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

Abstract

This application discloses a vehicle control method, device, vehicle, storage medium, and program product, belonging to the field of vehicle intelligent control technology. In this application, the steering correction angle predicted by the vehicle's autonomous driving system and the corresponding prediction confidence level are obtained; in response to the prediction confidence level being less than or equal to a specified confidence level, the driver's electroencephalogram (EEG) signal is obtained, and feature extraction is performed on the EEG signal to obtain EEG signal features; based on the EEG signal features and the prediction confidence level, a reliability evaluation value for the steering correction angle is determined, and if the reliability evaluation value is greater than or equal to the specified evaluation value, a steering operation corresponding to the steering correction angle is executed. This application significantly improves vehicle 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, vehicle, storage medium, and program product. Background Technology

[0002] With the development of autonomous driving technology, the ability to dynamically correct steering during vehicle operation is becoming increasingly important. When a vehicle detects a deviation from its trajectory, changes in road conditions, or unexpected situations, it needs to anticipate steering correction needs in real time and make reliable decisions to ensure driving safety.

[0003] Currently, autonomous driving steering correction is mostly based on multi-source sensor data to predict the steering correction angle, along with a confidence assessment mechanism. When the prediction confidence level meets the standard, the correction operation is performed to maintain the stability of the driving trajectory.

[0004] However, when the prediction confidence level is below a threshold, correction is usually abandoned or forced into execution. Abandoning correction may lead to trajectory deviation or missed hazard avoidance opportunities, while forced execution may compromise vehicle driving safety due to insufficient reliability of the decision. Summary of the Invention

[0005] This application provides a vehicle control method, device, vehicle, storage medium, and program product, which can solve the problem of poor steering correction accuracy in vehicle autonomous driving systems. The technical solution is as follows: On the one hand, a vehicle control method is provided, the method comprising: Obtain the steering correction angle predicted by the autonomous driving system of the vehicle and the corresponding prediction confidence level; In response to the prediction confidence being less than or equal to a specified confidence level, the driver's EEG signal is acquired, and feature extraction is performed on the EEG signal to obtain EEG signal features; Based on the EEG signal characteristics and the prediction confidence level, a reliability evaluation value for the steering correction angle is determined, and if the reliability evaluation value is greater than or equal to the specified evaluation value, a steering operation corresponding to the steering correction angle is executed.

[0006] In one possible implementation, the EEG signal features include the power spectral density of the alpha and beta wave bands; determining the reliability evaluation value for the steering correction angle based on the EEG signal features and the prediction confidence includes: The ratio of the power spectral density of the α-wave to the β-wave frequency band is determined, and a reliability evaluation value for the steering correction angle is determined based on the ratio and the prediction confidence level.

[0007] In another possible implementation, determining the reliability evaluation value for the steering correction angle based on the ratio and the prediction confidence level includes: The influence coefficient of the prediction confidence is determined based on the ratio and the specified mapping relationship, wherein the ratio is negatively correlated with the influence coefficient; The product of the influence coefficient and the prediction confidence level is used as the reliability evaluation value of the steering correction angle.

[0008] In another possible implementation, performing the steering operation corresponding to the steering correction angle includes: An execution coefficient is determined based on the difference between the reliability evaluation value and the specified evaluation value, and the execution coefficient is positively correlated with the difference; The product of the steering correction angle and the execution coefficient is taken as the actual steering angle, and the steering operation corresponding to the actual steering angle is executed.

[0009] In another possible implementation, performing the steering operation corresponding to the actual steering angle includes: In response to the actual steering angle being greater than or equal to the specified upper limit of steering angle, a steering operation corresponding to the upper limit of steering angle is performed.

[0010] In another possible implementation, performing the steering operation corresponding to the actual steering angle includes: The steering angular velocity is determined based on the difference between the reliability evaluation value and the specified evaluation value, wherein the difference is positively correlated with the steering angular velocity; Perform a steering operation corresponding to the actual steering angle based on the steering angular velocity.

