Self-adaptive control method, device and equipment for hand exoskeleton and medium

Abstract

The invention relates to a self-adaptive control method, device and equipment for a hand exoskeleton and a medium, and the method comprises the steps: obtaining a pressure signal generated on an object when a patient grabs the object; generating a stimulation signal acting on the normal part of the patient based on the pressure signal; electromyographic signals generated after the patient receives the stimulation signals are collected; inputting the pressure signal and the electromyographic signal into a self-adaptive control model to obtain a control signal of the hand exoskeleton; and the control signal is adopted to control the hand exoskeleton. According to the invention, closed-loop regulation and control of the human and the exoskeleton as a whole can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of motion assistance and rehabilitation equipment, and in particular to an adaptive control method, device, equipment and medium for a hand exoskeleton. Background Art

[0002] Damage to the central nervous system or peripheral nervous system can lead to abnormal sensory and motor functions of the limbs, especially the hands. Central nervous system damage such as cerebral hemorrhage, cerebral infarction and other strokes can cause hemiplegia of the limbs, manifested as spasms on one side of the limbs, especially the inability of the hands to complete grasping and opening movements, and decreased tactile sensation of the fingers. Peripheral nervous system damage such as full brachial plexus damage and single nerve damage can cause loss of overall or partial motor and sensory functions of the hands.

[0003] With the development and update of rehabilitation equipment technology, exoskeletons that assist hand movement rehabilitation have emerged. They can provide periodic rehabilitation treatment for hands with sensory motor disorders, or be worn daily to improve the movement ability of the hands to complete the behaviors required for life and work. Currently, electrical stimulation combined with exoskeleton assistance is used, and its control signal is fed back to the exoskeleton through sensory information. Therefore, the existing method can only achieve closed-loop control at the exoskeleton level, and cannot achieve closed-loop control of the human and exoskeleton as a whole. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide an adaptive control method, device, equipment and medium for a hand exoskeleton, which can realize closed-loop control of a person and an exoskeleton as a whole.

[0005] The technical solution adopted by the present invention to solve the technical problem is: to provide an adaptive control method for a hand exoskeleton, comprising the following steps:

[0006] Obtain the pressure signal generated by the patient on the object when grasping the object;

[0007] generating a stimulation signal acting on a normal part of the patient based on the pressure signal;

[0008] Collecting electromyographic signals generated by the patient after receiving the stimulation signal;

[0009] Inputting the pressure signal and the electromyographic signal into an adaptive control model to obtain a control signal of the hand exoskeleton;

[0010] The hand exoskeleton is controlled using the control signal.

[0011] The stimulation signal is proportional to the pressure signal.

[0012] The stimulation signal and the pressure signal have a linear growth relationship or a multi-step growth relationship.

[0013] The adaptive control model includes:

[0014] A first encoder module is used to extract electromyographic signal characteristic information from the electromyographic signal and convert the electromyographic signal characteristic information into electromyographic sequence data;

[0015] A second encoder module, used to extract pressure signal characteristic information from the pressure signal and convert the pressure signal characteristic information into pressure sequence data;

[0016] A bidirectional recurrent neural network module is used to generate a control signal for the hand exoskeleton according to the electromyographic sequence data and the pressure sequence data.

[0017] The first encoder module and the second encoder module both include three attention layers, and the attention layers are used to identify key time point information in the sequence data.

[0018] The signal window length of the adaptive control model input is 0.8-1.2 seconds.

[0019] The technical solution adopted by the present invention to solve the technical problem is: to provide an adaptive control device for a hand exoskeleton, comprising:

[0020] A pressure sensor, used to obtain a pressure signal generated by a patient on an object when the patient grasps the object;

[0021] A stimulation signal generator, used to generate a stimulation signal acting on a normal part of the patient based on the pressure signal;

[0022] An electromyographic signal collector, used to collect electromyographic signals generated by the patient after receiving the stimulation signal;

[0023] A control signal generator, used for inputting the pressure signal and the electromyographic signal into an adaptive control model to obtain a control signal for the hand exoskeleton;

[0024] A controller is used to control the hand exoskeleton using the control signal.

[0025] The technical solution adopted by the present invention to solve its technical problem is: to provide an electronic device, including a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned adaptive control method of the hand exoskeleton when executing the computer program.

[0026] The technical solution adopted by the present invention to solve its technical problem is: providing a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned adaptive control method of the hand exoskeleton are implemented.

