Vehicle control methods, devices, equipment and storage media

Abstract

This application relates to a vehicle control method, apparatus, device, and storage medium. The method includes: collecting real-time physiological data of a driver; determining whether the driver's physiological state meets preset state adjustment conditions based on the real-time physiological data; in response to the driver's physiological state meeting the preset state adjustment conditions, determining a control adjustment strategy suitable for the driver based on the real-time physiological data and the driver's real-time driving data; and controlling an operating module in the vehicle that matches the physiological state according to the control adjustment strategy. Therefore, this application can adaptively control the vehicle based on the driver's physiological state, reducing driving risks caused by physiological state and improving driving safety.

Description

Technical Field

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

[0002] With the continuous development and popularization of automotive technology, people's understanding of driving safety is no longer limited to the mechanical performance of the vehicle itself or driving skills. A growing body of research indicates that the driver's physiological state is one of the core factors affecting driving safety. Fatigue, drowsiness, distraction, and anger are all detrimental driving conditions that significantly impair a driver's judgment and reaction ability, becoming major hidden dangers that induce traffic accidents. This results in more than 1.35 million deaths annually worldwide due to road traffic accidents, a significant proportion of which are due to abnormal driver physiological states. Furthermore, research indicates that in some countries, sudden medical discomfort in drivers—such as acute physiological events like heart attacks or strokes—directly leads to approximately 10% of fatal traffic accidents. This data further confirms the high correlation between driver physiological health and driving safety. Against this backdrop, there is an urgent need for a method of controlling vehicles based on physiological state to reduce driving risks caused by physiological conditions at the source. Summary of the Invention

[0003] This application provides a vehicle control method, device, equipment, and storage medium that can adaptively control the vehicle according to the driver's physiological state, reducing driving risks caused by physiological state and improving driving safety.

[0004] In a first aspect, this application provides a vehicle control method, the method comprising: Collect real-time physiological data of the vehicle's driver; Based on the real-time physiological data, determine whether the driver's physiological state meets the preset state adjustment conditions; In response to the driver's physiological state meeting preset state adjustment conditions, a control adjustment strategy that conforms to the driver is determined based on the real-time physiological data and the driver's real-time driving data. According to the control adjustment strategy, the operating modules in the vehicle that match the physiological state are controlled.

[0005] Secondly, this application provides a vehicle control device, the device comprising: The data acquisition unit is used to collect real-time physiological data of the vehicle's driver. The detection unit is used to determine whether the driver's physiological state meets the preset state adjustment conditions based on the real-time physiological data. The first determining unit is configured to determine a control adjustment strategy that conforms to the driver based on the real-time physiological data and the driver's real-time driving data, in response to the driver's physiological state meeting the preset state adjustment conditions. An adjustment unit is used to control the operating modules in the vehicle that are matched with the physiological state according to the control adjustment strategy.

[0006] Optionally, the detection unit is used for: Obtain the dangerous driving behavior index of the vehicle, which is determined based on the driver's historical dangerous driving behavior; A safety risk score is determined based on the real-time physiological data and the dangerous driving behavior index; The driver's physiological state is determined based on the safety risk score to see if it meets the preset state adjustment conditions.

[0007] Optionally, the detection unit is used for: Obtain the driver's historical physiological data; By analyzing the historical physiological data and the real-time physiological data through a pre-trained prediction model, future physiological data can be obtained. Based on the future physiological data, determine whether the driver's physiological state meets the preset state adjustment conditions.

[0008] Optionally, the detection unit is used for: The real-time driving data and the real-time physiological data are analyzed to determine the target group type to which the driver belongs; Based on the target group type, a control strategy that suits the driver is determined from the preset control adjustment strategy.

[0009] Optionally, when the operating module includes a motion control module, the adjustment unit is used for: Acquire historical driving event data corresponding to historical driving events, wherein the historical driving event data includes the change in physiological disturbance index and speed parameters related to vehicle driving corresponding to the historical driving events; Based on the real-time driving event data corresponding to the driver's real-time driving events and each historical driving event data, fit the sensitivity coefficient corresponding to the speed parameter; The target speed parameters of the vehicle are determined based on the sensitivity coefficient corresponding to the speed parameters. The vehicle's motion control module is controlled according to the target speed parameters.