[0011] On the other hand, a vehicle control device is provided, the device comprising: The acquisition module is configured to acquire the steering correction angle predicted by the autonomous driving system of the vehicle and the corresponding prediction confidence. The feature extraction module is configured to acquire the driver's EEG signal in response to the prediction confidence being less than or equal to a specified confidence, and to extract features from the EEG signal to obtain EEG signal features. An execution module is configured to determine a reliability evaluation value for the steering correction angle based on the EEG signal features and the prediction confidence, and to perform a steering operation corresponding to the steering correction angle if the reliability evaluation value is greater than or equal to a specified evaluation value.

[0012] In one possible implementation, the EEG signal features include the power spectral density of the alpha and beta wave bands; the execution module is configured to: The ratio of the power spectral density of the α-wave to the β-wave frequency band is determined, and a reliability evaluation value for the steering correction angle is determined based on the ratio and the prediction confidence level.

[0013] In another possible implementation, the execution module is used for: The influence coefficient of the prediction confidence is determined based on the ratio and the specified mapping relationship, wherein the ratio is negatively correlated with the influence coefficient; The product of the influence coefficient and the prediction confidence level is used as the reliability evaluation value of the steering correction angle.

[0014] In another possible implementation, the execution module is used for: An execution coefficient is determined based on the difference between the reliability evaluation value and the specified evaluation value, and the execution coefficient is positively correlated with the difference; The product of the steering correction angle and the execution coefficient is taken as the actual steering angle, and the steering operation corresponding to the actual steering angle is executed.

[0015] In another possible implementation, the execution module is used for: In response to the actual steering angle being greater than or equal to the specified upper limit of steering angle, a steering operation corresponding to the upper limit of steering angle is performed.

[0016] In another possible implementation, the execution module is used for: The steering angular velocity is determined based on the difference between the reliability evaluation value and the specified evaluation value, wherein the difference is positively correlated with the steering angular velocity; Perform a steering operation corresponding to the actual steering angle based on the steering angular velocity.

[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 steering correction angle predicted by the vehicle's autonomous driving system and the corresponding prediction confidence level; in response to the prediction confidence level being less than or equal to a specified confidence level, it acquires the driver's brain signals acquired by the brain signal acquisition device, and performs feature extraction on the brain signals to obtain brain signal features; based on the brain signal features and the prediction confidence level, it determines a reliability evaluation value for the steering correction angle, and if the reliability evaluation value is greater than or equal to the specified evaluation value, it executes a steering operation corresponding to the steering correction angle.

[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 as follows: when the prediction confidence is low, the driver's brain signals are used as an auxiliary decision-making basis to conduct a reliability assessment of the steering correction angle. If the reliability evaluation value meets the standard, the corresponding correction operation is executed, thereby avoiding missing the opportunity to avoid danger and preventing control conflicts or safety risks caused by forced execution, thus significantly improving the driving safety of the vehicle. 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 5 This 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] As autonomous driving technology continues to evolve from assisted driving to higher levels of autonomous driving, the ability of a vehicle to autonomously maintain its driving trajectory in complex traffic environments has become a key technical indicator for measuring the performance of autonomous driving systems. During vehicle operation, due to the combined effects of various factors such as road surface unevenness, crosswind disturbances, changes in tire adhesion, and uncertainties in sensor perception, deviations inevitably occur between the vehicle's actual driving trajectory and its planned trajectory. Therefore, dynamic steering correction, as a core technology for maintaining vehicle lateral stability and ensuring driving safety, is becoming increasingly important. When the vehicle detects trajectory deviation, changes in road conditions, or sudden situations, the autonomous driving system must anticipate steering correction needs in real time and make reliable decisions. The accuracy and timeliness of these decisions directly affect driving safety.

[0026] Currently, autonomous driving steering correction technology in the industry mainly relies on prediction models driven by multi-source sensor data fusion. Multi-source sensors typically include, but are not limited to, cameras, millimeter-wave radar, lidar, high-precision positioning modules, and vehicle dynamics sensors. Autonomous driving systems fuse environmental perception data and vehicle state data collected by these multi-source sensors, using deep learning networks or traditional control algorithms to predict the steering correction angle, and employ a confidence assessment mechanism to quantify the reliability of the prediction results. The confidence assessment mechanism generally calculates the prediction confidence based on multi-dimensional information such as the model's output probability distribution, the consistency test results of sensor data, and historical prediction error statistics. When the prediction confidence exceeds a preset threshold, the autonomous driving system determines that the current prediction result is reliable and executes the corresponding steering correction operation to maintain a stable driving trajectory.

