Lower limb exoskeleton robot system based on virtual reality feedback

Abstract

The invention provides a lower limb exoskeleton robot system based on virtual reality feedback. The lower limb exoskeleton robot system can be applied to the technical field of medical treatment and the technical field of artificial intelligence. The system comprises an exoskeleton machine device used for collecting electromyographic signals and electrocardiographic signals of a user wearing an exoskeleton robot in the rehabilitation training process and conducting feature extraction on the electromyographic signals and the electrocardiographic signals to obtain physiological features, and the physiological features comprise the following information of heart rate variability, electromyographic amplitude and electromyographic average power; the communication server is used for transmitting the physiological features to the virtual reality device; the virtual reality device is used for inputting the physiological features into a fitting model to obtain the psychological state of the user, and a psychological function of the fitting model is obtained by fitting a set of preset psychological levels, a set of heart rate variability, a set of myoelectric amplitudes and a set of myoelectric average power; and updating the rehabilitation training mode of the virtual reality device according to the psychological state.

Description

Technical Field

[0001] The present invention relates to the fields of medical technology and artificial intelligence technology, and more specifically to a lower limb exoskeleton robot system with virtual reality feedback. Background Art

[0002] Stroke is a neurological disease with a high disability rate and is difficult to cure. In particular, limb movement disorders are difficult to recover in a short period of time, which brings great mental pain and heavy economic burden to the individual, family and society. Rehabilitation training can promote the plasticity of the central nervous system of the brain, and then change the functional connection and structure of the brain area to adapt to the needs of movement.

[0003] As the patients' physical fitness is still relatively low and the actual rehabilitation training environment they are exposed to is relatively simple, patients lack visual training scenes during the rehabilitation training process. Summary of the invention

[0004] In view of the above problems, the present invention provides a lower limb exoskeleton robot system based on virtual reality feedback.

[0005] According to a first aspect of the present invention, there is provided a lower limb exoskeleton robot system based on virtual reality feedback, comprising: an exoskeleton machine device, for collecting electromyographic signals and electrocardiographic signals of a user wearing the exoskeleton robot during rehabilitation training, and performing feature extraction on the electromyographic signals and electrocardiographic signals to obtain physiological characteristics, wherein the physiological characteristics include the following information: heart rate variability, electromyographic amplitude and electromyographic average power; a communication server, for transmitting the physiological characteristics to a virtual reality device; a virtual reality device, for inputting the physiological characteristics into a fitting model to obtain the user's psychological state, wherein the psychological function of the fitting model is obtained by fitting a set of preset psychological levels, a set of heart rate variability, a set of electromyographic amplitude and a set of electromyographic average power, and the psychological function characterizes the relationship between the preset psychological levels and the physiological characteristics; and updating the rehabilitation training mode of the virtual reality device according to the psychological state.

[0006] According to an embodiment of the present invention, the exoskeleton machine device includes: an electrophysiological module for collecting myoelectric signals and electrocardiographic signals of a user during rehabilitation training; and an exoskeleton robot module for collecting movement information of the user during rehabilitation training.

[0007] According to an embodiment of the present invention, the electrophysiological module includes: an electromyographic differential conditioning circuit, which is used to collect the electromyographic signals of the user during rehabilitation training; an electrocardiographic differential conditioning circuit, which is used to collect the electrocardiographic signals of the user during rehabilitation training; and an electrophysiological main control unit, which is used to extract features from the electromyographic signals and the electrocardiographic signals to obtain physiological features.

[0008] According to an embodiment of the present invention, the exoskeleton robot module includes: a sensor unit for collecting motion information of a user during rehabilitation training, and the motion information is used to evaluate the balance function of the exoskeleton robot.

[0009] According to an embodiment of the present invention, the sensor unit includes: a joint module encoder, which is used to collect the joint angles of a user wearing an exoskeleton robot during rehabilitation training, and the motion information includes the joint angles; a ranging sensor, which is used to measure the limb length of the user wearing the exoskeleton robot; a posture sensor, which is used to measure the posture and gait cycle of the user wearing the exoskeleton robot during rehabilitation training, and the motion information also includes the posture and gait cycle.

