is used to resist the gravity of the target object.

[0039] Hereinafter, the lower limb rehabilitation walking aid A will be described in detail with reference to the accompanying drawings. Figure 2 The lower limb rehabilitation walking aid A is shown as an example for illustrative description.

[0040] For example, from the perspective of hardware devices, the lower limb rehabilitation walking aid A includes a movable device A1, a first adjustment device A2, a second adjustment device A3, a human body fixing device A4, two torque motors (i.e., the first torque motor described above) A6 arranged on the first adjustment device A2, two torque motors (i.e., the second torque motor described above) A6 arranged on the second adjustment device A2, and a force feedback motor A7. On this basis, the master control device A5 can be understood as a software device in the lower limb rehabilitation walking aid A, which can be realized by a micro control unit (MCU) embedded in the lower limb rehabilitation walking aid A.

[0041] On this basis, the target object can be understood as an object wearing the human body fixing device A4, and the lower limb rehabilitation walking aid A is mainly responsible for assisting the target object to support and walk, thereby performing lower limb rehabilitation training. Through the force feedback motor A7, the pressure applied by the target object on the human body fixing device A4 can be obtained. Since the pressure and the supporting force actually provided by the human body fixing device A4 to the target object are mutual forces, the supporting force can be represented by the pressure.

[0042] The target weight reduction can be understood as the gravity that is expected to be reduced for the target object during the lower limb rehabilitation training, i.e., the supporting force that is expected to be provided for the target object. The target weight reduction can be calculated by the lower limb rehabilitation walking aid A or by other devices (such as a host computer) cooperating with the lower limb rehabilitation walking aid A. This can be set according to actual needs, and is not limited herein.

[0043] It should be noted that the lower limb rehabilitation walking aid A provides the supporting force for the target object through the torque motor A6, but there may be a difference between the actual output of the torque motor A6 and the expected output, which may result in a difference between the actual supporting force provided by the lower limb rehabilitation walking aid A for the target object and the expected supporting force (i.e., the target weight reduction), thereby failing to achieve precise weight reduction during rehabilitation training.

[0044] To solve the above technical problems, the embodiment of the present application carries out proportional-integral-derivative (PID) control according to the error between the pressure and the target weight loss, to obtain a motor output adjustment parameter, which can be understood as a parameter for adjusting the output of the torque motor A6, and further can be understood as a parameter for adjusting the output of the force feedback motor A7. On this basis, the PID control can be composed of the following three parts: proportional (P) control: providing an output proportional to the error, for quickly responding to the state change of the target object; integral (I) control: for eliminating accumulated error, compensating for long-term deviation through integral processing of the error, ensuring long-term accuracy; and derivative (D) control: predictive adjustment of the rate of change of the error, suppressing oscillation, providing smoother weight loss adjustment, and ensuring the stability of the target object training.

[0045] Further, the output of the first torque motor A6 and / or the second torque motor A6 can be adjusted according to the motor output adjustment parameter, to adjust the opening and closing angle Angle between the first adjustment device A2 and the second adjustment device A3, and further to adjust the opening and closing height Height between the movable device A1 and the second adjustment device A3. It should be noted that the smaller the opening and closing angle Angle, the higher the opening and closing height Height, so that the upward supporting force provided by the human body fixing device A4 to the target object is greater, i.e. the target object resists more gravity; and the larger the opening and closing angle Angle, the lower the opening and closing height Height, so that the upward supporting force provided by the human body fixing device A4 to the target object is smaller, i.e. the target object resists less gravity. That is, the human body fixing device A4 plays a role in protecting the target object and providing supporting force to achieve weight loss when the opening and closing angle Angle and the opening and closing height Height change, and the opening and closing angle Angle and the provided supporting force are negatively correlated.

[0046] The lower limb rehabilitation walking aid described in the embodiment of the present application carries out PID control on the error between the target weight loss and the actual supporting force provided to the target object, to adjust the output of the torque motor, thereby ensuring the accuracy of the torque motor output, and further achieving the effect of precise weight loss in the lower limb rehabilitation training process.

[0047] An optional technical solution, the master control device further comprises a force feedback motor output adjustment module:

[0048] The force feedback motor output adjustment module is configured to adjust the output of the force feedback motor according to the motor output adjustment parameter, to control the human body fixing device to rotate around the target object.

