Vehicle control method, apparatus, device, storage medium, and program product

Abstract

The application discloses a vehicle control method, device, equipment, storage medium and program product, and belongs to the technical field of intelligent vehicle control. In the application, an electroencephalogram signal of a driver is acquired, and feature extraction is performed on the electroencephalogram signal to obtain an electroencephalogram signal feature; a driving state category of the driver is determined based on the electroencephalogram signal feature, and the driving state category comprises at least one of a nervous state, a relaxed state and a fatigue state; and an automatic driving control parameter of the vehicle is adjusted based on the driving state category. The application significantly improves driving safety.

Description

Technical Field

[0001] This application relates to the field of vehicle intelligent control technology, and in particular to a vehicle control method, device, equipment, storage medium, and program product. Background Technology

[0002] Against the backdrop of the deep integration of artificial intelligence and intelligent driving, autonomous driving technology is developing from generalization to personalization, and the refined perception of individual differences among drivers is increasingly becoming the focus of industry attention.

[0003] In related technologies, driving strategies are often formulated based on external environmental information and pre-trained models, and driving operations are performed using fixed control parameters.

[0004] Due to the lack of means to identify driver state categories, the relevant technologies cannot dynamically adjust the autonomous driving control parameters, resulting in a disconnect between the driving strategy and the driver's actual state, making it difficult to achieve truly personalized adaptive driving. Summary of the Invention

[0005] This application provides a vehicle control method, apparatus, device, storage medium, and program product, which can solve the problem that existing autonomous driving systems cannot adjust control parameters according to the driver's neurophysiological state, resulting in insufficient driving safety. The technical solution is as follows: On the one hand, a vehicle control method is provided, the method comprising: The driver's electroencephalogram (EEG) signal is acquired, and features are extracted from the EEG signal to obtain EEG signal features; The driver's driving state category is determined based on the EEG signal characteristics, and the driving state category includes at least one of tension, relaxation and fatigue. The vehicle's automatic driving control parameters are adjusted based on the driving state category.

[0006] In one possible implementation, the EEG signal features include the power spectral density of the beta wave, alpha wave, and theta wave frequency bands; determining the driver's driving state category based on the EEG signal features includes: In response to the power spectral density of the β-wave band being greater than or equal to a first specified threshold, the driver's driving state category is determined to be a state of tension. In response to the power spectral density of the alpha wave band being greater than or equal to a second specified threshold, the driver's driving state category is determined to be a relaxed state. If the power spectral density in the theta band is greater than or equal to a third specified threshold, the driver's driving state category is determined to be fatigued.

[0007] In another possible implementation, the vehicle's autonomous driving control parameters include an upper limit value for the vehicle's acceleration; adjusting the vehicle's autonomous driving control parameters based on the driving state category includes: In response to the driver's driving state category being a tense state, the upper limit of the vehicle's acceleration is adjusted to a first specified upper limit value; In response to the driver's driving state category being relaxed, the upper limit of the vehicle's acceleration is adjusted to a second specified upper limit. In response to the driver's driving state being classified as fatigued, the upper limit of the vehicle's acceleration is adjusted to a third specified upper limit. Wherein, the first specified upper limit value and the third specified upper limit value are less than the second specified upper limit value, and the first specified upper limit value is greater than the third specified upper limit value.

[0008] In another possible implementation, the vehicle's autonomous driving control parameters include an upper limit value for the vehicle's steering angular velocity; adjusting the vehicle's autonomous driving control parameters based on the driving state category includes: In response to the driver's driving state category being tense, the upper limit of the vehicle's steering angular velocity is adjusted to the fourth specified upper limit value; In response to the driver's driving state category being relaxed, the upper limit of the vehicle's steering angular velocity is adjusted to the fifth specified upper limit value; In response to the driver's driving state being classified as fatigued, the upper limit of the vehicle's steering angular velocity is adjusted to the sixth specified upper limit. Wherein, the fourth specified upper limit value and the sixth specified upper limit value are less than the fifth specified upper limit value, and the fourth specified upper limit value is greater than the sixth specified upper limit value.

[0009] In another possible implementation, the vehicle's autonomous driving control parameters include the vehicle's collision warning time; adjusting the vehicle's autonomous driving control parameters based on the driving state category includes: In response to the driver's driving state category being a state of tension, the collision warning time of the vehicle is adjusted to a first specified time; In response to the driver's driving state category being relaxed, the collision warning time of the vehicle is adjusted to a second specified time; In response to the driver's driving state being classified as fatigued, the collision warning time of the vehicle is adjusted to a third specified time. Wherein, the first specified time and the third specified time are greater than the second specified time, and the first specified time is less than the third specified time.

[0010] In another possible implementation, the EEG signal features include frequency domain features and time domain features of the beta wave, alpha wave, and theta wave bands; determining the driver's driving state category based on the EEG signal features includes: Based on the frequency domain and time domain characteristics of the β wave, α wave and θ wave frequency bands, an EEG signal feature vector is constructed; The EEG signal feature vector is input into the driving state classification model to obtain the driving state category output by the driving state classification model.

[0011] On the other hand, a vehicle control device is provided, the device comprising: The acquisition module is configured to acquire the driver's electroencephalogram (EEG) signal and extract features from the EEG signal to obtain EEG signal features. A determination module is configured to determine the driver's driving state category based on the EEG signal characteristics, the driving state category including at least one of tension, relaxation and fatigue. An adjustment module is configured to adjust the autonomous driving control parameters of the vehicle based on the driving state category.

[0012] In one possible implementation, the EEG signal features include the power spectral density of the beta wave, alpha wave, and theta wave frequency bands; the determining module is configured to: In response to the power spectral density of the β-wave band being greater than or equal to a first specified threshold, the driver's driving state category is determined to be a state of tension. In response to the power spectral density of the alpha wave band being greater than or equal to a second specified threshold, the driver's driving state category is determined to be a relaxed state. If the power spectral density in the theta band is greater than or equal to a third specified threshold, the driver's driving state category is determined to be fatigued.