[0010] According to an embodiment of the present invention, the exoskeleton robot device also includes an execution module, which includes: a joint module unit for driving the user's limb joints to rotate; and an electric push-pull unit for adjusting the limb length of the exoskeleton robot worn by the user.

[0011] According to an embodiment of the present invention, the virtual reality device includes: a wearable device for presenting a virtual scene in a rehabilitation training mode to a user; a locator for locating the user's moving position during the rehabilitation training process; and a mixed reality processor for projecting the moving position onto the virtual scene and / or evaluating the motion information during the rehabilitation training process.

[0012] According to an embodiment of the present invention, a rehabilitation training mode includes training tasks and virtual scenes. The rehabilitation training mode of updating a virtual reality device according to a psychological state includes: updating the virtual scene of the virtual reality device in response to a preset psychological state represented by a psychological state, obtaining an updated virtual scene, and updating the training tasks of the virtual reality device in response to the user being in a preset psychological state in the updated virtual scene.

[0013] According to an embodiment of the present invention, the formula between the preset psychological level and the physiological characteristic prediction is:

[0014]

[0015] Y t is a set of preset psychological levels, X HRV is the set of heart rate variability, X EMGF is the set of myoelectric amplitudes, X EMGV is the set of average EMG power, and C is the psychological function predicted by the fitting model.

[0016] According to an embodiment of the present invention, the mixed reality processor is further used to: input a set of preset muscle fatigue levels, a set of myoelectric amplitudes, and a set of myoelectric average power into a fitting model to obtain a muscle fatigue function of the user; and predict the muscle fatigue level of the user using the muscle fatigue function, where the muscle fatigue function is as follows:

[0017]

[0018] B is the muscle fatigue function, F t is a collection of preset muscle fatigue levels. for The inverse matrix of .

[0019] According to an embodiment of the present invention, an exoskeleton machine device is used to collect the electromyographic signals and electrocardiographic signals of a user wearing an exoskeleton robot during rehabilitation training, perform feature extraction on the electromyographic signals and electrocardiographic signals of the user during rehabilitation training, and obtain physiological characteristics; the physiological characteristics are transmitted to a virtual reality device using a communication server; the virtual reality device is used to input the physiological characteristics into a fitting model to obtain the user's psychological state, and the psychological function of the fitting model is obtained by fitting using a set of preset psychological levels, a set of heart rate variability, a set of electromyographic amplitudes, and a set of electromyographic average powers, so the psychological state of the patient can be accurately predicted using the psychological function; the rehabilitation training mode of the virtual reality device is updated according to the psychological state, so that the patient can immerse himself in personalized rehabilitation training. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above contents and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0021] Figure 1 A diagram showing a rehabilitation training scenario combining virtual reality with a lower limb exoskeleton robot according to an embodiment of the present invention is shown;

[0022] Figure 2 A structural block diagram of a lower limb exoskeleton robot system based on virtual reality feedback according to an embodiment of the present invention is shown;

[0023] Figure 3 It shows a structural block diagram of an exoskeleton machine device according to an embodiment of the present invention;

[0024] Figure 4 It shows a structural block diagram of an electrophysiological module according to an embodiment of the present invention;

[0025] Figure 5 A structural block diagram of a sensor unit according to an embodiment of the present invention is shown;

[0026] Figure 6A flow chart showing updating of a rehabilitation training mode of a virtual reality device according to a psychological state according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0027] Below, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present invention. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of embodiments of the present invention. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of concepts of the present invention.

[0028] The terms used herein are only for describing specific embodiments and are not intended to limit the present invention. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0029] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0030] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0031] In the technical solution of the present invention, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, invention and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0032] In the scenario of using personal information for automated decision-making, the methods, devices, and systems provided by the embodiments of the present invention provide users with corresponding operation portals for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating an individual's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs, and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge and skills, and have reached a certain level of professionalism.

[0033] Rehabilitation training can promote the plasticity of the central nervous system of the brain, and then change the functional connections and structures of the brain to adapt to the needs of movement. Due to the low physical fitness of patients, the actual rehabilitation training environment they are exposed to is relatively simple, resulting in a lack of visual training scenes during the rehabilitation training process.

