An intelligent control method for a rehabilitation trainer robot

Abstract

The present invention relates to an intelligent control method for a rehabilitation trainer robot, belonging to the technical field of rehabilitation trainer robot control. The present invention constructs a joint intention motion model based on the sensor data information of each rehabilitation joint of a user, and obtains the motion intention feature data information of each joint position node based on the joint intention motion model. Thus, by performing a motion risk assessment on the motion intention feature data information of each joint position node, a risk assessment result is obtained, and the rehabilitation plan of the rehabilitation trainer robot is reconfigured according to the risk assessment result. Finally, motion control is performed on the rehabilitation trainer robot based on the rehabilitation plan of the rehabilitation trainer robot. By performing a motion risk assessment on the motion intention feature data information of each joint position node, the present invention reconfigures the rehabilitation plan of the rehabilitation trainer robot, fully considers the recovery situation of the user to formulate more reasonable rehabilitation training parameters, and avoids injuries during the recovery training process.

Description

Technical Field

[0001] The present invention relates to the technical field of rehabilitation trainer robots, and in particular to an intelligent control method for a rehabilitation trainer robot. Background Art

[0002] Rehabilitation training plays a great role in the early rehabilitation of stroke hemiplegia patients, seriously injured patients, etc. In the past, means such as walking ability training and standing balance training were mostly used. Conventional rehabilitation training can improve the limb movement function and balance ability of patients to a certain extent by training the gait and balance function of patients, but the effect is not obvious, and there is a lack of necessary feedback exercises, which is extremely easy to form an abnormal gait. A rehabilitation trainer robot is an intelligent lower limb feedback rehabilitation training system that can combine motion patterns and visual feedback to trigger the lower limb motor function and enable patients to regain the walking function, with high application value. Current rehabilitation trainer robots often achieve assisted rehabilitation by combining the movement intentions of users. However, if the rehabilitation exercise is only carried out according to the movement awareness of users, it is easy to cause injuries during the rehabilitation process, resulting in the rehabilitation effect of users not reaching the expected effect and delaying the rehabilitation period. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides an intelligent control method for a rehabilitation trainer robot.

[0004] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0005] The first aspect of the present invention provides an intelligent control method for a rehabilitation trainer robot, including the following steps:

[0006] Obtain the sensor data information of the user at each rehabilitation joint through a wearable rehabilitation trainer robot, and obtain the sensor data information after noise reduction processing by performing noise reduction processing on the sensor data information of the user at each rehabilitation joint;

[0007] Construct a joint intention motion model according to the sensor data information of the user at each rehabilitation joint, and obtain the motion intention feature data information of each joint position node based on the joint intention motion model;

[0008] Perform a motion risk assessment on the motion intention feature data information of each joint position node to obtain a risk assessment result, and reconfigure the rehabilitation plan of the rehabilitation trainer robot according to the risk assessment result;

[0009] Perform motion control on the rehabilitation trainer robot based on the rehabilitation plan of the rehabilitation trainer robot.

[0010] Further, in this method, sensor data information of the user at each rehabilitation joint is obtained by a wearable rehabilitation training robot. By performing noise reduction processing on the sensor data information of the user at each rehabilitation joint, sensor data information after noise reduction processing is obtained. Specifically:

[0011] Sensors are installed on the wearable rehabilitation training robot. Sensor data information of the user at each rehabilitation joint is obtained through the sensors, and a discrete wavelet transform algorithm is introduced to perform noise reduction processing on the sensor data information of the user at each rehabilitation joint;

[0012] Noise characteristics and original signal characteristics in the sensor data information are obtained through the discrete wavelet transform algorithm;

[0013] Wavelet bases are selected for the noise characteristics and original signal characteristics in the sensor data information, the number of layers is determined, and the original signal is hierarchically decomposed according to the number of layers;

[0014] Through hierarchical decomposition, low-frequency signals and high-frequency signals are obtained. Empirical thresholds are selected for the high-frequency signals of each layer, and the low-frequency signals and high-frequency preferences are reconstructed according to the empirical thresholds to obtain sensor data information after noise reduction processing.