[0013] In another possible implementation, the vehicle's autonomous driving control parameters include an upper limit value for the vehicle's acceleration; the adjustment module is configured to: In response to the driver's driving state category being a tense state, the upper limit of the vehicle's acceleration is adjusted to a first specified upper limit value; In response to the driver's driving state category being relaxed, the upper limit of the vehicle's acceleration is adjusted to a second specified upper limit. In response to the driver's driving state being classified as fatigued, the upper limit of the vehicle's acceleration is adjusted to a third specified upper limit. Wherein, the first specified upper limit value and the third specified upper limit value are less than the second specified upper limit value, and the first specified upper limit value is greater than the third specified upper limit value.

[0014] In another possible implementation, the vehicle's autonomous driving control parameters include an upper limit value for the vehicle's steering angular velocity; the adjustment module is further configured to: In response to the driver's driving state category being tense, the upper limit of the vehicle's steering angular velocity is adjusted to the fourth specified upper limit value; In response to the driver's driving state category being relaxed, the upper limit of the vehicle's steering angular velocity is adjusted to the fifth specified upper limit value; In response to the driver's driving state being classified as fatigued, the upper limit of the vehicle's steering angular velocity is adjusted to the sixth specified upper limit. Wherein, the fourth specified upper limit value and the sixth specified upper limit value are less than the fifth specified upper limit value, and the fourth specified upper limit value is greater than the sixth specified upper limit value.

[0015] In another possible implementation, the vehicle's autonomous driving control parameters include the vehicle's collision warning time; the adjustment module is further configured to: In response to the driver's driving state category being a state of tension, the collision warning time of the vehicle is adjusted to a first specified time; In response to the driver's driving state category being relaxed, the collision warning time of the vehicle is adjusted to a second specified time; In response to the driver's driving state being classified as fatigued, the collision warning time of the vehicle is adjusted to a third specified time. Wherein, the first specified time and the third specified time are greater than the second specified time, and the first specified time is less than the third specified time.

[0016] In another possible implementation, the EEG signal features include frequency domain features and time domain features of the beta wave, alpha wave, and theta wave frequency bands; the determining module is used for: Based on the frequency domain and time domain characteristics of the β wave, α wave and θ wave frequency bands, an EEG signal feature vector is constructed; The EEG signal feature vector is input into the driving state classification model to obtain the driving state category output by the driving state classification model.

[0017] On the other hand, a vehicle is provided, including: an electroencephalogram (EEG) signal acquisition device and a vehicle controller, wherein the EEG signal acquisition device is connected to the vehicle controller; The EEG signal acquisition device is used to acquire the driver's EEG signals; The vehicle controller is used to acquire the driver's brain signals collected by the brain signal acquisition device, and to extract features from the brain signals to obtain brain signal features; to determine the driver's driving state category based on the brain signal features, wherein the driving state category includes at least one of tension, relaxation and fatigue; and to adjust the vehicle's automatic driving control parameters based on the driving state category.

[0018] On the other hand, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the program to implement the method described in any of the above.

[0019] On the other hand, a non-transitory computer-readable storage medium is provided, the non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method described in any of the preceding claims.

[0020] On the other hand, a computer program product is provided, including computer program instructions that, when run on a computer, cause the computer to perform the method described in any of the preceding claims.

[0021] The beneficial effects of the technical solution provided in this application are: EEG signals can objectively reflect the driver's cognitive load and emotional state, extract features from them, and determine driving states such as tension, relaxation, or fatigue based on these features, thus realizing the mapping from neural signals to driving states. Since different states correspond to different safety requirements, the automatic driving control parameters can be adjusted accordingly to match the vehicle behavior with the driver's current state, significantly improving driving safety. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram of an implementation environment provided in an embodiment of this application; Figure 2 This is a flowchart of the vehicle control method provided in the embodiments of this application; Figure 3 This is a schematic diagram of the vehicle control device structure provided in the embodiments of this application; Figure 4 This is a schematic diagram of the vehicle structure provided in the embodiments of this application; Figure 5This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0025] This application provides a vehicle control method applied to a vehicle. The vehicle typically includes a vehicle controller. The vehicle controller is used to execute the vehicle control method provided in this application, such as... Figure 1 As shown, in some embodiments, the vehicle controller includes a processor 110, a memory 120, and a communication component 130, etc. The following describes each component separately: The processor 110 may be a central processing unit (CPU), which can be used to execute the vehicle control method described above.

[0026] The memory 120 can be various volatile or non-volatile memory, such as solid-state disk (SSD), dynamic random access memory (DRAM), etc. The memory can be used to store pre-stored data, intermediate data, and result data in the vehicle control processing, such as EEG signal characteristics and driver driving state categories.

[0027] The communication component 130 can be a wired network connector, a wireless fidelity (WiFi) module, a Bluetooth module, a cellular communication module, etc. The communication component can be used to transmit control parameters to control other devices, such as autonomous driving control parameters for a vehicle.

[0028] This application provides a vehicle control method, such as... Figure 2 As shown, in some embodiments, the method includes: S201. Acquire the driver's brainwave signal and extract features from the brainwave signal to obtain brainwave signal features.

[0029] Among them, electroencephalogram (EEG) signals refer to the spontaneous electrophysiological activity signals of the neuronal groups in the driver's brain obtained through EEG acquisition equipment. They reflect the excitation state and neural activity patterns of different brain regions and are objective biomarkers for identifying the driver's psychological and physiological state.

[0030] Feature extraction refers to the process of performing signal processing and mathematical transformations on electroencephalogram (EEG) signals to extract quantitative parameters that characterize the essential properties of the signal from multiple dimensions, including the time domain, frequency domain, and spatial domain. EEG signal features refer to the set of quantitative representations of EEG signals obtained after feature extraction, which can effectively distinguish different driving states. These features include, but are not limited to, power spectral density of different frequency bands, time-domain statistical characteristics, and spatial distribution characteristics.

[0031] In practice, the driver's brainwave signals are first acquired using an EEG acquisition device (such as a 16-channel dry EEG head-mounted device) placed on the driver's head. The sampling rate of the EEG acquisition device can be set to 512Hz, covering core brain regions related to driving attention and emotional state, such as the prefrontal cortex, parietal lobe, and temporal lobe. The acquired EEG signals are first preprocessed, including 0.5-45Hz bandpass filtering to remove power line interference and baseline drift, and independent component analysis algorithms are used to separate and remove motion artifacts such as blinking and head shaking to obtain clean EEG signals.

