Lower limb exoskeleton control method and device for ultra-high voltage power grid, computer equipment and storage medium

Abstract

The embodiment of the invention provides a lower limb exoskeleton control method and device for an ultra-high voltage power grid, computer equipment, a storage medium and a computer program product, and relates to the technical field of exoskeletons. The method comprises the following steps: acquiring load information data and motion information data of a target object; acquiring working mode information of a target exoskeleton matched with the target object based on the load information data by using a pre-trained load identification model; acquiring motion state information of the target exoskeleton by using a pre-trained attitude estimation model based on attitude information data included in the motion information data; according to the working mode information and the motion state information, the output torque of the target exoskeleton is obtained, and the operation state of the target exoskeleton is adjusted through the output torque. According to the method, the working efficiency and safety of the ultra-high-voltage power grid are improved.

Description

Technical Field

[0001] The present application relates to the field of exoskeleton technology, and in particular to a lower limb exoskeleton control method, device, computer equipment, storage medium and computer program product for an ultra-high voltage power grid. Background Art

[0002] In the maintenance of ultra-high voltage power grids, the working conditions and environment involved are often extremely harsh. In order to improve the working environment of the target object, improve work efficiency and ensure work safety, exoskeleton technology can be introduced into the maintenance work of high-voltage power grids.

[0003] The exoskeleton technology currently used in ultra-high voltage power grid maintenance often relies on pre-set operating modes or manual control, which can lead to problems such as slow exoskeleton response and low efficiency. For example, the working mode switches slowly, making it difficult to adapt to complex and changing working environments, and the response to the target object's actions is often not timely enough, posing safety hazards, low efficiency and low safety. Summary of the invention

[0004] Based on this, it is necessary to provide a lower limb exoskeleton control method, device, computer equipment, storage medium and computer program product for ultra-high voltage power grid to address the above technical problems.

[0005] In a first aspect, the present application provides a lower limb exoskeleton control method for an ultra-high voltage power grid. The method comprises:

[0006] Obtaining load information data and motion information data of the target object;

[0007] Using a pre-trained load recognition model, based on the load information data, obtaining working mode information of a target exoskeleton that matches the target object;

[0008] Using a pre-trained posture estimation model, based on the posture information data included in the motion information data, the motion state information of the target exoskeleton is acquired;

[0009] The output torque of the target exoskeleton is acquired according to the working mode information and the motion state information, and the operating state of the target exoskeleton is adjusted using the output torque.

[0010] In one embodiment, the use of a pre-trained load identification model to obtain the working mode information of a target exoskeleton that matches the target object based on the load information data includes: inputting the load information data into the load identification model to obtain the working mode information of the target exoskeleton; wherein the load identification model obtains the load label of the target object based on the load information data, and obtains the working mode information of the target exoskeleton based on the load label.

[0011] In one embodiment, the load identification model obtains the load label of the target object according to the load information data, and obtains the working mode information of the target exoskeleton according to the load label, including: a first feature extraction module included in the load identification model extracts features from the load information data, determines and outputs the load feature information of the target object; a first classification module included in the load identification model determines the load label of the target object according to the load feature information output by the first feature extraction module, and determines and outputs the working mode information of the target exoskeleton according to the load label.

[0012] In one embodiment, the method of using a pre-trained posture estimation model to obtain the motion state information of the target exoskeleton based on the posture information data included in the motion information data includes: inputting the posture information data into the posture estimation model to obtain the motion state information of the target exoskeleton; wherein the posture estimation model obtains the posture pattern of the target object based on the posture information data, and obtains the motion state information of the target exoskeleton based on the posture pattern.

[0013] In one of the embodiments, the posture estimation model obtains the posture mode of the target object according to the posture information data, and obtains the motion state information of the target exoskeleton according to the posture mode, including: a second feature extraction module included in the posture estimation model performs feature extraction on the posture information data, determines and outputs the posture feature information of the target object; a second classification module included in the posture estimation model determines the posture mode of the target object according to the posture feature information output by the second feature extraction module, and determines and outputs the motion state information of the target exoskeleton according to the posture mode.

[0014] In one of the embodiments, obtaining the output torque of the target exoskeleton according to the working mode information and the motion state information includes: using a pre-built exoskeleton system model of the exoskeleton system of the target exoskeleton, and obtaining the output torque of the target exoskeleton according to the working mode information and the motion state information.

[0015] In one embodiment, the exoskeleton system model includes an objective function and constraints; the exoskeleton system model of the exoskeleton system of the target exoskeleton, which is pre-built, obtains the output torque of the target exoskeleton according to the working mode information and the motion state information, including: under the constraints, solving the objective function according to the working mode information and the motion state information, and obtaining the output torque of the target exoskeleton in a future time period; the future time period includes at least one future time step; the output torque includes a single output torque for each of at least one of the future time steps.