[0034] According to an embodiment of the present invention, a lower limb exoskeleton robot system based on virtual reality feedback is provided, comprising: an exoskeleton machine device, used to collect electromyographic signals and electrocardiographic signals of a user wearing the exoskeleton robot during rehabilitation training, and extract features from the electromyographic signals and electrocardiographic signals to obtain physiological features, wherein the physiological features include the following information: heart rate variability, electromyographic amplitude and electromyographic average power; a communication server, used to transmit the physiological features to a virtual reality device; a virtual reality device, used to input the physiological features into a fitting model to obtain the user's psychological state, wherein the psychological function of the fitting model is obtained by fitting a set of preset psychological levels, a set of heart rate variability, a set of electromyographic amplitude and a set of electromyographic average power, and the psychological function represents the relationship between the preset psychological level and the physiological features; and the rehabilitation training mode of the virtual reality device is updated according to the psychological state. .

[0035] Figure 1 A diagram showing a rehabilitation training scenario combining virtual reality with a lower limb exoskeleton robot according to an embodiment of the present invention is shown.

[0036] like Figure 1 As shown, according to this embodiment, the rehabilitation training scene 100 combining virtual reality with a lower limb exoskeleton robot may include a wearable device 101, a lower limb exoskeleton robot 102, and a network 103. The network 103 is used to provide a medium for a communication link between the wearable device 101 and the lower limb exoskeleton robot 102. The network 103 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0037] The wearable device 101 can provide users with rich visual, auditory, tactile and other multi-dimensional experiences, immersing users in a synthetic virtual environment and increasing the interest of users in the rehabilitation training process. At the same time, the wearable device 101 can also show users training tasks of different intensities. For example, the wearable device can be glasses, helmets, etc.

[0038] The user wears the lower limb exoskeleton robot 102 (also referred to as an exoskeleton robot) to perform rehabilitation training.

[0039] For example, the lower limb exoskeleton robot 102 can be used as an external device to support the body of a stroke patient during rehabilitation training. For example, it can help patients train the limb movements of the hemiplegic limbs. Due to the low physical fitness of the patients, the actual rehabilitation training environment is relatively simple, making the rehabilitation training process boring and tedious. Due to the lack of visual goals in the rehabilitation training process, the rehabilitation training effect is reduced.

[0040] For example, the wearable device 101 is used to provide users with multi-dimensional training standard paradigms such as vision, hearing, and touch. The lower limb exoskeleton robot 102 provides real-time motion power. The lower limb exoskeleton robot 102 drives the user to complete the corresponding movement, and compares the completed work with the standard action provided by the virtual reality device to adjust the driving mode of the lower limb exoskeleton robot 102 in real time, thereby having a good training effect, and then achieving the purpose of personalized, intelligent, and interesting rehabilitation training.

[0041] The following will be based on Figure 1 The rehabilitation training scenario described by Figure 2~Figure 6 A lower limb exoskeleton robot system based on virtual reality feedback according to an embodiment of the invention is described in detail.

[0042] Figure 2 A structural block diagram of a lower limb exoskeleton robot system based on virtual reality feedback according to an embodiment of the present invention is shown.

[0043] like Figure 2 As shown, the lower limb exoskeleton robot system based on virtual reality feedback of this embodiment includes an exoskeleton machine device 110, a communication server 120 and a virtual reality device 130.

[0044] The exoskeleton robot device 110 is used to collect the electromyographic signals and electrocardiographic signals of the user wearing the exoskeleton robot during rehabilitation training, and extract features from the electromyographic signals and electrocardiographic signals to obtain physiological features.

[0045] According to an embodiment of the present disclosure, the physiological characteristics include the following information: heart rate variability, electromyographic amplitude, and electromyographic average power.

[0046] According to an embodiment of the present invention, the exoskeleton machine device may include an exoskeleton robot.

[0047] According to an embodiment of the present invention, the electromyographic signal represents the electrical signal generated by the muscle activity of the user during the rehabilitation training process. For example, the electromyographic signal can detect muscle activity by attaching electrodes to the surface of the user's skin.