[0032] Subsequently, feature extraction is performed on the preprocessed EEG signals. Specifically, the continuous EEG signals can be segmented into 2-second time windows with a 50% overlap rate. A Fast Fourier Transform (FFT) is performed on the signals within each time window to calculate the power spectral density of different frequency bands, thus obtaining EEG signal features. In addition to frequency domain features, temporal domain features (such as mean, variance, and kurtosis) and spatial distribution features (such as signal correlation between different brain regions) can be further extracted to construct a multidimensional EEG signal feature vector.

[0033] S202. Determine the driver's driving state category based on the EEG signal characteristics, wherein the driving state category includes at least one of tension state, relaxation state, and fatigue state.

[0034] Among them, the driving state category refers to the classification of the driver's psychological and physiological state during the driving process based on the recognition of EEG signal features. It usually includes tension, relaxation and fatigue. Different categories correspond to different driving behavior characteristics and risk levels.

[0035] In practice, a pre-trained driving state classification model (such as a Support Vector Machine (SVM) or Random Forest classifier) ​​can be used to classify the EEG signal feature vectors, outputting a probability distribution indicating whether the driver is in a tense, relaxed, or fatigued state. The state category with the highest probability is selected as the recognition result. The training process of the classification model can be based on sample data from 300 drivers of different ages, genders, and driving experiences, covering various driving environments such as urban roads, highways, and rural roads, to ensure the model's generalization ability.

[0036] S203. Adjust the automatic driving control parameters of the vehicle based on the driving state category.

[0037] Among them, autonomous driving control parameters refer to the set of configurable parameters used by the autonomous driving system in the process of making decisions such as path planning, vehicle control, and risk warning. The values ​​of these parameters directly affect the driving style, response speed, and safety boundaries of autonomous vehicles.

[0038] In practice, key control parameters such as acceleration, steering, and warning can be dynamically adjusted based on a preset state-parameter mapping relationship. For example, when the driver is determined to be in a tense state, the upper limits of vehicle acceleration and steering angular velocity are reduced, while the collision warning advance time is extended, using a more conservative and stable control strategy to alleviate the driver's tension; when the driver is determined to be in a relaxed state, the restrictions on various control parameters are appropriately relaxed, allowing for more flexible driving operations; when the driver is determined to be in a fatigued state, a more conservative safety strategy is adopted, further reducing the upper limits of motion parameters and significantly extending the warning time.

[0039] In this embodiment, real-time recognition of driving status based on electroencephalogram (EEG) signals is realized. It can objectively perceive changes in the driver's state from a neurophysiological perspective, with higher accuracy and earlier warning time. It can intervene in the early stage of changes in the driver's state, thereby improving driving safety.

[0040] In some embodiments, the EEG signal features include the power spectral density of the beta wave, alpha wave, and theta wave frequency bands; determining the driver's driving state category based on the EEG signal features includes: In response to a power spectral density in the β-band being greater than or equal to a first specified threshold, the driver's driving state category is determined to be a tense state; in response to a power spectral density in the α-band being greater than or equal to a second specified threshold, the driver's driving state category is determined to be a relaxed state; and in response to a power spectral density in the θ-band being greater than or equal to a third specified threshold, the driver's driving state category is determined to be a fatigued state.

[0041] Among them, beta waves refer to the brainwave components in the EEG signal with a frequency range of 13Hz to 30Hz. Beta waves are closely related to the brain's tension. When a driver is under mental stress, highly focused, or in a state of stress, the firing frequency of neurons in the cerebral cortex increases, and the power spectral density of the beta wave band usually increases significantly. Alpha waves refer to the brainwave components in the EEG signal with a frequency range of 8Hz to 13Hz. Alpha waves are most prominent when an individual is awake but relaxed and at rest with their eyes closed, especially in the occipital and parietal lobes where the power is higher. When a driver is relaxed, the brain processes external information more easily, and the power spectral density of the alpha wave band increases accordingly. Theta waves refer to the brainwave components in the EEG signal with a frequency range of 4Hz to 8Hz. Theta waves are associated with drowsiness, lethargy, and inattention. When a driver shows signs of fatigue, the excitability of the cerebral cortex decreases, and the synchronicity of neural activity increases, manifested as an increase in the power spectral density of the theta wave band.

[0042] Power spectral density (PSD) is a physical quantity that describes the distribution of power in an electroencephalogram (EEG) signal in the frequency domain, measured in microvolts squared per hertz (μV² / Hz). PSDD is obtained by performing a frequency domain transformation (such as a Fast Fourier Transform) on the EEG signal, reflecting the proportion of signal energy distributed across different frequency components. The relative relationships and absolute values ​​of PSDD across different frequency bands can be used to quantitatively assess the neurophysiological state of the brain.

[0043] In practice, a Fast Fourier Transform (FFT) is performed on the EEG signal within each time window to obtain the signal's spectral distribution. Then, the spectral amplitude is integrated within three frequency ranges: 13-30Hz, 8-13Hz, and 4-8Hz, respectively, to obtain the power spectral density for each frequency band. To improve feature stability, a moving average is applied to the calculation results of five consecutive time windows to obtain smoothed power spectral density values.

[0044] A first specified threshold, a second specified threshold, and a third specified threshold are preset. The specified thresholds are usually determined based on large sample statistical data. The first specified threshold is set to 1.5 times the average value of the β wave power spectral density under normal relaxation state, the second specified threshold is set to 1.3 times the average value of the α wave power spectral density under normal tension state, and the third specified threshold is set to 1.8 times the average value of the θ wave power spectral density under awake state.

[0045] When the power spectral density of the β-wave band is greater than or equal to a first specified threshold, the driver's driving state is determined to be a state of tension. At this time, the duration of this state can also be recorded; if the state of tension lasts longer than 30 seconds, subsequent parameter adjustment logic is triggered.

[0046] When the power spectral density of the alpha wave band is greater than or equal to a second specified threshold, the driver's driving state is determined to be a relaxed state. Considering that driving in a relaxed state is safer, a longer state duration determination time can be set (e.g., 60 seconds). When the relaxed state reaches 60 seconds, the subsequent parameter adjustment logic is triggered.

