Finger fine function training method, system, device and medium
Through the mirror synchronous exercise training of the combined force/position hybrid coordinated control system on the healthy or affected side, the problem of coordinated adjustment of finger force after stroke is solved, and the comprehensive recovery of fine finger functions is achieved, which is suitable for patients with different stages.
Patent Information
- Application Number
- CN202410934221.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-12
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-12
AI Technical Summary
The recovery of hand function after stroke is limited by the inability to adjust the coordination of finger force in real time in different situations, resulting in task failure or abnormal exercise patterns. The existing rehabilitation methods cannot effectively promote fine functional recovery.
The active training on the healthy side and the active training on the affected side are combined with the force/position hybrid coordinated control system, and mirror synchronous exercise training is completed through the healthy side or the affected side rehabilitation robot to achieve bidirectional force/position information transmission and feedback on the healthy side finger. Form a peripheral-center closed-loop nerve regulatory loop.
Adjust the coordination of finger force in real time in different situations to promote the comprehensive recovery of finger fine functions, and is suitable for patients with different Brunnstrom stages.
Smart Images

Figure CN118471432B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the technical field of hand rehabilitation, and in particular to a method, system, device and medium for training fine finger functions. Background Art
[0002] Stroke is one of the diseases that seriously threaten human life and health. The "China Stroke Prevention and Treatment Report 2021" points out that stroke is the leading cause of death and disability among adults in my country. More than 60% of stroke patients suffer from hand dysfunction, especially fine function, which is a difficult problem to be solved in the field of neurorehabilitation due to damage to the central nervous system. Exploring effective rehabilitation strategies and technologies to meet the actual needs of the current medical rehabilitation field has important social and economic significance.
[0003] The recovery of hand function after stroke depends largely on neuroplasticity, which is the process of reorganizing and repairing the brain's neural connections through repeated rehabilitation training. Currently, compulsory exercise therapy and motor relearning are often used in clinical practice to guide patients to conduct finger function training. However, due to the inability to adjust the coordination of finger force in real time under different situations, it often leads to task failure or abnormal movement patterns. Summary of the invention
[0004] The present disclosure provides a finger fine function training method, system, device and medium to solve the above-mentioned technical problems.
[0005] According to a first aspect of the present disclosure, a method for training fine finger functions is provided, the method comprising: identifying a patient's hand Brunnstrom stage; if the hand Brunnstrom stage is stage I or stage II, training the fine finger functions by a healthy side active training method, wherein the healthy side is used as the main execution end in the healthy side active training method; if the hand Brunnstrom stage is stage III, stage IV, stage V, or stage VI, training the fine finger functions by a healthy side active training method or an affected side active training method, wherein the affected side is used as the main execution end in the affected side active training method.
[0006] According to the above technical means, the active training method of the healthy side is suitable for patients in stages I to VI. During training, the movement information of the healthy hand is mainly used, and the rehabilitation manipulator on the affected side follows the movement of the healthy side rehabilitation manipulator for training. The muscle strength and muscle tension of the fingers on the affected side are poor and cannot complete the preset training plan. During training, this method mainly uses the force / position information of the healthy hand to complete the preset training plan, and the rehabilitation manipulator on the affected side drives the affected hand to follow the healthy side for mirror synchronous movement training; the active training method of the affected side is suitable for patients in stages III to VI. During training, the movement information of the affected hand is mainly used, and the rehabilitation manipulator on the healthy side follows the movement of the affected side rehabilitation manipulator for training. The active training method of the affected side is suitable for patients in stages III to VI. The fingers on the affected side have certain muscle strength and muscle tension, but poor coordination. During training, this method mainly uses the force / position information of the affected hand to complete the preset training plan, and the rehabilitation manipulator on the healthy side drives the healthy hand to follow the affected side to complete the movement. When the fine movements of the fingers on the affected side are not standardized, the patient can make corresponding movement adjustments in time through the healthy hand, and re-drive the affected side through the rehabilitation manipulator on the healthy side to complete the mirror synchronous movement training.
