Brain-controlled automobile driving intention determination method, device and equipment and medium

Abstract

The embodiment of the invention discloses a brain-controlled automobile driving intention determination method and device, equipment and a medium. The method comprises the following steps: acquiring a first electroencephalogram signal in a brain-controlled automobile in a vehicle driving process of a driver; preprocessing the first electroencephalogram signal based on a preset signal processing mode, and determining a second electroencephalogram signal corresponding to the driver; feature extraction is conducted on the second electroencephalogram signals based on a preset feature extraction mode, and electroencephalogram features corresponding to the driver are determined; and performing driving intention classification based on the electroencephalogram features and a target classification model, and determining the driving intention of the driver. Through the technical scheme of the embodiment of the invention, the vehicle driving intention of the driver can be accurately and conveniently determined, and the driving intention determination efficiency and accuracy are improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of automotive technology, and in particular to a method, device, equipment, and medium for determining driving intention of a brain-controlled car. Background Art

[0002] With the development of technology, the brain-computer interface (BCI) is applied to smart cars, and brain-controlled vehicles (BCV) have come into being.

[0003] At present, since the brain-computer interface serves as the information exchange channel for the driver to control the vehicle, its accuracy in classifying the driver's intention to drive the vehicle plays a key role in the brain-controlled vehicle interaction process. Therefore, the vehicle brain-computer interface's recognition of the driver's intention to drive the vehicle is the key to accelerating the development, application and deployment of brain-controlled vehicles.

[0004] However, traditional vehicle control methods don't utilize brain-computer interfaces (BCIs), and existing research into identifying a driver's driving intent through BCIs is still in its infancy. Therefore, there is an urgent need for a stable, accurate method that can directly reflect the driver's true intentions. This would help further improve the functionality of brain-controlled vehicles, enhance driving safety, and provide a more comfortable driving experience. Summary of the Invention

[0005] Embodiments of the present invention provide a method, device, equipment, and medium for determining the driving intention of a brain-controlled car, so as to accurately and conveniently determine the driver's intention to drive the vehicle, thereby improving the efficiency and accuracy of driving intention determination.

[0006] In a first aspect, an embodiment of the present invention provides a method for determining driving intention of a brain-controlled car, comprising:

[0007] Acquire the first EEG signal of the driver in the brain-controlled car during the driving process;

[0008] pre-processing the first EEG signal based on a preset signal processing method to determine a second EEG signal corresponding to the driver;

[0009] performing feature extraction on the second EEG signal based on a preset feature extraction method to determine EEG features corresponding to the driver;

[0010] Driving intention is classified based on the EEG features and the target classification model to determine the driver's driving intention.

[0011] Optionally, the method further includes: band-pass filtering the first EEG signal based on a preset frequency filter to determine a third EEG signal with noise removed; separating and removing the third EEG signal based on a preset blind source separation method to determine a second EEG signal corresponding to the driver.

[0012] Optionally, the method also includes: performing channel decomposition on the third EEG signal based on a preset independent component decomposition method to determine independent component information corresponding to each channel; performing artifact removal on each independent component information based on preset artifact characteristics to determine the second EEG signal corresponding to the driver.

[0013] Optionally, the method further includes: performing artifact identification on each of the independent component information based on preset artifact characteristics to determine removable artifacts; removing removable artifacts in the third EEG signal based on a preset artifact removal method to determine the second EEG signal corresponding to the driver.

[0014] Optionally, the method further includes: performing whitening processing on the third EEG signal from which noise has been removed, to determine third EEG signals in each channel that are independent of each other.

[0015] Optionally, the method also includes: performing feature extraction on the second EEG signal based on a preset time domain extraction method to determine the time domain features corresponding to the driver; performing feature extraction on the second EEG signal based on a preset frequency domain extraction method to determine the frequency domain features corresponding to the driver; performing feature extraction on the second EEG signal based on a preset time-frequency domain extraction method to determine the time-frequency domain features corresponding to the driver; and composing the EEG features corresponding to the driver based on the time domain features, the frequency domain features and the time-frequency domain features.

