Training mode determination method and system of lower limb exoskeleton rehabilitation robot

Abstract

The invention discloses a training mode determination method and system for a lower limb exoskeleton rehabilitation robot. The method comprises the steps that angle data, joint torque data and plantar pressure data when a patient executes multiple target actions are collected; according to the angle data and the joint torque data, calculating to obtain a joint motion range, and according to the angle data and the plantar pressure data, calculating a joint output torque; acquiring a pain score of the patient, and calculating a training mode score according to the joint motion range, the joint output torque and the pain score of the patient; and according to the training mode score, determining a training mode of the lower limb exoskeleton rehabilitation robot, wherein the training mode comprises a passive mode, an auxiliary mode and an anti-resistance mode. The motion range of the hip, knee and ankle joints can be accurately quantified, the joint motion range can be dynamically evaluated, the optimal training mode is dynamically recommended in combination with the training score calculated in real time, therefore, the rehabilitation efficiency can be improved, and the method can be widely applied to the technical field of rehabilitation training.

Description

Technical Field

[0001] This application relates to the field of rehabilitation training technology, and in particular to a method and system for determining the training mode of a lower limb exoskeleton rehabilitation robot. Background Technology

[0002] A lower limb exoskeleton rehabilitation robot is a wearable device made of lightweight, high-strength materials that mimics the shape and function of the human lower limb skeleton. This robot integrates motors, sensors (such as angle sensors and force sensors), and an intelligent control system, enabling it to monitor the patient's posture and movement in real time and assist the patient in standing, walking, and other movements based on preset parameters. Traditional methods for determining robot training patterns rely primarily on human experience and use preset, general training patterns for rehabilitation training. However, this method is limited by the physician's experience and is difficult to adjust in real time. Traditional methods also measure joint range of motion using goniometers or optical motion capture systems; however, these methods suffer from insufficient accuracy, environmental limitations, or high costs, and cannot reflect the true capabilities during dynamic movement. Summary of the Invention

[0003] The main objective of this application is to propose a method and system for determining the training mode of a lower limb exoskeleton rehabilitation robot that offers real-time intelligent adjustment and high rehabilitation efficiency.

[0004] To achieve the above objectives, one aspect of this application proposes a method for determining the training mode of a lower limb exoskeleton rehabilitation robot, comprising the following steps:

[0005] Collect angle data, joint torque data, and plantar pressure data when the patient performs multiple target movements;

[0006] Based on the angle data and the joint torque data, the joint range of motion is calculated, and based on the angle data and the plantar pressure data, the joint output torque is calculated.

[0007] Obtain the patient's pain score, and calculate the training mode score based on the joint range of motion, the joint output torque, and the patient's pain score;

[0008] The training mode of the lower limb exoskeleton rehabilitation robot is determined based on the training mode score. The training mode includes passive mode, assisted mode, and resistance mode.

[0009] In some embodiments, calculating the joint range of motion based on the angle data and the joint torque data specifically includes:

[0010] Determine the stiffness characteristics of the harmonic reducer in the lower limb exoskeleton rehabilitation robot, and establish a torque-deformation model based on the stiffness characteristics;

[0011] Calculate the angle deviation based on the joint torque data and the torque deformation model;

[0012] The angle data is compensated based on the angle deviation, and then outlier removal is performed on the compensated angle data.

[0013] Based on the angle data after outlier removal, the maximum range of motion of the joint is calculated to obtain the joint mobility.

[0014] In some embodiments, calculating the training mode score based on the joint range of motion, the joint output torque, and the patient pain score specifically includes:

[0015] Based on the range of motion of the joint, the degree of joint function recovery is extracted;

[0016] Based on the joint output torque, neuromuscular control ability is extracted;

[0017] Based on the patient's pain score, extract the trend of pain change;

[0018] The training mode score is calculated based on the degree of joint function recovery, the neuromuscular control ability, and the trend of pain change.