[0027] Beneficial Effects

[0028] Due to the adoption of the above-mentioned technical scheme, the present invention has the following advantages and positive effects compared with the prior art: the present invention converts the pressure signal into physical stimulation, and uses the electromyographic signal and the pressure signal generated after the physical stimulation as the input of the adaptive control model at the same time, to generate a control signal for the hand exoskeleton. The present invention realizes the conversion of shallow sensation into deep sensation, and then generates adaptive control parameters from the shallow sensation and the deep sensation. Since the electromyographic signal in the present invention is generated after being transmitted to the brain through the limbs after physical stimulation, it is integrated with the pressure signal as the input of the adaptive control model, realizing closed-loop regulation of the human and the exoskeleton as a whole. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a flow chart of an adaptive control method of a hand exoskeleton according to a first embodiment of the present invention;

[0030] Figure 2 It is a schematic diagram of the structure of the adaptive control model in the first embodiment of the present invention. DETAILED DESCRIPTION

[0031] The present invention will be further described below in conjunction with specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention. In addition, it should be understood that after reading the content taught by the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms fall within the scope limited by the appended claims of the application equally.

[0032] The first embodiment of the present invention relates to an adaptive control method of a hand exoskeleton, such as Figure 1 As shown, the following steps are included:

[0033] Step 1, obtaining the pressure signal generated by the patient on the object when grasping the object. In this step, the pressure signal generated by the patient on the object when grasping the object can be obtained by a pressure sensor. The pressure sensor can be a thin sheet that can cover the fingertips. When the patient touches the fingertips to the object to grasp the object, the pressure sensor can obtain the pressure signal generated on the object.

[0034] Step 2, based on the pressure signal, a stimulation signal is generated to act on the normal part of the patient. In this step, a stimulation signal is generated by a stimulation signal generator according to the pressure signal obtained by the pressure sensor. The stimulation signal may be an electrical stimulation signal, which acts on the normal part of the patient, such as the base of the thumb and the back of the hand, which are more sensitive than the fingertips. The electrical stimulation signal is proportional to the pressure signal, for example, there is a linear growth or multi-step growth relationship between the electrical stimulation signal and the pressure signal.

[0035] Step 3, collecting the electromyographic signal generated by the patient after receiving the stimulation signal. In this step, the electromyographic signal generated by the patient after receiving the electrical stimulation signal is collected by the electromyographic signal collector. This embodiment converts the fingertip pressure into electrical stimulation to act on the normal part of the patient, which can increase the brain's perception of the limbs, so that the brain has sensory feedback information when outputting the movement intention to the muscles, and realizes the conversion of the shallow feeling of fingertip pressure into the deep feeling of electric shock.

[0036] Step 4: Input the pressure signal and the electromyographic signal into the adaptive control model to obtain the control signal of the hand exoskeleton. Figure 2 As shown, the adaptive control model in this embodiment includes: a first encoder module, used to extract electromyographic signal characteristic information from the electromyographic signal, and convert the electromyographic signal characteristic information into electromyographic sequence data; a second encoder module, used to extract pressure signal characteristic information from the pressure signal, and convert the pressure signal characteristic information into pressure sequence data; a bidirectional recurrent neural network module, used to generate a control signal for the hand exoskeleton according to the electromyographic sequence data and the pressure sequence data.

[0037] The first encoder module and the second encoder module in this embodiment can extract useful features from the input signal, and these features can capture important information of the signal. The extracted features can be converted into sequence data through serialization operation. The first encoder module and the second encoder module in this embodiment both include 3 layers of attention layers, and the attention layers are used to identify key time point information in the sequence data. By introducing the attention mechanism, the adaptive control model can learn the dependencies between different time points. For example, it can find the correlation between the electromyographic signal at a certain time point and the pressure signal at a later time point, and this correlation can be used to adjust the control strategy.

[0038] The bidirectional recurrent neural network module in this embodiment is a special recurrent neural network (RNN) that uses its bidirectional structure to capture past and future information at each time point, thereby simultaneously considering past and future information. This structure enables the adaptive control model to better understand and predict the dynamic changes of time series data, thereby providing a more accurate control strategy.

[0039] It is worth mentioning that the signal window length of the adaptive control model input in this embodiment is 0.8-1.2 seconds, which means that the data processed by the model at each time point is the signal collected within the past 0.8-1.2 seconds. The selection of this time window can meet the output response of the hand exoskeleton.

[0040] Step 5: Use the control signal to control the hand exoskeleton.