[0016] In a second aspect, an embodiment of the present invention further provides a device for determining driving intention of a brain-controlled vehicle, the device comprising:

[0017] A first EEG signal acquisition module is used to acquire a first EEG signal of a driver in a brain-controlled car during driving;

[0018] a second EEG signal determination module, configured to pre-process the first EEG signal based on a preset signal processing method to determine a second EEG signal corresponding to the driver;

[0019] an EEG feature determination module, configured to extract features from the second EEG signal based on a preset feature extraction method to determine EEG features corresponding to the driver;

[0020] The driving intention determination module is used to classify the driving intention based on the EEG features and the target classification model to determine the driver's driving intention.

[0021] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising:

[0022] one or more processors;

[0023] a memory for storing one or more programs;

[0024] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the driving intention of a brain-controlled car as provided in any embodiment of the present invention.

[0025] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for determining driving intention of a brain-controlled car as provided in any embodiment of the present invention.

[0026] In a fifth aspect, an embodiment of the present invention provides a computer program product, including a computer program, which, when executed by a processor, implements the method for determining the driving intention of a brain-controlled car as provided in any embodiment of the present invention.

[0027] The technical solution of the embodiment of the present invention is to obtain a first EEG signal of a driver in a brain-controlled car during the process of driving the vehicle; pre-process the first EEG signal based on a preset signal processing method to determine a second EEG signal corresponding to the driver; perform feature extraction on the second EEG signal based on a preset feature extraction method to determine the EEG features corresponding to the driver; classify the driving intention based on the EEG features and a target classification model to determine the driving intention of the driver, thereby accurately and conveniently realizing the determination of the driver's driving intention, thereby improving the efficiency and accuracy of the driving intention determination.

[0028] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0030] Figure 1 This is a flow chart of a method for determining driving intention of a brain-controlled car provided in Example 1 of the present invention;

[0031] Figure 2This is a flow chart of a method for determining driving intention of a brain-controlled car provided in the second embodiment of the present invention;

[0032] Figure 3 This is a schematic diagram of the structure of a device for determining driving intention of a brain-controlled car provided in a third embodiment of the present invention;

[0033] Figure 4 2 is a schematic diagram of the structure of an electronic device that implements the method for determining the driving intention of a brain-controlled car according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] Example 1

[0037] Figure 1 A flowchart of a method for determining driving intention of a brain-controlled car is provided for the first embodiment of the present invention. This embodiment is applicable to the case of determining the driving intention of a driver in a brain-controlled car during driving. The method can be executed by a device for determining driving intention of a brain-controlled car. The device can be implemented in the form of hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0038] S110: Acquire a first electroencephalogram signal of a driver in a brain-controlled car while driving the vehicle.

[0039] A brain-controlled car may refer to a vehicle that uses brain-computer interface technology to directly control its movement via brain signals. Vehicle driving involves various driving behaviors, including going straight, turning, accelerating, and decelerating. In a brain-controlled car, the driver can control the vehicle to perform actions corresponding to these driving behaviors using a first EEG signal. This first EEG signal may be an electrical signal generated by the driver's brain and directly captured by a signal acquisition system.

[0040] In this embodiment, an EEG cap and an EEG amplifier are used in a brain-controlled car to collect the driver's EEG signals, i.e., the first EEG signals, while driving the vehicle, thereby ensuring that the data acquisition system has high temporal resolution and high signal-to-noise ratio, as well as good anti-interference capability.

[0041] S120 : Pre-process the first EEG signal based on a preset signal processing method to determine a second EEG signal corresponding to the driver.

[0042] The preset signal processing method may refer to a pre-set interference removal method for interference present during the acquisition, amplification, and transmission of the first EEG signal. For example, the preset signal processing method may include, but is not limited to, noise removal and normalization. The second EEG signal may refer to an EEG signal obtained by removing interference from the first EEG signal.

[0043] In this embodiment, the 50 Hz power frequency interference is mainly caused by the interference of the AC mains to the electronic equipment, which can be suppressed by the 50 Hz notch filter. The EEG signal obtained after the suppression by the 50 Hz notch filter can be normalized using the z-score normalization method to obtain a second EEG signal.