[0007] In some embodiments, the healthy side active training method includes: the healthy hand drives the healthy side rehabilitation robot to complete fine movements according to a preset training plan; a first force observer receives force signals and position signals from the healthy side rehabilitation robot, extracts data and uploads it to a force / position hybrid collaborative control system; the force signals and position signals are processed by the intelligent algorithm of the force / position hybrid collaborative control system to obtain a control amount; the control amount is fed back to the affected side rehabilitation robot; based on the learning mechanism of mirror neurons, the affected side rehabilitation robot assists the affected hand to complete healthy-affected mirror synchronous movement training.
[0008] In some embodiments, the preset training program is a rehabilitation training task developed by a rehabilitation therapist and is based on grasping, holding, and pinching objects of different shapes, sizes, and weights.
[0009] In some embodiments, the force signal and the position signal are processed by the intelligent algorithm of the force / position hybrid collaborative control system to obtain the control quantity, including: obtaining the force signal and the position signal from the healthy-side rehabilitation manipulator; obtaining the force signal and the position signal from the affected-side rehabilitation manipulator; performing a difference calculation between the force signal from the healthy-side rehabilitation manipulator and the force signal from the affected-side rehabilitation manipulator to obtain a force error; performing a difference calculation between the position signal from the healthy-side rehabilitation manipulator and the position signal from the affected-side rehabilitation manipulator to obtain a position error; and generating a control quantity based on the force error and the position error.
[0010] In some embodiments, the active training method for the affected side includes: the affected-side rehabilitation manipulator completes fine movements according to a preset training plan; the second force observer receives force signals and position signals from the affected-side rehabilitation manipulator, extracts data and uploads them to the force / position hybrid collaborative control system; the force signals and position signals are processed by the intelligent algorithm of the force / position hybrid collaborative control system, and the processing results are fed back to the healthy-side rehabilitation manipulator; the healthy-side rehabilitation manipulator assists the healthy hand in movement, and the healthy hand readjusts the fine movements according to the movement information; the first force observer receives force signals and position signals from the healthy-side rehabilitation manipulator, extracts data and uploads them to the force / position hybrid collaborative control system; the force signals and position signals are processed by the intelligent algorithm of the force / position hybrid collaborative control system, and the processing results are fed back to the affected-side rehabilitation manipulator; the affected-side rehabilitation manipulator again assists the affected hand in completing the healthy-affected mirror synchronous movement training.
[0011] According to a second aspect of the present disclosure, a finger fine function training system is provided, including a healthy-side rehabilitation manipulator, an affected-side rehabilitation manipulator, a first force observer, a second force observer, and a controller, wherein the controller has a force / position hybrid collaborative control system and a feedback module; the healthy-side rehabilitation manipulator and the first force observer are electrically connected to the controller, respectively, and the healthy-side rehabilitation manipulator is electrically connected to the first force observer; the affected-side rehabilitation manipulator and the second force observer are electrically connected to the controller, respectively, and the affected-side rehabilitation manipulator is electrically connected to the second force observer, and the healthy-side rehabilitation manipulator, the affected-side rehabilitation manipulator, the first force observer, the second force observer, and the controller cooperate with each other to implement the above-mentioned finger fine function training method.
[0012] In some embodiments, the healthy side rehabilitation robot and the affected side rehabilitation robot are both exoskeleton robots.
[0013] According to a third aspect of the present disclosure, a device for training fine finger function is provided, comprising: a stage identification module, for identifying the patient's hand Brunnstrom stage; a first finger fine function training module, for training the fine finger function by adopting a healthy side active training method if the hand Brunnstrom stage is stage I or stage II, wherein the healthy side active training method uses the healthy side as the main execution end; a second finger fine function training module, for training the fine finger function by adopting a healthy side active training method or an affected side active training method if the hand Brunnstrom stage is stage III, stage IV, stage V, or stage VI, wherein the affected side active training method uses the affected side as the main execution end.
[0014] According to a fourth aspect of the present disclosure, a device for training fine finger functions is provided, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the above-mentioned method for training fine finger functions based on instructions stored in the memory.