[0048] For example, the electromyographic signal is first filtered to remove high-frequency noise and low-frequency noise in the electromyographic signal. Then, the filtered electromyographic signal is interpolated to obtain an accurate interpolated electromyographic signal. The interpolated electromyographic signal is feature extracted to obtain the average amplitude, average electromyographic power, root mean square value, etc. of the electromyographic signal. The electromyographic amplitude can be the average amplitude of the electromyographic signal.

[0049] For example, due to the low physical fitness of patients, ECG signals cannot accurately determine changes in emotions. Myoelectric difference signals can partially reflect changes in muscle movement caused by emotional changes.

[0050] Therefore, the difference calculation is performed on the electromyographic signal to obtain a stable electromyographic difference signal to reflect the change of the amplitude of the electromyographic signal with time series. The feature extraction is performed on the electromyographic difference signal to obtain the average amplitude, average frequency, root mean square value, etc. of the electromyographic difference signal. The electromyographic amplitude can be the average amplitude of the electromyographic difference signal, and the electromyographic average power can be the average frequency of the electromyographic difference signal.

[0051] According to an embodiment of the present invention, the ECG signal represents the electrical signal generated by the cardiac muscle activity of the user during rehabilitation training. For example, by placing a motor on the skin surface of the user, the ECG signals of different parts of the user's body (such as the left and right legs) are obtained.

[0052] For example, if the ECG signals of the left and right legs are obtained, the ECG signals corresponding to the left and right legs are time-aligned according to the signal time information, and then the aligned ECG signals corresponding to the left and right legs are merged to obtain a merged signal. The merger can be a weighted summation of the ECG signals corresponding to the left and right legs, and the weight is determined according to the rehabilitation status of the user's left and right legs to reduce the impact of the user's leg rehabilitation status on the ECG signal. Feature extraction is performed on the fused signal to obtain the time domain features, frequency domain features, etc. of the signal waveform.

[0053] For example, if the ECG signal of a single leg is obtained, the ECG signal is subjected to waveform analysis to obtain an abnormal band, and feature extraction is performed on the ECG signal of the abnormal band to obtain the ECG feature of the abnormal band.

[0054] For example, based on the signal time information, the physiological features of the electromyographic signal and the physiological features of the electrocardiographic signal are time-aligned to obtain the physiological features based on the time series.

[0055] The communication server 120 is used to transmit the physiological characteristics to the virtual reality device 130 .

[0056] According to an embodiment of the present invention, the communication server can be respectively connected to the exoskeleton machine device 110 and the virtual reality device 130. The physiological characteristics extracted by the exoskeleton machine device 110 can be transmitted to the virtual reality device 130, reducing the data processing amount of the virtual reality device 130.

[0057] The virtual reality device 130 is used to input the physiological characteristics into the fitting model to obtain the user's psychological state. The psychological function of the fitting model is obtained by fitting a set of preset psychological levels, a set of heart rate variability, a set of electromyographic amplitudes and a set of electromyographic average power. The psychological function represents the relationship between the preset psychological level and the physiological characteristics. The rehabilitation training mode of the virtual reality device is updated according to the psychological state.

[0058] According to an embodiment of the present invention, the preset psychological level represents the degree of the user's psychological state during rehabilitation training. For example, the set of preset psychological levels can be set to 10 levels from a pleasant psychological state to a depressed psychological state, and the higher the level, the greater the degree of the depressed psychological state.

[0059] According to an embodiment of the present disclosure, a set of heart rate variability may be extracted from historical electrocardiogram signals of different users. A set of myoelectric amplitude and a set of myoelectric average power may be extracted from historical electromyographic signals of different users.

[0060] For example, the psychological state represents that the user is in a relatively depressed psychological state, and the rehabilitation training mode of the virtual reality device is updated, that is, updated to relatively relaxing auditory audio, colorful visual scenes, relatively relaxing training movements, etc.

[0061] For example, the psychological state indicates that the user is in a relatively pleasant psychological state, and stronger training movements in the virtual reality device can be updated to improve the training effect.

[0062] According to an embodiment of the present invention, the fitting model may be a nonlinear model, a time series model, a machine learning model, etc.

[0063] For example, the fitting model can be a time series model. A set of physiological characteristics based on the time series and a set of preset psychological levels are input into the time series model, and the least squares method is used to optimize the model parameters such as the autoregressive coefficient and the sliding average coefficient in the time series model to obtain the psychological function.