[0010] Optionally, the speed parameters include maximum braking deceleration, maximum yaw rate, and maximum lateral velocity change; the sensitivity coefficients corresponding to the speed parameters include a first sensitivity coefficient corresponding to the maximum braking deceleration, a second sensitivity coefficient corresponding to the maximum yaw rate, and a third sensitivity coefficient corresponding to the maximum lateral velocity change; the adjustment unit is used for: Obtain the preset maximum value of the change in the physiological disturbance index; The ratio of the preset maximum value to the first sensitivity coefficient is determined as the maximum braking deceleration of the vehicle; The ratio of the preset maximum value to the second sensitivity coefficient is determined as the maximum yaw rate of the vehicle; The ratio of the preset maximum value to the third sensitivity coefficient is determined as the maximum lateral speed change of the vehicle; The target speed parameters of the vehicle are composed of the vehicle's maximum braking deceleration, the vehicle's maximum yaw rate, and the vehicle's maximum lateral speed change.

[0011] Optionally, the apparatus further includes a second determining unit, used for: For each historical driving event, a first rate of change and a second rate of change corresponding to the historical driving event are obtained, wherein the first rate of change is the rate of change of the driver's physiological data before the occurrence of the historical driving event, and the second rate of change is the rate of change of the driver's physiological data after the occurrence of the historical driving event. Based on the first rate of change, determine the first physiological disturbance index; The second physiological disturbance index is determined based on the second rate of change; The change in physiological disturbance index corresponding to the historical driving event is determined based on the first physiological disturbance index and the second physiological disturbance index.

[0012] Thirdly, this application provides a vehicle control device, comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus, wherein the processor is configured to: Collect real-time physiological data of the vehicle's driver; Based on the real-time physiological data, determine whether the driver's physiological state meets the preset state adjustment conditions; In response to the driver's physiological state meeting preset state adjustment conditions, a control adjustment strategy that conforms to the driver is determined based on the real-time physiological data and the driver's real-time driving data. According to the control adjustment strategy, the operating modules in the vehicle that match the physiological state are controlled.

[0013] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described vehicle control method.

[0014] Compared with the prior art, the technical solution provided in this application has the following advantages: In this application embodiment, real-time physiological data of the driver of the vehicle is collected; the driver's physiological state is determined based on the real-time physiological data to see if it meets preset state adjustment conditions; in response to the driver's physiological state meeting the preset state adjustment conditions, a control adjustment strategy that conforms to the driver is determined based on the real-time physiological data and the driver's real-time driving data; and the operating modules in the vehicle that match the physiological state are controlled according to the control adjustment strategy. This application can adaptively control the vehicle according to the driver's physiological state, determine the control adjustment strategy by combining real-time physiological data and driving data, and control the vehicle operating modules accordingly, thereby reducing the driving risk caused by abnormal driver physiological state and effectively improving driving safety. Attached Figure Description

[0015] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0018] Figure 1 A schematic flowchart of a vehicle control method provided in an embodiment of this application; Figure 2 A schematic diagram of a vehicle control method provided in an embodiment of this application; Figure 3 A flowchart illustrating a physiological state detection method provided in an embodiment of this application; Figure 4 A flowchart illustrating a control adjustment method provided in an embodiment of this application; Figure 5This is a schematic flowchart of a vehicle control device provided in an embodiment of this application; Figure 6 This is a schematic diagram of a vehicle control device provided in an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] The following disclosure provides numerous different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of the invention. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0021] With the continuous development and popularization of automotive technology, people's understanding of driving safety is no longer limited to the mechanical performance of the vehicle itself or driving skills. A growing body of research indicates that the driver's physiological state is one of the core factors affecting driving safety. Fatigue, drowsiness, distraction, and anger are all detrimental driving conditions that significantly impair a driver's judgment and reaction ability, becoming major hidden dangers that induce traffic accidents. This results in more than 1.35 million deaths annually worldwide due to road traffic accidents, a significant proportion of which are due to abnormal driver physiological states. Furthermore, research indicates that in some countries, sudden medical discomfort in drivers—such as acute physiological events like heart attacks or strokes—directly leads to approximately 10% of fatal traffic accidents. This data further confirms the strong correlation between driver physiological health and driving safety.

[0022] To address the aforementioned problems, embodiments of this application provide a vehicle control method. This method adaptively controls the vehicle based on the driver's physiological state, reducing driving risks caused by physiological conditions and improving driving safety. Figure 1 As shown, the specific steps include: Step 101: During the vehicle's movement, collect the driver's real-time physiological data and determine whether the driver's physiological state meets the preset state adjustment conditions based on the real-time physiological data.

[0023] The driver's real-time physiological data includes, but is not limited to, one or more of the following: heart rate (HR), systolic blood pressure (SBP), diastolic blood pressure (DBP), and oxygen saturation (SpO2). This data can be collected through various sensing devices. These sensors can be placed in wearable devices such as smart bracelets and smartwatches, and then wirelessly transmitted to the vehicle control system via the driver's smart bracelet or smartwatch. Alternatively, it can be collected through contact sensors integrated into the steering wheel, seat belt, and seat; and non-contact sensors within the vehicle can also acquire data such as the driver's heart rate and respiration. Contact sensors include piezoelectric film sensors and capacitive sensors, while non-contact sensors include millimeter-wave radar and high-definition cameras.

