BCI control device and intelligent wheelchair

Abstract

The utility model discloses a BCI control system which comprises a head-mounted BCI device, a processing and calculating device and a control device. The head-mounted BCI device comprises a flexible shell, an attention collecting electrode, an emotion collecting electrode and a motion collecting electrode, and EEG signals of different parts of the head of the human body are collected. The attention collecting electrodes and the emotion collecting electrodes are arranged at the positions corresponding to the frontal lobe of the human brain, and the motion collecting electrodes are arranged at the positions corresponding to the apical lobe, occipital lobe, left temporal lobe and right temporal lobe of the human brain respectively. The processing and calculating device determines the attention, emotion and imaginary movement types of the human body based on the signals collected by the electrodes and outputs a control instruction to control the intelligent wheelchair to move. And the display device realizes interactive display of attention, emotion and imaginary motion categories and control instructions of the human body. The utility model further discloses the intelligent wheelchair comprising the BCI control system.

Description

Technical Field

[0001] The present disclosure relates to the field of smart wheelchairs, and in particular to a BCI control device for a smart wheelchair. Background Art

[0002] As a combination of modern technology and medical assistive devices, smart wheelchairs are designed to provide people with limited mobility with a more convenient and comfortable life. However, smart wheelchairs still face some problems in practical applications. Although smart wheelchairs already have some advanced functions, such as automatic navigation, object recognition and obstacle avoidance, in actual use, there will be problems such as navigation errors and inaccurate recognition, which will bring safety hazards to users. In addition, the degree of satisfaction of personalized needs of smart wheelchairs is not high. Due to differences in physical conditions, activity habits, etc., users have different needs for smart wheelchair models. However, most of the smart wheelchair products on the market currently adopt standardized designs, which are difficult to fully meet the personalized needs of users.

[0003] For ALS patients, they may encounter problems such as muscle weakness, uncoordinated movements, and gradual inability to move at different stages of the disease. This poses new problems for the control of smart wheelchairs. Especially when ALS patients face the problem of limited hand function, it becomes difficult to operate smart wheelchairs. At this time, smart wheelchairs need to design a variety of interactive methods, such as BCI control, to meet the special needs of patients. However, due to the disease, ALS patients have their own characteristics in terms of attention and emotions. These factors will affect the effect of controlling the wheelchair through EEG signals and bring new safety hazards.

[0004] The above information is presented only as background information to help understand the present disclosure. No confirmation or other related meaning is made as to whether any of the above can be used as prior art application with respect to the present disclosure. Utility Model Content

[0005] The disclosed embodiment of the utility model provides a BCI control device, including: a head-mounted BCI device, a processing and computing device, and a control device. Among them, the head-mounted BCI device includes a flexible shell, an attention collection electrode, an emotion collection electrode, and a motion collection electrode, and the attention collection electrode, the emotion collection electrode, and the motion collection electrode are arranged on the flexible shell. The attention collection electrode, the emotion collection electrode, and the motion collection electrode are configured to collect EEG signals from different parts of the human head. The processing and computing device determines the human attention category based on the EEG signal collected by the attention collection electrode and the preset attention condition, the processing and computing device determines the human emotion category based on the EEG signal collected by the emotion collection electrode and the preset emotion condition, the processing and computing device determines the human imagination movement category based on the EEG signal collected by the motion collection electrode and the preset movement condition, and the processing and computing device outputs a control instruction based on the human attention category, the human emotion category, the human imagination movement category, and the preset instruction condition. The control device is configured to control the movement of the wheelchair body based on the control instruction.

[0006] For example, it also includes a display device, which is configured to receive and display in real time the human attention category, human emotion category, human imaginary movement category and control instructions from the processing and computing device.

[0007] For example, attention collection electrodes and emotion collection electrodes are set in the area corresponding to the frontal lobe of the human brain.

[0008] For example, the motion collection electrodes include at least four electrodes, which are respectively arranged in the regions corresponding to the parietal lobe, occipital lobe, and left and right temporal lobes of the human brain.

[0009] For example, attention collection electrodes and emotion collection electrodes are set in the area corresponding to the frontal lobe of the human brain and close to the area corresponding to the parietal lobe of the human brain.

[0010] For example, the attention collection electrode is set at a position corresponding to the center of the frontal lobe of the human brain, and the emotion collection electrode includes at least 4 electrodes, 2 electrodes are set at positions corresponding to both sides of the frontal lobe of the human brain.