[0064] The set of physiological characteristics based on time series can be composed of a set of heart rate variability based on time series, a set of electromyographic amplitudes and a set of electromyographic average power. The data in the set of physiological characteristics is precise, and the predicted psychological state is more accurate.

[0065] For example, since the relationship between psychological state and physiological characteristics (heart rate variability, electromyographic amplitude, and electromyographic average power) is not linear, it may involve nonlinear relationships such as exponentials. Therefore, the fitting model can also be a nonlinear model.

[0066] A rich immersive rehabilitation training environment is constructed using virtual reality devices 130 and exoskeleton machine devices 110, creating a rich environment and effective interactive loop for users during rehabilitation training, and providing personalized, intelligent, and interesting rehabilitation training for the recovery of limb dysfunction and repair of psychological state of stroke patients.

[0067] According to an embodiment of the present invention, an exoskeleton machine device is used to collect the electromyographic signals and electrocardiographic signals of a user wearing an exoskeleton robot during rehabilitation training, perform feature extraction on the electromyographic signals and electrocardiographic signals of the user during rehabilitation training, and obtain physiological characteristics; the physiological characteristics are transmitted to a virtual reality device using a communication server; the virtual reality device is used to input the physiological characteristics into a fitting model to obtain the user's psychological state, because the psychological function of the fitting model is obtained by fitting using a set of preset psychological levels, a set of heart rate variability, a set of electromyographic amplitudes, and a set of electromyographic average powers, the psychological function can be used to accurately predict the patient's psychological state; the rehabilitation training mode of the virtual reality device is updated according to the psychological state, so that the patient can immerse himself in personalized rehabilitation training.

[0068] Figure 3 A structural block diagram of an exoskeleton machine device according to an embodiment of the present invention is shown.

[0069] like Figure 3 As shown, the exoskeleton machine device 110 of this embodiment includes an electrophysiological module 111, an exoskeleton robot module 112, an execution module 113, a human-machine interaction module 114, a main processing module 115 and a communication module 116.

[0070] The electrophysiological module 111 is used to collect the electromyographic signals and electrocardiographic signals of the user during rehabilitation training.

[0071] According to an embodiment of the present invention, the electrophysiological module 111 may be composed of a plurality of electrodes to collect myoelectric signals and electrocardiographic signals from multiple parts of the user.

[0072] The exoskeleton robot module 112 is used to collect the user's movement information during rehabilitation training.

[0073] According to an embodiment of the present invention, the exoskeleton robot module 112 may include a variety of sensors.

[0074] According to an embodiment of the present invention, the motion information may include gait, joint angles, center of gravity changes, walking speed, etc.

[0075] According to an embodiment of the present invention, heart rate variability characterizes the degree of change of the heartbeat cycle. For example, feature extraction is performed on the time domain information and frequency domain information of the electrocardiogram signal to obtain an index of heart rate variability. For example, the index of heart rate variability includes low frequency power, high frequency power, standard deviation of the time interval between adjacent heartbeats, etc.

[0076] According to an embodiment of the present invention, the myoelectric amplitude represents the strength of the electrical signal generated when the muscle contracts.

[0077] According to an embodiment of the present invention, the average myoelectric power represents the average power of the myoelectric signal within a period of time. The average myoelectric power reflects the contraction strength and fatigue strength of the muscle.

[0078] The execution module 113 is used to drive the user wearing the exoskeleton robot to perform limb movements.

[0079] The human-machine interaction module 114 is used to operate the exoskeleton robot according to the instructions of the user or the guardian. For example, the human-machine interaction module 114 may include a touch screen and buttons.

[0080] The main processing module 115 is used to control the electrophysiological module 111 , the exoskeleton robot module 112 , the execution module 113 , the human-computer interaction module 114 and the communication module 116 .

[0081] The communication module 116 is connected to the main processing module 115 and the electrophysiological module 111 , and is used to implement information interaction between the main processing module 115 , the electrophysiological module 111 and the communication server 120 .

[0082] The lower limb exoskeleton robot system based on virtual reality feedback can be battery-powered.