[0044] It should be noted that the purpose of the above z-score normalization method is to make the mean of the data 0 and the standard deviation 1, thereby eliminating the dimensional effects between different individuals or different time points, facilitating comparison and further analysis. The following are the specific steps and formulas for z-score normalization: (1) Calculate the mean: For each channel in the EEG signal, calculate the mean μ of its signal. (2) Calculate the standard deviation: Calculate the standard deviation σ of the signal for each channel. (3) Perform normalization: Use the following formula to normalize each data point: z = (x-μ)σ. Where x is the original data point and z is the normalized data point.

[0045] S130 . Perform feature extraction on the second EEG signal based on a preset feature extraction method to determine EEG features corresponding to the driver.

[0046] The preset feature extraction method may refer to a pre-set extraction method for each dimensional feature. For example, the preset feature extraction method may include, but is not limited to, a time domain feature extraction method and a frequency domain feature extraction method. The EEG feature may refer to a combination of multi-dimensional features extracted using the preset feature extraction method.

[0047] In this embodiment, the time domain features can be used to reflect the amplitude characteristics of the EEG signal that change over time, and are suitable for sudden or transient brain activities (such as event-related potentials, ERPs). For example, the time domain features may include but are not limited to amplitude and peak. Amplitude may refer to the voltage intensity of the signal waveform. Amplitude can be used to reflect the synchronization of neuronal discharges. For example, the amplitude of a specific frequency band may increase when attention is focused. Peak may refer to the local maximum in the signal. Peak may be related to a specific event (such as a decision moment). Frequency domain features can convert EEG signals from the time domain to the frequency domain through Fourier transform, thereby revealing the power distribution of different frequency components. For example, frequency domain features may include but are not limited to frequency band energy proportion. Frequency band energy proportion may refer to the proportion of energy in a specific frequency band (such as α waves, β waves) to the total energy. Frequency band energy proportion can be used to distinguish different intentions. The extracted time domain features and frequency domain features are combined or spliced ​​to obtain the EEG features corresponding to the driver.

[0048] On the basis of the above technical solution, "extracting features from the second EEG signal based on a preset feature extraction method to determine the EEG features corresponding to the driver" may include: extracting features from the second EEG signal based on a preset time domain extraction method to determine the time domain features corresponding to the driver; extracting features from the second EEG signal based on a preset frequency domain extraction method to determine the frequency domain features corresponding to the driver; extracting features from the second EEG signal based on a preset time-frequency domain extraction method to determine the time-frequency domain features corresponding to the driver; and composing the EEG features corresponding to the driver based on time domain features, frequency domain features, and time-frequency domain features.

[0049] Time-domain feature extraction directly extracts features from the EEG signal's time series without any transformation. These features typically reflect the statistical properties and dynamic changes of the EEG signal. Time-domain features may include, but are not limited to, mean, variance and standard deviation, skewness and kurtosis, amplitude, and zero-crossing rate. The mean is obtained by calculating the average value of each channel's signal. The mean can be used to provide a reference baseline for the EEG signal. The variance measures the dispersion of signal values. The standard deviation is the square root of the variance. The variance and standard deviation can reveal the volatility of the signal. Skewness can describe the asymmetry of the signal distribution, while kurtosis can describe the sharpness and heavy tail characteristics of the signal distribution. Skewness and kurtosis can be used to identify non-normal characteristics of the signal. Amplitude is the difference between the maximum and minimum values ​​of the signal. Amplitude can reflect the amplitude variation range of the signal. The zero-crossing rate can be determined by counting the number of times the signal waveform crosses the zero axis. The zero-crossing rate can reflect the oscillation frequency of the signal.

[0050] Among them, frequency domain feature extraction can analyze the frequency components of the signal by converting the time domain signal to the frequency domain, which can usually be achieved by Fourier transform. Fast Fourier Transform (FFT) can be used to convert the time domain signal into a frequency domain signal, revealing the amplitude and phase information of different frequency components. Frequency domain features may include but are not limited to power spectral density (PSD) and band power. Power spectral density can be obtained by calculating the power of each frequency component to obtain the distribution of the signal at different frequencies. Band power can be the total power of the signal calculated within a specific frequency range (such as δ, θ, α, β, and γ bands). Band power can be used to identify activities associated with specific brain states.