[0049] Wherein, in the case of the support force provided for the target object is reduced, the target object is likely to lean forward; and in the case of the support force provided for the target object is increased, the target object is likely to lean backward. On this basis, in order to ensure the stability of the center of gravity of the target object, in the case of the force feedback motor is rigidly connected with the human body fixing device, the output of the force feedback motor can be adjusted according to the motor output adjustment parameter, so that the human body fixing device rotates around the target object to ensure that the target object is in an upright state. For example, if the support force is reduced, the human body fixing device is controlled to rotate to the rear of the target object to pull up the target object; otherwise, the human body fixing device is controlled to rotate to the rear of the target object to prop up the target object.

[0050] The above technical solution, on the one hand, by adjusting the output of the force feedback motor, the stability of the center of gravity of the target object can be maintained, thereby ensuring the safety of the target object during the lower limb rehabilitation training process.

[0051] On the other hand, through the cooperative work between the torque motor and the force feedback motor, it is ensured that the target object is always properly supported during the entire lower limb rehabilitation training process, effectively improving the safety and comfort.

[0052] Figure 3 is another structural block diagram of a lower limb rehabilitation walking aid system provided by an embodiment of the present application. The present embodiment is optimized on the basis of the above technical solutions. In the present embodiment, optionally, the above system further comprises: an upper computer; wherein the upper computer comprises: a control instruction sending module; wherein the control instruction sending module is used to send control instructions to the lower limb rehabilitation walking aid; and a target weight reduction obtaining module, which is specifically used to analyze the control instructions to obtain the target weight reduction of the target object in response to the received control instructions. Wherein, the explanations of the same or corresponding terms as in the above embodiments are not repeated here.

[0053] Specifically, referring to Figure 3 The lower limb rehabilitation walking aid system described in the present embodiment comprises: a lower limb rehabilitation walking aid A and an upper computer B; wherein,

[0054] The lower limb rehabilitation walking aid A comprises a movable device A1 which can move on the ground, a first adjusting device A2, a second adjusting device A3, a human body fixing device A4 and a master control device A5, one end of the movable device A1 is connected with the first adjusting device A2 in a V-shaped rotary manner and the other end is connected with the second adjusting device A3 in a V-shaped rotary manner, the first adjusting device A2 is connected with the second adjusting device A3 in an X-shaped rotary manner, the first adjusting device A2 is provided with a first torque motor and a force feedback motor, the force feedback motor is rigidly connected with the human body fixing device A4, and the second adjusting device A3 is provided with a second torque motor;

[0055] The master device A5 comprises a pressure obtaining module A51, a target weight loss obtaining module A52, a motor output adjustment parameter obtaining module A53 and a torque motor output adjustment module A54.

[0056] The host computer B comprises a control instruction sending module B1; wherein,

[0057] The control instruction sending module B1 is configured to send the control instruction to the lower limb rehabilitation walker A.

[0058] The pressure obtaining module A51 is configured to obtain, through the force feedback motor, the pressure applied on the human body fixing device A4 by a target object performing lower limb rehabilitation training through the human body fixing device A4.

[0059] The target weight loss obtaining module A52 is configured to analyze the control instruction to obtain the target weight loss of the target object in response to the received control instruction.

[0060] The motor output adjustment parameter obtaining module A53 is configured to perform proportional-integral-derivative control according to the error between the pressure and the target weight loss to obtain the motor output adjustment parameter.

[0061] The torque motor output adjustment module A54 is configured to adjust the output of the first torque motor and / or the second torque motor according to the motor output adjustment parameter to adjust the opening and closing angle between the first adjustment device A2 and the second adjustment device A3, wherein the opening and closing angle is negatively correlated with the supporting force provided to the target object by the human body fixing device A4, and the supporting force is used to resist the gravity of the target object.

[0062] The technical scheme of the embodiment of the present application calculates the target weight loss through the host computer, generates a corresponding control instruction, and then sends the control instruction to the lower limb rehabilitation walker, so that the lower limb rehabilitation walker analyzes the target weight loss based on the control instruction, which can reduce the calculation pressure of the lower limb rehabilitation walker compared with calculating the target weight loss by the lower limb rehabilitation walker, so as to focus more on the PID control, and further realize precise weight loss.

[0063] Figure 4 is another structure block diagram of a lower limb rehabilitation walking system provided by the embodiment of the present application. The embodiment is optimized on the basis of the above technical schemes. In the embodiment, optionally, the host computer further comprises a data obtaining module and a control instruction generating module; wherein the data obtaining module is configured to obtain training data of the target object; and the control instruction generating module is configured to determine the motion state of the target object according to the training data, and generate the control instruction according to the motion state. Wherein, the same or corresponding terms as in the above embodiments are not repeated here.