[0027] However, the aforementioned technical solutions have significant limitations when dealing with situations where the prediction confidence level is below a threshold. When the prediction confidence level is below the threshold, existing systems typically adopt two extreme strategies: first, directly abandoning the steering correction operation, completely transferring vehicle control to the driver or maintaining the current steering state; second, ignoring the risk warning of insufficient confidence and forcibly executing the steering correction operation. The strategy of directly abandoning correction may lead to the vehicle trajectory continuously deviating from the planned path in scenarios such as complex driving environments, driver inattention, or emergency situations, potentially missing critical avoidance opportunities and causing collisions. The strategy of forcibly executing correction ignores the underlying technical nature of low confidence levels, including sensor data conflicts, blurred environmental perception, or increased uncertainty in model predictions. Rashly executing a steering operation with insufficient reliability may lead to sudden changes in vehicle attitude and impaired driving stability, thus posing a threat to vehicle safety.

[0028] 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 1As 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.

[0029] 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 during the vehicle control processing, such as EEG signal characteristics.

[0030] The communication component 130 can be a wired network connector, a wireless fidelity (WiFi) module, a Bluetooth module, a cellular network communication module, etc. The communication component can be used to transmit acquired signals from the device, such as acquiring the driver's brainwave signals collected by an EEG signal acquisition device.

[0031] This application provides a vehicle control method, such as... Figure 2 As shown, in some embodiments, the method includes: S201. Obtain the steering correction angle predicted by the vehicle's autonomous driving system and the corresponding prediction confidence level.

[0032] The steering correction angle refers to the steering angle value predicted by the vehicle's autonomous driving system based on multi-source sensor data to correct the vehicle's driving direction in response to trajectory deviations, road condition changes, or sudden situations detected during vehicle operation. For example, a hybrid model composed of convolutional neural networks and long short-term memory networks can predict obstacle trajectories and future deviation trends, thereby calculating the steering correction angle required for emergency avoidance. The prediction confidence level refers to the confidence assessment value output by the vehicle's autonomous driving system for the steering correction angle, used to characterize the predictive reliability of the steering correction angle.

[0033] In practice, the vehicle's autonomous driving system continuously monitors the vehicle's driving status during operation. When the autonomous driving system detects a trajectory deviation trend, it predicts a steering correction angle based on multi-source sensor data and outputs the prediction confidence level corresponding to that steering correction angle.

[0034] S202. In response to the prediction confidence being less than or equal to a specified confidence, the driver's EEG signal is acquired, and the EEG signal is used to extract features to obtain EEG signal features.

[0035] Here, the specified confidence level refers to a pre-set confidence threshold used to determine whether the predicted confidence level needs further evaluation in conjunction with the driver's EEG signals. For example, it can be set to 0.9. EEG signals refer to the electrophysiological signals generated by the activity of neurons in the driver's brain, acquired through an EEG signal acquisition device deployed on the driver's head. EEG signal features refer to quantitative feature parameters that reflect the driver's brain activity state obtained after feature extraction from the EEG signals.

[0036] In practice, the vehicle control system compares the predicted confidence level with a specified confidence level. When the predicted confidence level is greater than the specified confidence level, it indicates that the prediction reliability of the steering correction angle is sufficient, and the steering operation corresponding to the steering correction angle is directly executed.

[0037] When the predicted confidence level is less than or equal to the specified confidence level, it indicates that the predicted reliability of the steering correction angle is insufficient. In this case, the EEG signal acquisition device is activated to acquire the driver's EEG signal. The EEG signal acquisition device can acquire EEG signals through electrodes deployed in the driver's frontal and parietal lobes. Then, the EEG signals are filtered, denoised, and subjected to spectral analysis to obtain EEG signal characteristics.

[0038] S203. Based on the EEG signal characteristics and the prediction confidence, determine the reliability evaluation value for the steering correction angle, and if the reliability evaluation value is greater than or equal to the specified evaluation value, perform the steering operation corresponding to the steering correction angle.

