Intelligent compliant control system and method for lower extremity exoskeleton

Abstract

A lower limb exoskeleton intelligent compliance control system and method, the system includes active connection's mobile protection frame, exoskeleton robot, myoelectric information acquisition equipment, electroencephalogram information acquisition equipment and industrial computer;The exoskeleton robot includes leg bionics support structure, leg bionics support structure is located in waist mechanism's left and right symmetry installation;The leg bionics support structure includes the hip joint integrated motor, the thigh adjusting rod, the knee joint integrated motor, the lower leg adjusting rod and foot intelligent sensing boots that are connected in turn, the bottom of the intelligent sensing boots is equipped with foot pressure sensor;The control method includes passive control mode and active control mode.The present application introduces the active movement intention of patient, through electroencephalogram, myoelectric information real-time feedback patient's physiological state, real-time display and record rehabilitation training's step speed, time, joint trajectory, driving force and man-machine acting force etc.Information, good adaptation different patients, improve the enthusiasm of patient participation rehabilitation training.

Description

Technical Field

[0001] This invention relates to an intelligent compliant control system and method for a lower limb exoskeleton. Background Technology

[0002] With the continuous increase in my country's aging population, the number of patients with stroke, joint injuries, hemiplegia, and other diseases is also rising sharply. Stroke, joint injuries, hemiplegia, as well as spinal cord injuries, lower limb nerve injuries, and multiple sclerosis, often lead to loss of lower limb mobility, severely impacting patients' quality of life. Clinical studies have shown that for motor function loss caused by nerve damage, such as lower limb paralysis or hemiplegia, timely and scientific repeated restoration of impaired function can improve the degree of recovery of motor function in the affected limb.

[0003] Due to a lack of professional rehabilitation training resources in my country, many patients may miss the optimal rehabilitation window. Rehabilitation-assisted walking exoskeleton robots can address the problems of scarce rehabilitation resources and the heavy workload of manual training. Furthermore, through a sensing system, they can acquire human kinematic and physiological data, helping rehabilitation therapists to more accurately diagnose and assess conditions, and improve and optimize rehabilitation strategies. Data shows that with exoskeleton-assisted training, the time it takes for patients to regain walking ability can be shortened by 50%-70%. As people's living standards improve, patients' needs for daily activities and rehabilitation training are increasing, and rehabilitation-assisted walking exoskeleton robots will undoubtedly play a vital role in assisting patients with walking and rehabilitation treatment.

[0004] However, most rehabilitation exoskeleton training exercises in China are relatively simple in terms of movement types and have limited range of motion. Most of them ignore the patient's active movement intentions, lack real-time feedback on the patient's physiological state, and cannot be well adapted to different patients. Therefore, they are not conducive to stimulating the patient's initiative and improving the patient's enthusiasm for participating in rehabilitation training, and it is difficult to achieve the ideal rehabilitation effect. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides an intelligent compliant control system and method for a lower limb exoskeleton.

[0006] The object of this invention is achieved in the following manner:

[0007] A lower limb exoskeleton intelligent compliant control system includes a movable protective frame, an exoskeleton robot, an electromyography (EMG) information acquisition device, an electroencephalography (EEG) information acquisition device, and an industrial control computer. The exoskeleton robot includes a leg bionic support structure, which is symmetrically installed on both sides of the waist structure. The leg bionic support structure includes a hip joint integrated motor 6, a thigh adjustment rod, a knee joint integrated motor 9, a calf adjustment rod, and a foot intelligent sensing boot 11 connected in sequence. The bottom of the intelligent sensing boot is equipped with a foot pressure sensor. The thigh adjustment rod is equipped with a thigh root strap 7 and a thigh end sensing strap 8, and the calf adjustment rod is equipped with a calf sensing strap 10. The EMG information acquisition device, the EEG information acquisition device, the hip joint integrated motor 6, the knee joint integrated motor 9, the thigh end sensing strap 8, and the calf sensing strap 10 are all communicatively connected to the industrial control computer.