[0064] Specifically, referring to Figure 4The lower limb rehabilitation walking aid system comprises a lower limb rehabilitation walking aid A and a host computer B.

[0065] The lower limb rehabilitation walking aid A comprises a movable device A1 that can move on the ground, a first adjusting device A2, a second adjusting device A3, a human body fixing device A4, and a master control device A5. One end of the movable device A1 is connected to the first adjusting device A2 in a V-shaped manner, and the other end is connected to the second adjusting device A3 in a V-shaped manner. The first adjusting device A2 and the second adjusting device A3 are connected in an X-shaped manner. The first adjusting device A2 is provided with a first torque motor and a force feedback motor. The force feedback motor is rigidly connected to the human body fixing device A4. The second adjusting device A3 is provided with a second torque motor.

[0066] The master control device A5 comprises a pressure acquisition module A51, a target weight loss obtaining module A52, a motor output adjustment parameter obtaining module A53, and a torque motor output adjustment module A54.

[0067] The host computer B comprises a data acquisition module B3, a control instruction generation module B2, and a control instruction sending module B1.

[0068] The data acquisition module B3 is used to acquire training data of a target object.

[0069] The control instruction generation module B2 is used to determine the motion state of the target object according to the training data, and generate a control instruction according to the motion state.

[0070] The control instruction sending module B1 is used to send the control instruction to the lower limb rehabilitation walking aid A.

[0071] The pressure acquisition module A51 is used to acquire the pressure applied by the target object on the human body fixing device A4 during lower limb rehabilitation training through the force feedback motor.

[0072] The target weight loss obtaining module A52 is used to analyze the control instruction received to obtain the target weight loss of the target object.

[0073] The motor output adjustment parameter obtaining module A53 is used to perform proportional integral derivative control according to the error between the pressure and the target weight loss to obtain the motor output adjustment parameter.

[0074] The torque motor output adjustment module A54 is used to adjust the output of the first torque motor and / or the second torque motor according to the motor output adjustment parameter to adjust the opening and closing angle between the first adjusting device A2 and the second adjusting device A3. The opening and closing angle is negatively correlated with the supporting force provided by the human body fixing device A4 to the target object, and the supporting force is used to resist the gravity of the target object.

[0075] The training data of the target object can be understood as data related to the lower limb rehabilitation training process of the target object. On this basis, in combination with the application scenarios that the embodiments of the present application can involve, the training data can be multi-modal data, which can include at least two of lower limb surface electromyography signals, lower limb inertial measurement signals, plantar pressure signals, and actual body weight. Of course, the training data can also be single-modal data, which can be selected according to actual needs, and is not specifically limited here.

[0076] On this basis, in combination with the application scenarios that the embodiments of the present application can involve, in the case of multi-modal training data, the above system can further include at least one of an inertial measurement unit (IMU) sensor (or IMU acquisition module), a surface electromyography (sEMG) acquisition module, and a plantar pressure measurement module.

[0077] The data acquisition module is specifically configured to acquire multi-modal data of the target object through at least two steps as follows:

[0078] The lower limb inertial measurement signal of the target object is acquired through the inertial measurement unit sensor.

[0079] The lower limb surface electromyography signal of the target object is acquired through the surface electromyography acquisition module.

[0080] The plantar pressure signal of the target object is acquired through the plantar pressure measurement module; and

[0081] The actual body weight of the target object is acquired. The actual body weight can be directly measured by a weighing scale and then input into the host computer.

[0082] Exemplarily, Figure 5a The IMU sensor C and the sEMG acquisition module D are shown, Figure 5b The plantar pressure measurement module is shown, Figure 6a- Figure 6d The multi-modal data acquisition process is shown. Specifically,

[0083] (1) sEMG acquisition module: refer to Figure 6a and Figure 6b The signal amplified by the MCU processing operation amplifier is uploaded to the host computer through a Bluetooth serial communication mode for subsequent processing.

[0084] (2) IMU acquisition module: refer to Figure 6a and Figure 6cThe system transmits the changes in lower limb joint angles and lower limb movement trajectories acquired by the IMU sensor via serial communication and Bluetooth, and uploads the corresponding signals to the host computer for further processing. It may also include filtering circuits and calibration circuits (such as calibrating temperature difference and zero drift).

