A lower limb exoskeleton control device and method based on IMU

Abstract

The present invention discloses an IMU-based lower limb exoskeleton control device, the control device comprising an IMU (1), a hip joint servo motor (2), a knee joint servo motor (3), a central processing unit (4), an embedded controller (5) and a power module (6), wherein the IMU (1) is placed at four joint rings of the device, the hip joint servo motor (2) and the knee joint servo motor (3) are both placed on the isometric side wall of the device, and the central processing unit (4), the embedded controller (5) and the power module (6) are all placed on the back panel of the device. The exoskeleton control method proposed by the present invention can output personalized auxiliary torque for each patient, provide accurate rehabilitation training for the patient, and better help the user recover muscle function.

Description

Technical Field

[0001] The present invention belongs to the field of exoskeleton robots, and in particular relates to an IMU-based lower limb exoskeleton control device and method. Background Art

[0002] Lower limb rehabilitation medical exoskeletons can assist patients with lower limb movement disorders with rehabilitation training. Due to their vast application scenarios, they have become a research hotspot worldwide. With the aging population, the number of people with lower limb mobility impairments continues to rise. Lower limb exoskeletons have become one of the most promising solutions for patients with movement disorders to restore lower limb mobility. Rehabilitation exoskeletons can assist patients with spinal cord injuries, strokes, and traumatic brain injuries with rehabilitation training, helping them regain their mobility.

[0003] The lower limb rehabilitation exoskeletons currently available on the market mainly provide patients with simple repetitive exercises through fixed programs. They cannot determine how much auxiliary torque should be applied based on the patient's current movement state, and cannot provide effective rehabilitation training for the muscles at the patient's corresponding joints. The human-computer interaction and training effects are not ideal, resulting in poor rehabilitation results. Summary of the Invention

[0004] In response to the above-mentioned deficiencies in the prior art, the present invention provides an IMU-based lower limb exoskeleton control device and method, which can apply corresponding auxiliary torque to the patient according to the patient's movement state, achieve better human-computer interaction effects, effectively train the patient's corresponding joint muscles, and improve training accuracy.

[0005] In order to achieve the above-mentioned purpose of the invention, the technical solution adopted by the present invention is: an IMU-based lower limb exoskeleton control device includes an IMU, a hip joint servo motor, a knee joint servo motor, a central processing unit, an embedded controller and a power module, wherein the IMU is placed at the four joint rings of the device, the hip joint servo motor and the knee joint servo motor are both placed on the isometric side walls of the device, the central processing unit, the embedded controller and the power module are all placed on the back panel of the device, the central processing unit is respectively communicated with the IMU and the embedded controller, and the power module is respectively electrically connected to the IMU, the hip joint servo motor, the knee joint servo motor, the central processing unit and the embedded controller.

[0006] The beneficial effect of the above scheme is: through the above technical scheme, the patient's movement information can be obtained in real time, personalized auxiliary treatment can be provided to the patient, human-computer interaction can be realized, and accurate rehabilitation training can be provided to the patient.

[0007] Furthermore, the hip joint servo motor is connected to the two upper hip joint rings, and the knee joint servo motor is connected to the two lower knee joint rings.

[0008] The beneficial effect of the above further solution is: in the above technical solution, the hip joint servo motor controls the hip joint ring to train the user's hip joint, and the knee joint servo motor controls the knee joint ring to train the user's knee joint.

[0009] Furthermore, the IMU is placed outside the joint ring, and the joint ring is connected by metal and flexible straps.

[0010] The beneficial effect of the above further solution is: the joint ring in the above technical solution is composed of metal and flexible straps, which can provide good support and binding for the user, so that the exoskeleton fits the human body better and ensures the accuracy of applying auxiliary torque, while also ensuring the accuracy of IMU data collection.

[0011] Furthermore, the hip joint ring and knee joint ring are both placed on the inner side of the vertical axis of the device, the hip joint servo motor and knee joint servo motor are placed on the outer side of the vertical axis of the device, and the hip joint ring, knee joint ring and foot pedal placed on the inner side of the two vertical axes are all located in the same vertical plane.