[0016] In a second aspect, the present application provides a lower limb exoskeleton control device for an ultra-high voltage power grid. The device comprises:

[0017] A data acquisition module, used to acquire load information data and motion information data of a target object;

[0018] A first calculation module is used to obtain working mode information of a target exoskeleton matching the target object based on the load information data by using a pre-trained load recognition model;

[0019] A second calculation module is used to obtain the motion state information of the target exoskeleton based on the posture information data included in the motion information data by using a pre-trained posture estimation model;

[0020] The third calculation module is used to obtain the output torque of the target exoskeleton according to the working mode information and the motion state information, and adjust the operating state of the target exoskeleton using the output torque.

[0021] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0022] Obtaining load information data and motion information data of the target object;

[0023] Using a pre-trained load recognition model, based on the load information data, obtaining working mode information of a target exoskeleton that matches the target object;

[0024] Using a pre-trained posture estimation model, based on the posture information data included in the motion information data, the motion state information of the target exoskeleton is acquired;

[0025] The output torque of the target exoskeleton is acquired according to the working mode information and the motion state information, and the operating state of the target exoskeleton is adjusted using the output torque.

[0026] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0027] Obtaining load information data and motion information data of the target object;

[0028] Using a pre-trained load recognition model, based on the load information data, obtaining working mode information of a target exoskeleton that matches the target object;

[0029] Using a pre-trained posture estimation model, based on the posture information data included in the motion information data, the motion state information of the target exoskeleton is acquired;

[0030] The output torque of the target exoskeleton is acquired according to the working mode information and the motion state information, and the operating state of the target exoskeleton is adjusted using the output torque.

[0031] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0032] Obtaining load information data and motion information data of the target object;

[0033] Using a pre-trained load recognition model, based on the load information data, obtaining working mode information of a target exoskeleton that matches the target object;

[0034] Using a pre-trained posture estimation model, based on the posture information data included in the motion information data, the motion state information of the target exoskeleton is acquired;

[0035] The output torque of the target exoskeleton is acquired according to the working mode information and the motion state information, and the operating state of the target exoskeleton is adjusted using the output torque.

[0036] In the above-mentioned lower limb exoskeleton control method, device, computer equipment, storage medium and computer program product for ultra-high voltage power grid, first, the load information data and motion information data of the target object can be obtained; next, the pre-trained load recognition model can be used to obtain the working mode information of the target exoskeleton matching the target object based on the load information data; further, the pre-trained posture estimation model can be used to obtain the motion state information of the target exoskeleton based on the posture information data contained in the motion information data; finally, the output torque of the target exoskeleton can be obtained according to the working mode information and the motion state information, and the output torque can be used to adjust the operating state of the target exoskeleton. In the method provided in the embodiment of the present application, a load identification model is provided in the exoskeleton system of the target exoskeleton, and the load identification model can be used to realize real-time perception and identification of the load on the target object, so that the exoskeleton can autonomously adjust its structure and working mode to adapt to different load states; a posture estimation model is provided in the exoskeleton system of the target exoskeleton, so that the exoskeleton can naturally change its posture as the target object moves and operates, and keep synchronization with the movements of the target object, thereby improving comfort and efficiency of use, and further, the torque control module can be used to adjust the output torque of the target exoskeleton in real time according to the working mode information and motion state information of the target exoskeleton, thereby improving the efficiency and safety of the use of the exoskeleton, and further, the efficiency and safety of ultra-high voltage power grid operations can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 A flow chart of a method for controlling a lower limb exoskeleton in an ultra-high voltage power grid provided in an embodiment of the present application;

[0039] Figure 2 A schematic diagram of a process for obtaining working mode information provided in an embodiment of the present application;

[0040] Figure 3 A schematic diagram of a process for obtaining motion status information provided in an embodiment of the present application;

[0041] Figure 4 A structural block diagram of a lower limb exoskeleton control device for an ultra-high voltage power grid provided in an embodiment of the present application;

[0042] Figure 5An internal structure diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0044] In an exemplary embodiment, Figure 1 As shown, a method for controlling a lower limb exoskeleton for an ultra-high voltage power grid is provided. This embodiment uses the method applied to a server as an example. It is understandable that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0045] Step 102: Obtain load information data and motion information data of the target object.