[0039] The reliability evaluation value refers to a quantitative value determined by combining the EEG signal features and the prediction confidence level, used to evaluate the decision reliability of the steering correction angle. The specified evaluation value refers to a pre-set reliability evaluation value threshold, used to determine whether to perform the steering operation corresponding to the steering correction angle; for example, it can be set to 0.6.

[0040] In specific implementation, a reliability evaluation value for the steering correction angle is determined based on the EEG signal characteristics and the prediction confidence level. The driver's attention state and cognitive load level can be assessed based on the EEG signal characteristics, and the reliability evaluation value is calculated in conjunction with the prediction confidence level. The reliability evaluation value is compared with a specified evaluation value. When the reliability evaluation value is greater than or equal to the specified evaluation value, it indicates that although the prediction confidence level is low, the decision to determine the steering correction angle based on the driver's overall EEG signal state still has sufficient decision reliability; in this case, the steering operation corresponding to the steering correction angle is executed. When the reliability evaluation value is less than the specified evaluation value, the steering operation corresponding to the steering correction angle is not executed.

[0041] In this embodiment, when the predicted confidence level is less than or equal to the specified confidence level, the reliability of the steering correction angle is reassessed by introducing the driver's electroencephalogram (EEG) signal. This allows for a more reliable decision-making process by combining the driver's physiological state information when the autonomous driving system's predictive reliability is insufficient. This avoids issues such as trajectory deviation or missed hazard avoidance opportunities caused by abandoning correction, and also prevents the impact on vehicle driving safety caused by forcibly executing correction operations with insufficient reliability. Therefore, it effectively improves the safety and reliability of vehicle steering control.

[0042] In some embodiments, the EEG signal features include the power spectral density of the alpha and beta wave bands; determining the reliability evaluation value for the steering correction angle based on the EEG signal features and the prediction confidence includes: The ratio of the power spectral density of the α-wave to the β-wave frequency band is determined, and a reliability evaluation value for the steering correction angle is determined based on the ratio and the prediction confidence level.

[0043] Alpha waves refer to the brainwave components in the EEG signal with a frequency range of 8 Hz to 13 Hz, and are typically prominent when the driver is relaxed, awake, and has their eyes closed. Beta waves refer to the brainwave components in the EEG signal with a frequency range of 14 Hz to 30 Hz, and are typically prominent when the driver is tense, anxious, or mentally active. Power spectral density refers to the power distribution density of the EEG signal within a specific frequency band, used to quantify the energy intensity of the alpha and beta wave frequency bands.

[0044] In practice, the ratio of the power spectral density of the α-wave band to the power spectral density of the β-wave band is first calculated. Then, based on this ratio and the predicted confidence level, a reliability evaluation value for the steering correction angle is determined. When the ratio is small, it indicates that the power spectral density of the β-wave band is relatively high compared to the α-wave band, reflecting that the driver is in a tense and focused state, and the vehicle may pose a certain driving risk. In this case, the reliability evaluation value determined by combining the predicted confidence level is correspondingly high. When the ratio is large, it indicates that the power spectral density of the α-wave band is relatively high compared to the β-wave band, reflecting that the driver is in a relatively relaxed or distracted state, indicating that the vehicle's driving safety is high. In this case, the reliability evaluation value determined by combining the predicted confidence level is correspondingly low.

[0045] In this embodiment, by using the power spectral density of the alpha and beta wave frequency bands as EEG signal features, the ratio of the power spectral density of the alpha wave to that of the beta wave frequency band reflects the driver's attention state, providing an objective and quantitative physiological indicator basis for determining the reliability evaluation value. The ratio of the power spectral density of the alpha wave to that of the beta wave frequency band can effectively distinguish between the driver's level of concentration and relaxation, making the determination of the reliability evaluation value more closely reflect the driver's actual cognitive state, thereby improving the accuracy and reliability of steering control decisions when the prediction confidence is insufficient.

[0046] In some embodiments, determining the reliability evaluation value for the steering correction angle based on the ratio and the predicted confidence level includes: The influence coefficient of the predicted confidence level is determined based on the ratio and the specified mapping relationship, and the ratio is negatively correlated with the influence coefficient; the product of the influence coefficient and the predicted confidence level is used as the reliability evaluation value of the steering correction angle.