[0015] According to a fifth aspect of the present disclosure, a computer storable medium is provided, on which computer program instructions are stored, and when the instructions are executed by a processor, the above-mentioned method for training fine finger functions is implemented.
[0016] Advantages of the present invention: The present invention can realize the transmission and feedback of bidirectional force / position information between healthy and affected fingers, can adjust the coordination of finger force in real time under different situations, form a peripheral-central closed-loop neural regulation circuit, and can comprehensively promote the recovery of fine finger function. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0018] Figure 1 is a flow chart showing a method for training fine finger functions according to some embodiments of the present disclosure.
[0019] Figure 2 is a schematic diagram showing a method for training fine finger functions based on force / position mixed bidirectional control according to some embodiments of the present disclosure.
[0020] Figure 3 It is a flow chart showing a healthy side active training method according to some embodiments of the present disclosure (with the healthy side as the main execution end).
[0021] Figure 4 It is a flow chart showing the active training method of the affected side according to some embodiments of the present disclosure (with the affected side as the main execution end).
[0022] Figure 5 is a block diagram showing a device for training fine finger functions according to some embodiments of the present disclosure.
[0023] Figure 6 is a block diagram showing a finger fine function training device according to other embodiments of the present disclosure.
[0024] Figure 7 is a block diagram illustrating a computer system for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION
[0025] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless otherwise specifically stated.
[0026] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.
[0027] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.
[0028] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.
[0029] In all examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.
[0030] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.
[0031] At present, compulsory exercise therapy, motor relearning and other methods are often used in clinical practice to guide patients to perform finger function training. However, due to the inability to adjust the coordination of finger force in real time under different situations, it often leads to task failure or abnormal movement patterns.
[0032] In view of this, the present disclosure proposes a method, system, device and medium for training fine finger functions. The present disclosure can realize the transmission and feedback of bidirectional force / position information between healthy and affected fingers, can adjust the coordination of finger force in real time under different situations, form a peripheral-central closed-loop neural regulation circuit, and can comprehensively promote the recovery of fine finger functions.
[0033] Figure 1 FIG. 1 is a flow chart showing a method for training fine finger functions according to some embodiments of the present disclosure. Figure 1 As shown, the finger fine function training method includes steps 102 to 106.
[0034] At step 102, the patient's hand Brunnstrom stage is identified.
[0035] Brunnstrom's grading system is as follows: Grade I: no voluntary movements, no movement of the hand; Grade II: only slight flexion of the hand; Grade III: voluntary joint movements, the upper limbs can initiate coordinated movements at will, the hand can grasp but cannot stretch; Grade IV: the hand can pinch and stretch in a small range; Grade V: the fingers can stretch simultaneously, but individual extension is poor; Grade VI: the motor ability is close to normal, but the speed and accuracy are worse than normal.
[0036] In step 104, if the hand is in stage I or stage II according to the Brunnstrom stage, the healthy side active training method is used to train the fine finger functions, wherein the healthy side active training method uses the healthy side as the main execution end.
[0037] In some embodiments, the healthy side active training method includes: the healthy hand drives the healthy side rehabilitation robot to complete fine movements according to a preset training plan; a first force observer receives force signals and position signals from the healthy side rehabilitation robot, extracts data and uploads it to a force / position hybrid collaborative control system; the force signals and position signals are processed by the intelligent algorithm of the force / position hybrid collaborative control system to obtain a control amount; the control amount is fed back to the affected side rehabilitation robot; based on the learning mechanism of mirror neurons, the affected side rehabilitation robot assists the affected hand to complete healthy-affected mirror synchronous movement training.
[0038] In some embodiments, the preset training program is a rehabilitation training task developed by a rehabilitation therapist and is based on grasping, holding, and pinching objects of different shapes, sizes, and weights.
[0039] In some embodiments, the force signal and the position signal are processed by the intelligent algorithm of the force / position hybrid collaborative control system to obtain the control quantity, including: obtaining the force signal and the position signal from the healthy-side rehabilitation manipulator; obtaining the force signal and the position signal from the affected-side rehabilitation manipulator; performing a difference calculation between the force signal from the healthy-side rehabilitation manipulator and the force signal from the affected-side rehabilitation manipulator to obtain a force error; performing a difference calculation between the position signal from the healthy-side rehabilitation manipulator and the position signal from the affected-side rehabilitation manipulator to obtain a position error; and generating a control quantity based on the force error and the position error.