[0083] Figure 4 A structural block diagram of an electrophysiological module according to an embodiment of the present invention is shown.

[0084] like Figure 4 As shown, the electrophysiological module 111 of this embodiment includes an electromyographic differential conditioning circuit 1111 , an electrocardiographic differential conditioning circuit 1112 , an electrophysiological main control unit 1113 , an analog-to-digital conversion circuit 1114 and electrodes 1115 .

[0085] The myoelectric differential conditioning circuit 1111 is used to collect the myoelectric signals of the user during rehabilitation training.

[0086] According to the embodiment of the present invention, the myoelectric differential conditioning circuit 1111 is connected to the analog-to-digital conversion circuit 1114 and the electrode 1115. The myoelectric differential conditioning circuit 1111 can perform signal conditioning such as amplification and filtering on the myoelectric signal picked up by the electrode 1115.

[0087] The ECG differential conditioning circuit 1112 is used to collect the ECG signal of the user during rehabilitation training.

[0088] According to an embodiment of the present invention, the ECG differential conditioning circuit 1112 is connected to the analog-to-digital conversion circuit 1114 and the electrode 1115 respectively. The ECG differential conditioning circuit 1112 can amplify, filter, and perform other signal conditioning on the ECG signal picked up by the electrode 1115 .

[0089] The electrophysiological main control unit 1113 is used to extract features from the electromyographic signal and the electrocardiographic signal to obtain physiological features.

[0090] According to an embodiment of the present invention, the electrophysiological main control unit 1113 is respectively connected to the communication module 116 and the analog-to-digital conversion circuit 1114 in the exoskeleton robot device 110. The electrophysiological main control unit 1113 is used to control the operation of the analog-to-digital conversion circuit, pre-process the converted data, extract features from the electromyographic signal and the electrocardiographic signal, and obtain physiological features, such as heart rate variability, electromyographic amplitude, electromyographic median frequency, etc.

[0091] The analog-to-digital conversion circuit 1114 is respectively connected to the electrophysiological main control unit 1113, the myoelectric differential conditioning circuit 1111, and the ECG differential conditioning circuit 1112. The analog-to-digital conversion circuit 1114 is used to convert the analog myoelectric signals and ECG signals output by the myoelectric differential conditioning circuit 1111 and the ECG differential conditioning circuit 1112 into digital signals.

[0092] Electrodes 1115 are respectively connected to the myoelectric differential conditioning circuit 1111 and the ECG differential conditioning circuit 1112. Electrodes 1115 are attached to the lower limbs, the myoelectric electrodes are placed on the same-side leg to collect myoelectric signals, and one electrode is taken from each leg to configure as an ECG electrode to collect ECG signals.

[0093] According to an embodiment of the present invention, the exoskeleton robot module 112 includes a sensor unit 1121. The sensor unit 1121 is used to collect the motion information of the user during the rehabilitation training process, and the motion information is used to evaluate the balance function of the exoskeleton robot.

[0094] Figure 5 A structural block diagram of a sensor unit according to an embodiment of the present invention is shown.

[0095] like Figure 5As shown, the sensor unit 1121 of this embodiment includes a joint module encoder 11211, a ranging sensor 11212 and a posture sensor 11213.

[0096] The joint module encoder 11211 is used to collect the joint angles of a user wearing an exoskeleton robot during rehabilitation training, and the motion information includes the joint angles.

[0097] The distance measuring sensor 11212 is used to measure the length of the limbs of the user wearing the exoskeleton robot.

[0098] The posture sensor 11213 is used to measure the posture and gait cycle of the user wearing the exoskeleton robot during rehabilitation training. The motion information also includes posture and gait cycle.

[0099] According to an embodiment of the present invention, the execution module includes: a joint module unit for driving the user's limb joints to rotate; and an electric push-pull unit for adjusting the limb length of the exoskeleton robot worn by the user to adapt to different people.

[0100] According to an embodiment of the present invention, the virtual reality device includes: a wearable device for presenting a virtual scene in a rehabilitation training mode to a user; a locator for locating the user's moving position during the rehabilitation training process; and a mixed reality processor for projecting the moving position onto the virtual scene and / or evaluating the motion information during the rehabilitation training process.