[0019] In some embodiments, the training mode score includes a passive mode score, an assisted mode score, and a resistance mode score. The calculation of the training mode score corresponding to each training mode based on the degree of joint function recovery, the neuromuscular control ability, and the pain change trend specifically includes:

[0020] The passive mode score is calculated based on the degree of joint function recovery.

[0021] The assistive mode score is calculated based on the degree of joint function recovery and the trend of pain changes.

[0022] The resistance pattern score is calculated based on the degree of joint function recovery and the neuromuscular control ability.

[0023] In some embodiments, the passive mode score is calculated using the following formula:

[0024] passive_score=sigmoid(0.3-rom_ratio)*100;

[0025] Wherein, passive_score represents the passive mode score, and rom_ratio represents the degree of joint function recovery;

[0026] The auxiliary mode score is calculated using the following formula:

[0027] assist_score=relu(rom_ratio-0.3)*(1-pain_trend)*80;

[0028] Wherein, assist_score represents the assist mode score, and pain_trend represents the pain trend;

[0029] The resistance mode score is calculated using the following formula:

[0030] resist_score=tanh(rom_ratio-0.7)*torque_symmetry*120;

[0031] Wherein, resist_score represents the resistance mode score, and torque_symmetry represents the neuromuscular control ability.

[0032] In some embodiments, determining the training mode of the lower limb exoskeleton rehabilitation robot based on the training mode score specifically includes:

[0033] Determine the patient's current stage of rehabilitation, which includes the acute phase, recovery phase, and maintenance phase;

[0034] The training mode corresponding to the lower limb exoskeleton rehabilitation robot is determined based on the training mode score and the rehabilitation stage.

[0035] In some embodiments, determining the training mode corresponding to the lower limb exoskeleton rehabilitation robot based on the training mode score and the rehabilitation stage specifically includes:

[0036] Set the score weights for the acute phase, the recovery phase, and the maintenance phase;

[0037] The scores of the training modes are weighted according to the scoring weights to obtain the weighted scores corresponding to each training mode.

[0038] The training mode is determined to be the training mode corresponding to the largest weighted score.

[0039] To achieve the above objectives, another aspect of this application proposes a training mode determination system for a lower limb exoskeleton rehabilitation robot, comprising:

[0040] The data acquisition module is used to collect angle data, joint torque data, and plantar pressure data when the patient performs multiple target movements.

[0041] The data calculation module is used to calculate the joint range of motion based on the angle data and the joint torque data, and to calculate the joint output torque based on the angle data and the plantar pressure data.

[0042] The scoring calculation module is used to obtain the patient's pain score and calculate the training mode score based on the joint range of motion, the joint output torque, and the patient's pain score.

[0043] The mode determination module is used to determine the training mode of the lower limb exoskeleton rehabilitation robot based on the training mode score. The training mode includes passive mode, assisted mode and resistance mode.

[0044] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0045] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described above.

[0046] The embodiments of this application include at least the following beneficial effects: The training mode determination method and system for the lower limb exoskeleton rehabilitation robot of this application first collects angle data, joint torque data, and plantar pressure data when the patient performs multiple target movements; then, based on the angle data and joint torque data, the joint range of motion is calculated, and based on the angle data and plantar pressure data, the joint output torque is calculated; furthermore, the patient's pain score is obtained, and based on the joint range of motion, joint output torque, and patient pain score, a training mode score is calculated; finally, the training mode of the lower limb exoskeleton rehabilitation robot is determined based on the training mode score, and the training mode includes passive mode, assisted mode, and resistive mode. This application, by collecting and analyzing the patient's motion data in real time, can accurately quantify the range of motion of the hip, knee, and ankle joints, dynamically assess joint range of motion, and dynamically recommend the optimal training mode based on the real-time calculated training score, thereby improving rehabilitation efficiency. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the embodiments of this application are described below. It should be understood that the drawings described below are only for the purpose of clearly illustrating some embodiments of the technical solutions in this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0048] Figure 1 This is a flowchart illustrating the steps of a method for determining the training mode of a lower limb exoskeleton rehabilitation robot according to an embodiment of this application.