[0008] The hip joint integrated motor and knee joint integrated motor adopt an integrated drive unit with a built-in reducer, motor, encoder, torque sensor and driver. The output end of the motor is connected to the input end of the reducer, and the output end of the reducer is connected to the thigh adjustment rod. The encoder and driver are mounted on the motor, and the torque sensor is connected to the output shaft of the motor. The encoder, torque sensor and driver are all connected to the industrial control computer for communication.

[0009] A method for intelligent compliant control of a lower limb exoskeleton, the method comprising a passive control mode and an active control mode;

[0010] The passive control mode includes the following steps: S1: Input the angle and angular velocity q of the standard gait trajectory data from the industrial computer. IN , The thigh end sensing strap 8 and the calf sensing strap 10 respectively detect the contact force between the human leg and the exoskeleton leg in real time;

[0011] S2: The detected contact force is converted into corrected angle and angular velocity Δq using a force-potential mapping model. M ,

[0012] S3: Then compare the angle and angular velocity q with the standard gait trajectory data from the industrial control computer. IN , The difference is used to obtain the desired angle and angular velocity q. D , That is, q D =q IN -Δq M , To achieve closed-loop control at the upper level;

[0013] S4: The industrial computer will input the desired angle and angular velocity q D , The actual motion trajectory angle and angular velocity q are sent to the joint motor driver. F , Feedback is sent to the joint motor driver, and the difference between the two yields the control quantities angle and angular velocity Δq. D , That is, Δq D =q D -q F , The joint motor driver uses the control quantities angle and angular velocity Δq D , The output drives the motor, thereby moving the thigh adjustment rod and the calf adjustment rod, realizing the driver's low-level closed-loop control of the motor;

[0014] The active control mode includes the following steps: S1: Before rehabilitation training, electromyography (EMG) and electroencephalography (EEG) signals of the patient's various movements are collected by EMG and EEG information acquisition devices to establish the mapping relationship between the various movements of the human gait trajectory and EMG and EEG signals, that is, the correspondence between EMG and EEG signals and the movement angles and angular velocities of the human hip and knee joints. At the same time, the industrial control computer continuously records the plantar pressure, joint angles and joint torques of the patient during the movement process to establish a gait trajectory database.

[0015] S2: During the patient's rehabilitation training, the patient's electromyography (EMG) and electroencephalography (EEG) signals are collected in real time, compared with the EMG and EEG signals in the gait trajectory database, to determine the patient's movement intention and output the predicted gait trajectory.

[0016] S3: Judge the predicted gait trajectory based on the current joint angle and plantar pressure information; if the judgment is correct, proceed to step S4; if the judgment is incorrect, use the particle swarm optimization algorithm to match the optimal data from the gait trajectory library based on the previous motion state, thereby driving the joint movement at the current moment.

[0017] S4: Input the angle and angular velocity q of the standard gait trajectory data from the industrial computer. IN , The thigh end sensing strap 8 and the calf sensing strap 10 respectively detect the contact force between the human leg and the exoskeleton leg in real time;

[0018] S5: The detected contact force is converted into corrected angle and angular velocity Dq respectively through the force-potential mapping model. M ,

[0019] S6: Then compare the angle and angular velocity q with the standard gait trajectory data from the industrial control computer. IN , The difference is used to obtain the desired angle and angular velocity q. D , That is, qD =q IN -Δq M , To achieve closed-loop control at the upper level;

[0020] S7: The industrial control computer will input the desired angle and angular velocity q D , The actual motion trajectory angle and angular velocity q are sent to the joint motor driver. F , Feedback is sent to the joint motor driver, and the difference between the two yields the control quantities angle and angular velocity Δq. D , That is, Δq D =q D -q F , The joint motor driver uses the control quantities angle and angular velocity Δq D , The output drives the motor, which in turn moves the thigh and calf adjustment rods, thus achieving closed-loop control of the motor by the driver.

[0021] The beneficial effects of this invention are as follows: This invention introduces the patient's active movement intention, and uses EEG and EMG information to provide real-time feedback on the patient's physiological state. It also displays and records information such as walking speed, time, joint trajectory, driving force, and human-machine interaction force during rehabilitation training in real time, which is well adapted to different patients. Therefore, it helps to stimulate the patient's initiative, improve the patient's enthusiasm for participating in rehabilitation training, and achieve ideal rehabilitation results. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of the overall rehabilitation exoskeleton of the present invention.