[0047] When the power spectral density of the theta wave band is greater than or equal to a third specified threshold, the driver's driving state is determined to be fatigued. Fatigue is directly related to driving safety, so a parameter adjustment strategy can be triggered if the fatigue state lasts for more than 10 seconds.

[0048] In this embodiment, three classic EEG frequency bands—β waves, α waves, and θ waves—are used as state recognition features. The correspondence between these frequency bands and the driver's psychological state has been extensively verified in the field of neuroscience, demonstrating clear physiological significance and high reliability. By setting three independent specified thresholds, quantitative judgment of three driving states is achieved. These thresholds can be calibrated according to individual differences, ensuring both the universality of recognition and taking into account individual variations, thereby improving the accuracy of state recognition.

[0049] In some embodiments, the vehicle's autonomous driving control parameters include the vehicle's upper acceleration limit; adjusting the vehicle's autonomous driving control parameters based on the driving state category includes: In response to the driver's driving state category being tense, the upper limit of the vehicle's acceleration is adjusted to a first specified upper limit; in response to the driver's driving state category being relaxed, the upper limit of the vehicle's acceleration is adjusted to a second specified upper limit; in response to the driver's driving state category being fatigued, the upper limit of the vehicle's acceleration is adjusted to a third specified upper limit; wherein the first specified upper limit and the third specified upper limit are less than the second specified upper limit, and the first specified upper limit is greater than the third specified upper limit.

[0050] In practice, the vehicle's autonomous driving control parameters include the upper limit of the vehicle's acceleration, which controls the maximum longitudinal acceleration of the vehicle during autonomous driving. By default, the upper limit of the vehicle's acceleration can be set to 3.0 m / s².

[0051] When the driver's driving state is classified as "tense," the vehicle's maximum acceleration is adjusted to a first specified upper limit. This first specified upper limit can be set to 2.0 m / s², a 33% reduction compared to the default value. When the driver is tense, a lower maximum acceleration means a smoother acceleration process, preventing the sudden surge of acceleration from further exacerbating the driver's tension. The acceleration adjustment employs a gradual strategy, smoothly transitioning to the target value within 5 seconds to avoid sudden parameter changes that could cause vehicle jerking.

[0052] When the driver's driving state is relaxed, the vehicle's acceleration limit is adjusted to a second specified limit. This second specified limit can be set to 3.5 m / s², a 17% increase compared to the default value. When the driver is relaxed, their psychological tolerance is higher, allowing for more sensitive acceleration responses. A higher acceleration limit enables the autonomous vehicle to exhibit more human-like handling characteristics in scenarios such as overtaking and merging into main roads, thus enhancing the driving experience.

[0053] When the driver's driving state is classified as fatigued, the vehicle's acceleration upper limit is adjusted to a third specified upper limit. This third specified upper limit can be set to 1.5 m / s², a 50% reduction compared to the default value. When the driver is fatigued, their reaction time and judgment decrease, requiring the vehicle to adopt the most conservative control strategy. Slow acceleration changes reduce the driver's cognitive load, lower the probability of needing emergency intervention, and improve driving safety under fatigue conditions.

[0054] The first and third specified upper limit values ​​are less than the second specified upper limit value, and the first specified upper limit value is greater than the third specified upper limit value, reflecting the safety priority in different states: in a relaxed state, controllability is prioritized (highest acceleration upper limit); in a tense state, comfort is prioritized (moderate acceleration upper limit); and in a fatigued state, safety is prioritized (lowest acceleration upper limit).

[0055] At the same time, the upper limit of acceleration can be further adjusted based on the current vehicle speed and road conditions. For example, when cruising on a highway, the upper limit of acceleration in each state can be appropriately increased by 0.3-0.5 m / s² to adapt to the characteristics of high-speed driving; when in congested road sections, the upper limit of acceleration in each state can be appropriately decreased to adapt to road conditions with frequent starts and stops.

[0056] In this embodiment, by dynamically adjusting the vehicle's upper limit of acceleration according to the driving state, personalized adaptive longitudinal handling characteristics are achieved, matching the vehicle's acceleration behavior with the driver's psychological state, ensuring both safety and improved ride comfort. The upper limit of acceleration in the three states forms a reasonable gradient relationship, fully reflecting the design principle of flexibility when relaxed, smoothness when tense, and conservatism when fatigued, which conforms to the psychological laws of human driving behavior.

[0057] In some embodiments, the vehicle's autonomous driving control parameters include the upper limit of the vehicle's steering angular velocity; adjusting the vehicle's autonomous driving control parameters based on the driving state category includes: In response to the driver's driving state category being tense, the upper limit of the vehicle's steering angular velocity is adjusted to a fourth specified upper limit; in response to the driver's driving state category being relaxed, the upper limit of the vehicle's steering angular velocity is adjusted to a fifth specified upper limit; in response to the driver's driving state category being fatigued, the upper limit of the vehicle's steering angular velocity is adjusted to a sixth specified upper limit; wherein the fourth specified upper limit and the sixth specified upper limit are less than the fifth specified upper limit, and the fourth specified upper limit is greater than the sixth specified upper limit.

[0058] In practice, the vehicle's autonomous driving control parameters include the upper limit of the vehicle's steering angular velocity, which controls the maximum value of the steering mechanism's rotational angular velocity during autonomous driving. By default, the upper limit of the vehicle's steering angular velocity can be set to 30° / s, a value that meets the steering requirements of most normal driving scenarios.

[0059] When the driver's driving state is classified as tense, the upper limit of the vehicle's steering angular velocity is adjusted to the fourth specified upper limit. This fourth specified upper limit can be set to 20° / s, a 33% reduction compared to the default value. When the driver is tense, a lower upper limit of steering angular velocity means a smoother steering process and more gentle changes in lateral acceleration, preventing the centrifugal force generated by rapid steering from further exacerbating the driver's tension. Especially in scenarios such as obstacle avoidance and emergency lane changes, smooth steering can reduce the driver's psychological stress response. The steering angular velocity adjustment also employs a gradual strategy, smoothly transitioning to the target value within 3 seconds.