[0049] Figure 2 This is an overall schematic diagram of a lower limb exoskeleton rehabilitation robot provided in one embodiment of this application;

[0050] Figure 3 This is a schematic diagram of the internal structure of a lower limb exoskeleton rehabilitation robot system provided in one embodiment of this application;

[0051] Figure 4 This is a schematic diagram illustrating the logic of training mode selection provided in one embodiment of this application;

[0052] Figure 5 A schematic diagram of the structure of a training mode determination system for a lower limb exoskeleton rehabilitation robot provided in one embodiment of this application;

[0053] Figure 6 This is a schematic diagram of the hardware structure of an electronic device provided in one embodiment of this application. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0056] A lower limb exoskeleton rehabilitation robot is a wearable device made of lightweight, high-strength materials that mimics the shape and function of the human lower limb skeleton. This robot integrates motors, sensors (such as angle sensors and force sensors), and an intelligent control system, enabling it to monitor the patient's posture and movement in real time and assist the patient in standing, walking, and other movements based on preset parameters. Traditional methods for determining robot training patterns rely primarily on human experience and use preset, general training patterns for rehabilitation training. However, this method is limited by the physician's experience and is difficult to adjust in real time. Traditional methods also measure joint range of motion using goniometers or optical motion capture systems; however, these methods suffer from insufficient accuracy, environmental limitations, or high costs, and cannot reflect the true capabilities during dynamic movement.

[0057] In view of this, this application proposes a method for determining the training mode of a lower limb exoskeleton rehabilitation robot. First, angle data, joint torque data, and plantar pressure data are collected when the patient performs multiple target movements. Then, the joint range of motion is calculated based on the angle and joint torque data, and the joint output torque is calculated based on the angle and plantar pressure data. Next, the patient's pain score is obtained, and a training mode score is calculated based on the joint range of motion, joint output torque, and patient pain score. Finally, the training mode of the lower limb exoskeleton rehabilitation robot is determined based on the training mode score. The training modes include passive mode, assisted mode, and resistive mode. This application, by collecting and analyzing the patient's motion data in real time, can accurately quantify the range of motion of the hip, knee, and ankle joints, dynamically assess joint range of motion, and dynamically recommend the optimal training mode based on the real-time calculated training score, thereby improving rehabilitation efficiency.

[0058] Reference Figure 1 , Figure 1 This is a flowchart illustrating the steps of a method for determining the training mode of a lower limb exoskeleton rehabilitation robot according to an embodiment of this application. This application proposes a method for determining the training mode of a lower limb exoskeleton rehabilitation robot, which may include, but is not limited to, the following steps S101 to S104:

[0059] Step S101: Collect angle data, joint torque data, and plantar pressure data when the patient performs multiple target movements;

[0060] Specifically, such as Figure 2 The image shown is an overall schematic diagram of a lower limb exoskeleton rehabilitation robot. Figure 3The diagram shows the internal structure of the lower limb exoskeleton rehabilitation robot system. First, the length of the exoskeleton frame is adjusted according to the patient's height, and adjustable straps are used to secure the patient's thighs, calves, and torso. The joint axes are aligned with human anatomical joints to ensure patient comfort. After donning the system, the patient remains in an upright, static position for 10 seconds. The robot automatically performs sensor zero-point calibration, verifying that the initial readings of each joint angle are 0°±0.5°. After sensor calibration, the patient is guided to complete three standard hip flexion (90°) / knee flexion (120°) movements; hip joint: flexion 0-90° / extension 0-30°; knee joint: flexion 0-120°. During the target movements, angle sensors read the angle data of the ankle, knee, and hip joints, and torque sensors measure the joint torque data of the ankle, knee, and hip joints. Plantar pressure sensors collect real-time data on the distribution of ground reaction forces, including vertical support force and horizontal shear force, and calculate the position of the pressure center to determine the patient's center of gravity shift.