[0051] It should be noted that power changes in different frequency bands are directly related to cognitive states. For example: Alpha waves (8-13Hz): Increased when eyes are closed and relaxed, and decreased when eyes are open or focused. Beta waves (14-30Hz): Increased power when focused or nervous. Theta waves (4-7Hz): Significant during deep relaxation or meditation, and may be related to the decision-making process. Gamma waves (30-100Hz): High-frequency oscillations, related to higher-level cognitive functions (such as information integration). For example, when a driver imagines "turning left", the beta wave power in the left motor cortex may increase, while the alpha wave in the right motor cortex is suppressed.

[0052] Among them, time-frequency domain feature extraction combines time and frequency information, and is usually implemented using wavelet transform. Continuous wavelet transform (CWT) can be used to extract the time-frequency domain features of EEG signals by performing wavelet transform on the signal at different scales and positions. Time-frequency domain features may include but are not limited to wavelet energy, wavelet phase, and wavelet entropy. Wavelet energy can be determined by calculating the sum of the squares of wavelet transform coefficients. Wavelet energy can be used to reflect the energy distribution of a signal at a specific time and frequency scale. Wavelet phase can be determined by extracting the phase information of the wavelet transform coefficients. Wavelet phase can be used to identify phase locking phenomena in signals. Wavelet entropy can be determined by calculating the entropy of the wavelet energy distribution. Wavelet entropy can be used to quantify the complexity and uncertainty of a signal in the time-frequency domain.

[0053] Specifically, based on the above-mentioned feature determination method, the time domain features, frequency domain features, and time-frequency domain features corresponding to the driver's EEG signal during driving the vehicle are determined, so that the time domain features, frequency domain features, and time-frequency domain features can be combined or spliced ​​to obtain the EEG features corresponding to the driver. In this embodiment, when extracting features, it is necessary to consider the noise level of the signal, the influence of artifacts, and individual differences. In order to improve the interpretability and reliability of the features, a plurality of pre-set feature extraction methods are used to extract features of multiple dimensions, thereby further improving the efficiency and accuracy of determining driving intentions.

[0054] Exemplarily, time-frequency domain features may also include: event-related desynchronization (ERD) and event-related synchronization (ERS). Event-related desynchronization may refer to a decrease in the power of the μ rhythm (8-12Hz) or β rhythm of the corresponding motor cortex before performing an action. Event-related synchronization may refer to a recovery increase in the power of the same frequency band after the action is completed. For example, when the user is about to step on the brakes, ERD may appear in the β wave of the motor cortex, followed by ERS indicating that the action is completed.

[0055] S140: Classify the driving intention based on the EEG features and the target classification model to determine the driver's driving intention.

[0056] The target classification model may refer to a pre-trained classification model. The target classification model can be used to analyze EEG signals generated by the driver while driving a vehicle to determine driving intent. Driving intent may refer to the driving action the driver intends to complete. For example, driving intent may include, but is not limited to, driving straight, turning, accelerating, and decelerating.

[0057] Specifically, the EEG features are input into the target classification model to classify the driving intention and determine the driver's driving intention during the process of driving the vehicle.

[0058] The technical solution of the embodiment of the present invention is to obtain the first EEG signal of the driver in the process of driving the vehicle in a brain-controlled car; pre-process the first EEG signal based on a preset signal processing method to determine the second EEG signal corresponding to the driver; extract features from the second EEG signal based on a preset feature extraction method to determine the EEG features corresponding to the driver; classify the driving intention based on the EEG features and the target classification model to determine the driver's driving intention, so as to accurately and conveniently realize the determination of the driver's driving intention, thereby improving the efficiency and accuracy of the driving intention determination.

[0059] Example 2

[0060] Figure 2 This is a flowchart of a method for determining driving intention of a brain-controlled vehicle, provided in Example 2 of the present invention. Building on the previous example, this example describes in detail the process of determining the driver's corresponding second EEG signal. Explanations of terms that are identical or corresponding to those in the previous examples are omitted here.