[0015] Further, in this method, a joint intention motion model is constructed based on the sensor data information of the user at each rehabilitation joint. Specifically, it includes:

[0016] Based on the sensor data information of the user at each rehabilitation joint, the human joint motion torque characteristics corresponding to each sensor data are obtained, and a global human joint characteristic is constructed based on the human joint motion torque characteristics corresponding to each sensor data;

[0017] Based on the global human joint characteristic, parameterization of the three-dimensional posture of the human joint is performed to obtain three-dimensional posture parameters, and based on the three-dimensional posture parameters, joint and three-dimensional posture prediction are performed to obtain human posture joint intention characteristics;

[0018] Based on the human posture joint intention characteristics, a three-dimensional model is constructed. Through the construction, a joint intention motion model in the motion perception time stage is obtained, and the joint intention motion model is output.

[0019] Further, in this method, motion intention characteristic data information of each joint position node is obtained based on the joint intention motion model. Specifically, it includes:

[0020] By performing dimensionality reduction processing on the joint intention motion model, a two-dimensional map of the motion model of each joint position node is obtained, and motion feature extraction is performed on the two-dimensional map of the motion model of each joint position node;

[0021] Through motion feature extraction, motion intention feature data information of each joint position node is obtained, and the motion intention feature data information of each joint position node is output.

[0022] Furthermore, in this method, by performing motion risk assessment on the motion intention feature data information of each joint position node, a risk assessment result is obtained, specifically including:

[0023] Through big data, injury risk assessment feature data caused by a user using different motion states under the disease states of each joint is obtained, and a motion risk knowledge graph is constructed. The injury risk assessment feature data caused by the user using different motion states under the disease states of each joint is stored by inputting it into the motion risk knowledge graph;

[0024] The disease state information of each joint of the user is obtained, and the disease state information of each joint of the user and the motion intention feature data information of each joint position node are input into the knowledge graph for data search;

[0025] Through data search, injury risk assessment feature data caused by motion according to the motion intention feature data information of the joint position node under the disease state information of each joint of the user is obtained;

[0026] A risk assessment result is generated based on the injury risk assessment feature data caused by motion according to the motion intention feature data information of the joint position node under the disease state information of each joint of the user, and the risk assessment result is output.

[0027] Furthermore, in this method, according to the risk assessment result, the rehabilitation plan of the rehabilitation trainer robot is reconfigured, specifically:

[0028] The motion intention feature data information of the joint position node corresponding to the injury risk assessment feature data greater than the preset risk assessment index is obtained, and the motion parameters of the joint position node corresponding to the injury risk assessment feature data greater than the preset risk assessment index are re-initialized to reduce the motion parameters of the rehabilitation trainer robot;

[0029] The motion parameters of the rehabilitation trainer robot after initialization are obtained, and it is judged whether the motion parameters of the rehabilitation trainer robot after initialization still result in a situation where there is injury risk assessment feature data greater than the preset risk assessment index;

[0030] When the motion parameters of the rehabilitation trainer robot after initialization still result in a situation where there is injury risk assessment feature data greater than the preset risk assessment index, the motion parameters of the rehabilitation trainer robot are reconfigured and reduced;

[0031] When there is no situation where the injury risk assessment feature data of the post-initialization rehabilitation trainer robot motion parameters is greater than the preset risk assessment index, output the post-initialization rehabilitation trainer robot motion parameters and generate a rehabilitation plan for the rehabilitation trainer robot.

[0032] Further, in this method, the motion control of the rehabilitation trainer robot is performed based on the rehabilitation plan of the rehabilitation trainer robot. Specifically:

[0033] Judge whether the motion parameters in the rehabilitation plan of the rehabilitation trainer robot are greater than the maximum motion parameters of the rehabilitation trainer robot;

[0034] When the motion parameters in the rehabilitation plan of the rehabilitation trainer robot are greater than the maximum motion parameters of the rehabilitation trainer robot, perform motion control according to the maximum motion parameters of the rehabilitation trainer robot;

[0035] When the motion parameters in the rehabilitation plan of the rehabilitation trainer robot are not greater than the maximum motion parameters of the rehabilitation trainer robot, perform motion control according to the motion parameters in the current rehabilitation plan.