[0012] The beneficial effect of the above further solution is that the above technical solution can ensure the flexibility of the user when wearing the exoskeleton for exercise, and the movement will not be hindered by the structure of the exoskeleton. The structural design of the device also provides the user with a better user experience.

[0013] Furthermore, the heights of the two vertical axes in the device can be freely adjusted by bolts.

[0014] The beneficial effect of the above further solution is that the above technical solution can flexibly adjust the height of the vertical axis of the device, and adjust different heights according to the user's height and other personal conditions, providing users with more comfortable and convenient training services. At the same time, the flexible adjustment also expands the user range.

[0015] In addition, the present invention also adopts a technical solution: a lower limb exoskeleton control method based on IMU, characterized in that the method includes the following steps:

[0016] S1: Use IMU to collect user's motion information;

[0017] S2: Use the central processing unit to process the collected motion information according to the deep learning algorithm to generate motor control signals;

[0018] S3: transmits the motor control signal to the embedded controller for signal conversion;

[0019] S4: Controlling the joint servo motor to perform corresponding auxiliary actions through the signal converted by the embedded controller;

[0020] S5: Use the angle sensors and torque sensors in the joint servo motors to monitor whether the exoskeleton has reached the target position and feed back the execution status to the embedded controller. If the expected target value is not reached, the embedded controller calculates the error and promptly adjusts the predicted values ​​of the next joint angle and joint torque.

[0021] The beneficial effects of the above scheme are: the above technical scheme uses IMU means to accurately and safely obtain the athlete's gait information. The central processing unit uses deep learning algorithms to process the data and transmit the signal to the embedded controller to control the joint servo motor to execute the corresponding auxiliary torque. At the same time, the angle sensor and torque sensor will monitor the current movement state of the lower limb exoskeleton and promptly feedback to the central processing unit for analysis and processing, reducing the use error of the device and providing users with more accurate training.

[0022] Furthermore, the deep learning algorithm in S2 includes the following sub-steps:

[0023] S2-1: Filter the data collected by the IMU and extract the appropriate feature values ​​to input into the trained neural network model;

[0024] S2-2: Determine the current motion state and gait phase of the human body based on the input feature values ​​through the neural network model;

[0025] S2-3: Predict the joint torque and joint angle at time T+1ms based on the human body motion state and gait phase data for the previous 20ms including the current time T;

[0026] S2-4: The central processing unit generates motor control signals based on the predicted data of joint torque and joint angle at the next moment.

[0027] The beneficial effect of the above further scheme is: the above technical scheme uses a deep learning algorithm to analyze and process the acquired human gait information, and then predict the joint torque and joint angle at the next moment, and at the same time convert the prediction results into motor control signals, thereby controlling the motor to perform corresponding auxiliary actions.

[0028] Furthermore, the embedded controller in S3 adopts a cascade PID closed-loop control algorithm, taking the expected joint angles and joint torques obtained by the deep learning algorithm as input.

[0029] The beneficial effect of the above further solution is that the above solution converts the control signal into an auxiliary torque and rotation angle output by the motor, so as to achieve good human-computer interaction and good rehabilitation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1An isometric view of the IMU-based lower limb exoskeleton control device.

[0031] Figure 2 Back view of the exoskeleton showing the IMU-based lower limb exoskeleton control device.

[0032] Figure 3 This is the schematic diagram of the lower limb exoskeleton control method based on IMU.

[0033] Figure 4 The flowchart of the lower limb exoskeleton control method based on IMU and video stream.

[0034] Figure 5 This is the flow chart of the cascade PID control algorithm.

[0035] Figure 6 Simplified single-degree-of-freedom model of the hip and knee joints.