[0085] (3) Plantar pressure measurement module: See Figure 6a and Figure 6d The system acquires plantar pressure signals via a pressure sensor, a multi-channel data acquisition circuit, and an analog-to-digital converter (ADC) array. These signals are then transmitted via serial communication and Bluetooth to a host computer for further processing. The system may also include filtering and operational amplifier circuits.

[0086] The power module may include a 3.3V voltage regulator circuit and a lithium battery charging and discharging circuit.

[0087] The signal amplification circuit can use a three-op-amp differential amplifier circuit to amplify the electrical signal.

[0088] The signal filtering circuit filters the acquired electrical signal based on its characteristics to obtain a high-quality signal.

[0089] The Bluetooth module can upload the corresponding signals to the host computer via transparent transmission, adopting a slave mode.

[0090] The electromyography (EMG) acquisition electrodes can be dry electrode pads. Each EMG acquisition module requires a pair of dry electrode pads. The electrode pair is worn on the rectus femoris, sartorius, vastus medialis, and vastus lateralis muscles of the target subject's left and right legs.

[0091] Multi-channel data acquisition circuits commonly use multiplexers (MUX) to switch between multiple sensors, or use multi-channel ADCs to acquire data from multiple sensors at once.

[0092] In practical applications, optionally, the host computer can perform data preprocessing after acquiring multimodal data. For example, data preprocessing mainly includes:

[0093] Denoising techniques, such as filtering and wavelet transform, are employed. High-pass filters remove low-frequency noise, such as sensor drift or slow changes, making them suitable for extracting the dynamic components of lower limb IMU signals. Band-pass filters are used to process sEMG signals, extracting muscle activity features. Moving average filtering is used to smooth the signal, reducing random noise and making it suitable for smoothing pressure sensors. Wavelet transform is used to analyze non-stationary signals, such as sEMG and lower limb IMU signals. Wavelet transform can effectively separate noise from useful signals, making it suitable for processing complex signals with multiple frequency components.

[0094] Data cleaning, abnormal signal detection and processing, rejection or replacement, and missing signal processing, including deletion and interpolation, etc.

[0095] Further, according to the training data, the motion state of the target object is determined, and then the control instruction is generated according to the motion state, and in the embodiment of the application, the motion state can include at least one of gait stability, muscle fatigue condition and center of gravity change, etc., to adjust the weight reduction support of the lower limb rehabilitation walking aid.

[0096] The technical scheme of the embodiment of the application can realize adaptive weight reduction by determining the target weight reduction matched with the motion state, so as to ensure that the target object can obtain appropriate support intensity in different motion states, and avoid the cases of excessive weight reduction or insufficient weight reduction; in particular, the above adaptive weight reduction process can be performed in real time, so as to better ensure that the target object is always in the best weight-bearing state, and effectively improve the training effect.

[0097] An optional technical scheme, in the case that the motion state indicates that the target object has a falling tendency, the control instruction includes a weight adjustment sub-instruction and a support force adjustment sub-instruction, and the master control device further includes a support force adjustment module; wherein,

[0098] The target weight reduction obtaining module is further used for analyzing the weight adjustment sub-instruction in response to the received weight adjustment sub-instruction, to obtain the target weight reduction of the target object.

[0099] The support force adjustment module is used for adjusting the output of the force feedback motor in response to the received support force adjustment sub-instruction, to realize the rotation of the human body fixing device around the target object.

[0100] The above technical scheme, in the case that the target object has a falling tendency is judged by the muscle fatigue degree and the gait stability, etc., can provide additional support force for the target object by adjusting the output of the force feedback motor, to ensure the safety of the target object in the lower limb rehabilitation training process, and avoid accidental injury.

[0101] Another optional technical scheme, the upper computer further includes a personalized training scheme obtaining module; wherein,

[0102] The personalized training scheme obtaining module is used for obtaining the personalized training scheme of the target object.

[0103] The control instruction generation module is specifically used for determining the motion state of the target object according to the fusion result, and generating the control instruction according to the motion state and the personalized training scheme.

[0104] The above technical solution determines the target weight loss by combining a personalized training scheme, the personalized weight loss process ensures the personalization of the lower limb rehabilitation training of the target object, thereby improving the training effect.

[0105] On this basis, the upper computer further includes a rehabilitation training record acquisition module and a personalized training scheme generation module.