[0036] The second aspect of the present invention provides an intelligent control system for a rehabilitation trainer robot, including a memory and a processor. The memory includes a program for the intelligent control method of the rehabilitation trainer robot. When the program for the intelligent control method of the rehabilitation trainer robot is executed by the processor, the steps of any one of the intelligent control methods of the rehabilitation trainer robot are implemented.

[0037] The third aspect of the present invention provides a computer-readable storage medium, including a program for the intelligent control method of the rehabilitation trainer robot. When the program for the intelligent control method of the rehabilitation trainer robot is executed by a processor, the steps of any one of the intelligent control methods of the rehabilitation trainer robot are implemented.

[0038] The present invention solves the defects in the background technology and has the following beneficial effects:

[0039] The present invention obtains the sensor data information of the user at each rehabilitation joint through a wearable rehabilitation training robot. By performing noise reduction processing on the sensor data information of the user at each rehabilitation joint, the sensor data information after noise reduction processing is obtained. Then, a joint intention motion model is constructed based on the sensor data information of the user at each rehabilitation joint. Based on the joint intention motion model, the motion intention feature data information of each joint position node is obtained. Thus, by performing motion risk assessment on the motion intention feature data information of each joint position node, a risk assessment result is obtained. According to the risk assessment result, the rehabilitation plan of the rehabilitation training robot is reconfigured. Finally, the motion control of the rehabilitation training robot is performed based on the rehabilitation plan of the rehabilitation training robot. The present invention reconfigures the rehabilitation plan of the rehabilitation training robot by performing motion risk assessment on the motion intention feature data information of each joint position node, fully considering the user's recovery situation to formulate more reasonable rehabilitation training parameters and avoid injuries during the recovery process. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0041] Figure 1 Shows the overall flowchart of the intelligent control method of the rehabilitation training robot;

[0042] Figure 2 Shows a partial method flowchart of the intelligent control method of the rehabilitation training robot;

[0043] Figure 3 Shows the system block diagram of the intelligent control system of the rehabilitation training robot. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] In order to be able to more clearly understand the above-mentioned objects, features, and advantages of the present invention, the following will further describe the present invention in detail in conjunction with the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0045] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0046] Such as Figure 1As shown in the figure, the first aspect of the present invention provides an intelligent control method for a rehabilitation trainer robot, including the following steps:

[0047] S102: Obtain the sensor data information of the user at each rehabilitation joint through a wearable rehabilitation training robot, and obtain the sensor data information after noise reduction processing by performing noise reduction processing on the sensor data information of the user at each rehabilitation joint;

[0048] S104: Construct a joint intention motion model based on the sensor data information of the user at each rehabilitation joint, and obtain the motion intention characteristic data information of each joint position node based on the joint intention motion model;

[0049] S106: Perform a motion risk assessment on the motion intention characteristic data information of each joint position node to obtain a risk assessment result, and reconfigure the rehabilitation plan of the rehabilitation trainer robot according to the risk assessment result;

[0050] S108: Perform motion control on the rehabilitation trainer robot based on the rehabilitation plan of the rehabilitation trainer robot.

[0051] It should be noted that the present invention reconfigures the rehabilitation plan of the rehabilitation trainer robot by performing a motion risk assessment on the motion intention characteristic data information of each joint position node, fully considering the user's recovery situation to formulate more reasonable rehabilitation training parameters and avoid injuries during the recovery process.

[0052] Further, in this method, obtaining the sensor data information of the user at each rehabilitation joint through a wearable rehabilitation training robot, and obtaining the sensor data information after noise reduction processing by performing noise reduction processing on the sensor data information of the user at each rehabilitation joint, specifically:

[0053] Install sensors on the wearable rehabilitation training robot, obtain the sensor data information of the user at each rehabilitation joint through the sensors, and introduce the discrete wavelet transform algorithm to perform noise reduction processing on the sensor data information of the user at each rehabilitation joint;

[0054] Obtain the noise characteristics and the original signal characteristics in the sensor data information, and introduce the discrete wavelet transform algorithm;

[0055] Select wavelet bases for the noise characteristics and the original signal characteristics in the sensor data information, determine the number of layers, and decompose the original signal hierarchically according to the number of layers;

[0056] Through hierarchical decomposition, obtain the low-frequency signal and the high-frequency signal, select an empirical threshold for each layer of high-frequency signal, and reconstruct the low-frequency signal and the high-frequency preference according to the empirical threshold to obtain the sensor data information after noise reduction processing.