[0061] It should be noted that the embodiments of this application do not require additional optical equipment. Instead, they use angle sensors, torque sensors, and plantar pressure sensors built into the exoskeleton to monitor the motion data of the ankle, hip, and knee joints in real time. This allows for the accurate quantification of the range of motion of the ankle, hip, and knee joints, dynamic assessment of joint mobility, reduction of errors, and overcoming the static limitations of manual measurement and the environmental dependence of optical systems.

[0062] Step S102: Calculate the joint range of motion based on the angle data and joint torque data, and calculate the joint output torque based on the angle data and plantar pressure data.

[0063] Specifically, by fusing angle data and torque information, the angle measurement error is compensated, and then the joint range of motion of each joint is calculated based on the compensated angle data and joint torque data; and the joint output torque of each joint is calculated based on the compensated angle data and plantar pressure data.

[0064] As an optional implementation, this step, based on the angle data and joint torque data, can be further divided into the following steps S1021 to S1024:

[0065] Step S1021: Determine the stiffness characteristics of the harmonic reducer in the lower limb exoskeleton rehabilitation robot, and establish a torque deformation model based on the stiffness characteristics;

[0066] Step S1022: Calculate the angle deviation based on the joint torque data and torque deformation model;

[0067] Step S1023: Compensate the angle data according to the angle deviation, and then remove outliers from the compensated angle data.

[0068] Step S1024: Calculate the maximum range of motion of the joint based on the angle data after outlier removal to obtain the joint range of motion.

[0069] Specifically, the harmonic reducer undergoes elastic deformation when transmitting torque, causing a deviation between the angle measured by the encoder and the actual joint output angle. Therefore, by experimentally calibrating the stiffness characteristics of the harmonic reducer, the relationship between torque τ and angle offset Δθ is determined, and the following torque deformation model is constructed:

[0070] Δθ=k·τ

[0071] Where k is the elasticity coefficient.

[0072] Real-time reading of joint torque data, calculation of angular deviation Δθ caused by deformation, and calculation of the original angle θ from the encoder. encoder After subtraction, the true joint angle θ after compensation is obtained. real :

[0073] θ real =θ encoder -Δθ

[0074] Abnormal values ​​in the actual joint angles (such as attempts that did not reach the target due to pain) were removed. The range of motion for each exercise was calculated based on the angle data before and after the patient performed the target movement. Finally, the joint range of motion corresponding to the maximum range of motion was recorded.

[0075] For calculating the joint output torque, we start from the plantar reaction force and calculate the torque joint by joint from bottom to top. First, we consider the lever arm of the point of application of the plantar reaction force relative to the center of the ankle joint, and add the gravitational torque of the foot itself to calculate the ankle joint torque. Next, we consider the inertial effect of the lower leg and the force and torque transmission from the ankle joint to calculate the knee joint torque. Finally, we calculate the hip joint torque by taking into account the movement state of the thigh.

[0076] S103. Obtain the patient's pain score, and calculate the training mode score based on the joint range of motion, joint output torque, and the patient's pain score.

[0077] Specifically, a 10-centimeter-long horizontal or vertical line is used, with "no pain" (0 points) and "most severe pain" (10 points) marked at both ends. During the patient's rehabilitation training, the patient marks the position on the line based on their subjective feelings, and measures the distance (in centimeters) from the marked point to the starting point as the score (e.g., 6cm = 6 points) to obtain the patient's pain score (VAS score).

[0078] As an optional implementation, the step of calculating the training mode score based on joint range of motion, joint output torque, and patient pain score can be further divided into the following steps S1031 to S1034:

[0079] Step S1031: Extract the degree of joint function recovery based on the range of motion;

[0080] Specifically, the degree of joint function recovery (rom_ratio) is calculated using joint range of motion (ROM) data, which is the ratio of the current range of motion of the affected side to that of the healthy side. The ROM of the healthy side is pre-calibrated based on the patient's historical data or population standard values. If both sides are affected, clinical standard values ​​are used as the benchmark. The final extracted degree of joint function recovery (rom_ratio) reflects the progress of joint mobility recovery; the closer the value is to 1, the better the functional recovery.