[0011] For example, the motion collection electrodes are respectively set at positions corresponding to the parietal lobe, occipital lobe, and left and right temporal lobes of the human brain.

[0012] For example, the processing and computing device includes a noise reduction module, a conversion module, an extraction module, a classification module and an instruction module. The noise reduction module is configured to filter the EEG signals collected by the attention collection electrode, the emotion collection electrode and the motion collection electrode based on a preset filtering algorithm. The conversion module is configured to perform Fourier transform or wavelet transform on the signal filtered by the noise reduction module. The extraction module is configured to extract the signal converted by the conversion module to obtain a characteristic value. The classification module determines the human attention category, the human emotion category, and the human imaginary movement category based on the characteristic value. The instruction module generates a control instruction based on the human attention category, the human emotion category, the human imaginary movement category and the preset instruction conditions.

[0013] For example, it also includes an active braking device and an alarm device. The processing and calculation device outputs abnormal instructions based on human attention categories, human emotion categories, human imagined movement categories and preset abnormal conditions; the active braking device performs emergency braking based on the abnormal instructions; and the alarm device alarms based on the abnormal instructions.

[0014] For example, it also includes a cloud computing platform, which is wirelessly connected to the processing and computing device. The cloud computing platform is configured to update the algorithm model of the processing and computing device in real time based on the data sent back by the processing and computing device.

[0015] The disclosed embodiment of the utility model further provides an intelligent wheelchair, which includes the above-mentioned BCI control device. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments will be briefly introduced below. Obviously, the drawings in the following description only relate to some embodiments of the present disclosure, but are not intended to limit the present disclosure.

[0017] Figure 1 is a system schematic diagram of a BCI control device and a smart wheelchair according to an embodiment of the present disclosure;

[0018] Figure 2 is a schematic structural diagram of a head-mounted BCI device according to an embodiment of the present disclosure;

[0019] Figure 3 is a schematic structural diagram of another head-mounted BCI device according to an embodiment of the present disclosure;

[0020] Figure 4 Schematic diagram of the control principle of the intelligent wheelchair according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings of the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the described embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0022] Unless otherwise defined, the technical terms or scientific terms used in the present disclosure should be understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly. In the present disclosure, "multiple" refers to two or more.

[0023] According to the embodiment of the present disclosure, Figure 1 As shown, a BCI control device includes: a head-mounted BCI device 1, a processing and computing device 2, and a control device 3. The head-mounted BCI device 1 collects original EEG signals of different parts and types through a non-invasive brain-computer interface. Figure 2 As shown, the head-mounted BCI device 1 includes a flexible shell 11, an attention collection electrode 12, an emotion collection electrode 13 and a motion collection electrode 14, and the attention collection electrode 12, the emotion collection electrode 13 and the motion collection electrode 14 are arranged on the flexible shell 11. The attention collection electrode 12, the emotion collection electrode 13 and the motion collection electrode 14 are configured to collect EEG signals from different parts of the human head. Because ALS patients often lack operational ability, the BCI control device is particularly suitable for use by ALS patients, so as to collect EEG signals of ALS patients for the control of smart wheelchairs.

[0024] For example, the attention collection electrode 12 and the emotion collection electrode 13 are set in the area corresponding to the frontal lobe of the human brain. The area of ​​the frontal lobe of the human brain is highly correlated with mental functions such as attention and emotion. Setting the attention collection electrode 12 and the emotion collection electrode 13 in the area corresponding to the frontal lobe of the human brain is conducive to improving the correlation between the collected EEG signals and attention and emotion.

[0025] For example, the attention acquisition electrode 12 is set at a position corresponding to the middle of the frontal lobe of the human brain. This position has a strong correlation with human attention. The emotion acquisition electrode 13 includes at least 4 electrodes, 2 electrodes are set at positions corresponding to both sides of the frontal lobe of the human brain, and this position has a strong correlation with human emotions. Setting 2 electrodes on each side can filter out artifacts in subsequent data processing, perform frequency analysis on the EEG of both sides, and calculate the frontal wave asymmetry index. This is conducive to eliminating signal interference in some areas, checking and fusing each measurement result, and improving the accuracy of the measurement.