[0047] In practice, the specified mapping relationship can be a lookup table or a function mapping relationship. The vehicle control system typically stores a pre-defined table of correspondence between the ratio and the influence coefficient, where the ratio and influence coefficient are negatively correlated. For example, when the ratio is 0.5, the corresponding influence coefficient is 0.9; when the ratio is 1.0, the corresponding influence coefficient is 0.6; and when the ratio is 2.0, the corresponding influence coefficient is 0.3. The larger the ratio, the smaller the corresponding influence coefficient.

[0048] Based on the calculated ratio, the corresponding influence coefficient is determined by looking up a table or using a function. The product of the influence coefficient and the predicted confidence level is used as the reliability evaluation value of the steering correction angle. Specifically, the reliability evaluation value is equal to the influence coefficient multiplied by the predicted confidence level. Since the influence coefficient is negatively correlated with the ratio, when the driver is tense, anxious, and focused (the ratio is smaller), the influence coefficient is larger, and the reliability evaluation value is larger; when the driver is relaxed and distracted (the ratio is larger), the influence coefficient is smaller, and the reliability evaluation value is smaller.

[0049] In this embodiment, by using a pre-established mapping relationship, the driver's EEG state is quantified as a modulating factor on the predicted confidence level, thus achieving dynamic modulation of the driver's physiological state on the decision reliability of the autonomous driving system. The negative correlation between the influence coefficient and the ratio ensures that the more focused the driver's attention, the higher their tolerance for low-confidence steering correction angles, and vice versa. This makes the reliability evaluation value more accurately reflect the decision reliability in the human-machine collaborative state, further ensuring vehicle driving safety.

[0050] In some embodiments, performing the steering operation corresponding to the steering correction angle includes: An execution coefficient is determined based on the difference between the reliability evaluation value and the specified evaluation value, and the execution coefficient is positively correlated with the difference; the product of the steering correction angle and the execution coefficient is taken as the actual steering angle, and a steering operation corresponding to the actual steering angle is performed.

[0051] The execution coefficient refers to the coefficient used to adjust the actual degree of execution of the steering correction angle, and the value of the execution coefficient ranges from 0 to 1. The actual steering angle refers to the steering angle value obtained by multiplying the steering correction angle by the execution coefficient, which is used to actually execute steering control.

[0052] In practice, the difference between the reliability evaluation value and the specified evaluation value is first calculated. An execution coefficient is determined based on this difference, and the execution coefficient is positively correlated with the difference. Specifically, the vehicle control system can determine the execution coefficient using a linear or nonlinear mapping method. For example, when the difference is 0, the execution coefficient is 0.5; when the difference reaches a preset maximum value (e.g., 0.3), the execution coefficient is 1.0. The larger the difference, the larger the execution coefficient.

[0053] The product of the steering correction angle and the execution coefficient is taken as the actual steering angle. For example, when the steering correction angle is 15 degrees and the execution coefficient is 0.8, the actual steering angle is 12 degrees. Finally, the steering operation corresponding to the actual steering angle is executed, that is, the vehicle's steering system is controlled to perform the steering action according to the actual steering angle.

[0054] In this embodiment, by introducing an execution coefficient, smooth execution control of the steering correction angle is achieved. The execution coefficient is positively correlated with the difference, meaning that the greater the degree to which the reliability evaluation value exceeds the specified evaluation value, the closer the actual steering angle is to the steering correction angle; conversely, the smaller the degree of exceedance, the greater the attenuation of the actual steering angle relative to the steering correction angle. This avoids the risks that may arise from fully executing the steering correction angle under low reliability margins, achieving an adaptive match between steering control strength and decision reliability, thus improving the smoothness and safety of steering control.

[0055] In some embodiments, performing the steering operation corresponding to the actual steering angle includes: In response to the actual steering angle being greater than or equal to the specified upper limit of steering angle, a steering operation corresponding to the upper limit of steering angle is performed.

[0056] The upper limit of the steering angle refers to the maximum allowable value of the actual steering angle that is preset, which is used to limit the maximum steering range when the vehicle control system performs steering operations.