[0081] Step S1032: Extract neuromuscular control ability based on joint output torque;

[0082] Specifically, based on joint output torque data, the torque ratio (torque_symmetry) between the affected and healthy sides under the same movement is calculated. First, peak torque data from standardized movements (such as uniform knee flexion) within the past 7 days are screened to exclude invalid data due to fatigue or improper movement. The mean torque ratio between the affected and healthy sides is used to assess the symmetry of neuromuscular control: a ratio close to 1 indicates bilateral muscle coordination; a ratio significantly lower than 1 (e.g., 0.6) indicates insufficient muscle strength on the affected side. This indicator dynamically reflects the muscle strength reconstruction effect during rehabilitation.

[0083] Step S1033: Extract the trend of pain changes based on the patient's pain score;

[0084] Specifically, the average rate of change (pain_trend) is calculated based on the patient's three most recent VAS scores. If the score continues to decrease (e.g., from 6 to 4 to 3), the pain trend is negative, indicating pain improvement; if the score increases (e.g., from 3 to 5 to 7), it is positive, indicating worsening pain.

[0085] Step S1034: Calculate the training mode score corresponding to each training mode based on the degree of joint function recovery, neuromuscular control ability, and pain change trend.

[0086] As an optional implementation, the training mode score includes passive mode score, assisted mode score, and resistance mode score. The step of calculating the training mode score corresponding to each training mode based on the degree of joint function recovery, neuromuscular control ability, and pain change trend can be further divided into the following steps S10341 to S10343:

[0087] Step S10341: Calculate the passive mode score based on the degree of joint function recovery;

[0088] The passive mode score is calculated using the following formula:

[0089] passive_score=sigmoid(0.3-rom_ratio)*100;

[0090] Here, passive_score represents the passive mode score, and rom_ratio represents the degree of joint function recovery.

[0091] Specifically, the passive mode score (passive_score) is primarily generated based on the degree of joint function recovery (rom_ratio). The Sigmoid function is used to convert the deficiency in joint mobility into a priority for passive training. When the range of motion of the affected joint is significantly lower than that of the healthy side (e.g., rom_ratio < 0.3), the output value of the Sigmoid function is close to 1, indicating that the patient's voluntary movement ability is severely insufficient and they need to rely entirely on the passive movement of the exoskeleton.

[0092] Step S10342: Calculate the assistive mode score based on the degree of joint function recovery and the trend of pain changes;

[0093] The assist mode score is calculated using the following formula:

[0094] assist_score=relu(rom_ratio-0.3)*(1-pain_trend)*80;

[0095] Here, assist_score represents the assist mode score, and pain_trend represents the pain trend.

[0096] Specifically, the assist score is determined by the degree of joint function recovery (rom_ratio) and the pain trend (pain_trend). The ReLU function sets a minimum threshold for joint function recovery (rom_ratio > 0.3) to ensure that assisted training is considered only after the patient has basic mobility. The pain trend is used as a penalty; if the pain worsens (e.g., pain_trend > 0), the score is directly reduced. For example, if the patient's joint function recovery reaches 50% (rom_ratio = 0.5) and the pain decreases (pain_trend = -0.1), the assist score is 17.6; if the pain intensifies (pain_trend = 0.2), the assist score drops to 12.8, reflecting the inhibitory effect of pain on training intensity.

[0097] Step S10343: Calculate the resistance pattern score based on the degree of joint function recovery and neuromuscular control ability.

[0098] The resistance mode score is calculated using the following formula:

[0099] resist_score=tanh(rom_ratio-0.7)*torque_symmetry*120;

[0100] Here, resist_score represents the resistance mode score, and torque_symmetry represents the neuromuscular control ability.