[0036] Among them: 1. Inertial sensing unit (IMU); 2. Hip joint servo motor; 3. Knee joint servo motor; 4. Central processing unit; 5. Embedded controller; 6. Power module. DETAILED DESCRIPTION

[0037] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0038] Example 1, as Figure 1 and Figure 2 As shown, an IMU-based lower limb exoskeleton control device includes an IMU1, a hip joint servo motor 2, a knee joint servo motor 3, a central processing unit 4, an embedded controller 5 and a power module 6. The IMU1 is placed at the four joint rings of the device, the hip joint servo motor 2 and the knee joint servo motor 3 are both placed on the isometric side walls of the device, the central processing unit 4, the embedded controller 5 and the power module 6 are all placed on the back panel of the device, the central processing unit 4 is communicated with the IMU1 and the embedded controller 5 respectively, and the power module 5 is electrically connected to the IMU1, the hip joint servo motor 2, the knee joint servo motor 3, the central processing unit 4 and the embedded controller 5 respectively.

[0039] Among them, the hip joint servo motor 2 is connected to the two hip joint rings above, the knee joint servo motor 3 is connected to the two knee joint rings below, the IMU1 is placed on the outside of the joint ring, the joint ring is connected by metal and flexible straps, the hip joint ring and the knee joint ring are both placed on the inside of the vertical axis of the device, the hip joint servo motor 2 and the knee joint servo motor 3 are placed on the outside of the vertical axis of the device, and the hip joint ring, knee joint ring and foot pedal placed on the inside of the two vertical axes are all in the same vertical plane, and the two vertical axes in the device can be freely adjusted in height by bolts.

[0040] Example 2, as Figure 3 and Figure 4 As shown, a lower limb exoskeleton control method based on IMU is characterized in that the method comprises the following steps:

[0041] S1: Use IMU to collect user's motion information;

[0042] S2: Use the central processing unit to process the collected motion information according to the deep learning algorithm to generate motor control signals;

[0043] S3: transmits the motor control signal to the embedded controller for signal conversion;

[0044] S4: Controlling the joint servo motor to perform corresponding auxiliary actions through the signal converted by the embedded controller;

[0045] S5: Use the angle sensors and torque sensors in the joint servo motors to monitor whether the exoskeleton has reached the target position and feed back the execution status to the embedded controller. If the expected target value is not reached, the embedded controller calculates the error and adjusts the predicted values ​​of the next joint angle and joint torque in a timely manner.

[0046] The deep learning algorithm in S2 includes the following sub-steps:

[0047] S2-1: Filter the data collected by the IMU and extract the appropriate feature values ​​to input into the trained neural network model;

[0048] S2-2: Determine the current motion state and gait phase of the human body based on the input feature values ​​through the neural network model;

[0049] S2-3: Predict the joint torque and joint angle at time T+1ms based on the human body motion state and gait phase data for the previous 20ms including the current time T;

[0050] S2-4: The central processing unit generates motor control signals based on the predicted data of joint torque and joint angle at the next moment.

[0051] The embedded controller in S3 adopts cascade PID closed-loop control algorithm. The cascade PID control algorithm uses the position loop as the first loop to realize joint angle control, the speed loop as the second loop to realize joint angular velocity control, and the torque loop as the third loop to realize output torque control. The specific implementation process of the cascade PID algorithm is as follows: Figure 5As shown in the figure: Using the expected joint angle and joint torque obtained by the deep learning algorithm as input, the embedded controller obtains the expected joint angle θ and passes it to the position loop PID controller. The speed loop PID controller calculates the expected speed based on the position increment, and the torque loop PID controller controls the output torque of the motor based on the expected torque. At the same time, the position loop and torque loop use angle sensors and torque sensors for real-time feedback to reduce execution errors.