[0057] It should be noted that the sensors include data such as electromyogram signal sensors and torque sensors, and the sensor data information includes pressure data, torque data, electromyogram signal data, etc. The sensor data is denoised by the discrete wavelet transform algorithm to obtain more reliable signals.

[0058] Furthermore, in this method, a joint intention motion model is constructed based on the sensor data information of the user at each rehabilitation joint, which specifically includes:

[0059] Based on the sensor data information of the user at each rehabilitation joint, the human joint motion torque characteristics corresponding to each sensor data are obtained, and the global human joint characteristics are constructed based on the human joint motion torque characteristics corresponding to each sensor data;

[0060] Based on the global human joint characteristics, the three-dimensional pose parameters of the human joints are parameterized to obtain the three-dimensional pose parameters, and based on the three-dimensional pose parameters, the joints and the three-dimensional pose are estimated to obtain the human pose joint intention characteristics;

[0061] Based on the human pose joint intention characteristics, a three-dimensional model is constructed. Through the construction, the joint intention motion model in the motion perception time stage is obtained, and the joint intention motion model is output.

[0062] It should be noted that based on the human pose joint intention characteristics, a three-dimensional model is constructed through three-dimensional modeling software or virtual reality technology, so as to obtain the joint intention motion model in the motion perception time stage and form the joint motion intention prediction.

[0063] Furthermore, in this method, the motion intention characteristic data information of each joint position node is obtained based on the joint intention motion model, which specifically includes:

[0064] By performing dimensionality reduction processing on the joint intention motion model, a two-dimensional diagram of the motion model of each joint position node is obtained, and motion feature extraction is performed on the two-dimensional diagram of the motion model of each joint position node;

[0065] Through motion feature extraction, the motion intention characteristic data information of each joint position node is obtained, and the motion intention characteristic data information of each joint position node is output.

[0066] Furthermore, in this method, the motion risk assessment is performed on the motion intention characteristic data information of each joint position node to obtain the risk assessment result, which specifically includes:

[0067] Obtain the injury risk assessment feature data caused by users using different motion states under the disease states of each joint through big data, construct a motion risk knowledge graph, and input the injury risk assessment feature data caused by users using different motion states under the disease states of each joint into the motion risk knowledge graph for storage;

[0068] Obtain the disease state information of each joint of the user, and input the disease state information of each joint of the user and the motion intention feature data information of each joint position node into the knowledge graph for data search;

[0069] Through data search, obtain the injury risk assessment feature data caused by the user when exercising according to the motion intention feature data information of the joint position node under the disease state information of each joint of the user;

[0070] Generate a risk assessment result according to the injury risk assessment feature data caused by the user when exercising according to the motion intention feature data information of the joint position node under the disease state information of each joint of the user, and output the risk assessment result.

[0071] It should be noted that the joint disease state includes the disease assessment state of each joint of the user, such as low-degree injury state, moderate-degree injury state, high-degree injury state, etc., and the injury risks (such as low-degree risk, moderate risk, high risk, etc.) caused by the user using different motion states (motion intention features, such as torque features) under the disease states of each joint are different. Through this method, a risk assessment result can be obtained, so as to optimize the control parameters.