[0046] Wherein, the target object can be any object equipped with a target exoskeleton, for example, a staff member equipped with a lower limb exoskeleton. The target exoskeleton can be a human exoskeleton and / or a power exoskeleton, for example, a lower limb exoskeleton, and the human exoskeleton and / or the power exoskeleton can be a machine device that uses a mechanical device to enhance the structural strength, motor strength and endurance of human limbs, and its working principle is to detect the movement intention and state of the human body through a sensor, and then the power unit provides energy, and the power is transmitted to the execution unit through a transmission device, thereby assisting or enhancing the movement of the human body. The lower limb exoskeleton control method for an ultra-high voltage power grid provided in the embodiment of the present application can be applied to the exoskeleton system of the target exoskeleton, and the exoskeleton system can include multiple sensors, a load identification module, a posture estimation module and a torque control module. The multiple sensors can include but are not limited to force sensors, pressure sensors, accelerometers and gyroscopes, etc., wherein the force sensor and the pressure sensor can be used to measure the external load of the target object, and the initial load information data of the target object can be monitored; the accelerometer and the gyroscope can be used to monitor the posture and motion state of the target object, and the initial motion information data of the target object can be monitored. The initial load information data may include the force and pressure data, torque data, etc. of the target object. The force sensor and pressure sensor directly measure the external load borne by the target object. For example, when the target object is carrying power grid equipment, the force sensors in the hands, shoulders and other parts can measure the pulling force or pressure generated by the gravity of the equipment, which can intuitively reflect the target object's immediate load situation and help the exoskeleton determine the support strength required. Some force sensors can measure the output torque. For example, sensors at the joints can monitor the torque generated by limb movement and load. When climbing or stretching in the maintenance of ultra-high voltage power grids, the joint torque data helps the exoskeleton adjust the auxiliary strength of the corresponding joint to ensure synchronization with the target object's movements. The initial motion information data may include the initial posture information data of the target object. For example, the gyroscope measures the angular velocity of each part of the target object's body, reflecting the rotation speed of the joints. When the target object performs twisting, turning and other movements, the angular velocity data can help the exoskeleton perceive posture changes, adjust its own posture, maintain the balance of the target object, and improve the comfort and safety of use. The initial motion information data may also include the speed and acceleration of the target object. For example, when the target object walks quickly, starts or stops suddenly, the acceleration data will change accordingly. The target exoskeleton can predict the movement trend of the target object based on this, adjust its own state in advance, provide appropriate assistance, and ensure smooth movement of the target object.Next, the initial load information data monitored by the force sensor and the pressure sensor may be subjected to data preprocessing, for example, filtering and denoising, to obtain load information data corresponding to the initial load information data; and the initial motion information data of the target object monitored by the accelerometer and the gyroscope may be subjected to data preprocessing, for example, filtering and denoising, to obtain motion information data corresponding to the initial motion information data. In one possible implementation, a low-pass filter may be used to smooth the data, and a Kalman filter may be used to fuse multi-sensor data to improve the accuracy of posture estimation.

[0047] Step 104 , using the pre-trained load recognition model, based on the load information data, obtain the working mode information of the target exoskeleton that matches the target object.

[0048] The exoskeleton system of the target exoskeleton includes a load identification module, which can sense the load change of the target object in real time, and then, according to the load state of the target object, the target skeleton can be switched to the corresponding working mode. The target exoskeleton has at least one working mode, and there is a corresponding relationship between the working mode and the load state of the target object. The load identification module is configured with a load identification model. First, the pre-processed load information data monitored by the force sensor and the pressure sensor can be obtained; next, the pre-trained load identification model can be used to obtain the working mode information of the target exoskeleton matching the target object based on the load information data, and the load information data can be input into the pre-trained load identification model, and the corresponding working mode of the target exoskeleton can be determined and output. The training process of the load recognition model may include: collecting multiple initial sample load data through sensor monitoring, and performing data preprocessing on the initial sample load data to obtain multiple sample load data; next, a load sample training set may be obtained from the sample load data, and the load sample training set may include sample load data corresponding to each load state under multiple load states, and the actual working mode label of the target exoskeleton corresponding to each load state; further, the multiple sample load data may be input into the load recognition model to be trained, and the load recognition model may be a neural network model, such as a multi-layer perceptron, a convolutional neural network, and a recurrent neural network. The load recognition model may include at least one convolution layer and at least one pooling layer, and the convolution layer is used to extract the features of the input data; the pooling layer is used to sample the input data. Both the convolution layer and the pooling layer include an activation function.

[0049] Specifically, the convolution layer can be used to extract the initial features of multiple sample load data. The first step is to convert multiple sample load data into vectors to obtain multiple sample load data vectors, which can be combined into a vector matrix; the second step is to input the vector matrix into the convolution layer, and use the convolution kernel to perform convolution operation with the vector matrix, that is, to perform inner product operation on the vector matrix and the convolution kernel to obtain the convolution result corresponding to the vector matrix; next, the convolution result is nonlinearly transformed based on the activation function, and the bias vector is added to obtain the initial feature vector; the third step is to input the initial feature vector into the pooling layer, and the initial feature vector can be sampled; then, the feature sampling result is nonlinearly transformed based on the activation function, and the bias vector is added to obtain the sample load feature.