[0040] In some embodiments, the learning mechanism based on mirror neurons, that is, the "observation-execution matching mechanism" of unified action perception and action execution provided by the mirror neuron system, can activate the reproduction or resonance of similar actions when observing actions, which helps to execute and imitate the observed actions.
[0041] In step 106, if the hand Brunnstrom stage is stage III, stage IV, stage V, or stage VI, the fine function of the fingers is trained by using the healthy side active training method or the affected side active training method, wherein the affected side active training method uses the affected side as the main execution end.
[0042] In some embodiments, the active training method for the affected side includes: the affected-side rehabilitation manipulator completes fine movements according to a preset training plan; the second force observer receives force signals and position signals from the affected-side rehabilitation manipulator, extracts data and uploads them to the force / position hybrid collaborative control system; the force signals and position signals are processed by the intelligent algorithm of the force / position hybrid collaborative control system, and the processing results are fed back to the healthy-side rehabilitation manipulator; the healthy-side rehabilitation manipulator assists the healthy hand in movement, and the healthy hand readjusts the fine movements according to the movement information; the first force observer receives force signals and position signals from the healthy-side rehabilitation manipulator, extracts data and uploads them to the force / position hybrid collaborative control system; the force signals and position signals are processed by the intelligent algorithm of the force / position hybrid collaborative control system, and the processing results are fed back to the affected-side rehabilitation manipulator; the affected-side rehabilitation manipulator again assists the affected hand in completing the healthy-affected mirror synchronous movement training.
[0043] like Figure 2 As shown, a finger fine function training system includes a healthy side rehabilitation manipulator, an affected side rehabilitation manipulator, a first force observer, a second force observer, and a controller, wherein the controller has a force / position hybrid collaborative control system and a feedback module; the healthy side rehabilitation manipulator and the first force observer are electrically connected to the controller respectively, and the healthy side rehabilitation manipulator is electrically connected to the first force observer; the affected side rehabilitation manipulator and the second force observer are electrically connected to the controller respectively, and the affected side rehabilitation manipulator is electrically connected to the second force observer, and the healthy side rehabilitation manipulator, the affected side rehabilitation manipulator, the first force observer, the second force observer, and the controller cooperate with each other to implement the above-mentioned finger fine function training method.
[0044] The system can realize bidirectional force / position hybrid coordinated control and form a motion adaptive force / position perception interactive training method. Each component cooperates with each other to complete the set training plan. Based on this system, the active training mode of the healthy side and the active training mode of the affected side can be realized.
[0045] Based on the system in this embodiment, the rehabilitation manipulator: adopts a bilateral exoskeleton rehabilitation manipulator, which conforms to the biomechanical and kinematic characteristics of the human hand and can adapt to the fine movements of different fingers; the force observer: can achieve high-precision force estimation, solve the problem of accurate acquisition and transmission of force signals during finger movement; the force / position hybrid collaborative control system: can convert the multi-level parallel control in complex hand fine movements into multiple independent feedback controls, and connect with the bilateral rehabilitation manipulator to form a human-machine physical contact interface to realize a mirror loop; the feedback module: feeds back the force / position signal to the contralateral rehabilitation manipulator. The healthy side rehabilitation manipulator is an exoskeleton manipulator. The affected side rehabilitation manipulator is an exoskeleton manipulator.
[0046] like Figure 3 As shown in the figure, the healthy side active training method is suitable for patients with hand Brunnstrom stage I-VI, and the healthy side active training method includes: according to the degree of fine function disorder of the patient's fingers and related assessment results, the rehabilitation therapist presets a rehabilitation training plan for the patient and assists the patient to wear the rehabilitation robot; the healthy hand drives the healthy side rehabilitation robot to complete fine movements according to the training plan; the force observer receives the force / position signal (i.e., force signal, position signal) from the healthy side rehabilitation robot, extracts the data and uploads it to the force / position hybrid collaborative control system; the force / position signal is calculated and analyzed accordingly through the intelligent algorithm of the force / position hybrid collaborative control system; the force / position information is output in real time and fed back to the affected side rehabilitation robot; based on the learning mechanism of mirror neurons, the affected side rehabilitation robot assists the affected hand to complete the healthy-affected mirror synchronous movement rehabilitation training.