[0060] When the driver's driving state is relaxed, the upper limit of the vehicle's steering angular velocity is adjusted to the fifth specified upper limit. The fifth specified upper limit can be set to 35° / s, which is 17% higher than the default value. When the driver is relaxed, their psychological tolerance and acceptance of vehicle dynamics are stronger, allowing for more sensitive steering responses. A higher steering angular velocity upper limit enables autonomous vehicles to have smoother and more natural handling performance in scenarios such as cornering and lane changing, enhancing the naturalness of the driving experience.

[0061] When the driver's driving state is classified as fatigued, the upper limit of the vehicle's steering angular velocity is adjusted to the sixth specified upper limit. The sixth specified upper limit can be set to 15° / s, which is 50% lower than the default value. When the driver is fatigued, the driver's perception and reaction ability to the vehicle's lateral dynamics decreases, requiring the vehicle to adopt the most conservative steering strategy. Slow changes in steering angular velocity can reduce the driver's cognitive load, reduce the stimulation of the vehicle's lateral dynamics on the driver, and improve driving safety and comfort under fatigue conditions.

[0062] Wherein, the fourth and sixth specified upper limits are less than the fifth specified upper limit, and the fourth specified upper limit is greater than the sixth specified upper limit. In a relaxed state, agility is prioritized (highest steering angular velocity upper limit); in a tense state, stability is prioritized (moderate steering angular velocity upper limit); and in a fatigued state, safety is prioritized (lowest steering angular velocity upper limit), ensuring logical consistency in the adjustment of longitudinal and lateral handling characteristics.

[0063] The upper limit of the steering angle velocity can also be adjusted based on the current vehicle speed and road curvature. For example, when driving at low speed (vehicle speed <30km / h), the upper limit of the steering angle velocity in each state can be appropriately increased to meet the large-angle steering requirements in scenarios such as parking lots and residential areas; when driving at high speed (vehicle speed >80km / h), the upper limit of the steering angle velocity in each state can be appropriately decreased to ensure the stability of high-speed driving.

[0064] In this embodiment, by dynamically adjusting the upper limit of the vehicle's steering angular velocity according to the driving state, personalized adaptive lateral handling characteristics are achieved, matching the vehicle's steering behavior with the driver's psychological state and enhancing the harmony of human-machine co-driving. The gradient configuration of the upper limit of steering angular velocity is consistent with the configuration logic of the upper limit of acceleration, ensuring a unified strategy for adjusting the overall vehicle handling characteristics and avoiding handling confusion caused by inconsistencies in longitudinal and lateral adjustment logic.

[0065] In some embodiments, the vehicle's autonomous driving control parameters include the vehicle's collision warning time; adjusting the vehicle's autonomous driving control parameters based on the driving state category includes: In response to the driver's driving state category being tense, the collision warning time of the vehicle is adjusted to a first specified time; in response to the driver's driving state category being relaxed, the collision warning time of the vehicle is adjusted to a second specified time; in response to the driver's driving state category being fatigued, the collision warning time of the vehicle is adjusted to a third specified time; wherein the first specified time and the third specified time are greater than the second specified time, and the first specified time is less than the third specified time.

[0066] In practice, the vehicle's autonomous driving control parameters include the collision warning time, which controls the triggering timing of the Automatic Emergency Braking (AEB) system and the Forward Collision Warning (FCW) system. By default, the vehicle's collision warning time is set to 2.0 seconds, meaning that a collision warning is triggered when the calculated time to collision (TTC) with an obstacle ahead is less than or equal to 2.0 seconds.

[0067] When the driver's driving state is classified as "tense," the vehicle's collision warning time is adjusted to a first specified time. This first specified time can be set to 2.5 seconds, 0.5 seconds longer than the default value. When a driver is tense, their psychological burden is already heavy, and their ability to cope with unexpected situations decreases. A longer collision warning time means earlier detection of potential risks and issuance of warnings, giving the driver more time for psychological preparation and reaction decisions, preventing further exacerbation of tension due to sudden warnings. During tense driving conditions, the warning method primarily uses relatively mild visual cues (gradual icons on the dashboard), reducing the frequency of audible and vibration warnings.

[0068] When the driver's driving state is relaxed, the collision warning time of the vehicle is adjusted to a second specified time. The second specified time can be set to 1.8 seconds, which is 0.2 seconds shorter than the default value. When the driver is relaxed, their attention and reaction ability are at a good level, enabling them to react to risks in a shorter time. A shorter collision warning time can avoid overly sensitive warnings disturbing the driver's relaxed state. At the same time, since the driver's trust in the vehicle is high in a relaxed state, appropriately delaying the warning will not significantly affect safety.

[0069] When the driver's driving status is classified as fatigued, the collision warning time for the vehicle is adjusted to a third specified time. This third specified time can be set to 3.0 seconds, an extension of 1.0 second compared to the default value. When a driver is fatigued, reaction time is significantly prolonged, and judgment is impaired, requiring the provision of the most sufficient warning time. A longer collision warning time ensures that warnings are issued at the earliest stage of risk development, allowing sufficient reaction time for fatigued drivers. Simultaneously, in a fatigued state, the warning method employs a multimodal approach combining visual, auditory, and vibration warnings to ensure that warning information is effectively conveyed to the driver whose attention has diminished.

[0070] Among these, the first and third specified times are greater than the second specified time, and the first specified time is less than the third specified time. In a relaxed state, priority is given to experience (shortest warning time to reduce disturbance); in a tense state, priority is given to emotional care (moderate warning time to avoid excessive stress); and in a fatigued state, priority is given to safety (longest warning time to fully compensate for decreased reaction time).

[0071] The collision warning time can also be further adjusted based on the current vehicle speed and road type. For example, when driving on a highway, due to the high speed and long braking distance, the collision warning time in all states is uniformly increased by 0.5-1.0 seconds; when driving on congested urban roads, due to the slow speed and close following distance, the collision warning time in all states can be appropriately shortened to avoid frequent false warnings.

[0072] In this embodiment, by dynamically adjusting the vehicle's collision warning time according to the driving state, a personalized and adaptive safety warning strategy is achieved, taking into account the experience needs under different conditions while ensuring a safety baseline. The gradient configuration of the collision warning time complements the configuration logic of acceleration and steering parameters, achieving state adaptation from both active control and risk warning dimensions, thus forming a more complete personalized driving adjustment system.