[0057] In practice, the upper limit of the steering angle is preset based on the vehicle's current speed, road surface adhesion coefficient, and vehicle dynamics characteristics. For example, when the vehicle speed is 60 km / h, the upper limit of the steering angle is set to 20 degrees; when the vehicle speed is 120 km / h, the upper limit of the steering angle is set to 10 degrees. When the actual steering angle is less than the upper limit, the steering operation corresponding to the actual steering angle is executed directly. When the actual steering angle is greater than or equal to the upper limit, the steering operation corresponding to the actual steering angle is not executed; instead, the steering operation corresponding to the upper limit is executed. In other words, the steering operation is performed after the actual steering angle is limited to the upper limit.

[0058] In this embodiment, by setting the upper limit of the steering angle, a safety boundary constraint is imposed on the actual steering angle. Even when the reliability evaluation value is high, oversteering caused by excessive steering correction angle or abnormal calculation of the execution coefficient can be prevented, avoiding the risk of vehicle instability or loss of control due to excessive steering amplitude, and further improving the active safety of vehicle driving.

[0059] In some embodiments, performing the steering operation corresponding to the actual steering angle includes: The steering angular velocity is determined based on the difference between the reliability evaluation value and the specified evaluation value, and the difference is positively correlated with the steering angular velocity; a steering operation corresponding to the actual steering angle is performed based on the steering angular velocity.

[0060] Among them, steering angular velocity refers to the rate of change of angle when the vehicle steering system performs steering operation, that is, how fast the steering angle changes per unit time.

[0061] In specific implementation, the steering angular velocity is determined based on the difference between the reliability evaluation value and the specified evaluation value, where the difference is positively correlated with the steering angular velocity. The steering angular velocity is determined according to a preset mapping relationship. For example, when the difference is 0, the steering angular velocity is set to 15 degrees / second; when the difference reaches a preset maximum value (0.3), the steering angular velocity is set to 45 degrees / second. The larger the difference, the larger the steering angular velocity; the smaller the difference, the smaller the steering angular velocity. The vehicle control system controls the steering system to perform steering actions according to the actual steering angle as the target angle and the steering angular velocity as the rate of change.

[0062] In this embodiment, the steering angular velocity is determined based on the difference, thereby achieving adaptive adjustment of the steering execution rate. The difference is positively correlated with the steering angular velocity, allowing for faster steering operation when the reliability evaluation value is significantly higher than the specified evaluation value, quickly responding to changes in driving conditions; conversely, when the reliability evaluation value just reaches the specified evaluation value, a slower steering operation is performed, maintaining a smooth and controllable steering process. This balances the timeliness of steering response with the comfort of the steering process, effectively improving the overall quality of human-machine cooperative steering control.

[0063] In some embodiments, the method further includes: during the process of acquiring the driver's EEG signal and extracting EEG signal features when the prediction confidence is less than or equal to the specified confidence, performing a temporal sliding window analysis on the EEG signal to predict the migration trend of the driver's cognitive state.

[0064] Specifically, taking the current moment as the endpoint, a 3-5 second segment of EEG signal is extracted as an analysis window. The EEG signal within this window is then segmented second by second to obtain multiple consecutive time-segment EEG signal segments. For each EEG signal segment, the power spectral density of the alpha wave band and the power spectral density of the beta wave band are extracted. The ratio of the power spectral density of the alpha wave to the power spectral density of the beta wave band in each time segment is calculated to obtain a ratio time series. When the ratio time series shows a continuous downward trend, and the absolute value of the downward slope exceeds a preset slope threshold (0.1 / second), it indicates that the driver's cognitive state is shifting towards tension and anxiety. Even if the influence coefficient corresponding to the ratio at the current moment is low, pre-activation compensation is performed on the influence coefficient based on the trend prediction result.

[0065] The pre-activation increment is determined based on the influence coefficient obtained from the specified mapping relationship at the current moment, combined with the absolute value of the descent slope. For example, when the absolute value of the descent slope is 0.15 / second, the pre-activation increment is 0.1; when the absolute value of the descent slope is 0.3 / second, the pre-activation increment is 0.2. The pre-activation increment is positively correlated with the absolute value of the descent slope. The sum of the influence coefficient and the pre-activation increment is used as the trend compensation influence coefficient, and the trend compensation influence coefficient does not exceed 1.0.