[0050] The load identification model may include at least one fully connected layer, which may classify the sample load features to obtain a predicted working mode label of the target exoskeleton corresponding to the sample load data. In addition, the fully connected layer may include an activation function, which includes a weight matrix and a bias constant.

[0051] Specifically, the sample load features can be input into the fully connected layer, and the sample load features can be nonlinearly transformed based on the weight matrix and bias vector of the activation function. Then, through normalization, the predicted working mode label of the target exoskeleton corresponding to the sample load data can be obtained.

[0052] Furthermore, the load recognition model to be trained can be trained according to the difference between the predicted working mode label of the target exoskeleton corresponding to the sample load data and the actual working mode label of the target exoskeleton corresponding to the sample load data, wherein the difference between the predicted working mode label and the actual working mode label can be obtained by using the loss function of the load recognition model to be trained. The training process of the load recognition model to be trained can be referred to in formula (1):

[0053]

[0054] in, are model parameters, is the loss function, is the predicted output of the model, is the true label, is the regularization parameter, is the regularization term.

[0055] Thus, the trained load identification model can be deployed in the load identification module of the exoskeleton system of the target exoskeleton.

[0056] Step 106 , using the pre-trained posture estimation model, based on the posture information data included in the motion information data, obtain the motion state information of the target exoskeleton.

[0057] The exoskeleton system of the target exoskeleton includes a posture estimation module, which can sense the posture change of the target object in real time and adjust the motion state of the target exoskeleton according to the posture change of the target object. First, the posture information data contained in the pre-processed motion information data monitored by the accelerometer and the gyroscope can be obtained; next, the posture feature information of the target object can be obtained according to the posture information data using a pre-trained posture estimation model. In a possible implementation, the posture change of the target object can be estimated using quaternions and / or direction cosine matrices; further, the posture category of the target object can be determined according to the posture feature information of the target object using a pre-trained posture estimation model, such as standing, walking, squatting, etc., and then the motion state of the target exoskeleton can be adjusted according to the posture category of the target object.

[0058] Step 108: acquiring the output torque of the target exoskeleton according to the working mode information and the motion state information, and adjusting the operating state of the target exoskeleton using the output torque.

[0059] In this step, the model predictive control (MPC) can be used to predict the output torque of the target exoskeleton in the future time period. First, an exoskeleton system model of the exoskeleton system of the target exoskeleton can be established. The exoskeleton system model can be a dynamic model. The dynamic model can describe the behavior of each component of the target exoskeleton (for example, the multiple joints included in the target exoskeleton) based on the kinematics and dynamics principles of the target exoskeleton. In a possible implementation, the dynamic model of the exoskeleton system can be constructed based on the Lagrange equation or the Newton-Euler law. The target exoskeleton may include multiple joints, and the state of each of the multiple joints can be expressed in the form of a spatial state, as shown in equations (2) and (3):

[0060]

[0061] in, It can be the target exoskeleton at time step The state vector may include, for example, the position, velocity, acceleration and other information of multiple joints; It can be in time step A control input, the control input may include a joint torque of each joint in the plurality of joints; It can be that the exoskeleton system is in the time step An output vector of the target exoskeleton, the output vector may include variables that can be measured in the exoskeleton system, for example, angles of various joints of the target exoskeleton; , , , is the system matrix.

[0062] Next, in MPC, the motion state of the target exoskeleton in the future can be predicted based on the current state information of the target exoskeleton at each time step, that is, the state vector. The current state information may include but is not limited to the working mode information and motion state information of the target exoskeleton, and the working mode information of the target exoskeleton is associated with the load state information of the target object; the future period of time, that is, the future time period, may include multiple future time steps. In a possible implementation, a rolling time window with a prediction window of 𝑁 can be used to predict the motion state of the target exoskeleton in N future time steps, as shown in equations (4) and (5):

[0063]

[0064] in, It can be the target exoskeleton in the future time step The state vector may include, for example, the position, velocity, acceleration and other information of multiple joints; It can be in the future time step A control input, the control input may include a joint torque of each joint in the plurality of joints; It can be the exoskeleton system in the future time step An output vector of the target exoskeleton, the output vector may include variables that can be measured in the exoskeleton system, for example, angles of various joints of the target exoskeleton; , , , is the system matrix;

[0065] Furthermore, the control input of the target exoskeleton in N future time steps, i.e., the joint matrix, can be predicted based on the motion state of the target exoskeleton in N future time steps, i.e., the output vector. In a possible implementation, the objective function of the target exoskeleton can be constructed, and constraints can be set. Under the constraints, the objective function can be solved. By minimizing the objective function, a set of optimal control input sequences can be obtained. The control input sequence can include control inputs in N future time steps. The objective function can be referred to in equation (6), and the constraints can include control input constraints, see equation (7):

[0066]

[0067] in, It may be the desired output of the exoskeleton system (e.g., the joint positions and joint velocities of the target exoskeleton); Can be a future time step The control input is the joint torque. and is the weight matrix.