[0106] The rehabilitation training record acquisition module is configured to acquire rehabilitation training records of the target object during the rehabilitation training process using the lower limb rehabilitation walker.

[0107] The personalized training scheme generation module is configured to generate a personalized training scheme based on the rehabilitation training records.

[0108] The above technical solution can generate a personalized training scheme using rehabilitation training records, and on this basis, the personalized training scheme can be adjusted in combination with multi-modal data, thereby adapting to different training progress and training needs of the target object, enabling the target object to obtain the most suitable rehabilitation training for their own situation, and improving the training effect.

[0109] Figure 7 is another structure block diagram of a lower limb rehabilitation walking system provided by an embodiment of the present application. The present embodiment is optimized based on the above technical solutions. In the present embodiment, the training data is multi-modal data, the multi-modal data includes at least two kinds of single-modal data, the control instruction generation module includes a fusion sub-module and a control instruction generation sub-module, the fusion sub-module is configured to perform fusion related to the at least two kinds of single-modal data to obtain a fusion result, and the control instruction generation sub-module is configured to determine the motion state of the target object according to the fusion result and generate the control instruction according to the motion state. The explanations of the same or corresponding terms as in the above embodiments are not repeated here.

[0110] Specifically, referring to Figure 7 The lower limb rehabilitation walking system described in the present embodiment includes a lower limb rehabilitation walker A and an upper computer B, wherein

[0111] The lower limb rehabilitation walker A includes a movable device A1 that can move on the ground, a first adjusting device A2, a second adjusting device A3, a human body fixing device A4, and a main control device A5. One end of the movable device A1 is connected to the first adjusting device A2 in a V-shaped rotation, and the other end is connected to the second adjusting device A3 in a V-shaped rotation. The first adjusting device A2 and the second adjusting device A3 are connected in an X-shaped rotation. The first adjusting device A2 is provided with a first torque motor and a force feedback motor. The force feedback motor is rigidly connected to the human body fixing device A4. The second adjusting device A3 is provided with a second torque motor.

[0112] The master device A5 comprises a pressure acquisition module A51, a target weight loss obtaining module A52, a motor output adjustment parameter obtaining module A53 and a torque motor output adjustment module A54.

[0113] The host computer B comprises a data acquisition module B3, a control instruction generation module B2 and a control instruction sending module B1, the control instruction generation module B2 comprises a fusion sub-module B21 and a control instruction generation sub-module B22; wherein,

[0114] The data acquisition module B3 is configured to acquire multi-modal data of the target object, wherein the multi-modal data comprises at least two kinds of single-modal data.

[0115] The fusion sub-module B21 is configured to perform fusion related to the at least two kinds of single-modal data to obtain a fusion result.

[0116] The control instruction generation sub-module B22 is configured to determine a motion state of the target object according to the fusion result, and generate a control instruction according to the motion state.

[0117] The control instruction sending module B1 is configured to send the control instruction to the lower limb rehabilitation walker A.

[0118] The pressure acquisition module A51 is configured to acquire, through the force feedback motor, a pressure applied on the human body fixing device A4 by the target object performing lower limb rehabilitation training through the human body fixing device A4.

[0119] The target weight loss obtaining module A52 is configured to analyze the control instruction received to obtain a target weight loss of the target object.

[0120] The motor output adjustment parameter obtaining module A53 is configured to perform proportional integral differential control according to an error between the pressure and the target weight loss to obtain a motor output adjustment parameter.

[0121] The torque motor output adjustment module A54 is configured to adjust an output of the first torque motor and / or the second torque motor according to the motor output adjustment parameter to adjust an opening and closing angle between the first adjustment device A2 and the second adjustment device A3, wherein the opening and closing angle is negatively correlated with a supporting force provided to the target object by the human body fixing device A4, and the supporting force is used to resist a gravity of the target object.

[0122] Wherein, the fusion related to the at least two kinds of single-modal data is performed to obtain the fusion result, and then the motion state is determined according to the fusion result, and the fusion result helps to more comprehensively evaluate the motion state.

[0123] On this basis, in combination with the application scenarios that may be involved in the embodiments of the present application, optional fusion schemes include a data level fusion scheme, a feature level fusion scheme and a decision level fusion scheme.