[0072] Such as Figure 2 As shown, further, in this method, reconfigure the rehabilitation plan of the rehabilitation trainer robot according to the risk assessment result, specifically:

[0073] S202: Obtain the motion intention feature data information of the joint position node corresponding to the injury risk assessment feature data greater than the preset risk assessment index, and re-initialize the motion parameters of the joint position node corresponding to the injury risk assessment feature data greater than the preset risk assessment index, and reduce the motion parameters of the rehabilitation trainer robot;

[0074] S204: Obtain the motion parameters of the rehabilitation trainer robot after initialization, and determine whether the motion parameters of the rehabilitation trainer robot after initialization still result in the situation that there is injury risk assessment feature data greater than the preset risk assessment index;

[0075] S206: When the motion parameters of the rehabilitation trainer robot after initialization still result in the situation that there is injury risk assessment feature data greater than the preset risk assessment index, reconfigure and reduce the motion parameters of the rehabilitation trainer robot;

[0076] S208: When there is no situation where the injury risk assessment feature data of the rehabilitation trainer robot motion parameters after initialization is greater than the preset risk assessment index, output the motion parameters of the rehabilitation trainer robot after initialization, and generate a rehabilitation plan for the rehabilitation trainer robot.

[0077] It should be noted that the motion parameters of the rehabilitation trainer robot include the operating speed of the motor, the number of revolutions of the motor, the swing angle of the motor, etc. When there is still a situation where the injury risk assessment feature data of the rehabilitation trainer robot motion parameters after initialization is greater than the preset risk assessment index, reconfigure and reduce the motion parameters of the rehabilitation trainer robot. When there is no situation where the injury risk assessment feature data of the rehabilitation trainer robot motion parameters after initialization is greater than the preset risk assessment index, output the motion parameters of the rehabilitation trainer robot after initialization. Optimize when there is no situation where the injury risk assessment feature data of the rehabilitation trainer robot motion parameters after initialization is greater than the preset risk assessment index, output the motion parameters of the rehabilitation trainer robot after initialization, so as to improve the rationality of the user's recovery exercise.

[0078] Furthermore, in this method, based on the rehabilitation plan of the rehabilitation trainer robot, motion control is performed on the rehabilitation trainer robot. Specifically:

[0079] Judge whether the motion parameters in the rehabilitation plan of the rehabilitation trainer robot are greater than the maximum motion parameters of the rehabilitation trainer robot;

[0080] When the motion parameters in the rehabilitation plan of the rehabilitation trainer robot are greater than the maximum motion parameters of the rehabilitation trainer robot, perform motion control according to the maximum motion parameters of the rehabilitation trainer robot;

[0081] When the motion parameters in the rehabilitation plan of the rehabilitation trainer robot are not greater than the maximum motion parameters of the rehabilitation trainer robot, perform motion control according to the motion parameters in the current rehabilitation plan.

[0082] It should be noted that through this method, the rehabilitation plan of the rehabilitation trainer robot can be further optimized, and the rationality of control can be improved.

[0083] Such as Figure 3 , The second aspect of the present invention provides an intelligent control system 4 for a rehabilitation trainer robot, including a memory 41 and a processor 42. The memory 41 includes an intelligent control method program for the rehabilitation trainer robot. When the intelligent control method program for the rehabilitation trainer robot is executed by the processor 42, the following steps are implemented:

[0084] Obtain the sensor data information of the user at each rehabilitation joint through the wearable rehabilitation training robot, and obtain the sensor data information after noise reduction processing by performing noise reduction processing on the sensor data information of the user at each rehabilitation joint.

[0085] Construct a joint intention motion model based on the sensor data information of each rehabilitation joint of the user, and obtain the motion intention feature data information of each joint position node based on the joint intention motion model;

[0086] By performing a motion risk assessment on the motion intention feature data information of each joint position node, obtain a risk assessment result, and reconfigure the rehabilitation plan of the rehabilitation trainer robot according to the risk assessment result;

[0087] Perform motion control on the rehabilitation trainer robot based on the rehabilitation plan of the rehabilitation trainer robot.