[0068]

[0069] in, and are the upper and lower limits of the control input.

[0070] In each prediction cycle, MPC needs to determine the best control input sequence by solving the optimization problem. This optimization process is usually solved by a numerical optimization algorithm, such as gradient descent method, least squares method, etc. The result of the solution is the optimal control input sequence for a period of time in the future. The control input sequence can include control inputs for multiple future time steps. Usually, in multiple future time steps of the current prediction cycle, the control input of the target exoskeleton in the first future time step of the multiple future time steps, that is, the joint torque, can be used. When the exoskeleton system enters the next time step of the current time step, the next prediction cycle of the current prediction cycle can be started, and the control input of the first future time step of the new multiple future time steps will be obtained, and this cycle will continue.

[0071] In addition, the exoskeleton system may include a safety protection module, which immediately turns on the protection mode if the target exoskeleton is detected to be operating abnormally. In one possible implementation, a detection threshold for the target exoskeleton may be set based on historical sensor data to detect abnormal operation of the target exoskeleton, such as a torque threshold, an acceleration threshold, and an angular velocity threshold, as shown in formula (8):

[0072]

[0073] in, is the mean of the sensor data, is the standard deviation of the sensor data, is a constant used to adjust the sensitivity. In another possible implementation, a machine learning model can also be used for anomaly detection, or a statistical-based method can be used to identify anomalies.

[0074] The design of protection mode can include:

[0075] 1. Torque limitation: Immediately limit the output torque of the exoskeleton to prevent excessive mechanical load on the target object. This can be achieved by dynamically adjusting the output limit of the torque controller, see equation (9):

[0076]

[0077] in, is the safety torque after limitation, is the currently calculated torque, is the maximum allowable torque set.

[0078] 2. Movement stop: When a serious abnormality is detected, all movements of the exoskeleton are stopped immediately to prevent further damage. This can be achieved by setting the control input to zero, see equation (10):

[0079]

[0080] 3. Alarm system: trigger sound and light alarms or send alarm signals to the target object and monitoring system so that further safety measures can be taken in time.

[0081] 4. Data recording: Record data of abnormal events for post-analysis and system improvement.

[0082] In the method of this embodiment, first, the load information data and motion information data of the target object can be obtained; next, a pre-trained load recognition model can be used to obtain the working mode information of the target exoskeleton that matches the target object based on the load information data; further, a pre-trained posture estimation model can be used to obtain the motion state information of the target exoskeleton based on the posture information data contained in the motion information data; finally, the output torque of the target exoskeleton can be obtained based on the working mode information and the motion state information, and the output torque can be used to adjust the operating state of the target exoskeleton. In the method provided in the embodiment of the present application, a load identification model is provided in the exoskeleton system of the target exoskeleton, and the load identification model can be used to realize real-time perception and identification of the load on the target object, so that the exoskeleton can autonomously adjust its structure and working mode to adapt to different load states; a posture estimation model is provided in the exoskeleton system of the target exoskeleton, so that the exoskeleton can naturally change its posture as the target object moves and operates, and keep synchronization with the movements of the target object to improve comfort and efficiency of use, and further, the torque control module can be used to adjust the output torque of the target exoskeleton in real time according to the working mode information and motion state information of the target exoskeleton, thereby improving the efficiency and safety of the use of the exoskeleton, and further, the efficiency and safety of ultra-high voltage power grid operations can be improved.

[0083] In an exemplary embodiment, step 104 may include:

[0084] The load information data is input into the load identification model to obtain the working mode information of the target exoskeleton; wherein the load identification model obtains the load label of the target object according to the load information data, and obtains the working mode information of the target exoskeleton according to the load label.

[0085] In an exemplary embodiment, Figure 2 As shown, the load identification model obtains the load label of the target object according to the load information data, and obtains the working mode information of the target exoskeleton according to the load label, which may include steps 202 to 204. Among them:

[0086] Step 202: A first feature extraction module included in the load identification model extracts features from the load information data to determine and output load feature information of the target object.

[0087] The first feature extraction module may include at least one convolution layer and at least one pooling layer, wherein the convolution layer is used to extract features of input data; and the pooling layer is used to sample the input data. Both the convolution layer and the pooling layer include an activation function. The load information data may include multiple text information.