[0047] like Figure 4 As shown, the active training method on the affected side is suitable for patients with hand Brunnstrom stage III-VI, and the active training method on the affected side includes: according to the degree of fine function disorder of the patient's fingers and related assessment results, the rehabilitation therapist presets a rehabilitation training plan for the patient and assists the patient to wear the rehabilitation manipulator; the rehabilitation manipulator on the affected side completes fine movements according to the training plan; the force observer receives the force / position signal from the rehabilitation manipulator on the affected side, extracts the data and uploads it to the force / position hybrid collaborative control system; the force / position signal is correspondingly calculated and analyzed by the intelligent algorithm of the force / position hybrid collaborative control system; the force / position information is fed back to the rehabilitation manipulator on the healthy side; the rehabilitation manipulator on the healthy side assists the healthy hand in movement, and the healthy hand readjusts the fine movements according to the movement information; the force observer receives the force / position signal from the rehabilitation manipulator on the healthy side, extracts the data and uploads it to the force / position hybrid collaborative control system; the force / position signal is correspondingly calculated and analyzed by the intelligent algorithm of the force / position hybrid collaborative control system; the force / position information is fed back to the rehabilitation manipulator on the affected side; the rehabilitation manipulator on the affected side again assists the affected hand in completing the healthy-affected mirror synchronous movement rehabilitation training.
[0048] In the finger fine function training method of the embodiment of the present disclosure, the present disclosure can realize the transmission and feedback of bidirectional force / position information between healthy and affected fingers, can adjust the coordination of finger force in real time under different situations, form a peripheral-central closed-loop neural regulation circuit, and can comprehensively promote the recovery of finger fine function.
[0049] Figure 5 is a block diagram showing a device for training fine finger functions according to some embodiments of the present disclosure. Figure 5 As shown, the finger fine function training device 500 includes a stage identification module 502 , a first finger fine function training module 504 , and a second finger fine function training module 506 .
[0050] The stage identification module 502 is configured to identify the patient's hand Brunnstrom stage;
[0051] The first finger fine function training module 504 is configured to train the finger fine function by using the healthy side active training method if the hand Brunnstrom stage is stage I or stage II, wherein the healthy side active training method uses the healthy side as the execution master end;
[0052] The second finger fine function training module 506 is configured to train the finger fine function by using the healthy side active training method or the affected side active training method if the hand Brunnstrom stage is stage III, stage IV, stage V, or stage VI, wherein the affected side active training method uses the affected side as the execution main end.
[0053] In the device of the embodiment of the present disclosure, the present disclosure can realize the transmission and feedback of bidirectional force / position information between healthy and affected fingers, can adjust the coordination of finger force in real time under different situations, form a peripheral-central closed-loop neural regulation circuit, and can comprehensively promote the recovery of fine finger function.
[0054] Figure 6 FIG. 1 is a block diagram showing a finger fine function training device according to some other embodiments of the present disclosure. Figure 6 As shown, the finger fine function training device 600 includes a memory 610; and a processor 620 coupled to the memory 610. The memory 610 is used to store instructions for executing the corresponding embodiments of the finger fine function training method. The processor 620 is configured to execute the finger fine function training method in any of the embodiments of the present disclosure based on the instructions stored in the memory 610.
[0055] Figure 7 is a block diagram showing a computer system for implementing some embodiments of the present disclosure. Figure 7As shown, computer system 700 may be embodied in the form of a general purpose computing device. Computer system 700 includes memory 710, processor 720, and bus 730 that connects various system components.