[0023] Figure 2 This is a side view schematic diagram of the rehabilitation exoskeleton of the present invention.

[0024] Figure 3 This is a frontal view of the rehabilitation exoskeleton of the present invention.

[0025] Figure 4 This is a block diagram of the passive control principle of the present invention.

[0026] Figure 5 This is the passive control flowchart of the present invention.

[0027] Figure 6 This is a block diagram of the active control principle of the present invention.

[0028] Figure 7 This is the active control flowchart of the present invention.

[0029] Among them, 1. Main control box, 2. Mobile protective frame, 3. Back strap, 4. Connecting mechanism, 5. Waist mechanism, 6. Hip joint integrated motor, 7. Thigh root strap, 8. Thigh end sensor strap, 9. Knee joint integrated motor, 10. Lower leg sensor strap, 11. Smart sensor boot. Detailed Implementation

[0030] The present invention will now be described in further detail with reference to the accompanying drawings and specific embodiments.

[0031] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of this application. Unless otherwise specified, all technical and scientific terms used herein have the same technical meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0032] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0033] In this invention, terms such as "fixed connection," "connected," and "linked" should be interpreted broadly, indicating a fixed connection, an integral connection, or a detachable connection; a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can determine the specific meaning of these terms in this invention based on the specific circumstances, and they should not be construed as limitations on the invention.

[0034] like Figure 1-3As shown (excluding EEG and EMG data acquisition devices and display terminals), a lower limb exoskeleton intelligent compliant control system is described. The system includes a movable protective frame, an exoskeleton robot, EMG data acquisition devices, EEG data acquisition devices, and an industrial control computer. The exoskeleton robot includes a leg bionic support structure, symmetrically mounted on either side of the waist structure. The leg bionic support structure includes a hip joint integrated motor 6, a thigh adjustment rod, a knee joint integrated motor 9, a calf adjustment rod, and a foot intelligent sensing boot 11 connected in sequence. The bottom of the intelligent sensing boot is equipped with a foot pressure sensor. The thigh adjustment rod has a thigh root strap 7 and a thigh end sensing strap 8, and the calf adjustment rod has a calf sensing strap 10. The EMG data acquisition devices, EEG data acquisition devices, hip joint integrated motor 6, knee joint integrated motor 9, thigh end sensing strap 8, and calf sensing strap 10 are all communicatively connected to the industrial control computer. The exoskeleton and protective frame can be connected or separated via a connecting mechanism 4. Patients can choose to undergo rehabilitation training together with the two mobile protective frames, or separately from the exoskeleton, depending on their individual circumstances. The patient is smoothly connected to the exoskeleton via a strap (3), a thigh root strap (7), a thigh end sensor strap (8), a lower leg sensor strap (10), and a smart sensor boot (11). Passive or active modes can be selected based on the patient's rehabilitation stage, and the exoskeleton can be connected or separated from the two mobile protective frames via a connection mechanism (4) to ensure the patient achieves the most comfortable training state.

[0035] The hip joint integrated motor and knee joint integrated motor adopt an integrated drive unit with a built-in reducer, motor, encoder, torque sensor and driver. The output end of the motor is connected to the input end of the reducer, and the output end of the reducer is connected to the thigh adjustment rod. The encoder and driver are mounted on the motor, and the torque sensor is connected to the output shaft of the motor. The encoder, torque sensor and driver are all connected to the industrial control computer for communication.

[0036] A method for intelligent compliant control of a lower limb exoskeleton, the method comprising a passive control mode and an active control mode;

[0037] The passive control mode includes the following steps: S1: Input the angle and angular velocity q of the standard gait trajectory data from the industrial computer. IN , The thigh end sensing strap 8 and the calf sensing strap 10 respectively detect the contact force between the human leg and the exoskeleton leg in real time;

[0038] S2: The detected contact force is converted into corrected angle and angular velocity Δq using a force-potential mapping model. M , The corrected angle and angular velocity Δq M , The value reflects the degree of rejection of the current standard gait by the human lower limbs; the larger the value, the greater the rejection.