[0073] In some embodiments, the EEG signal features include frequency domain features and time domain features of the beta wave, alpha wave, and theta wave frequency bands; determining the driver's driving state category based on the EEG signal features includes: Based on the frequency domain and time domain characteristics of the β wave, α wave and θ wave frequency bands, an EEG signal feature vector is constructed; the EEG signal feature vector is input into the driving state classification model to obtain the driving state category output by the driving state classification model.

[0074] In practical implementation, for frequency domain feature extraction, a Fast Fourier Transform is performed on the signal in each time window to calculate the absolute power spectral density, relative power ratio, and power spectral entropy of each frequency band. For time domain feature extraction, bandpass filtering is used to obtain the time-domain waveforms of each frequency band, and statistical features such as mean, variance, standard deviation, kurtosis, and skewness are calculated. All the above features are concatenated in channel order to construct the EEG signal feature vector. The feature vector is then input into a pre-trained support vector machine (driving state classification model). The model outputs the probability distribution of the three states, and the one with the highest probability is selected as the final driving state category.

[0075] In this embodiment, by fusing frequency domain and time domain features, the essential characteristics of EEG signals are characterized from multiple dimensions, reducing the misjudgment rate; by adopting a machine learning classification model, it can automatically learn the complex mapping relationship between different features and driving states, and has stronger generalization ability and adaptability.

[0076] In some embodiments, prior to acquiring the driver's EEG signals, the method further includes: The system acquires EEG signal feature data within a specified historical time period, determines the stability evaluation value of the driver's EEG signal features based on the EEG signal feature data, determines the sampling frequency of the driver's original EEG signal based on the stability evaluation value, and samples the original EEG signal based on the sampling frequency to obtain the driver's EEG signal.

[0077] In practice, EEG signal feature data within a specified historical time period is acquired. This specified historical time period can be set to 300 seconds (5 minutes). EEG signal feature data extracted within the past 300 seconds is retrieved from the historical database, including the power spectral density values ​​of the β wave, α wave, and θ wave frequency bands corresponding to each 2-second time window. If the driver has just started the vehicle and the historical data is less than 300 seconds, the default sampling frequency is used initially, and the adaptive adjustment function is gradually enabled as data accumulates.

[0078] Based on the aforementioned EEG signal feature data, a stability evaluation value for the driver's EEG signal features is determined. First, the coefficient of variation (CV), the ratio of standard deviation to mean, is calculated for the power spectral density time series of each frequency band, characterizing the relative fluctuation of the feature in that frequency band. Then, the CVs of variation for the three frequency bands are averaged to obtain the comprehensive CV. Finally, the comprehensive CV is converted into a stability evaluation value in the 0-1 interval using a mapping function. The mapping relationship is: Stability evaluation value = exp(-k × comprehensive CV), where k is an adjustment coefficient (k = 5 in this embodiment). When the comprehensive CV is 0 (completely stable), the stability evaluation value is 1; as the comprehensive CV increases, the stability evaluation value decreases exponentially. For example, when the comprehensive CV is 0.2, the stability evaluation value is approximately 0.37; when the comprehensive CV is 0.1, the stability evaluation value is approximately 0.61.

[0079] Based on the stability evaluation value, the sampling frequency of the driver's original EEG signal is determined. In this embodiment, the sampling frequency is adjusted from 128Hz to 512Hz. The specific mapping relationship can be set as follows: when the stability evaluation value is ≥0.7, it indicates that the EEG signal characteristics are highly stable. At this time, the sampling frequency is set to 128Hz to reduce system power consumption and computational load; when 0.4≤stability evaluation value<0.7, it indicates that the EEG signal characteristics are moderately stable. At this time, the sampling frequency is set to 256Hz to balance signal quality and system overhead; when the stability evaluation value<0.4, it indicates that the EEG signal characteristics fluctuate greatly and may contain rich state change information. At this time, the sampling frequency is set to 512Hz to improve the signal time resolution to capture subtle state changes.

[0080] Finally, the raw EEG signal is sampled based on the determined sampling frequency to obtain the driver's EEG signal. The EEG acquisition device receives the sampling frequency command issued by the system, adjusts the sampling rate to the target value, and acquires the raw EEG signal at the new sampling frequency. The sampling frequency adjustment interval can be set to 60 seconds to avoid system instability caused by frequent adjustments.

[0081] In this embodiment, adaptive adjustment of the EEG signal sampling frequency is implemented. The sampling strategy is dynamically optimized based on the stability of EEG signal characteristics, effectively reducing system power consumption, data transmission bandwidth, and computational load while ensuring accurate state recognition, thus improving the operating efficiency of the vehicle-mounted system. The adjustment of the sampling frequency is based on the stability evaluation values ​​of historical data, providing clear quantitative evidence and avoiding resource waste or insufficient sampling problems caused by a fixed sampling frequency.

[0082] All of the above-mentioned optional technical solutions can be combined in any way to form the optional embodiments of this application, and will not be described in detail here.

[0083] Based on the same inventive concept, and corresponding to the vehicle control method provided in the embodiments of this application, this application also provides a vehicle control device.

[0084] refer to Figure 3 The vehicle control device includes: The acquisition module 301 is configured to acquire the driver's electroencephalogram (EEG) signal and extract features from the EEG signal to obtain EEG signal features. The determination module 302 is configured to determine the driver's driving state category based on the electroencephalogram (EEG) signal characteristics, the driving state category including at least one of tension, relaxation and fatigue. Adjustment module 303 is configured to adjust the autonomous driving control parameters of the vehicle based on the driving state category.

[0085] In one possible implementation, the EEG signal features include the power spectral density of the beta wave, alpha wave, and theta wave frequency bands; the determining module 302 is used for: In response to the power spectral density of the β-wave band being greater than or equal to a first specified threshold, the driver's driving state category is determined to be a state of tension. In response to the power spectral density of the alpha wave band being greater than or equal to a second specified threshold, the driver's driving state category is determined to be a relaxed state. If the power spectral density in the theta band is greater than or equal to a third specified threshold, the driver's driving state category is determined to be fatigued.