[0061] like Figure 2 As shown, the method includes:

[0062] S210: Acquire a first electroencephalogram signal of a driver in a brain-controlled car during the process of driving the vehicle.

[0063] S220 . Perform band-pass filtering on the first EEG signal based on a preset frequency filter to determine a third EEG signal with noise removed.

[0064] Among them, the preset frequency filter may refer to a filter corresponding to different frequencies that is pre-set. In this embodiment, the preset frequency filter may include: a 50Hz notch filter and a 4-30Hz filter. The 50Hz power frequency interference is mainly caused by the interference of the AC mains to the electronic equipment, which can be suppressed by the 50Hz notch filter. In order to allow the measurement of negative values, there is a DC component of about 4200μV in the EEG signal recorded by the EEG instrument. The 4Hz high-pass filter can not only eliminate the DC component, but also eliminate long-term signal drift, and the effect is better than the simple common average reference method. Electrocardiogram (ECG) is an interference signal caused by the beating of the heart. Since the heart is far away from the brain, the interference to the EEG signal is very small and generally does not need to be processed. Myoelectricity is easy to appear when a person's head is tense, the face moves, or swallows, etc. The frequency is usually greater than 30Hz, which is in a different frequency band from the EEG signal and can be suppressed by a 30Hz low-pass filter.

[0065] Specifically, the first EEG signal is band-pass filtered using a 50 Hz notch filter and a 4-30 Hz filter to determine a third EEG signal with noise removed.

[0066] On the basis of the above technical solution, before determining the second EEG signal corresponding to the driver, the method further includes: performing whitening processing on the third EEG signal from which noise is removed, and determining third EEG signals that are independent of each other in each channel.

[0067] Specifically, the third EEG signal after noise removal is whitened so that the channels of the signal are statistically uncorrelated, so as to ensure the statistical independence of the signals of each channel and have the same variance, thereby obtaining the third EEG signal with independent channels.

[0068] S230: Separate and remove the third EEG signal based on a preset blind source separation method to determine the second EEG signal corresponding to the driver.

[0069] Among them, electro-oculogram (EOG) is mainly caused by actions such as eye movement or blinking. Its amplitude is generally greater than that of electroencephalography (EEG), and the frequency aliasing with EEG is relatively large. It is difficult to effectively remove it through conventional frequency domain filters, and it is one of the main sources of noise in EEG signals. Blind source separation (BSS) refers to separating the unobserved original signal from multiple observable mixed signals. Independent component analysis (ICA) is a method that can achieve blind source separation. The preset blind source separation method can refer to independent component analysis (ICA).

[0070] Specifically, independent component analysis (ICA) is used to remove electrooculogram (EOG) and other artifacts from the third EEG signal to determine the second EEG signal corresponding to the driver.

[0071] On the basis of the above technical solution, "separating and removing the third EEG signal based on a preset blind source separation method to determine the second EEG signal corresponding to the driver" may include: performing channel decomposition on the third EEG signal based on a preset independent component decomposition method to determine the independent component information corresponding to each channel; performing artifact removal on each independent component information based on preset artifact characteristics to determine the second EEG signal corresponding to the driver.

[0072] The preset independent component decomposition method may refer to an independent component analysis (ICA) algorithm or an independent component analysis (ICA) mathematical model. Independent component information may refer to information obtained by independently dividing the driver's entire EEG activity. For example, independent component information may include, but is not limited to, real EEG activity and various artifacts (such as eye movements, electrocardiogram, etc.). Preset artifact characteristics may refer to pre-configured characteristics corresponding to each artifact. Artifacts in the independent component information can be identified using the preset artifact characteristics.

[0073] Specifically, the independent component analysis (ICA) mathematical model is used to decompose the third EEG signal into different channels, determining the independent component information corresponding to each channel. This mathematical model can be expressed as: X = A·S, where X is the observed EEG signal matrix, A is the mixing matrix, and S is the independent component matrix. Artifacts are removed from each independent component information based on preset artifact characteristics to determine the driver's corresponding second EEG signal.