[0039] S3: Then compare the angle and angular velocity q with the standard gait trajectory data from the industrial control computer. IN , The difference is used to obtain the desired angle and angular velocity q. D , That is, q D =q IN -Δq M , To achieve closed-loop control at the upper level;

[0040] S4: The industrial computer will input the desired angle and angular velocity q D , The angle and angular velocity q of the actual motion trajectory are sent to the joint motor drivers (hip and knee joint motor drivers). F , Feedback is sent to the joint motor driver, and the difference between the two yields the control quantities angle and angular velocity Δq. D , That is, Δq D =q D -q F , The joint motor driver uses the control quantities angle and angular velocity Δq D , The output drives the motor, which in turn moves the thigh and calf adjustment levers, achieving low-level closed-loop control of the motor by the driver.

[0041] The key to this model is the force-position mapping model, which specifically states that: assuming the maximum and minimum values ​​of the leg contact force under comfortable walking conditions are F... Max and F Min (F in a comfortable state for patients who have completely lost the ability to walk) Max and F Min The value used differs from that for patients with some walking ability (this value can be determined based on experimental results), and the actual leg contact force sensor feedback value is F. When the leg contact force F... Min <F<F Max At this point, we can assume that walking with an exoskeleton is relatively comfortable, and the exoskeleton's walking trajectory does not require correction. When the leg contact force F... <F Min At this point, the exoskeleton's forward leg lift is relatively fast, causing the human body to tend to move backward relative to the exoskeleton. Therefore, the exoskeleton's trajectory needs to be corrected based on the value of F. Where m is the mass of the exoskeleton leg, K1 is a coefficient that needs to be determined based on the debugging situation, and dt is one control cycle of the control system. When the leg contact force F > F... MaxAt this point, the exoskeleton swings its legs backward at a relatively fast speed, causing the human body to tend to move forward relative to the exoskeleton. Therefore, the exoskeleton's walking trajectory needs to be corrected based on the value of F. Where m is the mass of the exoskeleton leg, K2 is a coefficient that needs to be determined based on the debugging situation, and dt is one control cycle of the control system.

[0042] The active control mode includes the following steps: S1: Before rehabilitation training, electromyography (EMG) and electroencephalography (EEG) signals of the patient's various movements are collected using EMG and EEG information acquisition devices to establish a mapping relationship between the various movements of the human gait trajectory and EMG and EEG signals, that is, the correspondence between EMG and EEG signals and the movement angles and angular velocities of the human hip and knee joints. At the same time, the industrial control computer continuously records the plantar pressure, joint angles, and joint torques of the patient during the movement process to establish a gait trajectory database. The plantar pressure is obtained through an intelligent sensing boot pressure sensor, and the joint angles and joint torques are obtained from the encoder and torque sensor of the joint motor, respectively.

[0043] S2: During the patient's rehabilitation training, the patient's electromyography (EMG) and electroencephalography (EEG) signals are collected in real time, compared with the EMG and EEG signals in the gait trajectory database, to determine the patient's movement intention and output the predicted gait trajectory.

[0044] S3: Judge the predicted gait trajectory based on the current joint angle and plantar pressure information; if the judgment is correct, proceed to step S4; if the judgment is incorrect, use the particle swarm optimization algorithm to match the optimal data from the gait trajectory library based on the previous motion state, thereby driving the joint movement at the current moment.

[0045] S4: Input the angle and angular velocity q of the standard gait trajectory data from the industrial computer. IN , The thigh end sensing strap 8 and the calf sensing strap 10 respectively detect the contact force between the human leg and the exoskeleton leg in real time;

[0046] S5: The detected contact force is converted into corrected angle and angular velocity Δq using a force-potential mapping model. M ,

[0047] S6: Then compare the angle and angular velocity q with the standard gait trajectory data from the industrial control computer. IN , The difference is used to obtain the desired angle and angular velocity q. D , That is, q D =q IN -Δq M , To achieve closed-loop control at the upper level;

[0048] S7: The industrial control computer will input the desired angle and angular velocity q D , The actual motion trajectory angle and angular velocity q are sent to the joint motor driver. F , Feedback is sent to the joint motor driver, and the difference between the two yields the control quantities angle and angular velocity Δq. D , That is, Δq D =q D -q F , The joint motor driver uses the control quantities angle and angular velocity Δq D , The output drives the motor, which in turn moves the thigh and calf adjustment rods, thus achieving closed-loop control of the motor by the driver.