[0026] For example, the attention collection electrode 12 and the emotion collection electrode 13 are set in the area corresponding to the frontal lobe of the human brain and close to the area corresponding to the parietal lobe of the human brain. Although the frontal lobe area of ​​the human brain also produces a strong EEG signal and can be well correlated with human attention and emotions, during the signal collection process, when the electrode is set in the frontal lobe area corresponding to the human brain, it will be interfered by the electrooculogram signal. Therefore, setting the attention collection electrode 12 and the emotion collection electrode 13 in the area corresponding to the frontal lobe of the human brain and as close to the parietal lobe of the human brain as possible, that is, setting them away from the human eyes, is conducive to avoiding the interference of the electrooculogram signal on the EEG signal.

[0027] For example, the attention collection electrode 12 and the emotion collection electrode 13 are metal dry electrodes with a sampling frequency of 500-1000-2000 Hz, and the electrode sampling frequency is adjustable. By adjusting the electrode sampling frequency, the accuracy of the sampling point is improved. The use of metal dry electrodes is conducive to reducing interface impedance and better signal collection.

[0028] For example, the motion collection electrode 14 includes at least 4 electrodes, which are respectively arranged in the regions corresponding to the parietal lobe, occipital lobe, and left and right temporal lobes of the human brain. Collecting and fusing EEG signals from at least 4 regions is conducive to eliminating external interference generated in local regions and improving the accuracy of EEG signal collection related to motor imagery.

[0029] For example, the motion collection electrode 14 is a conductive rubber dry electrode with a sampling frequency of 500-1000-2000 Hz, and the electrode sampling frequency is adjustable. By adjusting the electrode sampling frequency, the accuracy of the sampling point is improved. The use of a conductive rubber dry electrode is conducive to improving the flexibility and durability of the electrode. The conductive rubber dry electrode is more friendly to the human body and is conducive to the wearer feeling comfortable.

[0030] For example, the processing and computing device 2 determines the human attention category based on the EEG signal collected by the attention collection electrode 12 and the preset attention condition. For example, the human attention category is "concentrated" and "unfocused". The processing and computing device 2 amplifies, filters, and reduces noise on the original EEG signal collected by the attention collection electrode 12, and uses an artificial intelligence algorithm to calculate the attention feature value based on the waveform and intensity of the EEG signal. The processing and computing device 2 determines whether the human attention category is "concentrated" or "unfocused" based on the attention feature value and the preset attention condition. For example, only when the attention category is determined to be "concentrated" can the control instruction for changing the movement state be output. When the attention category is determined to be "unfocused", the control instruction for changing the movement state cannot be output to avoid miscontrol when the human attention is not focused.

[0031] For example, the processing and computing device 2 determines the human emotion category based on the EEG signal collected by the emotion collection electrode 13 and the preset emotion condition. For example, the human emotion categories are "sadness", "peace", "joy" and "instability". The processing and computing device 2 amplifies, filters and reduces noise on the original EEG signal collected by the emotion collection electrode 13, and uses an artificial intelligence algorithm to calculate the emotion feature value based on the waveform and intensity of the EEG signal. The processing and computing device 2 determines that the human emotion category is "sadness", "peace", "joy" or "instability" based on the emotion feature value and the preset emotion condition. For example, when the emotion category is determined to be "sadness", a control instruction biased towards a stable mode is output to avoid stimulation to the human body during movement. When the emotion category is determined to be "peace", a control instruction biased towards a normal mode is output. When the emotion category is determined to be "joy", a control instruction biased towards a motion mode is output to optimize the human experience. When the emotion category is determined to be "instability", the control instruction cannot be output to avoid miscontrol when the human body is emotionally unstable.

[0032] For example, the processing and computing device 2 determines the category of human imagined movement based on the EEG signal collected by the motion collection electrode 14 and the preset movement conditions. For example, the categories of human imagined movement are "forward", "acceleration", "deceleration", "left turn", "right turn" and "stop". The processing and computing device 2 amplifies, filters and reduces noise on the original EEG signal collected by the motion collection electrode 14, and uses an artificial intelligence algorithm to calculate the imagined movement feature value based on the waveform and intensity of the EEG signal. The processing and computing device 2 determines the category of human imagined movement as "forward", "acceleration", "deceleration", "left turn", "right turn" or "stop" based on the imagined movement feature value and the preset imagined movement conditions. This helps the human body realize the imagined movement experience.