[0052] In one embodiment of the present invention, an IMU is used to collect kinematic data of the user's hip and knee joints at the current moment. The central processing unit processes the data collected by the IMU in real time through a deep learning algorithm, identifies the gait phase, and predicts the joint angles and joint torques of the hip and knee joints at the next moment. The central processing unit converts the auxiliary torque and joint angle target values ​​to be output into motor control signals based on the prediction results and the user's current motion state, and transmits them to the embedded controller to control the servo motor to perform the corresponding auxiliary action. The torque sensor and angle sensor are used to monitor whether the auxiliary torque and joint angle output by the motor reach the target. If the expected target value is not reached, the embedded controller will calculate the error and make timely adjustments to the predicted values ​​of the joint angle and joint torque for the next time to prevent the error from being too large and affecting the control of the exoskeleton. This can avoid the cumulative error that may occur after the system has been running for a period of time, while improving the stability and execution accuracy of the system.

[0053] To improve the accuracy of the deep learning algorithm, the present invention uses a public biomechanical dataset to train the deep learning model. Before the deep neural network algorithm is trained using the dataset, the data processing calculation formula is determined:

[0054] The formula for calculating joint torque is as follows:

[0055]

[0056] Where J is the moment of inertia of the thigh or calf about the center of mass, is the angular acceleration of the thigh or calf, M1 is the first joint torque, M2 is the second joint torque, F 1x and F 1y are the horizontal and vertical forces acting on the distal end of the thigh or calf, respectively, 2x and F 2y are the horizontal and vertical forces acting on the proximal thigh or calf, respectively, L 1x , L 2x 、L 1y and L 2y are the moment arms of the relevant forces about the center of mass;

[0057] The formula for calculating joint angular velocity is: ω joint=ω2j2-ω1j1, integrating the joint angular velocity to obtain the joint angle is: q = ∫ω joint dt;

[0058] in, Figure 6 This is a simplified model of the hip and knee joints with a single degree of freedom. IMU1 is placed on the thigh to obtain hip joint motion data, and IMU2 is placed on the calf to obtain knee joint motion data. The P axis is established based on IMU1 and IMU2. j1 and j2 are the orientation vectors of the P axis observed in the IMU1 and IMU2 coordinate systems. ω1 and ω2 are the angular velocities of IMU1 and IMU2, respectively.

[0059] Based on the above formula, the dataset collected kinematic data from dozens of subjects using four IMUs placed at the center of mass of the thigh and calf. The data were then calculated using the professional biomechanical analysis software OpenSim to obtain kinematic and dynamic data such as joint angles and joint torques during walking, and a corresponding relationship between gait phase and joint angles and joint torques was established. During model training, the acceleration and angular velocity data of the human lower limbs collected by four IMUs are filtered using a fourth-order Butterworth filter and then the eigenvalues ​​are calculated. Appropriate eigenvalues ​​are selected as model inputs. To obtain good prediction accuracy, the deep learning model integrates a 2D convolutional neural network and a bidirectional long short-term memory network. When the model's prediction accuracy meets the usage requirements, the deep learning model is deployed to the central processing unit. Since the relationship between gait phase and joint angle and joint torque has been established in the early stage, when the user wears the exoskeleton to exercise, the central processing unit will calculate the joint angle and joint torque at the current time T in real time to determine the user's gait phase at the current time T, and predict the joint angle and joint torque at the time T+1ms based on the previous 20ms data including the current time T to generate the motor control signal.

[0060] Through the technical solutions of the above-mentioned embodiments 1 and 2, the user's movement information can be accurately obtained, personalized auxiliary torque can be provided for each patient, and good human-computer interaction performance can be achieved, thereby providing patients with more accurate and effective rehabilitation training.

[0061] The present invention proposes an IMU-based lower limb exoskeleton control device and method, which uses IMU non-invasive sensors to obtain accurate human motion data, combines deep learning algorithms to predict joint torque and joint angle, and then obtains the target values ​​of the auxiliary torque and joint angle output by the motor at different times in the gait cycle. The torque sensor and angle sensor monitor the execution status of the exoskeleton to achieve closed-loop control of the exoskeleton. In this way, the exoskeleton can follow the human body's movement in real time, obtain good human-computer interaction performance, and output personalized auxiliary torque for each patient, providing patients with precise rehabilitation training, which can better help users restore muscle function and achieve the purpose of rehabilitation training.