[0056] The memory 710 may include, for example, a system memory, a non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, and other programs. The system memory may include a volatile storage medium, such as a random access memory (RAM) and / or a cache memory. The non-volatile storage medium may store, for example, instructions for executing at least one of the corresponding embodiments of the finger fine function training method. The non-volatile storage medium includes, but is not limited to, a disk storage, an optical storage, a flash memory, and the like.
[0057] The processor 720 can be implemented by a general processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistors, etc. Discrete hardware components. Accordingly, each module such as the stage recognition module, the first finger fine function training module, and the second finger fine function training module can be implemented by a central processing unit (CPU) running instructions in a memory to execute corresponding steps, or can be implemented by a dedicated circuit to execute corresponding steps.
[0058] The bus 730 may use any of a variety of bus architectures, including, but not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, and a Peripheral Component Interconnect (PCI) bus.
[0059] The computer system 700 may also include an input / output interface 740, a network interface 750, a storage interface 760, etc. These interfaces 740, 750, 760, the memory 710, and the processor 720 may be connected via a bus 730. The input / output interface 740 may provide a connection interface for input / output devices such as a display, a mouse, and a keyboard. The network interface 750 may provide a connection interface for various networked devices. The storage interface 760 may provide a connection interface for external storage devices such as a floppy disk, a USB flash drive, and an SD card.
[0060] Here, various aspects of the present disclosure are described with reference to flowcharts and / or block diagrams of methods, devices, and computer program products according to embodiments of the present disclosure. It should be understood that each frame of the flowchart and / or block diagram and the combination of frames can be implemented by computer-readable program instructions.
[0061] These computer-readable program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable device to produce a machine, so that the processor executes the instructions to produce means for implementing the functions specified in one or more blocks in the flowchart and / or block diagram.
[0062] These computer-readable program instructions may also be stored in a computer-readable memory, which cause the computer to work in a specific manner to produce an article of manufacture, including instructions for implementing the functions specified in one or more blocks in the flowchart and / or block diagram.
[0063] The present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects.
[0064] The present invention can realize the transmission and feedback of bidirectional force / position information between healthy and affected fingers, can adjust the coordination of finger force in real time under different situations, form a peripheral-central closed-loop neural regulation circuit, and can comprehensively promote the recovery of fine finger function.
[0065] So far, the finger fine function training method, system, device and medium according to the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.
[0066] Although some specific embodiments of the present disclosure have been described in detail by way of examples, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.
Claims
1. A method for training fine finger functions, characterized in that: The method comprises: Identify the patient's hand Brunnstrom stage; If the hand Brunnstrom stage is stage I or stage II, the healthy side active training method is used to train the fine function of the fingers, wherein the healthy side active training method uses the healthy side as the main execution end; If the hand is in stage III, IV, V, or VI according to the Brunnstrom stage, the affected side active training method is used to train the fine function of the fingers, wherein the affected side active training method uses the affected side as the main execution end; The active training method for the affected side comprises: The rehabilitation robot on the affected side completes fine movements according to the preset training plan; The second force observer receives the force signal and position signal from the rehabilitation manipulator on the affected side, extracts the data and uploads it to the force / position hybrid collaborative control system; The force signal and position signal are processed by the intelligent algorithm of the force / position hybrid collaborative control system, and the processing results are fed back to the rehabilitation manipulator on the healthy side; The rehabilitation robot arm on the healthy side assists the healthy hand in movement, and the healthy hand readjusts fine movements based on the movement information; The first force observer receives the force signal and position signal from the rehabilitation manipulator on the healthy side, extracts the data and uploads it to the force / position hybrid collaborative control system; The force signal and position signal are processed by the intelligent algorithm of the force / position hybrid collaborative control system, and the processing results are fed back to the rehabilitation manipulator on the affected side; The rehabilitation robot on the affected side once again assisted the affected hand to complete the healthy-affected mirror-image synchronous movement training.