[0088] Specifically, the convolution layer can be used to extract the initial features of multiple text information. The first step is to convert multiple text information into vectors to obtain multiple text information vectors, which can be combined into a text information vector matrix; the second step is to input the text information vector matrix into the convolution layer, and use the convolution kernel to perform convolution operation with the text information vector matrix, that is, to perform inner product operation on the text information vector matrix and the convolution kernel to obtain the convolution result corresponding to the text information vector matrix; next, the convolution result is nonlinearly transformed based on the activation function, and the bias vector is added to obtain the initial feature vector; the third step is to input the initial feature vector into the pooling layer, and the initial feature vector can be sampled; then, the feature sampling result is nonlinearly transformed based on the activation function, and the bias vector is added to obtain the load feature information.

[0089] Step 204, the first classification module included in the load identification model determines the load label of the target object according to the load feature information output by the first feature extraction module, and determines and outputs the working mode information of the target exoskeleton according to the load label.

[0090] The first classification module may include at least one fully connected layer, which can classify the load feature information so as to obtain the working mode information of the target exoskeleton. In addition, the fully connected layer may include an activation function, which includes a weight matrix and a bias constant.

[0091] Specifically, the load characteristic information can be input into the fully connected layer, and based on the weight matrix and bias vector of the activation function, the load characteristic information is nonlinearly transformed, and then normalized to obtain the working mode information of the target exoskeleton.

[0092] In the method of this embodiment, a load recognition model is provided in the exoskeleton system of the target exoskeleton, and the load recognition model can be used to realize real-time perception and recognition of the load on the target object, so that the exoskeleton can autonomously adjust its structure and working mode to adapt to different load states, thereby improving the efficiency of the use of the exoskeleton.

[0093] In an exemplary embodiment, step 106 may include:

[0094] The posture information data is input into the posture estimation model to obtain the motion state information of the target exoskeleton; wherein the posture estimation model obtains the posture mode of the target object according to the posture information data, and obtains the motion state information of the target exoskeleton according to the posture mode.

[0095] In an exemplary embodiment, Figure 3 As shown, the posture estimation model obtains the posture mode of the target object according to the posture information data, and obtains the motion state information of the target exoskeleton according to the posture mode, which may include steps 302 to 304. Among them:

[0096] Step 302: A second feature extraction module included in the posture estimation model extracts features from the posture information data to determine and output posture feature information of the target object.

[0097] The second feature extraction module may include at least one convolution layer and at least one pooling layer, wherein the convolution layer is used to extract features of input data; and the pooling layer is used to sample the input data. Both the convolution layer and the pooling layer include an activation function. The posture information data may include multiple text information.

[0098] Specifically, the convolution layer can be used to extract the initial features of multiple text information. The first step is to convert multiple text information into vectors to obtain multiple text information vectors, which can be combined into a text information vector matrix; the second step is to input the text information vector matrix into the convolution layer, and use the convolution kernel to perform convolution operation with the text information vector matrix, that is, to perform inner product operation on the text information vector matrix and the convolution kernel to obtain the convolution result corresponding to the text information vector matrix; next, the convolution result is nonlinearly transformed based on the activation function, and the bias vector is added to obtain the initial feature vector; the third step is to input the initial feature vector into the pooling layer, and the initial feature vector can be sampled; then, the feature sampling result is nonlinearly transformed based on the activation function, and the bias vector is added to obtain the posture feature information.

[0099] Step 304: The second classification module included in the posture estimation model determines the posture mode of the target object according to the posture feature information output by the second feature extraction module, and determines and outputs the motion state information of the target exoskeleton according to the posture mode.

[0100] The second classification module may include at least one fully connected layer, which can classify the posture feature information to obtain the motion state information of the target exoskeleton. In addition, the fully connected layer may include an activation function, which includes a weight matrix and a bias constant.

[0101] Specifically, the posture feature information can be input into the fully connected layer, and the posture feature information can be nonlinearly transformed based on the weight matrix and bias vector of the activation function, and then normalized to obtain the motion state information of the target exoskeleton.

[0102] In the method of this embodiment, a posture estimation model is provided in the exoskeleton system of the target exoskeleton, so that the exoskeleton can change its posture naturally as the target object moves and operates, keep in sync with the movements of the target object, and improve comfort and efficiency of use.

[0103] In an exemplary embodiment, step 108 may include:

[0104] The output torque of the target exoskeleton is obtained by using the pre-built exoskeleton system model of the exoskeleton system of the target exoskeleton according to the working mode information and the motion state information.

[0105] Among them, the model predictive control (MPC) can be used to predict the output torque of the target exoskeleton in the future time period. First, an exoskeleton system model of the exoskeleton system of the target exoskeleton can be established. The exoskeleton system model can be a dynamic model. The dynamic model can describe the behavior of each component of the target exoskeleton (for example, multiple joints included in the target exoskeleton) based on the kinematics and dynamics principles of the target exoskeleton. In a possible implementation, the dynamic model of the exoskeleton system can be constructed based on the Lagrange equation or the Newton-Euler law. The target exoskeleton may include multiple joints, and the state of each of the multiple joints can be represented in the form of a spatial state, as shown in equations (2) and (3). Furthermore, the exoskeleton system model can be used to obtain the output torque of the target exoskeleton based on the working mode information and the motion state information.