[0101] Specifically, the resistance mode score (resist_score) is jointly determined by the degree of joint function recovery (rom_ratio) and the neuromuscular control ability (torque_symmetry). The Tanh function smooths the transition of joint function recovery, avoiding abrupt threshold changes. For example, when a patient's joint function recovery reaches 80% (rom_ratio = 0.8) and the neuromuscular control ability is 1.1 (slightly stronger on the affected side than the healthy side), the resistance mode score is 13.2. If the neuromuscular control ability is insufficient (e.g., torch_symmetry = 0.6), the resistance mode score drops to 7.2, reflecting the risk of resistance training when neuromuscular control ability is insufficient.

[0102] The role of joint function recovery degree rom_ratio in the calculation of the above training mode scores is as follows: when joint function recovery degree rom_ratio < 30%, the passive mode score is biased; when joint function recovery degree rom_ratio > 30%, the assist mode score is biased; when joint function recovery degree rom_ratio > 70%, the resistance mode score is biased.

[0103] It should be noted that the embodiments of this application use mathematical functions to quantitatively evaluate the patient's multidimensional physiological indicators (including the degree of joint function recovery, neuromuscular control ability, and pain change trend), which can objectively recommend the most suitable training mode for the current rehabilitation stage and achieve personalized recommendations.

[0104] S104. Determine the training mode of the lower limb exoskeleton rehabilitation robot based on the training mode score. The training modes include passive mode, assisted mode and resistance mode.

[0105] Specifically, the passive mode fully drives the patient's limb movements through the exoskeleton; the assistive mode provides adaptive assistance based on the patient's voluntary exertion; and the resistance mode strengthens muscle strength through controllable resistance.

[0106] As an optional implementation, step S104 can be further divided into the following steps S1041 and S1042:

[0107] Step S1041: Determine the patient's rehabilitation stage, which includes the acute phase, recovery phase, and maintenance phase;

[0108] Step S1042: Determine the training mode corresponding to the lower limb exoskeleton rehabilitation robot based on the training mode score and rehabilitation stage.

[0109] As an optional implementation, step S1042 can be further divided into the following steps S10421 to S10423:

[0110] Step S10421: Set the score weights for the acute phase, recovery phase, and maintenance phase;

[0111] Specifically, historical data is used to determine the patient's rehabilitation stage, and corresponding score weights are assigned according to the rehabilitation stage. In the acute phase, the focus is on restoring joint mobility, with passive mode having a high priority; therefore, the weights for joint function recovery (rom_ratio) are set at 60%, neuromuscular control (torque_symmetry) at 30%, and pain trend at 10%. In the recovery phase, the training focus is on muscle strength reconstruction; therefore, the weights for joint function recovery (rom_ratio) are set at 40%, neuromuscular control (torque_symmetry) at 50%, and pain trend at 10%. In the maintenance phase, the training objective is to further strengthen muscle strength; therefore, the weights for joint function recovery (rom_ratio) are set at 30%, neuromuscular control (torque_symmetry) at 60%, and pain trend at 10%.

[0112] Step S10422: Weight the training mode scores according to the score weights to obtain the weighted scores corresponding to each training mode;

[0113] Step S10423: Determine the training mode as the training mode corresponding to the largest weighted score;

[0114] In some optional embodiments, when the degree of joint function recovery rom_ratio < 30%, it indicates that the patient's joint movement is severely restricted, and the exoskeleton needs to fully drive the movement to avoid secondary injury. Therefore, in this embodiment, the degree of joint function recovery rom_ratio < 30% is used as the condition for determining the passive mode. When the degree of joint function recovery rom_ratio ≥ 30%, the training mode of the lower limb exoskeleton rehabilitation robot is determined by comprehensively evaluating the degree of joint function recovery, neuromuscular control ability, and pain change trend.