[0124] The data-level fusion scheme can be understood as directly fusing the original signals after the sensors collect the original signals, for example, putting the features of the plantar pressure signals, sEMG signals and lower limb IMU signals into a feature vector for analysis. This fusion scheme can retain all information, but is susceptible to noise and signal redundancy. The feature-level fusion scheme is to extract features from each sensor first, and then fuse the features of each sensor. This fusion scheme can reduce noise while maintaining signal diversity. For example, muscle activity features of sEMG, acceleration features of IMU and gait features of plantar pressure can be combined to evaluate the motor ability of the target object. The decision-level fusion scheme is to analyze and decide independently by each sensor, and then fuse the decision results of each sensor. This fusion scheme is suitable for distributed decision of a multi-sensor system.

[0125] The optional fusion scheme includes machine learning algorithms and deep learning models. The machine learning algorithm may be, for example, a decision tree, a support vector machine (SVM) and a random forest, which can be based on multi-modal features for classification or regression analysis to determine the movement state and weight-bearing requirement of the target object in real time. The deep learning model may be, for example, a convolutional neural network (CNN) and a recurrent neural network (RNN), which can automatically extract high-dimensional features from multi-modal data to achieve more accurate state recognition and weight adjustment.

[0126] The optional fusion scheme includes Kalman filtering, which can be used to fuse lower limb IMU signals and plantar pressure signals to improve the accuracy of gait analysis and posture analysis. There can also be weighted fusion, which gives different weights to the features of different sensors, for example, giving higher weight to sEMG signals when detecting fatigue, and giving higher weight to lower limb IMU signals when detecting posture, etc., which is not specifically limited herein.

[0127] The technical scheme of the embodiment of the application can provide comprehensive evaluation of the movement state by collecting and fusing multi-modal data, thereby improving the accuracy of movement state evaluation and the accuracy of target weight determination.

[0128] An optional technical scheme, the fusion sub-module includes a single-modal feature obtaining unit and a feature fusion unit; wherein,

[0129] The single-modal feature obtaining unit is configured to, for each single-modal data in the multi-modal data, extract features from the single-modal data to obtain single-modal features;

[0130] The feature fusion unit is configured to fuse the obtained single-modal features to obtain a fusion result.

[0131] The feature-level fusion scheme can reduce noise while maintaining signal diversity.

[0132] Optionally, the single-modal feature obtaining unit is specifically configured to, in a case where the single-modal data is a lower limb surface electromyography signal, perform feature extraction on the lower limb surface electromyography signal to obtain single-modal features representing an activation degree and / or a fatigue condition of a lower limb muscle of the target object.

[0133] For example, the sEMG signal is used to analyze the activation degree and / or the fatigue condition of the lower limb muscle. The feature extraction scheme can include at least one of a time-domain feature, a frequency-domain feature, and a time-frequency domain feature. Specifically,

[0134] The time-domain feature includes: (1) mean and variance: used to analyze the overall level and fluctuation of muscle activity; (2) root mean square (RMS): reflecting the muscle contraction intensity, which is a commonly used feature for analyzing muscle workload; and (3) integrated electromyography (IEMG): used to evaluate the overall intensity of muscle activity.

[0135] The frequency-domain feature includes: (1) medium frequency (MDF) and mean power frequency (MPF): these two features can reflect the fatigue state of the muscle. As fatigue increases, the signal frequency usually decreases.

[0136] The time-frequency domain feature includes: (1) wavelet transform and short-time Fourier transform: through time-frequency analysis methods, the frequency components of the electromyography signal at different times can be extracted, which helps to identify the muscle contraction pattern and fatigue condition.

[0137] The above technical solution realizes effective feature extraction of the lower limb surface electromyography signal.

[0138] Optionally, the single-modal feature obtaining unit is specifically configured to, in a case where the single-modal data is a lower limb inertial measurement signal, perform feature extraction on the lower limb inertial measurement signal to obtain single-modal features representing at least one of a swing amplitude, a swing rhythm, a stability, an abnormality, and a tilt condition of a gait of the target object.

[0139] For example, the IMU sensor can measure the acceleration, angular velocity, and attitude of the target object through an accelerometer and a gyroscope. The feature extraction scheme can include: angular velocity: measuring the rotational angular velocity during lower limb movement through the gyroscope to analyze the swing amplitude and rhythm of the gait; linear acceleration: used to detect the acceleration and deceleration of the lower limb during walking, which helps to judge the stability of the gait; and attitude estimation: calculating the attitude change of the lower limb through the fusion of the accelerometer and the gyroscope to analyze the abnormality or tilt phenomenon in the gait.