[0033] For example, the processing and computing device 2 outputs control instructions based on the human attention category, human emotion category, human imaginary movement category and preset instruction conditions. The collected original EEG signal is constantly changing, and the control instructions output by the processing and computing device 2 change in real time. The control device 3 is configured to control the movement of the wheelchair body 4 based on the control instructions. The wheelchair body 4 is driven by a conventional driving method, such as a motor drive.

[0034] For example, it also includes a display device 5, which is configured to receive and display in real time the human attention category, human emotion category, human imaginary movement category and control instructions from the processing and computing device 2. The display device 5 is set in front of the user of the smart wheelchair, at a position and height that is convenient for the wheelchair user to observe. In this way, the calculation results output by the processing and computing device 2 can be visualized. On the one hand, the user of the smart wheelchair can intuitively observe the calculation results and control instructions, evaluate the accuracy of the calculation results, and feed back to the processing and computing device 2 for training the artificial intelligence model. On the other hand, it is convenient for the guardian to understand the calculation results and control instructions in real time and deal with special situations.

[0035] For example, the processing and computing device 2 includes a noise reduction module 21, a conversion module 22, an extraction module 23, a classification module 24 and an instruction module 25. The noise reduction module 21 is configured to amplify the original EEG signals collected by the attention collection electrode 12, the emotion collection electrode 13 and the motion collection electrode 14 by different multiples based on a preset filtering algorithm, and then filter the amplified signals to filter out high-frequency and low-frequency artifacts, power frequency interference noise and electrooculographic noise in the EEG signals, so as to obtain a stably distributed EEG signal. The conversion module 22 is configured to perform Fourier transform or wavelet transform on the signal filtered by the noise reduction module 21, and calculate the energy distribution density of waves of different frequencies and frequency bands. The extraction module 23 is configured to extract the signal converted by the conversion module 22 to obtain a characteristic value, extract the main characteristic band and the signal data in the main characteristic band. The signal data characteristics and distribution trend in the main characteristic band are calculated, and the signal data characteristics and distribution trend in a reasonable interval are extracted as characteristic values. The classification module 24 receives the feature values ​​extracted by the extraction module 23, and identifies and classifies the feature values ​​through the artificial intelligence algorithm model to determine the human attention category, human emotion category, and human imaginary movement category. The instruction module 25 generates control instructions through the artificial intelligence algorithm model based on the human attention category, human emotion category, human imaginary movement category and preset instruction conditions. Before the BCI control device and the smart wheelchair are officially used, they are configured with a preset artificial intelligence algorithm. The preset artificial intelligence algorithm is obtained through multiple trainings of healthy people.

[0036] For example, the artificial intelligence algorithm model is a deep learning model, which adopts one or more deep learning models such as SVM, decision tree, KNN, random forest, naive Bayes classification, least squares method, logistic regression, CNN and RNN.

[0037] For example, it also includes an active braking device 6 and an alarm device 7. The processing and computing device 2 outputs abnormal instructions based on the human attention category, human emotion category, human imaginary movement category and preset abnormal conditions. The active braking device performs emergency braking based on the abnormal instruction. The active braking device can perform emergency braking when the processing and computing device 2 identifies an abnormal situation, further protecting the safety of the user of the smart wheelchair. The alarm device alarms based on the abnormal instruction. The alarm device alarms for abnormal situations, which helps the accompanying personnel to quickly pay attention to the abnormal situation and provide help to the user of the smart wheelchair.

[0038] For example, a cloud computing platform 8 is also included, and the cloud computing platform 8 is wirelessly connected to the processing and computing device 2. The cloud computing platform 8 can effectively improve the computing power of the entire system with the help of communication technology. The communication method can be any wireless connection method, including but not limited to Bluetooth, NFC, GSM, 3G, 4G, 5G and WiFi.

[0039] For example, the cloud computing platform 8 is configured to update the algorithm model of the processing and computing device 2 in real time based on the data transmitted back by the processing and computing device 2. After the BCI control device and the smart wheelchair are officially used, the data output by the processing and computing device 2 can be sent to the cloud computing platform 8 wirelessly in real time. The communication method can be any wireless connection method, not limited to Bluetooth, NFC, GSM, 3G, 4G, 5G and WiFi. The cloud computing platform 8 continuously trains the artificial intelligence model through the data output in real time by the processing and computing device 2, and the continuous optimization of the model helps to improve the accuracy and robustness of the control.