[0101] The mixed reality processor can provide different virtual scenes and training goals, and can evaluate the completion and standardization of the movement based on the feedback of the movement state parameters.

[0102] According to an embodiment of the present invention, the wearable device may be a helmet or glasses, which are used to present different virtual scenes to the user.

[0103] The mixed reality processor and the locator may be powered by a power source, and the wearable device may be powered by a battery.

[0104] According to an embodiment of the present invention, the heart rate variability is , the myoelectric amplitude is The average electromyographic power is , then the muscle fatigue prediction value F t for:

[0105] (1)

[0106] f1 is the muscle fatigue function. Use muscle strength test to determine the preset muscle fatigue level , F t for Any combination of Its coefficient matrix is ​​B, which can characterize the muscle fatigue function.

[0107] According to an embodiment of the present invention, the mixed reality processor is further used to: input a set of preset muscle fatigue levels, a set of myoelectric amplitudes, and a set of myoelectric average power into a fitting model to obtain a muscle fatigue function of the user; and predict the muscle fatigue level of the user using the muscle fatigue function, where the muscle fatigue function is as follows:

[0108] (2)

[0109] B is the muscle fatigue function, F t is a collection of preset muscle fatigue levels. for The inverse matrix of .

[0110] y t is the preset psychological level, f2 is the psychological function, which can be expressed as:

[0111] (3)

[0112] A collection of preset psychological levels, representing .

[0113] For example, using a scale test to determine the preset psychological level y t ,y t for Any level of psychological state, while recording synchronized heart rate variability , EMG amplitude , EMG average power .

[0114] According to an embodiment of the present invention, the formula between the preset psychological level and the physiological characteristic prediction is:

[0115] (4)

[0116] Y t is a set of preset psychological levels, X HRV is the set of heart rate variability, X EMGF is the set of myoelectric amplitudes, X EMGV is the set of average EMG power, and C is the psychological function predicted by the fitting model.

[0117] According to an embodiment of the present invention, a rehabilitation training mode includes training tasks and virtual scenes. The rehabilitation training mode of updating a virtual reality device according to a psychological state includes: updating the virtual scene of the virtual reality device in response to a preset psychological state represented by a psychological state, obtaining an updated virtual scene, and updating the training tasks of the virtual reality device in response to the user being in a preset psychological state in the updated virtual scene.

[0118] According to an embodiment of the present invention, the preset psychological state is that the user is in a depressed or nervous psychological state.

[0119] According to an embodiment of the present invention, the training task may involve sports movements, sports intensity, sports standards, etc.

[0120] Figure 6 A flow chart showing updating of a rehabilitation training mode of a virtual reality device according to a psychological state according to an embodiment of the present invention is shown.

[0121] like Figure 6 As shown, updating the rehabilitation training mode of the virtual reality device according to the psychological state includes operations S610-S680.

[0122] In operation S610, in response to the virtual reality device evaluating the user's actions in the rehabilitation training mode, features of the user's psychological state are extracted according to the electromyographic signal and the electrocardiographic signal to obtain physiological features.

[0123] In operation S620, the physiological characteristics are input into the fitting model to obtain the user's psychological state.

[0124] In operation S630, it is determined whether the user's psychological state is in a preset psychological state. If so, operation S640 is performed; if not, operation S670 is performed.

[0125] In operation S640, the virtual scene of the virtual reality device is updated to obtain an updated virtual scene.

[0126] In operation S650, it is determined whether the user is in a preset psychological state in the updated virtual scene. If so, operation S660 is performed; if not, operation S670 is performed.

[0127] In operation S660, the training task of the virtual reality device is updated.

[0128] In operation S670, determine whether the user has completed the training task. If so, execute operation S680; if not, execute operation S610.

[0129] In operation S680, the exercise effect of the user under the training task is evaluated.

[0130] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0131] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present invention may be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in the present invention. In particular, without departing from the spirit and teachings of the present invention, the features described in the various embodiments of the present invention may be combined and / or combined in various ways. All of these combinations and / or combinations fall within the scope of the present invention.