[0066] The product of the trend compensation influence coefficient and the prediction confidence level is used as the reliability evaluation value. If the reliability evaluation value is greater than or equal to the specified evaluation value, a steering operation corresponding to the steering correction angle is performed.

[0067] In this embodiment, by incorporating trend prediction and pre-activation compensation of the ratio time series into the determination process of the reliability evaluation value, a more proactive steering execution decision can be made in advance before the driver is in a state of tension and anxiety. This effectively shortens the time window between low confidence warning and reliable steering execution, and improves the vehicle's response timeliness in emergency avoidance scenarios.

[0068] 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.

[0069] 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.

[0070] refer to Figure 3 The vehicle control device includes: The acquisition module 301 is configured to acquire the steering correction angle predicted by the autonomous driving system of the vehicle and the corresponding prediction confidence. The feature extraction module 302 is configured to acquire the driver's EEG signal in response to the prediction confidence being less than or equal to a specified confidence, and to extract features from the EEG signal to obtain EEG signal features. The execution module 303 is configured to determine a reliability evaluation value for the steering correction angle based on the EEG signal features and the prediction confidence, and to perform a steering operation corresponding to the steering correction angle if the reliability evaluation value is greater than or equal to a specified evaluation value.

[0071] In one possible implementation, the EEG signal features include the power spectral density of the alpha and beta wave bands; the execution module 303 is configured to: The ratio of the power spectral density of the α-wave to the β-wave frequency band is determined, and a reliability evaluation value for the steering correction angle is determined based on the ratio and the prediction confidence level.

[0072] In another possible implementation, the execution module 303 is used to: The influence coefficient of the prediction confidence is determined based on the ratio and the specified mapping relationship, wherein the ratio is negatively correlated with the influence coefficient; The product of the influence coefficient and the prediction confidence level is used as the reliability evaluation value of the steering correction angle.

[0073] In another possible implementation, the execution module 303 is used to: An execution coefficient is determined based on the difference between the reliability evaluation value and the specified evaluation value, and the execution coefficient is positively correlated with the difference; The product of the steering correction angle and the execution coefficient is taken as the actual steering angle, and the steering operation corresponding to the actual steering angle is executed.

[0074] In another possible implementation, the execution module 303 is used to: In response to the actual steering angle being greater than or equal to the specified upper limit of steering angle, a steering operation corresponding to the upper limit of steering angle is performed.

[0075] In another possible implementation, the execution module 303 is used to: The steering angular velocity is determined based on the difference between the reliability evaluation value and the specified evaluation value, wherein the difference is positively correlated with the steering angular velocity; Perform a steering operation corresponding to the actual steering angle based on the steering angular velocity.

[0076] 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.

[0077] 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 402 is used to acquire the steering correction angle predicted by the vehicle's autonomous driving system and the corresponding prediction confidence level; in response to the prediction confidence level being less than or equal to a specified confidence level, it acquires the driver's brain signals acquired by the brain signal acquisition device 401, and performs feature extraction on the brain signals to obtain brain signal features; based on the brain signal features and the prediction confidence level, it determines a reliability evaluation value for the steering correction angle, and if the reliability evaluation value is greater than or equal to the specified evaluation value, it executes a steering operation corresponding to the steering correction angle.

[0078] In one possible implementation, the EEG signal features include the power spectral density of the alpha and beta wave bands; the vehicle controller 402 is used for: The ratio of the power spectral density of the α-wave to the β-wave frequency band is determined, and a reliability evaluation value for the steering correction angle is determined based on the ratio and the prediction confidence level.

[0079] In another possible implementation, the vehicle controller 402 is used for: The influence coefficient of the prediction confidence is determined based on the ratio and the specified mapping relationship, wherein the ratio is negatively correlated with the influence coefficient; The product of the influence coefficient and the prediction confidence level is used as the reliability evaluation value of the steering correction angle.

[0080] In another possible implementation, the vehicle controller 402 is used for: An execution coefficient is determined based on the difference between the reliability evaluation value and the specified evaluation value, and the execution coefficient is positively correlated with the difference; The product of the steering correction angle and the execution coefficient is taken as the actual steering angle, and the steering operation corresponding to the actual steering angle is executed.