[0074] On the basis of the above technical solution, "removing artifacts from each independent component information based on preset artifact characteristics to determine the second EEG signal corresponding to the driver" may include: identifying artifacts from each independent component information based on preset artifact characteristics to determine removable artifacts; removing removable artifacts from the third EEG signal based on a preset artifact removal method to determine the second EEG signal corresponding to the driver.

[0075] The removable artifacts may be split into all artifacts identified according to the characteristics. The preset artifact removal method may be a method of resetting the weights corresponding to the independent component information of the removable artifacts to zero.

[0076] Specifically, each independent component information is identified based on preset artifact characteristics (such as time series, scalp topography, and spectral characteristics) to determine the removable artifacts. For example, eye movement artifacts are usually manifested as spike activities of forehead electrodes, while electrocardiogram artifacts are manifested as periodic fluctuations of a specific frequency. Artifact removal is performed by setting the weights corresponding to the independent component information of the removable artifacts to zero, and the second EEG signal corresponding to the driver is determined. After removing the artifacts, the inverse mixing matrix W can be used to reconstruct the clean EEG signal, such as X′=W·X, where W is the inverse mixing matrix obtained by the ICA algorithm and X′ is the second EEG signal after artifact removal.

[0077] It is important to note that after removing artifacts, the quality of the cleaned signal can also be verified to ensure that important neural information has not been mistakenly removed. Finally, the processed data is saved for further analysis.

[0078] S240: Perform feature extraction on the second EEG signal based on a preset feature extraction method to determine EEG features corresponding to the driver.

[0079] S250: Classify the driving intention based on the EEG features and the target classification model to determine the driver's driving intention.

[0080] The technical solution of the embodiment of the present invention is to determine a third EEG signal with noise removed by bandpass filtering the first EEG signal based on a preset frequency filter; and to determine the second EEG signal corresponding to the driver by separating and removing the third EEG signal based on a preset blind source separation method, thereby improving the signal quality, and further improving the accuracy of the EEG characteristics, and further improving the accuracy of the driving intention determination.

[0081] It should be noted that by accurately identifying the driver's driving intentions, brain-controlled vehicles can better predict and respond to changes in the traffic environment, thereby improving driving safety and ride comfort.

[0082] For example, an embodiment of the present invention also provides an optional target classification model training process. The process includes: (1) designing a simulated driving experiment and collecting data; (2) EEG signal preprocessing; (3) feature extraction; (4) training a preset classification model; (5) model evaluation and prediction; and (6) result analysis and parameter adjustment.

[0083] During the design of the simulated driving experiment and data collection process, a series of simulated driving tasks were designed, including straight driving, turning, acceleration, and deceleration, to simulate various situations likely encountered in real driving. This ensured that the experimental environment truly reflected the psychological and physiological state of the driver. Straight driving, turning, acceleration, and deceleration served as model training labels, i.e., driving intentions.

[0084] In the process of training the preset classification model, the extracted features are formed into a feature matrix, each row represents a sample, and each column represents a feature. The label vector corresponds to the feature matrix, and each label represents the category of the corresponding sample. The preset classification model can be a support vector machine (SVM) model. Select a suitable SVM model and kernel function (such as a linear kernel, a polynomial kernel, a radial basis function (RBF) kernel, etc.), and set the key parameters of the SVM model, such as the penalty coefficient C, the kernel function parameters (such as γ of the RBF kernel), and whether to use class weights. Use the training data set (feature matrix and corresponding labels) to train the SVM model, and optimize the model parameters through cross-validation. During the training process, the SVM searches for the hyperplane that maximizes the classification interval while minimizing the classification error.

[0085] During model evaluation and prediction, the trained SVM model is evaluated using the test dataset. Model performance metrics such as accuracy, precision, recall, and F1 score are calculated.

[0086] During the results analysis and parameter adjustment process, SVM model parameters were adjusted using methods such as cross-validation and grid search to achieve optimal model performance. Grid search can be used to determine the optimal parameter combination. Cross-validation can be used to assess the model's stability and generalization capabilities. The specific operations in other steps are the same as those used during model application and are not detailed here.