[0086] In another possible implementation, the vehicle's autonomous driving control parameters include the vehicle's upper acceleration limit; the adjustment module 303 is used for: In response to the driver's driving state category being a tense state, the upper limit of the vehicle's acceleration is adjusted to a first specified upper limit value; In response to the driver's driving state category being relaxed, the upper limit of the vehicle's acceleration is adjusted to a second specified upper limit. In response to the driver's driving state being classified as fatigued, the upper limit of the vehicle's acceleration is adjusted to a third specified upper limit. Wherein, the first specified upper limit value and the third specified upper limit value are less than the second specified upper limit value, and the first specified upper limit value is greater than the third specified upper limit value.

[0087] In another possible implementation, the vehicle's autonomous driving control parameters include an upper limit value for the vehicle's steering angular velocity; the adjustment module 303 is further configured to: In response to the driver's driving state category being tense, the upper limit of the vehicle's steering angular velocity is adjusted to the fourth specified upper limit value; In response to the driver's driving state category being relaxed, the upper limit of the vehicle's steering angular velocity is adjusted to the fifth specified upper limit value; In response to the driver's driving state being classified as fatigued, the upper limit of the vehicle's steering angular velocity is adjusted to the sixth specified upper limit. Wherein, the fourth specified upper limit value and the sixth specified upper limit value are less than the fifth specified upper limit value, and the fourth specified upper limit value is greater than the sixth specified upper limit value.

[0088] In another possible implementation, the vehicle's autonomous driving control parameters include the vehicle's collision warning time; the adjustment module 303 is further configured to: In response to the driver's driving state category being a state of tension, the collision warning time of the vehicle is adjusted to a first specified time; In response to the driver's driving state category being relaxed, the collision warning time of the vehicle is adjusted to a second specified time; In response to the driver's driving state being classified as fatigued, the collision warning time of the vehicle is adjusted to a third specified time. Wherein, the first specified time and the third specified time are greater than the second specified time, and the first specified time is less than the third specified time.

[0089] In another possible implementation, the EEG signal features include frequency domain features and time domain features of the beta wave, alpha wave, and theta wave frequency bands; the determining module 302 is used for: Based on the frequency domain and time domain characteristics of the β wave, α wave and θ wave frequency bands, an EEG signal feature vector is constructed; The EEG signal feature vector is input into the driving state classification model to obtain the driving state category output by the driving state classification model.

[0090] It should be noted that the vehicle control device provided in the above embodiments is only illustrated by the division of the above functional modules when controlling the vehicle. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the vehicle control device and the vehicle control method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0091] Based on the same inventive concept, and corresponding to the vehicle control method provided in the embodiments of this application, this application also provides a vehicle, as referenced. Figure 4 The vehicle includes: an electroencephalogram (EEG) signal acquisition device 401 and a vehicle controller 402, wherein the EEG signal acquisition device 401 is connected to the vehicle controller 402; The EEG signal acquisition device 401 is used to acquire the driver's EEG signals; The vehicle controller 401 is used to acquire the driver's brain signals acquired by the brain signal acquisition device 401, and to extract features from the brain signals to obtain brain signal features; to determine the driver's driving state category based on the brain signal features, the driving state category including at least one of tension state, relaxation state and fatigue state; and to adjust the vehicle's automatic driving control parameters based on the driving state category.

[0092] In one possible implementation, the EEG signal features include the power spectral density of the beta wave, alpha wave, and theta wave frequency bands; the vehicle controller 402 is used for: In response to the power spectral density of the β-wave band being greater than or equal to a first specified threshold, the driver's driving state category is determined to be a state of tension. In response to the power spectral density of the alpha wave band being greater than or equal to a second specified threshold, the driver's driving state category is determined to be a relaxed state. If the power spectral density in the theta band is greater than or equal to a third specified threshold, the driver's driving state category is determined to be fatigued.

[0093] In another possible implementation, the vehicle's autonomous driving control parameters include the vehicle's upper acceleration limit; the vehicle controller 402 is used for: In response to the driver's driving state category being a tense state, the upper limit of the vehicle's acceleration is adjusted to a first specified upper limit value; In response to the driver's driving state category being relaxed, the upper limit of the vehicle's acceleration is adjusted to a second specified upper limit. In response to the driver's driving state being classified as fatigued, the upper limit of the vehicle's acceleration is adjusted to a third specified upper limit. Wherein, the first specified upper limit value and the third specified upper limit value are less than the second specified upper limit value, and the first specified upper limit value is greater than the third specified upper limit value.

[0094] In another possible implementation, the vehicle's autonomous driving control parameters include the upper limit of the vehicle's steering angular velocity; the vehicle controller 402 is further configured to: In response to the driver's driving state category being tense, the upper limit of the vehicle's steering angular velocity is adjusted to the fourth specified upper limit value; In response to the driver's driving state category being relaxed, the upper limit of the vehicle's steering angular velocity is adjusted to the fifth specified upper limit value; In response to the driver's driving state being classified as fatigued, the upper limit of the vehicle's steering angular velocity is adjusted to the sixth specified upper limit. Wherein, the fourth specified upper limit value and the sixth specified upper limit value are less than the fifth specified upper limit value, and the fourth specified upper limit value is greater than the sixth specified upper limit value.

[0095] In another possible implementation, the vehicle's autonomous driving control parameters include the vehicle's collision warning time; the vehicle controller 402 is further configured to: In response to the driver's driving state category being a state of tension, the collision warning time of the vehicle is adjusted to a first specified time; In response to the driver's driving state category being relaxed, the collision warning time of the vehicle is adjusted to a second specified time; In response to the driver's driving state being classified as fatigued, the collision warning time of the vehicle is adjusted to a third specified time. Wherein, the first specified time and the third specified time are greater than the second specified time, and the first specified time is less than the third specified time.

[0096] In another possible implementation, the EEG signal features include frequency domain features and time domain features of the beta wave, alpha wave, and theta wave frequency bands; the vehicle controller 402 is used for: Based on the frequency domain and time domain characteristics of the β wave, α wave and θ wave frequency bands, an EEG signal feature vector is constructed; The EEG signal feature vector is input into the driving state classification model to obtain the driving state category output by the driving state classification model.

[0097] The vehicle and vehicle control method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0098] Based on the same inventive concept, corresponding to the vehicle control method provided in the embodiments of this application, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the vehicle control method described in the above embodiments.