[0132] The embodiments of the present invention are described above. However, these embodiments are only for the purpose of illustration, and are not intended to limit the scope of the present invention. Although each embodiment is described above, it does not mean that the measures in each embodiment cannot be used in combination advantageously. Without departing from the scope of the present invention, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

Claims

1. A lower limb exoskeleton robot system based on virtual reality feedback, characterized in that: The system comprises: An exoskeleton robot device is used to collect electromyographic signals and electrocardiographic signals of a user wearing an exoskeleton robot during rehabilitation training, and extract features from the electromyographic signals and the electrocardiographic signals to obtain physiological features, wherein the physiological features include the following information: heart rate variability, electromyographic amplitude, and electromyographic average power; a communication server, for transmitting the physiological characteristics to a virtual reality device; The virtual reality device is used to input the physiological characteristics into a fitting model to obtain the psychological state of the user, wherein the psychological function of the fitting model is obtained by fitting a set of preset psychological levels, a set of heart rate variability, a set of electromyographic amplitudes and a set of electromyographic average power, and the psychological function represents the relationship between the preset psychological levels and the physiological characteristics; and the rehabilitation training mode of the virtual reality device is updated according to the psychological state.

2. The system according to claim 1, characterized in that The exoskeleton machine device comprises: An electrophysiological module, used for collecting the electromyographic signal and the electrocardiographic signal of the user during the rehabilitation training; The exoskeleton robot module is used to collect the movement information of the user during the rehabilitation training.

3. The system according to claim 2, characterized in that The electrophysiological module comprises: An electromyographic differential conditioning circuit, used for collecting the electromyographic signal of the user during the rehabilitation training; An ECG differential conditioning circuit, used for collecting the ECG signal of the user during the rehabilitation training; The electrophysiological main control unit is used to extract features from the electromyographic signal and the electrocardiographic signal to obtain the physiological features.

4. The system according to claim 2, characterized in that The exoskeleton robot module comprises: The sensor unit is used to collect the movement information of the user during the rehabilitation training, and the movement information is used to evaluate the balance function of the exoskeleton robot.

5. The system according to claim 4, characterized in that The sensor unit comprises: A joint module encoder, used for collecting joint angles of the user wearing the exoskeleton robot during the rehabilitation training process, wherein the motion information includes the joint angles; A distance measuring sensor, used to measure the length of the limbs of the user wearing the exoskeleton robot; A posture sensor is used to measure the posture and gait cycle of the user wearing the exoskeleton robot during the rehabilitation training process, and the motion information also includes the posture and the gait cycle.

6. The system according to claim 5, characterized in that The exoskeleton robot device further includes an execution module, wherein the execution module includes: A joint module unit, used to drive the user's limb joints to rotate; An electric push-pull unit is used to adjust the length of the limbs of the exoskeleton robot worn by the user.

7. The system according to claim 1, characterized in that The virtual reality device comprises: A wearable device, used for presenting a virtual scene in the rehabilitation training mode to the user; A locator, used to locate the moving position of the user during the rehabilitation training; A mixed reality processor is used to project the movement position onto the virtual scene and / or evaluate the movement information during the rehabilitation training.

8. The system according to claim 7, characterized in that The rehabilitation training mode includes a training task and the virtual scene, and the rehabilitation training mode of updating the virtual reality device according to the psychological state includes: In response to the mental state representing a preset mental state, updating the virtual scene of the virtual reality device to obtain an updated virtual scene; In response to the user being in the preset psychological state in the updated virtual scene, updating the training task of the virtual reality device.

9. The system according to claim 1, characterized in that The formula between the preset psychological level and the physiological characteristic prediction is: Y t is the set of preset psychological levels, X HRV is the set of heart rate variability, X EMGF is the set of myoelectric amplitudes, X EMGV is the set of the average myoelectric power, and C is the psychological function predicted by using the fitting model.

10. The system according to claim 9, characterized in that The Mixed Reality Processor is also used to: Inputting a set of preset muscle fatigue levels, a set of myoelectric amplitudes, and a set of myoelectric average powers into the fitting model to obtain a muscle fatigue function of the user; The muscle fatigue level of the user is predicted using the muscle fatigue function, and the muscle fatigue function is as follows: B is the muscle fatigue function, F t is a set of preset muscle fatigue levels, for The inverse matrix of .

Images