[0041] It is not difficult to find that the present invention converts the pressure signal into physical stimulation, and uses the electromyographic signal and pressure signal generated after the physical stimulation as the input of the adaptive control model at the same time, thereby generating a control signal for the hand exoskeleton. The present invention realizes the conversion of shallow sensation into deep sensation, and then generates adaptive control parameters from the shallow sensation and the deep sensation. Since the electromyographic signal in the present invention is generated after being transmitted to the brain through the limbs after physical stimulation, it is integrated with the pressure signal as the input of the adaptive control model, thereby realizing closed-loop regulation of humans and exoskeletons as a whole.

[0042] A second embodiment of the present invention relates to an adaptive control device for a hand exoskeleton, comprising:

[0043] A pressure sensor, used to obtain a pressure signal generated by a patient on an object when the patient grasps the object;

[0044] A stimulation signal generator, used to generate a stimulation signal acting on a normal part of the patient based on the pressure signal;

[0045] An electromyographic signal collector, used to collect electromyographic signals generated by the patient after receiving the stimulation signal;

[0046] A control signal generator, used for inputting the pressure signal and the electromyographic signal into an adaptive control model to obtain a control signal for the hand exoskeleton;

[0047] A controller is used to control the hand exoskeleton using the control signal.

[0048] The stimulation signal is proportional to the pressure signal.

[0049] The stimulation signal and the pressure signal have a linear growth relationship or a multi-step growth relationship.

[0050] The adaptive control model includes:

[0051] A first encoder module is used to extract electromyographic signal characteristic information from the electromyographic signal and convert the electromyographic signal characteristic information into electromyographic sequence data;

[0052] A second encoder module, used to extract pressure signal characteristic information from the pressure signal and convert the pressure signal characteristic information into pressure sequence data;

[0053] A bidirectional recurrent neural network module is used to generate a control signal for the hand exoskeleton according to the electromyographic sequence data and the pressure sequence data.

[0054] The first encoder module and the second encoder module both include three attention layers, and the attention layers are used to identify key time point information in the sequence data.

[0055] The signal window length of the adaptive control model input is 0.8-1.2 seconds.

[0056] A third embodiment of the present invention relates to an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the adaptive control method of the hand exoskeleton of the first embodiment when executing the computer program.

[0057] A fourth embodiment of the present invention relates to a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the adaptive control method for a hand exoskeleton of the first embodiment are implemented.

[0058] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program codes.

[0059] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0060] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction method, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0061] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0062] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An adaptive control method for a hand exoskeleton, characterized in that: The following steps are involved: Obtain the pressure signal generated by the patient on the object when grasping the object; generating a stimulation signal acting on a normal part of the patient based on the pressure signal; Collecting electromyographic signals generated by the patient after receiving the stimulation signal; Inputting the pressure signal and the electromyographic signal into an adaptive control model to obtain a control signal of the hand exoskeleton; The hand exoskeleton is controlled using the control signal.

2. The adaptive control method of hand exoskeleton according to claim 1, characterized in that: The stimulation signal is proportional to the pressure signal.

3. The adaptive control method of hand exoskeleton according to claim 2, characterized in that: The stimulation signal and the pressure signal have a linear growth relationship or a multi-step growth relationship.

4. The adaptive control method of hand exoskeleton according to claim 1, characterized in that: The adaptive control model includes: A first encoder module is used to extract electromyographic signal characteristic information from the electromyographic signal and convert the electromyographic signal characteristic information into electromyographic sequence data; A second encoder module, used to extract pressure signal characteristic information from the pressure signal and convert the pressure signal characteristic information into pressure sequence data; A bidirectional recurrent neural network module is used to generate a control signal for the hand exoskeleton according to the electromyographic sequence data and the pressure sequence data.

5. The adaptive control method of hand exoskeleton according to claim 4, characterized in that: The first encoder module and the second encoder module both include three attention layers, and the attention layers are used to identify key time point information in the sequence data.

6. The adaptive control method of hand exoskeleton according to claim 1, characterized in that: The signal window length of the adaptive control model input is 0.8-1.2 seconds.

7. An adaptive control device for a hand exoskeleton, characterized in that: include: A pressure sensor, used to obtain a pressure signal generated by a patient on an object when the patient grasps the object; A stimulation signal generator, used to generate a stimulation signal acting on a normal part of the patient based on the pressure signal; An electromyographic signal collector, used to collect electromyographic signals generated by the patient after receiving the stimulation signal; A control signal generator, used for inputting the pressure signal and the electromyographic signal into an adaptive control model to obtain a control signal for the hand exoskeleton; A controller is used to control the hand exoskeleton using the control signal.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the adaptive control method of the hand exoskeleton as claimed in any one of claims 1 to 6 are implemented.

9. 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 adaptive control method of the hand exoskeleton as claimed in any one of claims 1 to 6 are implemented.

Images