[0106] In an exemplary embodiment, the exoskeleton system model includes an objective function and constraints; the step of using a pre-built exoskeleton system model of an exoskeleton system of a target exoskeleton to obtain the output torque of the target exoskeleton according to the working mode information and the motion state information may include:

[0107] Under constraint conditions, according to working mode information and motion state information, solve the objective function to obtain the output torque of the target exoskeleton in a future time period; the future time period includes at least one future time step; the output torque includes a single output torque of each future time step in at least one future time step.

[0108] Among them, in MPC, the motion state of the target exoskeleton in a future period of time can be predicted based on the current state information of the target exoskeleton at each time step, that is, the state vector. The current state information may include but is not limited to the working mode information and motion state information of the target exoskeleton, and the working mode information of the target exoskeleton is associated with the load state information of the target object; the future period of time, that is, the future time period, may include multiple future time steps. In a possible implementation, a rolling time window with a prediction window of 𝑁 can be used to predict the motion state of the target exoskeleton in N future time steps, as shown in equations (4) and (5). Further, the control input of the target exoskeleton in N future time steps, that is, the joint matrix, can be predicted based on the motion state of the target exoskeleton in N future time steps, that is, the output vector. In a possible implementation, the objective function of the target exoskeleton can be constructed, and constraints can be set. Under the constraints, the objective function is solved. By minimizing the objective function, a set of optimal control input sequences can be obtained. The control input sequence may include the control input of N future time steps, that is, the output torque. In each prediction cycle, MPC needs to determine the best control input sequence by solving the optimization problem. This optimization process is usually solved by a numerical optimization algorithm, such as gradient descent method, least squares method, etc. The result of the solution is the optimal control input sequence for a period of time in the future. The control input sequence can include control inputs for multiple future time steps. Usually, in multiple future time steps of the current prediction cycle, the control input of the target exoskeleton in the first future time step of the multiple future time steps, that is, the joint torque, can be used. When the exoskeleton system enters the next time step of the current time step, the next prediction cycle of the current prediction cycle can be started, and the control input of the first future time step of the new multiple future time steps will be obtained, and this cycle will continue.

[0109] In the method of this embodiment, the torque control module can be used to adjust the output torque of the target exoskeleton in real time according to the working mode information and motion state information of the target exoskeleton, thereby improving the efficiency and safety of the exoskeleton use, and further improving the efficiency and safety of ultra-high voltage power grid operations.

[0110] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0111] Based on the same inventive concept, the embodiment of the present application also provides a lower limb exoskeleton control device for ultra-high voltage power grid for implementing the lower limb exoskeleton control method for ultra-high voltage power grid involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the lower limb exoskeleton control device for ultra-high voltage power grid provided below can refer to the limitations of the lower limb exoskeleton control method for ultra-high voltage power grid above, and will not be repeated here.

[0112] In one embodiment, Figure 4 As shown, a lower limb exoskeleton control device for an ultra-high voltage power grid is provided, comprising: a data acquisition module 402, a first calculation module 404, a second calculation module 406 and a third calculation module 408, wherein:

[0113] The data acquisition module 402 is used to acquire the load information data and motion information data of the target object;

[0114] A first calculation module 404 is used to obtain working mode information of a target exoskeleton matching the target object based on the load information data using a pre-trained load recognition model;

[0115] A second calculation module 406 is used to obtain the motion state information of the target exoskeleton based on the posture information data included in the motion information data by using a pre-trained posture estimation model;

[0116] The third calculation module 408 is used to obtain the output torque of the target exoskeleton according to the working mode information and the motion state information, and adjust the operating state of the target exoskeleton using the output torque.

[0117] In one embodiment, the first calculation module 404 is also used to: input the load information data into the load identification model to obtain the working mode information of the target exoskeleton; wherein the load identification model obtains the load label of the target object according to the load information data, and obtains the working mode information of the target exoskeleton according to the load label.

[0118] In one embodiment, the first calculation module 404 is also used for: using a first feature extraction module included in the load identification model to perform feature extraction on the load information data, and determining and outputting the load feature information of the target object; using a first classification module included in the load identification model to determine the load label of the target object according to the load feature information output by the first feature extraction module, and determining and outputting the working mode information of the target exoskeleton according to the load label.

[0119] In one embodiment, the second calculation module 406 is also used to: input the posture information data into the posture estimation model to obtain the motion state information of the target exoskeleton; wherein the posture estimation model obtains the posture pattern of the target object based on the posture information data, and obtains the motion state information of the target exoskeleton based on the posture pattern.