[0062] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and it should be understood that the scope of protection of the present invention is not limited to such specific descriptions and embodiments. Those skilled in the art can make various other specific variations and combinations based on the technical teachings disclosed in the present invention without departing from the essence of the present invention, and such variations and combinations are still within the scope of protection of the invention.

Claims

1. A lower limb exoskeleton control method based on an IMU, which is implemented by a lower limb exoskeleton control device based on an IMU, the device comprising an IMU (1), a hip joint servo motor (2), a knee joint servo motor (3), a central processing unit (4), an embedded controller (5) and a power module (6), wherein the IMU (1) is placed at four joint rings of the device, the hip joint servo motor (2) and the knee joint servo motor (3) are both placed on the isometric side wall of the device, the central processing unit (4), the embedded controller (5) and the power module (6) are all placed on the back panel of the device, the central processing unit (4) is respectively connected to the IMU (1) and the embedded controller (5), and the power module (6) is respectively connected to the IMU (1), the hip joint servo motor (2), the knee joint servo motor (3), the central processing unit (4) and the embedded controller (5); It is characterized by: The method comprises the following steps: S1: Use IMU to collect user's motion information; S2: Use the central processing unit to process the collected motion information according to the deep learning algorithm to generate motor control signals; S3: transmits the motor control signal to the embedded controller for signal conversion; S4: Controlling the joint servo motor to perform corresponding auxiliary actions through the signal converted by the embedded controller; S5: Use the angle sensors and torque sensors in the joint servo motors to monitor whether the exoskeleton has reached the target position and feed back the execution status to the embedded controller. If the expected target value is not reached, the embedded controller calculates the error and promptly adjusts the predicted values ​​of the next joint angle and joint torque; The deep learning algorithm in S2 includes the following steps: S2-1: Filter the data collected by the IMU and extract the appropriate feature values ​​to input into the trained neural network model; S2-2: Determine the current motion state and gait phase of the human body based on the input feature values ​​through the neural network model; S2-3: Predict the joint torque and joint angle at time T+1ms based on the human body motion state and gait phase data for the previous 20ms including the current time T; S2-4: Using the central processing unit to generate motor control signals based on the data of the predicted joint torque and joint angle at the next moment; The embedded controller in S3 adopts a cascade PID closed-loop control algorithm, and takes the expected joint angle and joint torque obtained by the deep learning algorithm as input. The cascade PID closed-loop control algorithm uses the position loop as the first loop to realize joint angle control, the speed loop as the second loop to realize joint angular velocity control, and the torque loop as the third loop to realize output torque control. The specific implementation process is: using the expected joint angle and joint torque obtained by the deep learning algorithm as input, the embedded controller obtains the expected joint angle θ and transmits it to the position loop PID controller, the speed loop PID controller calculates the expected speed according to the position increment, and the torque loop PID controller controls the output torque of the motor according to the expected torque. At the same time, the position loop and the torque loop use angle sensors and torque sensors for real-time feedback to reduce execution errors.

2. The IMU-based lower limb exoskeleton control method according to claim 1, characterized in that: The hip joint servo motor (2) is connected to the two upper hip joint rings, and the knee joint servo motor (3) is connected to the two lower knee joint rings.

3. The IMU-based lower limb exoskeleton control method according to claim 1, characterized in that: The IMU (1) is placed outside the joint ring, and the joint ring is formed by connecting metal and flexible straps.

4. The IMU-based lower limb exoskeleton control method according to claim 2, characterized in that: The hip joint ring and the knee joint ring are both placed inside the vertical axis of the device, the hip joint servo motor (2) and the knee joint servo motor (3) are placed outside the vertical axis of the device, and the hip joint ring, the knee joint ring and the foot pedal placed inside the two vertical axes are all located in the same vertical plane.

5. The IMU-based lower limb exoskeleton control method according to claim 1, characterized in that: The two vertical axes in the device can be freely adjusted in height by means of bolts.

Images