[0088] Furthermore, in this system, obtain the sensor data information of each rehabilitation joint of the user through a wearable rehabilitation trainer robot, and obtain the sensor data information after noise reduction processing by performing noise reduction processing on the sensor data information of each rehabilitation joint of the user. Specifically:

[0089] Install sensors on the wearable rehabilitation trainer robot, obtain the sensor data information of each rehabilitation joint of the user through the sensors, and introduce a discrete wavelet transform algorithm to perform noise reduction processing on the sensor data information of each rehabilitation joint of the user;

[0090] Obtain the noise characteristics and the original signal characteristics in the sensor data information through the discrete wavelet transform algorithm;

[0091] Select wavelet bases for the noise characteristics and the original signal characteristics in the sensor data information, determine the number of layers, and decompose the original signal hierarchically according to the number of layers;

[0092] Through hierarchical decomposition, obtain the low-frequency signal and the high-frequency signal, select an empirical threshold for each layer of high-frequency signal, and reconstruct the low-frequency signal and the high-frequency preference according to the empirical threshold to obtain the sensor data information after noise reduction processing.

[0093] Furthermore, in this system, construct a joint intention motion model according to the sensor data information of each rehabilitation joint of the user, specifically including:

[0094] Obtain the human joint motion torque characteristics corresponding to each sensor data based on the sensor data information of each rehabilitation joint of the user, and construct a global human joint feature based on the human joint motion torque characteristics corresponding to each sensor data;

[0095] Perform three-dimensional pose parameterization of the human joints based on the global human joint feature, obtain three-dimensional pose parameters, and perform joint and three-dimensional pose estimation based on the three-dimensional pose parameters to obtain the human pose joint intention feature;

[0096] Construct a 3D model based on the joint intention features of human body postures. Through the construction, obtain the joint intention motion model in the motion perception time stage and output the joint intention motion model.

[0097] Furthermore, in this system, obtain the motion intention feature data information of each joint position node based on the joint intention motion model, specifically including:

[0098] Through dimensionality reduction processing of the joint intention motion model, obtain the two-dimensional diagram of the motion model of each joint position node, and extract motion features from the two-dimensional diagram of the motion model of each joint position node;

[0099] Through motion feature extraction, obtain the motion intention feature data information of each joint position node and output the motion intention feature data information of each joint position node.

[0100] Furthermore, in this system, through motion risk assessment of the motion intention feature data information of each joint position node, obtain the risk assessment result, specifically including:

[0101] Through big data, obtain the injury risk assessment feature data caused by different motion states of users under the disease states of each joint, and construct a motion risk knowledge graph, and input the injury risk assessment feature data caused by different motion states of users under the disease states of each joint into the motion risk knowledge graph for storage;

[0102] Obtain the disease state information of each joint of the user, and input the disease state information of each joint of the user and the motion intention feature data information of each joint position node into the knowledge graph for data search;

[0103] Through data search, obtain the injury risk assessment feature data caused by motion according to the motion intention feature data information of the joint position node under the disease state information of each joint of the user;

[0104] Generate a risk assessment result according to the injury risk assessment feature data caused by motion according to the motion intention feature data information of the joint position node under the disease state information of each joint of the user, and output the risk assessment result.

[0105] Furthermore, in this system, reconfigure the rehabilitation plan of the rehabilitation trainer robot according to the risk assessment result, specifically:

[0106] Obtain the motion intention feature data information of the joint position node corresponding to the injury risk assessment feature data greater than the preset risk assessment index, and re-initialize the motion parameters of the joint position node corresponding to the injury risk assessment feature data greater than the preset risk assessment index, and reduce the motion parameters of the rehabilitation trainer robot;

[0107] Obtain the motion parameters of the rehabilitation trainer robot after initialization, and determine whether the motion parameters of the rehabilitation trainer robot after initialization still result in a situation where the injury risk assessment feature data is greater than the preset risk assessment index;

[0108] When the motion parameters of the rehabilitation trainer robot after initialization still result in a situation where the injury risk assessment feature data is greater than the preset risk assessment index, reconfigure and reduce the motion parameters of the rehabilitation trainer robot;

[0109] When the motion parameters of the rehabilitation trainer robot after initialization do not result in a situation where the injury risk assessment feature data is greater than the preset risk assessment index, output the motion parameters of the rehabilitation trainer robot after initialization, and generate a rehabilitation plan for the rehabilitation trainer robot.