[0099] Figure 5 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0100] The processor 1010 can be implemented using a general-purpose CPU (central processing unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0101] The memory 1020 can be implemented in the form of ROM (read-only memory), RAM (random access memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0102] The input / output interface 1030 is used to connect input / output modules to realize information input and output. The input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.

[0103] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0104] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0105] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0106] The electronic devices described above are used to implement the corresponding vehicle control methods in the foregoing embodiments and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0107] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including instructions that can be executed by a processor in a terminal to perform the vehicle control method described above. This computer-readable storage medium can be non-transitory. For example, the computer-readable storage medium can be ROM (read-only memory), RAM (random access memory), CD-ROM (compact disc read-only memory), magnetic tape, floppy disk, and optical data storage devices, etc.

[0108] In an exemplary embodiment, a computer program product is also provided, including computer program instructions that, when executed on a computer, cause the computer to perform the vehicle control method described above.

[0109] It should be noted that the information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to data used for analysis, data stored, data displayed, etc.) and signals (including but not limited to signals transmitted between user terminals and other devices, etc.) involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0110] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0111] It should be understood that "multiple" as used herein refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. Furthermore, the step numbers described herein are merely illustrative of one possible execution order. In some other embodiments, the steps may not be executed in numerical order, such as two steps with different numbers being executed simultaneously, or two steps with different numbers being executed in the reverse order of the illustration. This application does not limit this.

[0112] The above description is merely an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A vehicle control method, characterized in that, include: The driver's electroencephalogram (EEG) signal is acquired, and features are extracted from the EEG signal to obtain EEG signal features; The driver's driving state category is determined based on the EEG signal characteristics, and the driving state category includes at least one of tension, relaxation and fatigue. The vehicle's automatic driving control parameters are adjusted based on the driving state category.

2. The vehicle control method according to claim 1, characterized in that, The EEG signal features include the power spectral density of the beta wave, alpha wave, and theta wave frequency bands; determining the driver's driving state category based on the EEG signal features includes: In response to the power spectral density of the β-wave band being greater than or equal to a first specified threshold, the driver's driving state category is determined to be a state of tension. In response to the power spectral density of the alpha wave band being greater than or equal to a second specified threshold, the driver's driving state category is determined to be a relaxed state. If the power spectral density in the theta band is greater than or equal to a third specified threshold, the driver's driving state category is determined to be fatigued.

3. The vehicle control method according to claim 2, characterized in that, The vehicle's autonomous driving control parameters include the vehicle's maximum acceleration value; adjusting the vehicle's autonomous driving control parameters based on the driving state category includes: In response to the driver's driving state category being a tense state, the upper limit of the vehicle's acceleration is adjusted to a first specified upper limit value; In response to the driver's driving state category being relaxed, the upper limit of the vehicle's acceleration is adjusted to a second specified upper limit. In response to the driver's driving state being classified as fatigued, the upper limit of the vehicle's acceleration is adjusted to a third specified upper limit. Wherein, the first specified upper limit value and the third specified upper limit value are less than the second specified upper limit value, and the first specified upper limit value is greater than the third specified upper limit value.

4. The vehicle control method according to claim 2, characterized in that, The vehicle's autonomous driving control parameters include the upper limit of the vehicle's steering angular velocity; The adjustment of the vehicle's autonomous driving control parameters based on the driving state category includes: In response to the driver's driving state category being tense, the upper limit of the vehicle's steering angular velocity is adjusted to the fourth specified upper limit value; In response to the driver's driving state category being relaxed, the upper limit of the vehicle's steering angular velocity is adjusted to the fifth specified upper limit value; In response to the driver's driving state being classified as fatigued, the upper limit of the vehicle's steering angular velocity is adjusted to the sixth specified upper limit. Wherein, the fourth specified upper limit value and the sixth specified upper limit value are less than the fifth specified upper limit value, and the fourth specified upper limit value is greater than the sixth specified upper limit value.

5. The vehicle control method according to claim 2, characterized in that, The vehicle's autonomous driving control parameters include the vehicle's collision warning time; The adjustment of the vehicle's autonomous driving control parameters based on the driving state category includes: In response to the driver's driving state category being a state of tension, the collision warning time of the vehicle is adjusted to a first specified time; In response to the driver's driving state category being relaxed, the collision warning time of the vehicle is adjusted to a second specified time; In response to the driver's driving state being classified as fatigued, the collision warning time of the vehicle is adjusted to a third specified time. Wherein, the first specified time and the third specified time are greater than the second specified time, and the first specified time is less than the third specified time.

6. The vehicle control method according to claim 1, characterized in that, The EEG signal characteristics include frequency domain characteristics and time domain characteristics of the β wave, α wave and θ wave frequency bands; Determining the driver's driving state category based on the EEG signal features includes: Based on the frequency domain and time domain characteristics of the β wave, α wave and θ wave frequency bands, an EEG signal feature vector is constructed; The EEG signal feature vector is input into the driving state classification model to obtain the driving state category output by the driving state classification model.

7. A vehicle control device, characterized in that, include: The acquisition module is configured to acquire the driver's electroencephalogram (EEG) signal and extract features from the EEG signal to obtain EEG signal features. A determination module is configured to determine the driver's driving state category based on the EEG signal characteristics, the driving state category including at least one of tension, relaxation and fatigue. An adjustment module is configured to adjust the autonomous driving control parameters of the vehicle based on the driving state category.

8. A vehicle, characterized in that, include: The electroencephalogram (EEG) signal acquisition device and the vehicle controller are connected to the EEG signal acquisition device. The EEG signal acquisition device is used to acquire the driver's EEG signals; The vehicle controller is used to acquire the driver's brain signals acquired by the brain signal acquisition device, and to extract features from the brain signals to obtain brain signal features. The driver's driving state category is determined based on the EEG signal characteristics, and the driving state category includes at least one of tension, relaxation and fatigue; the automatic driving control parameters of the vehicle are adjusted based on the driving state category.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method described in any one of claims 1 to 6.

10. A computer program product comprising computer program instructions, characterized in that, When the computer program instructions are executed on a computer, the computer causes the computer to perform the method as described in any one of claims 1 to 6.

Images