2. The method for training finger fine function according to claim 1, characterized in that: The active training method for the healthy side comprises: The healthy hand drives the healthy side rehabilitation robot to complete fine movements according to the preset training plan; The first force observer receives the force signal and position signal from the healthy-side rehabilitation manipulator, extracts the data and uploads it to the force / position hybrid collaborative control system; The force signal and the position signal are processed by the intelligent algorithm of the force / position hybrid coordinated control system to obtain the control amount; Feeding back the control amount to the rehabilitation robot on the affected side; Based on the learning mechanism of mirror neurons, the affected-side rehabilitation robot assists the affected hand in completing healthy-affected mirror synchronous movement training.
3. The method for training finger fine function according to claim 2, characterized in that: The preset training program is a rehabilitation training task formulated by a rehabilitation therapist and is based on grasping, holding and pinching objects of different shapes, sizes and weights.
4. The method for training finger fine function according to claim 2, characterized in that: The force signal and the position signal are processed by the intelligent algorithm of the force / position hybrid coordinated control system to obtain the control quantity, including: Acquiring force signals and position signals from the healthy-side rehabilitation manipulator; Obtain force signals and position signals from the rehabilitation robot on the affected side; Performing a difference calculation on the force signal from the healthy-side rehabilitation manipulator and the force signal from the affected-side rehabilitation manipulator to obtain a force error; Performing a difference calculation on the position signal from the healthy-side rehabilitation robot and the position signal from the affected-side rehabilitation robot to obtain a position error; A control variable is generated based on the force error and the position error.
5. A finger fine function training system, characterized in that: It includes a healthy-side rehabilitation manipulator, an affected-side rehabilitation manipulator, a first force observer, a second force observer, and a controller. The controller has a force / position hybrid collaborative control system and a feedback module. The healthy-side rehabilitation manipulator and the first force observer are electrically connected to the controller, respectively, and the healthy-side rehabilitation manipulator is electrically connected to the first force observer. The affected-side rehabilitation manipulator and the second force observer are electrically connected to the controller, respectively, and the affected-side rehabilitation manipulator is electrically connected to the second force observer. The healthy-side rehabilitation manipulator, the affected-side rehabilitation manipulator, the first force observer, the second force observer, and the controller cooperate with each other to implement the finger fine function training method described in any one of claims 1 to 4.
6. The finger fine function training system according to claim 5, characterized in that: The healthy side rehabilitation manipulator and the affected side rehabilitation manipulator are both exoskeleton manipulators.
7. A finger fine function training device, characterized in that: include: Stage recognition module, used to identify the patient's hand Brunnstrom stage; A first finger fine function training module is used to train the fine function of the fingers by using a healthy side active training method if the hand Brunnstrom stage is stage I or stage II, wherein the healthy side active training method uses the healthy side as the main execution end; The second finger fine function training module is used to train the fine function of the fingers by using the active training method on the affected side if the hand is in the Brunnstrom stage of stage III, stage IV, stage V, or stage VI, wherein the active training method on the affected side uses the affected side as the execution master; the active training method on the affected side includes: the rehabilitation manipulator on the affected side completes fine movements according to a preset training plan; the second force observer receives force signals and position signals from the rehabilitation manipulator on the affected side, extracts data and uploads them to the force / position hybrid collaborative control system; the force signals and position signals are processed by the intelligent algorithm of the force / position hybrid collaborative control system, and the processing results are fed back to the rehabilitation manipulator on the healthy side; the rehabilitation manipulator on the healthy side assists the healthy hand in movement, and the healthy hand readjusts the fine movements according to the movement information; the first force observer receives force signals and position signals from the rehabilitation manipulator on the healthy side, extracts data and uploads them to the force / position hybrid collaborative control system; the force signals and position signals are processed by the intelligent algorithm of the force / position hybrid collaborative control system, and the processing results are fed back to the rehabilitation manipulator on the affected side; the rehabilitation manipulator on the affected side assists the affected hand in completing the healthy-affected mirror synchronous movement training again.
8. A finger fine function training device, characterized in that: include: Memory; And a processor coupled to the memory, wherein the processor is configured to execute the finger fine function training method according to any one of claims 1 to 4 based on instructions stored in the memory.
9. A computer storable medium, characterized in that: Computer program instructions are stored thereon, and when the instructions are executed by a processor, a method for training the fine functions of fingers as described in any one of claims 1 to 4 is implemented.