[0120] In one embodiment, the second calculation module 406 is also used for: the second feature extraction module included in the posture estimation model performs feature extraction on the posture information data, determines and outputs the posture feature information of the target object; the second classification module included in the posture estimation model determines the posture mode of the target object according to the posture feature information output by the second feature extraction module, and determines and outputs the motion state information of the target exoskeleton according to the posture mode.

[0121] In one embodiment, the third calculation module 408 is further used to: use a pre-built exoskeleton system model of the exoskeleton system of the target exoskeleton to obtain the output torque of the target exoskeleton according to the working mode information and the motion state information.

[0122] In one embodiment, the third calculation module 408, the exoskeleton system model includes an objective function and constraints; and is also used to: under the constraints, solve the objective function according to the working mode information and the motion state information, and obtain the output torque of the target exoskeleton in a future time period; the future time period includes at least one future time step; the output torque includes a single output torque for each of at least one future time step.

[0123] Each module in the above-mentioned lower limb exoskeleton control device for ultra-high voltage power grid can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0124] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data related to the control of lower limb exoskeleton for ultra-high voltage power grid. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a lower limb exoskeleton control method for ultra-high voltage power grid is implemented.

[0125] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0126] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0127] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0128] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0129] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0130] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0131] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0132] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A lower limb exoskeleton control method for an ultra-high voltage power grid, characterized in that: The method comprises: Obtaining load information data and motion information data of the target object; Using a pre-trained load recognition model, based on the load information data, obtaining working mode information of a target exoskeleton that matches the target object; Using a pre-trained posture estimation model, based on the posture information data included in the motion information data, the motion state information of the target exoskeleton is acquired; The output torque of the target exoskeleton is acquired according to the working mode information and the motion state information, and the operating state of the target exoskeleton is adjusted using the output torque.

2. The method according to claim 1, characterized in that: The method of using a pre-trained load recognition model to obtain working mode information of a target exoskeleton matching the target object based on the load information data includes: Inputting the load information data into the load identification model to obtain the working mode information of the target exoskeleton; The load identification model obtains the load label of the target object according to the load information data, and obtains the working mode information of the target exoskeleton according to the load label.

3. The method according to claim 2, characterized in that The step of obtaining the load label of the target object according to the load information data by the load identification model, and obtaining the working mode information of the target exoskeleton according to the load label, includes: The first feature extraction module included in the load identification model performs feature extraction on the load information data to determine and output the load feature information of the target object; The first classification module included in the load identification model determines the load label of the target object according to the load feature information output by the first feature extraction module, and determines and outputs the working mode information of the target exoskeleton according to the load label.

4. The method according to claim 1, characterized in that The method of using a pre-trained posture estimation model to obtain the motion state information of the target exoskeleton based on the posture information data included in the motion information data includes: Inputting the posture information data into the posture estimation model to obtain the motion state information of the target exoskeleton; The posture estimation model obtains the posture mode of the target object according to the posture information data, and obtains the motion state information of the target exoskeleton according to the posture mode.

5. The method according to claim 4, characterized in that The step of obtaining the posture mode of the target object according to the posture information data by the posture estimation model, and acquiring the motion state information of the target exoskeleton according to the posture mode, comprises: A second feature extraction module included in the posture estimation model performs feature extraction on the posture information data to determine and output posture feature information of the target object; The second classification module included in the posture estimation model determines the posture mode of the target object according to the posture feature information output by the second feature extraction module, and determines and outputs the motion state information of the target exoskeleton according to the posture mode.

6. The method according to claim 1, characterized in that The step of obtaining the output torque of the target exoskeleton according to the working mode information and the motion state information includes: The output torque of the target exoskeleton is obtained according to the working mode information and the motion state information by using a pre-constructed exoskeleton system model of the exoskeleton system of the target exoskeleton.

7. The method according to claim 6, characterized in that The exoskeleton system model includes an objective function and constraint conditions; The method of using the pre-built exoskeleton system model of the exoskeleton system of the target exoskeleton to obtain the output torque of the target exoskeleton according to the working mode information and the motion state information comprises: Under the constraint conditions, according to the working mode information and the motion state information, the objective function is solved to obtain the output torque of the target exoskeleton in a future time period; the future time period includes at least one future time step; the output torque includes a single output torque of each of at least one future time step.

8. A lower limb exoskeleton control device for an ultra-high voltage power grid, characterized in that: The device comprises: A data acquisition module, used to acquire load information data and motion information data of a target object; A first calculation module is used to obtain working mode information of a target exoskeleton matching the target object based on the load information data by using a pre-trained load recognition model; A second calculation module is used to obtain the motion state information of the target exoskeleton based on the posture information data included in the motion information data by using a pre-trained posture estimation model; The third calculation module is used to obtain the output torque of the target exoskeleton according to the working mode information and the motion state information, and adjust the operating state of the target exoskeleton using the output torque.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images