[0049] Figure 5 The diagram shows the passive control flowchart of the rehabilitation exoskeleton robot. The patient selects the passive training mode through the main control. In the passive training mode, the robot's various joints are actually tracked and controlled. Therefore, the system input is the corrected desired gait trajectory curve, and the feedback data is the robot's actual joint motion data (including joint angle, angular velocity, joint torque, etc.) and human-machine interaction force information.

[0050] The active control algorithm for rehabilitation exoskeleton robots is designed for patients with some lower limb motor ability. It assists them in completing lower limb movements by judging their intention and tendency to move. Figure 6 As shown, the active control algorithm employs a gait recognition and prediction algorithm based on the fusion of multi-source information from EEG, EMG, and mechanical sensors. In active rehabilitation training, the patient's active movement intention serves as the excitation signal for the rehabilitation training system. This signal is primarily acquired by EMG and EMG information acquisition devices, and then a mapping relationship is established between the human gait trajectory and EMG and EMG signals, i.e., the correspondence between EMG and EMG signals and the movement angles and angular velocities of the hip and knee joints. Simultaneously, the master controller continuously records information such as plantar pressure, joint angles, and joint torques during the patient's walking process to build a gait trajectory database.

[0051] To verify the accuracy of the predicted gait trajectory, the intelligent sensing boot 11 needs to be used to judge the predicted gait trajectory. Assume the reading of the pressure sensor inside the intelligent sensing boot 11 is F. f The maximum and minimum values ​​when the human foot comes into contact with the sensor are F, respectively. f max and F f min. When the system detects F three times consecutively. f min <F f <F fWhen the value is max, the sensor state is considered to be 1; when the system detects F three times consecutively... f <F f At the minimum value, the sensor state is considered to be 0. Assuming the pressure sensor at the sole of the exoskeleton is A, and the pressure sensor at the heel is B, there are four possible classifications based on the states of sensors A and B: (A=0, B=0), (A=0, B=1), (A=1, B=0), (A=1, B=1), and (A=0, B=0) represent the swing phase; (A=0, B=1) represents the early support phase; (A=1, B=1) represents the middle support phase; and (A=1, B=0) represents the late support phase. The gait segmentation based on plantar pressure information is used to determine the accuracy of gait trajectories predicted by EEG and EMG: During normal walking, the standard gait cycle repeats continuously from swing phase → early support phase → middle support phase → late support phase → swing phase, without skipping stages. For example, if the current gait is in the swing phase, the next moment should be the early support phase. If the predicted gait trajectory is roughly consistent with the joint movement trend during the transition from the swing phase to the early support phase in the standard gait, and the joint movement angle is within the range of human joint movement angles, then the predicted gait trajectory is considered correct; otherwise, it is considered incorrect. If the judgment is correct, the main controller inputs the correct predicted gait trajectory data, and the subsequent processing steps are consistent with inputting the standard gait trajectory data in passive control mode. If the judgment is incorrect, the optimal data is matched from the gait trajectory library based on the previous moment's movement state using a particle swarm optimization algorithm, thereby driving the joint movement at the current moment.

[0052] After obtaining the actual gait and movement trend information of the rehabilitation patient, the control system predicts the next trajectory by referring to the standard gait trajectory. After obtaining the next gait trajectory, it calculates the joint motion angles to track the desired trajectory and adjusts the joint angle outputs in real time by detecting the robot's current motion state to help the patient complete the gait movement. The flowchart of the active control algorithm is as follows: Figure 7 As shown.