[0140] The technical solution achieves effective feature extraction of the lower limb IMU signal.

[0141] In another optional solution, the single-modal feature obtaining unit is specifically configured to: in the case that the single-modal data is a plantar pressure signal, performing feature extraction on the plantar pressure signal to obtain single-modal features representing the stability of the gait of the target object.

[0142] For example, the plantar pressure measurement module sensor can detect the pressure changes of different areas of the foot during gait. In this example, the pressure distribution can be analyzed to determine whether the target object has an abnormal force mode, and to help determine the stability of walking; the foot contact area: according to the pressure distribution, the size of the contact area between the foot and the ground is determined, and then the stability during gait is evaluated.

[0143] The technical solution achieves effective feature extraction of the plantar pressure signal.

[0144] In order to better understand the working process of the lower limb rehabilitation walking aid system as a whole, the following examples are given for illustrative purposes. For example, refer to Figure 8 : Figure 8

[0145] In order to realize adaptive weight reduction of the lower limb rehabilitation walking aid based on multi-modal, the actual body weight, sEMG signal, lower limb IMU signal and plantar pressure signal of the target object are collected in this example, and these signals are processed by feature extraction and feature fusion, and the control instructions are sent to the lower limb rehabilitation walking aid through the upper computer. At this time, the lower limb rehabilitation walking aid can realize adaptive weight reduction by adjusting the opening and closing height of the lower limb rehabilitation walking aid in real time through the built-in torque motor and force feedback motor through PID control.

[0146] The PID control adjusts the motor output to ensure that the support force provided by the lower limb rehabilitation walking aid to the target object matches the real-time motion state of the target object. For example, the support force needs to be increased when the gait is unstable, and the support force is gradually reduced when the muscle activity is normal. The PID control calculates the error between the current motor output support force and the target weight reduction, and calculates a new motor output adjustment parameter according to the error, and adjusts the motor output accordingly. Moreover, the force feedback motor can detect the real-time weight of the target object, and if the pressure applied by the target object exceeds the set range, the PID control can automatically increase the weight reduction support.

[0147] In addition, the system can continuously monitor the motion state and support condition of the target object, and dynamically adjust the parameters of the PID control according to the real-time monitoring results, so as to optimize the weight reduction effect.

[0148] The specific steps of adaptive weight reduction are as follows: ​

[0149] Initialization: The system sets the initial weight loss support according to the actual body weight of the target object and the training target. Real-time monitoring and data collection: Real-time collection of multi-modal data and analysis of the motion state of the target object through multi-modal data fusion. PID control adjustment: Through PID control, the motor output is adjusted according to the real-time error, and the weight loss intensity is dynamically adjusted. State feedback and adjustment: If the target object appears to have unstable gait, muscle fatigue, or abnormal force feedback, etc., the PID control can quickly adjust the support intensity to ensure the safety of the target object, and provide more accurate support to the target object through the force feedback motor. Training completion and summary: At the end of each training, the system can record the motion data and weight loss support of the target object, generate a report and adjust the initial settings for the next training, thereby ensuring the individualization of lower limb rehabilitation training.

[0150] The above examples realize adaptive weight loss of the lower limb rehabilitation walker through the combination of multi-modal data, and according to the characteristics of adaptive weight loss, the lower limb rehabilitation walker also has the characteristics of individualized training scheme generation, long-period data evaluation, and multi-level safety feedback mechanism, thereby completely innovating the way of lower limb rehabilitation training, and greatly improving the accuracy, safety and effect of the target object in the training process.