[0115] Specifically, such as Figure 4 The diagram shows the logic for selecting the training mode. Based on the above training mode score calculation formula and weighted score settings, the training mode selection logic is as follows: When the joint function recovery degree rom_ratio is less than 30%, the passive mode score is high, while the auxiliary mode score and the resistance mode score are both zero, thus determining the training mode of the lower limb exoskeleton rehabilitation robot as passive training; when the joint function recovery degree rom_ratio is greater than 30% but less than 70%, the training mode of the lower limb exoskeleton rehabilitation robot is determined as passive mode or auxiliary mode based on whether the pain change degree decreases; when the joint function recovery degree rom_ratio is greater than 70%, the training mode of the lower limb exoskeleton rehabilitation robot is determined as auxiliary mode or resistance mode based on whether the neuromuscular control ability torque_symmetry is greater than 0.8%.

[0116] It should be noted that the embodiments of this application comprehensively evaluate the degree of joint function recovery, neuromuscular control ability and pain change trend, and use weighted calculation to determine the training mode of the lower limb exoskeleton rehabilitation robot, which can further improve the accuracy and effect of rehabilitation training and realize real-time adjustment of the training mode.

[0117] The above describes the method for determining the training mode of the lower limb exoskeleton rehabilitation robot according to embodiments of this application. It can be recognized that, compared with traditional robot training mode determination methods, embodiments of this application have the following advantages:

[0118] 1. No additional optical equipment is required. The exoskeleton uses built-in angle sensors, torque sensors, and plantar pressure sensors to monitor the motion data of the ankle, hip, and knee joints in real time. It can accurately quantify the range of motion of the ankle, hip, and knee joints, dynamically assess joint mobility, reduce errors, and overcome the static limitations of manual measurement and the environmental dependence of optical systems.

[0119] Second, by using mathematical functions to quantitatively assess the patient's multidimensional physiological indicators (including the degree of joint function recovery, neuromuscular control ability, and pain change trend), it is possible to objectively recommend the most suitable training mode for the current rehabilitation stage and achieve personalized recommendations.

[0120] Third, by comprehensively assessing the degree of joint function recovery, neuromuscular control ability, and pain trends, and using weighted calculations to determine the training mode of the lower limb exoskeleton rehabilitation robot, the accuracy and effectiveness of rehabilitation training can be further improved, and the training mode can be adjusted in real time.

[0121] Reference Figure 5 This application also provides a training mode determination system for a lower limb exoskeleton rehabilitation robot, including:

[0122] The data acquisition module is used to collect angle data, joint torque data, and plantar pressure data when the patient performs multiple target movements.

[0123] The data calculation module is used to calculate the joint range of motion based on angle data and joint torque data, and to calculate the joint output torque based on angle data and plantar pressure data.

[0124] The scoring module is used to obtain the patient's pain score and calculate the training mode score based on the joint range of motion, joint output torque, and the patient's pain score.

[0125] The mode determination module is used to determine the training mode of the lower limb exoskeleton rehabilitation robot based on the training mode score. The training modes include passive mode, assisted mode and resistance mode.

[0126] It is understood that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0127] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0128] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0129] Please see Figure 6 , Figure 6 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0130] The processor 1001 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0131] The memory 1002 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 1002 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1002 and is called and executed by the processor 1001 using the methods described in the embodiments of this application.

[0132] Input / output interface 1003 is used to implement information input and output;

[0133] The communication interface 1004 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0134] Bus 1005 transmits information between various components of the device (e.g., processor 1001, memory 1002, input / output interface 1003, and communication interface 1004);

[0135] The processor 1001, memory 1002, input / output interface 1003 and communication interface 1004 are connected to each other within the device via bus 1005.

[0136] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0137] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0138] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0139] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0140] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0141] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0142] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0143] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0144] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0145] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0146] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0147] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0148] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0149] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0150] If the integrated unit is implemented as 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 this application, in essence, 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. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0151] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for determining the training mode of a lower limb exoskeleton rehabilitation robot, characterized in that, Includes the following steps: Collect angle data, joint torque data, and plantar pressure data when the patient performs multiple target movements; Based on the angle data and the joint torque data, the joint range of motion is calculated, and based on the angle data and the plantar pressure data, the joint output torque is calculated. Obtain the patient's pain score, and calculate the training mode score based on the joint range of motion, the joint output torque, and the patient's pain score; The training mode of the lower limb exoskeleton rehabilitation robot is determined based on the training mode score. The training mode includes passive mode, assisted mode, and resistance mode.