[0110] Furthermore, in this system, the motion control of the rehabilitation trainer robot is performed based on the rehabilitation plan of the rehabilitation trainer robot. Specifically:

[0111] Determine whether the motion parameters in the rehabilitation plan of the rehabilitation trainer robot are greater than the maximum motion parameters of the rehabilitation trainer robot;

[0112] When the motion parameters in the rehabilitation plan of the rehabilitation trainer robot are greater than the maximum motion parameters of the rehabilitation trainer robot, perform motion control according to the maximum motion parameters of the rehabilitation trainer robot;

[0113] When the motion parameters in the rehabilitation plan of the rehabilitation trainer robot are not greater than the maximum motion parameters of the rehabilitation trainer robot, perform motion control according to the motion parameters in the current rehabilitation plan.

[0114] The third aspect of the present invention provides a computer-readable storage medium, including a program for the intelligent control method of the rehabilitation trainer robot. When the program for the intelligent control method of the rehabilitation trainer robot is executed by a processor, the steps of the intelligent control method of the rehabilitation trainer robot in any one of the above are implemented.

[0115] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed with each other can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical, or other forms.

[0116] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units; and some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0117] In addition, in each embodiment of the present invention, each functional unit may be fully integrated in a processing unit, or each unit may be separately taken as a unit, or two or more units may be integrated in one unit; the above integrated units may be implemented in the form of hardware or in the form of a combination of hardware and software functional units.

[0118] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including the above method embodiments; and the foregoing storage medium includes: various media such as removable storage devices, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks that can store program codes.

[0119] Alternatively, if the above integrated units of the present invention are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention essentially or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the various embodiments of the present invention. And the foregoing storage medium includes: various media such as removable storage devices, ROM, RAM, magnetic disks or optical disks that can store program codes.

[0120] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. An intelligent control method for a rehabilitation trainer robot, characterized in that, Including the following steps: Obtain the sensor data information of the user at each rehabilitation joint through a wearable rehabilitation training robot, and obtain the denoised sensor data information by performing denoising processing on the sensor data information of the user at each rehabilitation joint; Construct a joint intention motion model based on the sensor data information of the user at each rehabilitation joint, and obtain the motion intention feature data information of each joint position node based on the joint intention motion model; Perform motion risk assessment on the motion intention feature data information of each joint position node to obtain a risk assessment result, and reconfigure the rehabilitation plan of the rehabilitation training robot according to the risk assessment result; Perform motion control on the rehabilitation training robot based on the rehabilitation plan of the rehabilitation training robot.

2. The intelligent control method of a rehabilitation trainer robot according to claim 1, wherein, Obtain the sensor data information of the user at each rehabilitation joint through a wearable rehabilitation training robot, and obtain the denoised sensor data information by performing denoising processing on the sensor data information of the user at each rehabilitation joint. Specifically: Install sensors on the wearable rehabilitation training robot, obtain the sensor data information of the user at each rehabilitation joint through the sensors, and introduce a discrete wavelet transform algorithm to perform denoising processing on the sensor data information of the user at each rehabilitation joint; Obtain the noise characteristics and the original signal characteristics in the sensor data information, select wavelet bases for the noise characteristics and the original signal characteristics in the sensor data information through the discrete wavelet transform algorithm, determine the number of layers, and decompose the original signal according to the number of layers; Through hierarchical decomposition, obtain the low-frequency signal and the high-frequency signal, select an empirical threshold for each layer of high-frequency signal, and reconstruct the low-frequency signal and the high-frequency signal according to the empirical threshold to obtain the denoised sensor data information.

3. The intelligent control method of a rehabilitation trainer robot according to claim 1, characterized in that, Construct a joint intention motion model according to the sensor data information of the user at each rehabilitation joint, specifically including: Obtain the human joint motion torque characteristics corresponding to each sensor data based on the sensor data information of the user at each rehabilitation joint, and construct the global human joint characteristics based on the human joint motion torque characteristics corresponding to each sensor data; Perform three-dimensional pose parameterization of the human joints based on the global human joint characteristics, obtain the three-dimensional pose parameters, and perform joint and three-dimensional pose estimation based on the three-dimensional pose parameters to obtain the human pose joint intention characteristics; Perform three-dimensional model construction based on the human pose joint intention characteristics, and obtain the joint intention motion model in the motion perception time stage through the construction, and output the joint intention motion model.