[0087] After model training is complete, the trained SVM model (i.e., the target classification model) can be applied to new EEG signals to predict driving intention classification. For new samples, the target classification model determines its category by calculating its distance from the hyperplane.

[0088] The following is an embodiment of a device for determining driving intentions of a brain-controlled car provided by an embodiment of the present invention. This device and the methods for determining driving intentions of a brain-controlled car described in the above embodiments belong to the same inventive concept. For details not fully described in the embodiments of the device for determining driving intentions of a brain-controlled car, please refer to the embodiments of the methods for determining driving intentions of a brain-controlled car described above.

[0089] Example 3

[0090] Figure 3 This is a schematic diagram of a device for determining driving intention of a brain-controlled car provided in the third embodiment of the present invention. Figure 3 As shown, the device includes: a first EEG signal acquisition module 310 , a second EEG signal determination module 320 , an EEG feature determination module 330 and a driving intention determination module 340 .

[0091] Among them, the first EEG signal acquisition module 310 is used to obtain the first EEG signal of the driver in the process of driving the vehicle in the brain-controlled car; the second EEG signal determination module 320 is used to pre-process the first EEG signal based on a preset signal processing method to determine the second EEG signal corresponding to the driver; the EEG feature determination module 330 is used to extract features of the second EEG signal based on a preset feature extraction method to determine the EEG features corresponding to the driver; the driving intention determination module 340 is used to classify the driving intention based on the EEG features and the target classification model to determine the driver's driving intention.

[0092] The technical solution of the embodiment of the present invention is to obtain the first EEG signal of the driver in the process of driving the vehicle in a brain-controlled car; pre-process the first EEG signal based on a preset signal processing method to determine the second EEG signal corresponding to the driver; extract features from the second EEG signal based on a preset feature extraction method to determine the EEG features corresponding to the driver; classify the driving intention based on the EEG features and the target classification model to determine the driver's driving intention, so as to accurately and conveniently realize the determination of the driver's driving intention, thereby improving the efficiency and accuracy of the driving intention determination.

[0093] Based on the above technical solution, the second EEG signal determination module 320 may include:

[0094] a third EEG signal determination submodule, configured to perform bandpass filtering on the first EEG signal based on a preset frequency filter to determine a third EEG signal from which noise has been removed;

[0095] The second EEG signal determination submodule is used to separate and remove the third EEG signal based on a preset blind source separation method to determine the second EEG signal corresponding to the driver.

[0096] Based on the above technical solution, the second EEG signal determination submodule may include:

[0097] an independent component information determining unit, configured to perform channel decomposition on the third EEG signal based on a preset independent component decomposition method, and determine independent component information corresponding to each channel;

[0098] The second EEG signal determination unit is configured to remove artifacts from each independent component information based on preset artifact characteristics, and determine a second EEG signal corresponding to the driver.

[0099] Based on the above technical solution, the second EEG signal determination unit is specifically used to: identify artifacts of each independent component information based on preset artifact characteristics, and determine removable artifacts; remove removable artifacts in the third EEG signal based on a preset artifact removal method, and determine the second EEG signal corresponding to the driver.

[0100] On the basis of the above technical solution, the device further includes:

[0101] The signal whitening submodule is used to perform whitening processing on the third EEG signal after noise removal to determine the third EEG signals of each channel that are independent of each other.

[0102] Based on the above technical solution, the EEG feature determination module 330 is specifically used to: extract features from the second EEG signal based on a preset time domain extraction method to determine the time domain features corresponding to the driver; extract features from the second EEG signal based on a preset frequency domain extraction method to determine the frequency domain features corresponding to the driver; extract features from the second EEG signal based on a preset time-frequency domain extraction method to determine the time-frequency domain features corresponding to the driver; and compose the EEG features corresponding to the driver based on time domain features, frequency domain features and time-frequency domain features.

[0103] The brain-controlled car driving intention determination device provided in an embodiment of the present invention can execute the brain-controlled car driving intention determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the brain-controlled car driving intention determination method.

[0104] It is worth noting that in the above-mentioned embodiment of determining the driving intention of a brain-controlled car, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention.

[0105] Example 4

[0106] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0107] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0108] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0109] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for determining driving intention of a brain-controlled vehicle.