[0081] In another possible implementation, the vehicle controller 402 is used for: In response to the actual steering angle being greater than or equal to the specified upper limit of steering angle, a steering operation corresponding to the upper limit of steering angle is performed.

[0082] In another possible implementation, the vehicle controller 402 is used for: The steering angular velocity is determined based on the difference between the reliability evaluation value and the specified evaluation value, wherein the difference is positively correlated with the steering angular velocity; Perform a steering operation corresponding to the actual steering angle based on the steering angular velocity.

[0083] 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.

[0084] 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.

[0085] Figure 5This 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.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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.).

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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 by, include: Obtain the steering correction angle predicted by the autonomous driving system of the vehicle and the corresponding prediction confidence level; In response to the prediction confidence being less than or equal to a specified confidence level, the driver's EEG signal is acquired, and feature extraction is performed on the EEG signal to obtain EEG signal features; Based on the EEG signal characteristics and the prediction confidence level, a reliability evaluation value for the steering correction angle is determined, and if the reliability evaluation value is greater than or equal to the specified evaluation value, a steering operation corresponding to the steering correction angle is performed.

2. The vehicle control method according to claim 1, characterized by, The EEG signal features include the power spectral density of the alpha and beta wave bands; determining the reliability evaluation value for the steering correction angle based on the EEG signal features and the prediction confidence includes: The ratio of the power spectral density of the α-wave to the β-wave frequency band is determined, and a reliability evaluation value for the steering correction angle is determined based on the ratio and the prediction confidence level.

3. The vehicle control method according to claim 2, characterized by, Determining the reliability evaluation value for the steering correction angle based on the ratio and the predicted confidence level includes: The influence coefficient of the prediction confidence is determined based on the ratio and the specified mapping relationship, wherein the ratio is negatively correlated with the influence coefficient; The product of the influence coefficient and the prediction confidence level is used as the reliability evaluation value of the steering correction angle.

4. The vehicle control method according to claim 1, characterized by The execution of the steering operation corresponding to the steering correction angle includes: An execution coefficient is determined based on the difference between the reliability evaluation value and the specified evaluation value, and the execution coefficient is positively correlated with the difference; The product of the steering correction angle and the execution coefficient is taken as the actual steering angle, and the steering operation corresponding to the actual steering angle is executed.

5. The vehicle control method according to claim 4, characterized by The execution of the steering operation corresponding to the actual steering angle includes: In response to the actual steering angle being greater than or equal to the specified upper limit of steering angle, a steering operation corresponding to the upper limit of steering angle is performed.

6. The vehicle control method according to claim 4, characterized by The execution of the steering operation corresponding to the actual steering angle includes: The steering angular velocity is determined based on the difference between the reliability evaluation value and the specified evaluation value, wherein the difference is positively correlated with the steering angular velocity; Perform a steering operation corresponding to the actual steering angle based on the steering angular velocity.

7. A vehicle control device characterized by comprising: include: The acquisition module is configured to acquire the steering correction angle predicted by the autonomous driving system of the vehicle and the corresponding prediction confidence. The feature extraction module is configured to acquire the driver's EEG signal in response to the prediction confidence being less than or equal to a specified confidence, and to extract features from the EEG signal to obtain EEG signal features. An execution module is configured to determine a reliability evaluation value for the steering correction angle based on the EEG signal features and the prediction confidence, and to perform a steering operation corresponding to the steering correction angle if the reliability evaluation value is greater than or equal to a specified evaluation value.

8. A vehicle characterized by comprising: 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 steering correction angle predicted by the vehicle's autonomous driving system and the corresponding prediction confidence level; in response to the prediction confidence level being less than or equal to a specified confidence level, it acquires the driver's brain signals acquired by the brain signal acquisition device, and performs feature extraction on the brain signals to obtain brain signal features. Based on the EEG signal characteristics and the prediction confidence level, a reliability evaluation value for the steering correction angle is determined, and if the reliability evaluation value is greater than or equal to the specified evaluation value, a steering operation corresponding to the steering correction angle is executed.

9. A non-transitory computer-readable storage medium storing computer instructions, wherein, 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, characterised 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