[0053] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0054] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A lower limb exoskeleton intelligent compliance control system, characterized in that: The system includes a movable protective frame, an exoskeleton robot, an electromyography (EMG) information acquisition device, an electroencephalography (EEG) information acquisition device, and an industrial control computer. The exoskeleton robot includes a leg bionic support structure, which is symmetrically installed on the left and right sides of the waist structure. The leg bionic support structure includes a hip joint integrated motor (6), a thigh adjustment rod, a knee joint integrated motor (9), a calf adjustment rod, and a foot intelligent sensing boot (11) connected in sequence. The bottom of the intelligent sensing boot is equipped with a foot pressure sensor. The thigh adjustment rod is equipped with a thigh root strap (7) and a thigh end sensing strap (8). The calf adjustment rod (110) is equipped with a calf sensing strap (10). The EMG information acquisition device, the EEG information acquisition device, the hip joint integrated motor (6), the knee joint integrated motor (9), the thigh end sensing strap (8), and the calf sensing strap (10) are all connected to the industrial control computer. The control system executes a control method, which includes a passive control mode and an active control mode. The passive control mode includes the following steps: S1: Input the angle and angular velocity of the standard gait trajectory data from the industrial computer. The contact force between the human leg and the exoskeleton leg is detected in real time by the thigh end sensing strap (8) and the calf sensing strap (10). S2: The detected contact force is converted into corrected angle and angular velocity using a force-potential mapping model. ; S3: The angle and angular velocity of the standard gait trajectory data... With the corrected angle and angular velocity The difference is used to obtain the desired angle and angular velocity. ,Right now This enables closed-loop control at the upper level. S4: The industrial control computer will input the desired angle and angular velocity. The angle and angular velocity of the actual motion trajectory of the hip joint integrated motor and the knee joint integrated motor are sent to the joint motor driver. Feedback is sent to the joint motor driver, and the difference between the two yields the control quantities: angle and angular velocity. Right now The joint motor driver operates according to the control parameters of angle and angular velocity. The output drives the hip joint integrated motor and the knee joint integrated motor, thereby driving the thigh adjustment rod and the calf adjustment rod to move, realizing the driver's low-level closed-loop control of the motor; The active control mode includes the following steps: S1: Establish and store a gait trajectory library through the industrial control computer. The gait trajectory library contains the mapping relationship between electromyography signals, electroencephalography signals and the movement angles and angular velocities of the human hip and knee joints. S2: During operation, signals are collected in real time by electromyography (EMG) and electroencephalography (EEG) acquisition devices, and the industrial control computer compares the real-time acquired signals with the signals in the gait trajectory database to determine the movement intention and output the predicted gait trajectory. S3: The industrial control computer judges the predicted gait trajectory based on the current plantar pressure information detected by the foot smart sensing boot and the current joint angles of the hip joint integrated motor and knee joint integrated motor; if the judgment is correct, proceed to step S4; if the judgment is incorrect, use the particle swarm optimization algorithm to match the optimal data from the gait trajectory library according to the previous motion state, thereby driving the joint movement at the current moment. S4: Input the angle and angular velocity of the standard gait trajectory data from the industrial computer. The contact force between the human leg and the exoskeleton leg is detected in real time by the thigh end sensing strap (8) and the calf sensing strap (10). S5: The detected contact force is converted into corrected angle and angular velocity using a force-potential mapping model. ; S6: Calculate the angle and angular velocity of the standard gait trajectory data. With the corrected angle and angular velocity The difference is used to obtain the desired angle and angular velocity. This enables closed-loop control at the upper level. S7: The industrial control computer will input the desired angle and angular velocity. The angle and angular velocity of the actual motion trajectory of the hip joint integrated motor and the knee joint integrated motor are sent to the joint motor driver. Feedback is sent to the joint motor driver, and the difference between the two yields the control quantities: angle and angular velocity. The joint motor driver operates according to the control parameters of angle and angular velocity. The output drives the hip joint integrated motor and the knee joint integrated motor, thereby driving the thigh adjustment rod and the calf adjustment rod to move, realizing the driver's low-level closed-loop control of the motor.

2. The intelligent compliance control system for a lower limb exoskeleton according to claim 1, characterized in that: The hip joint integrated motor and knee joint integrated motor adopt an integrated drive unit with a built-in reducer, motor, encoder, torque sensor and driver. The output end of the motor is connected to the input end of the reducer, and the output end of the reducer is connected to the thigh adjustment rod. The encoder and driver are mounted on the motor, and the torque sensor is connected to the output shaft of the motor. The encoder, torque sensor and driver are all connected to the industrial control computer for communication.

Images