[0110] In some embodiments, the method for determining the driving intention of a brain-controlled car can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining the driving intention of a brain-controlled car described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the method for determining the driving intention of a brain-controlled car by any other appropriate means (for example, by means of firmware).

[0111] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0112] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0113] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0114] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0115] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0116] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0117] An embodiment of the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the method for determining the driving intention of a brain-controlled car as provided in any embodiment of the present application.

[0118] During the implementation of the computer program product, the computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or a combination thereof, and the programming language includes an object-oriented programming language, such as Java, Smalltalk, C++, and also includes a conventional procedural programming language, such as "C" language or similar programming language. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). The program product and the method for determining the driving intention of a brain-controlled car disclosed in each embodiment of the present application belong to the same inventive concept, so they are not described here.

[0119] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0120] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for determining driving intention of a brain-controlled car, characterized in that: include: Acquire the first EEG signal of the driver in the brain-controlled car during the driving process; pre-processing the first EEG signal based on a preset signal processing method to determine a second EEG signal corresponding to the driver; performing feature extraction on the second EEG signal based on a preset feature extraction method to determine EEG features corresponding to the driver; Driving intention is classified based on the EEG features and the target classification model to determine the driver's driving intention.

2. The method according to claim 1, characterized in that The pre-processing of the first EEG signal based on a preset signal processing method to determine a second EEG signal corresponding to the driver includes: performing bandpass filtering on the first EEG signal based on a preset frequency filter to determine a third EEG signal from which noise is removed; The third EEG signal is separated and removed based on a preset blind source separation method to determine the second EEG signal corresponding to the driver.

3. The method according to claim 2, characterized in that The step of separating and removing the third EEG signal based on a preset blind source separation method to determine the second EEG signal corresponding to the driver includes: Performing channel decomposition on the third EEG signal based on a preset independent component decomposition method to determine independent component information corresponding to each channel; Artifacts are removed from each of the independent component information based on preset artifact characteristics to determine a second EEG signal corresponding to the driver.

4. The method according to claim 3, characterized in that The performing artifact removal on each of the independent component information based on preset artifact characteristics to determine the second EEG signal corresponding to the driver includes: performing artifact recognition on each of the independent component information based on preset artifact characteristics to determine whether the artifact can be removed; Removable artifacts in the third EEG signal are removed based on a preset artifact removal method to determine a second EEG signal corresponding to the driver.

5. The method according to claim 2, characterized in that Before determining the second EEG signal corresponding to the driver, the method further includes: The third EEG signal after noise removal is whitened to determine the third EEG signals of each channel that are independent of each other.

6. The method according to claim 1, characterized in that The performing feature extraction on the second EEG signal based on a preset feature extraction method to determine the EEG features corresponding to the driver includes: performing feature extraction on the second EEG signal based on a preset time domain extraction method to determine a time domain feature corresponding to the driver; performing feature extraction on the second EEG signal based on a preset frequency domain extraction method to determine frequency domain features corresponding to the driver; Performing feature extraction on the second EEG signal based on a preset time-frequency domain extraction method to determine the time-frequency domain features corresponding to the driver; The EEG features corresponding to the driver are composed based on the time domain features, the frequency domain features and the time-frequency domain features.

7. A device for determining driving intention of a brain-controlled car, characterized in that: The device comprises: A first EEG signal acquisition module is used to acquire a first EEG signal of a driver in a brain-controlled car during driving; a second EEG signal determination module, configured to pre-process the first EEG signal based on a preset signal processing method to determine a second EEG signal corresponding to the driver; an EEG feature determination module, configured to extract features from the second EEG signal based on a preset feature extraction method to determine EEG features corresponding to the driver; The driving intention determination module is used to classify the driving intention based on the EEG features and the target classification model to determine the driver's driving intention.

8. An electronic device, characterized in that: The electronic device comprises: one or more processors; a memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the driving intention of a brain-controlled car as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for determining the driving intention of a brain-controlled car as described in any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When executed by a processor, the computer program implements the method for determining the driving intention of a brain-controlled car as described in any one of claims 1 to 6.

Images