[0040] According to the embodiment of the present disclosure, Figure 1 As shown, a smart wheelchair is also provided, and the smart wheelchair includes the above-mentioned BCI control device.

[0041] There are a few points to note:

[0042] (1) The drawings of the embodiments of the present disclosure only relate to the structures related to the embodiments of the present disclosure, and other structures may refer to the general design.

[0043] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present disclosure, the thickness of the device, layer or region is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0044] (3) In the absence of conflict, the embodiments of the present disclosure and the features therein may be combined with each other to obtain new embodiments.

[0045] The above are only specific implementations of the present disclosure, but the protection scope of the present disclosure is not limited thereto, and the protection scope of the present disclosure shall be based on the protection scope of the claims.

Claims

1. A BCI control device, characterized in that: include: Head-mounted BCI device, processing and computing device, and control device; Wherein, the head-mounted BCI device includes a flexible shell, an attention collection electrode, an emotion collection electrode and a motion collection electrode, and the attention collection electrode, the emotion collection electrode and the motion collection electrode are arranged on the flexible shell; The attention collection electrode, the emotion collection electrode and the movement collection electrode are configured to collect EEG signals from different parts of the human head; The processing and computing device determines the human attention category based on the EEG signal collected by the attention collection electrode and the preset attention condition, the processing and computing device determines the human emotion category based on the EEG signal collected by the emotion collection electrode and the preset emotion condition, the processing and computing device determines the human imagination movement category based on the EEG signal collected by the movement collection electrode and the preset movement condition, and the processing and computing device outputs a control instruction based on the human attention category, the human emotion category, the human imagination movement category and the preset instruction condition; The control device is configured to control the movement of the wheelchair body based on the control instruction.

2. The BCI control device according to claim 1, characterized in that: It also includes a display device, which is configured to receive and display in real time the human attention category, the human emotion category, the human imagined movement category and the control instruction from the processing and computing device.

3. The BCI control device according to claim 1, characterized in that: The attention collection electrode and the emotion collection electrode are arranged in the area corresponding to the frontal lobe of the human brain; The motion collection electrodes include at least four electrodes, which are respectively arranged in the regions corresponding to the parietal lobe, occipital lobe, and left and right temporal lobes of the human brain.

4. The BCI control device according to claim 3, characterized in that: The attention collection electrode and the emotion collection electrode are arranged in an area corresponding to the frontal lobe of the human brain and close to the parietal lobe of the human brain.

5. The BCI control device according to claim 3, characterized in that: The attention collection electrode is arranged at a position corresponding to the center of the frontal lobe of the human brain, and the emotion collection electrode includes at least four electrodes, two of which are arranged at positions corresponding to both sides of the frontal lobe of the human brain.

6. The BCI control device according to claim 3, characterized in that: The motion collection electrodes are respectively arranged in the regions corresponding to the parietal lobe, occipital lobe and left and right temporal lobes of the human brain.

7. The BCI control device according to claim 3, characterized in that: The processing and computing device includes a noise reduction module, a conversion module, an extraction module, a classification module and an instruction module; The noise reduction module is configured to filter the EEG signals collected by the attention collection electrode, the emotion collection electrode and the motion collection electrode based on a preset filtering algorithm; The conversion module is configured to perform Fourier transform or wavelet transform on the signal filtered by the noise reduction module; The extraction module is configured to extract the signal converted by the conversion module to obtain a characteristic value; The classification module determines the human attention category, the human emotion category, and the human imaginary movement category based on the feature value; The instruction module generates the control instruction based on the human attention category, the human emotion category, the human imaginary movement category and the preset instruction condition.

8. The BCI control device according to claim 1, characterized in that: It also includes active braking devices and alarm devices; The processing and computing device outputs an abnormal instruction based on the human attention category, the human emotion category, the human imaginary movement category and a preset abnormal condition; The active braking device performs emergency braking based on the abnormal instruction; The alarm device alarms based on the abnormal instruction.

9. The BCI control device according to claim 1, characterized in that: Also included is a cloud computing platform, the cloud computing platform being wirelessly connected to the processing and computing device; The cloud computing platform is configured to update the algorithm model of the processing and computing device in real time based on the data sent back by the processing and computing device.

10. An intelligent wheelchair, characterized in that: The intelligent wheelchair comprises the BCI control device according to any one of claims 1-9.

Images