4. The intelligent control method of a rehabilitation trainer robot according to claim 1, wherein Obtain the motion intention feature data information of each joint position node based on the joint intention motion model, specifically including: Perform dimensionality reduction processing on the joint intention motion model to obtain the two-dimensional map of the motion model of each joint position node, and extract motion features from the two-dimensional map of the motion model of each joint position node; Through motion feature extraction, motion intention feature data information of each joint position node is obtained, and the motion intention feature data information of each joint position node is output.

5. A method for intelligent control of a rehabilitation trainer robot according to claim 1, characterized in that, Through motion risk assessment of the motion intention feature data information of each joint position node, a risk assessment result is obtained, specifically including: Through big data, injury risk assessment feature data caused by a user using different motion states under the disease states of each joint is obtained, and a motion risk knowledge graph is constructed, and the injury risk assessment feature data caused by the user using different motion states under the disease states of each joint is input and stored in the motion risk knowledge graph; The disease state information of each joint of the user is obtained, and the disease state information of each joint of the user and the motion intention feature data information of each joint position node are input into the knowledge graph for data search; Through data search, injury risk assessment feature data caused by motion according to the motion intention feature data information of the joint position node under the disease state information of each joint of the user is obtained; A risk assessment result is generated according to the injury risk assessment feature data caused by motion according to the motion intention feature data information of the joint position node under the disease state information of each joint of the user, and the risk assessment result is output.

6. The intelligent control method of a rehabilitation trainer robot according to claim 1, characterized in that, According to the risk assessment result, the rehabilitation plan of the rehabilitation trainer robot is reconfigured, specifically: The motion intention feature data information of the joint position node corresponding to the injury risk assessment feature data greater than the preset risk assessment index is obtained, and the motion parameters of the joint position node corresponding to the injury risk assessment feature data greater than the preset risk assessment index are re-initialized to reduce the motion parameters of the rehabilitation trainer robot; The motion parameters of the rehabilitation trainer robot after initialization are obtained, and it is judged whether the motion parameters of the rehabilitation trainer robot after initialization still result in the situation that the injury risk assessment feature data is greater than the preset risk assessment index; When the motion parameters of the rehabilitation trainer robot after initialization still result in the situation that the injury risk assessment feature data is greater than the preset risk assessment index, the motion parameters of the rehabilitation trainer robot are reconfigured and reduced; When there is no situation where the injury risk assessment feature data of the rehabilitation trainer robot after initialization is greater than the preset risk assessment index, the motion parameters of the rehabilitation trainer robot after initialization are output, and a rehabilitation plan for the rehabilitation trainer robot is generated.

7. A method for intelligent control of a rehabilitation trainer robot according to claim 1, characterized in that, Based on the rehabilitation plan of the rehabilitation trainer robot, motion control of the rehabilitation trainer robot is performed, specifically: It is judged whether the motion parameters in the rehabilitation plan of the rehabilitation trainer robot are greater than the maximum motion parameters of the rehabilitation trainer robot; When the motion parameters in the rehabilitation plan of the rehabilitation trainer robot are greater than the maximum motion parameters of the rehabilitation trainer robot, motion control is performed according to the maximum motion parameters of the rehabilitation trainer robot; When the motion parameters in the rehabilitation plan of the rehabilitation trainer robot are not greater than the maximum motion parameters of the rehabilitation trainer robot, motion control is performed according to the motion parameters in the current rehabilitation plan.

8. An intelligent control system for a rehabilitation trainer robot, characterized in that, It includes a memory and a processor. The memory includes a program for the intelligent control method of the rehabilitation trainer robot. When the program for the intelligent control method of the rehabilitation trainer robot is executed by the processor, the steps of the intelligent control method of the rehabilitation trainer robot as described in any one of claims 1-7 are implemented.

9. A computer-readable storage medium, characterized in that, It includes a program for the intelligent control method of the rehabilitation trainer robot. When the program for the intelligent control method of the rehabilitation trainer robot is executed by the processor, the steps of the intelligent control method of the rehabilitation trainer robot as described in any one of claims 1-7 are implemented.

Images