[0151] The above specific embodiments do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A lower limb rehabilitation walking aid system, characterized in that, The application relates to a lower limb rehabilitation walking aid, and relates to a movable device, a first adjusting device, a second adjusting device, a human body fixing device and a master control device. The movable device is connected with the first adjusting device in a V-shaped rotating mode at one end and connected with the second adjusting device in a V-shaped rotating mode at the other end; the first adjusting device is connected with the second adjusting device in an X-shaped rotating mode; the first adjusting device is provided with a first torque motor and a force feedback motor; the force feedback motor is rigidly connected with the human body fixing device; and the second adjusting device is provided with a second torque motor. The master control device comprises a pressure acquisition module, a target weight loss obtaining module, a motor output adjusting parameter obtaining module and a torque motor output adjusting module. The pressure acquisition module is used for acquiring, through the force feedback motor, the pressure applied on the human body fixing device by a target object performing lower limb rehabilitation training by wearing the human body fixing device. The target weight loss obtaining module is used for obtaining the target weight loss of the target object; wherein the target weight loss is the gravity expected to be reduced for the target object during the lower limb rehabilitation training, i.e. the supporting force expected to be provided for the target object. The motor output adjusting parameter obtaining module is used for performing proportional integral differential control according to the error between the pressure and the target weight loss to obtain the motor output adjusting parameter. The torque motor output adjusting module is used for adjusting the output of the first torque motor and / or the second torque motor according to the motor output adjusting parameter to adjust the opening and closing angle between the first adjusting device and the second adjusting device, wherein the opening and closing angle is negatively correlated with the supporting force provided for the target object by the human body fixing device, and the supporting force is used for resisting the gravity of the target object. The master control device further comprises a force feedback motor output adjusting module. The force feedback motor output adjusting module is used for adjusting the output of the force feedback motor according to the motor output adjusting parameter to control the human body fixing device to rotate around the target object. The application further relates to an upper computer.

2. The system of claim 1, wherein, The upper computer comprises a control instruction sending module. The control instruction sending module is used for sending a control instruction to the lower limb rehabilitation walking aid. The target weight loss obtaining module is specifically used for analyzing the control instruction to obtain the target weight loss of the target object in response to the received control instruction. The upper computer further comprises a data acquisition module and a control instruction generation module. The data acquisition module is used for acquiring training data of the target object.

3. The system of claim 2, wherein, The control instruction generation module is used for determining the motion state of the target object according to the training data and generating the control instruction according to the motion state. The training data is multi-modal data, and the multi-modal data comprises at least two single-modal data. The control instruction generation module comprises a fusion sub-module and a control instruction generation sub-module.

4. The system of claim 3, wherein, The fusion sub-module is used for fusing the single-modal data to obtain the motion state of the target object. ​ The fusion submodule is configured to perform fusion on the at least two single-modal data to obtain a fusion result. The control instruction generation submodule is configured to determine a motion state of the target object according to the fusion result, and generate the control instruction according to the motion state.

5. The system of claim 4, wherein, The fusion submodule comprises a single-modal feature obtaining unit and a feature fusion unit. The single-modal feature obtaining unit is configured to perform feature extraction on each of the at least two single-modal data to obtain single-modal features. The feature fusion unit is configured to fuse the obtained single-modal features to obtain a fusion result.

6. The system of claim 5, wherein, In a case where the single-modal data is a lower limb surface electromyography signal, the single-modal feature obtaining unit is configured to perform feature extraction on the lower limb surface electromyography signal to obtain single-modal features representing an activation degree and / or a fatigue condition of a lower limb muscle of the target object. In a case where the single-modal data is a lower limb inertial measurement signal, the single-modal feature obtaining unit is configured to perform feature extraction on the lower limb inertial measurement signal to obtain single-modal features representing at least one of a swing amplitude, a swing rhythm, a stability, an abnormal condition, and a tilt condition of a gait of the target object. In a case where the single-modal data is a plantar pressure signal, the single-modal feature obtaining unit is configured to perform feature extraction on the plantar pressure signal to obtain single-modal features representing the stability. In a case where the motion state represents that the target object has a falling tendency, the control instruction comprises a weight adjustment sub-instruction and a support force adjustment sub-instruction, and the host device further comprises a support force adjustment module. The target weight reduction obtaining module is further configured to analyze the weight adjustment sub-instruction to obtain a target weight reduction of the target object in response to the received weight adjustment sub-instruction.

7. The system of claim 3, wherein, The support force adjustment module is configured to adjust an output of the force feedback motor to control the human body fixing device to rotate around the target object in response to the received support force adjustment sub-instruction. The host computer further comprises a personalized training scheme obtaining module. The personalized training scheme obtaining module is configured to obtain a personalized training scheme of the target object.

8. The system of claim 3, wherein, The control instruction generation module is configured to determine a motion state of the target object according to the training data, and generate the control instruction according to the motion state and the personalized training scheme. The host computer further comprises a rehabilitation training record obtaining module and a personalized training scheme generation module. The rehabilitation training record obtaining module is configured to obtain a rehabilitation training record of the target object in a process of applying the lower limb rehabilitation walker for rehabilitation training.

9. The system of claim 8, wherein, The personalized training scheme generation module is configured to generate the personalized training scheme based on the rehabilitation training record. ​ ​

Images