2. The method according to claim 1, characterized in that, The calculation of joint range of motion based on the angle data and the joint torque data specifically includes: Determine the stiffness characteristics of the harmonic reducer in the lower limb exoskeleton rehabilitation robot, and establish a torque-deformation model based on the stiffness characteristics; Calculate the angle deviation based on the joint torque data and the torque deformation model; The angle data is compensated based on the angle deviation, and then outlier removal is performed on the compensated angle data. Based on the angle data after outlier removal, the maximum range of motion of the joint is calculated to obtain the joint mobility.

3. The method according to claim 1, characterized in that, The calculation of the training mode score based on the joint range of motion, the joint output torque, and the patient's pain score specifically includes: Based on the range of motion of the joint, the degree of joint function recovery is extracted; Based on the joint output torque, neuromuscular control ability is extracted; Based on the patient's pain score, extract the trend of pain change; The training mode score is calculated based on the degree of joint function recovery, the neuromuscular control ability, and the trend of pain change.

4. The method according to claim 3, characterized in that, The training mode score includes passive mode score, assisted mode score, and resistance mode score. The training mode score is calculated based on the degree of joint function recovery, the neuromuscular control ability, and the pain change trend, specifically including: The passive mode score is calculated based on the degree of joint function recovery. The assistive mode score is calculated based on the degree of joint function recovery and the trend of pain changes. The resistance pattern score is calculated based on the degree of joint function recovery and the neuromuscular control ability.

5. The method according to claim 4, characterized in that, The passive mode score is calculated using the following formula: passive_score=sigmoid(0.3-rom_ratio)*100; Wherein, passive_score represents the passive mode score, and rom_ratio represents the degree of joint function recovery; The auxiliary mode score is calculated using the following formula: assist_score=relu(rom_ratio-0.3)*(1-pain_trend)*80; Wherein, assist_score represents the assist mode score, and pain_trend represents the pain trend; The resistance mode score is calculated using the following formula: resist_score=tanh(rom_ratio-0.7)*torque_symmetry*120; Wherein, resist_score represents the resistance mode score, and torque_symmetry represents the neuromuscular control ability.

6. The method according to claim 1, characterized in that, The step of determining the training mode of the lower limb exoskeleton rehabilitation robot based on the training mode score specifically includes: Determine the patient's current stage of rehabilitation, which includes the acute phase, recovery phase, and maintenance phase; The training mode corresponding to the lower limb exoskeleton rehabilitation robot is determined based on the training mode score and the rehabilitation stage.

7. The method according to claim 6, characterized in that, The step of determining the training mode corresponding to the lower limb exoskeleton rehabilitation robot based on the training mode score and the rehabilitation stage specifically includes: Set the score weights for the acute phase, the recovery phase, and the maintenance phase; The scores of the training modes are weighted according to the scoring weights to obtain the weighted scores corresponding to each training mode. The training mode is determined to be the training mode corresponding to the largest weighted score.

8. A training mode determination system for a lower limb exoskeleton rehabilitation robot, characterized in that, include: The data acquisition module is used to collect angle data, joint torque data, and plantar pressure data when the patient performs multiple target movements. The data calculation module is used to calculate the joint range of motion based on the angle data and the joint torque data, and to calculate the joint output torque based on the angle data and the plantar pressure data. The scoring calculation module is used to obtain the patient's pain score and calculate the training mode score based on the joint range of motion, the joint output torque, and the patient's pain score. The mode determination module is used to determine the training mode of the lower limb exoskeleton rehabilitation robot based on the training mode score. The training mode includes passive mode, assisted mode and resistance mode.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method of any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images