[0024] The aforementioned real-time physiological data can be physiological data collected by the sensor at the current point in time, or it can be a set of physiological data collected during the current time period.

[0025] Before introducing the subsequent steps, the subject of this application will be described as a vehicle control system. This vehicle control system may include a vehicle controller and a server, or it may only include a server. When the vehicle control system includes both a vehicle controller and a server, such as... Figure 2 As shown, sensors can be controlled to send collected physiological data to the vehicle controller, allowing the controller to perform basic checks on the driver's normal physiological data. When the vehicle controller detects abnormalities in the collected physiological data, it sends the data to the server for further processing. This processing method reduces the server's processing load by requiring it to handle only a portion of the collected physiological data. When the vehicle control system consists only of a server, sensors can be directly controlled to send the collected physiological data to the server for further processing.

[0026] During the process of the vehicle controller sending data to the server, the vehicle controller can remove the user's identity identifier, replace it with anonymous data, and package it using differential privacy perturbation (ε=0.5, TLS 1.3 or national cryptographic SM4 encryption, JSON, etc.), and upload the data packet to the server via 4G / 5G / Wi-Fi (once every 30 seconds by default).

[0027] In this step, during vehicle movement, real-time physiological data of the driver is periodically collected, and the driver's physiological state is checked based on the real-time physiological data to see if it meets the preset state adjustment conditions. When the driver's physiological state meets the preset state adjustment conditions, it is determined that the driver's physiological state is abnormal; when the driver's physiological state does not meet the preset state adjustment conditions, it is determined that the driver's physiological state is normal.

[0028] The preset state adjustment conditions include several types. One is that the real-time physiological data deviates from the normal value, that is, the driver's current physiological state is abnormal. Another is that the future physiological data deviates from the normal value, that is, the future physiological data is abnormal.

[0029] For the first type, the preset state adjustment condition is that the real-time physiological data deviates from the standard physiological data. The standard physiological data can be determined based on test experiments or based on preset methods. For example, since some driving events can trigger abnormal physiological states in drivers, physiological data of drivers driving on smooth, straight roads can be collected and averaged to obtain standard physiological data.

[0030] For example, the preset state adjustment condition is that the driver's safety risk score is greater than the preset risk threshold. The calculation steps for the safety risk score are as follows: obtain the driver's dangerous driving behavior in the historical time period, calculate the dangerous driving behavior index according to the number of occurrences of the same type of dangerous driving behavior and the weight corresponding to each type of dangerous driving behavior, and fuse the real-time physiological data and dangerous driving behavior data to obtain the safety risk score.

[0031] For the second type, the preset state adjustment condition is that the future physiological data deviates from the standard physiological data. The calculation steps for the future physiological data are as follows: call the pre-trained prediction model, input historical physiological data and real-time physiological data, so that the prediction model can predict the physiological data in the future time period and obtain the future physiological data.

[0032] The prediction model is a machine learning model or an artificial intelligence model, used to predict physiological data in future time periods based on historical and real-time physiological data. It can be an LSTM time series model or other models, which are not limited here. The training method of this prediction model is similar to that of existing models, and will not be described in detail here.

[0033] In addition, the future time period is a fixed time period starting from the current moment. For example, the future time period could be 5 minutes or 10 minutes. The future time period can also be determined based on the driver's real-time status, driving duration, or road environment. For example, when the vehicle is detected to be on a high-load road section, which is more prone to abnormal physiological data, the prediction window can be shortened to 2-3 minutes in advance to improve the sensitivity of response to sudden anomalies. When the driver is cruising at high speed and the physiological data is stable, the prediction window can be appropriately extended to 10-15 minutes to provide overall trend warnings.

[0034] Step 102: In response to the driver's physiological state meeting the preset state adjustment conditions, a control adjustment strategy that conforms to the driver is determined based on real-time physiological data and the driver's real-time driving data.

[0035] Among them, the control adjustment strategy refers to the control strategy used to alleviate or eliminate current physiological abnormalities. Driving data is obtained from the vehicle's CAN bus or ADAS system, including driving behavior data such as vehicle speed, braking intensity, steering angle rate, and lane change frequency.

[0036] In this step, there are several ways to determine the control adjustment strategy. For example, analyzing the driver's real-time driving and physiological data can determine the target group type to which the driver belongs. The control adjustment strategy corresponding to this target group type is then selected from a pre-set control adjustment strategy library; this is the control adjustment strategy to be used. Alternatively, a pre-trained data detection model can be called to perform a more precise analysis of the real-time driving and physiological data. If the analysis results indicate an abnormal physiological state in the driver, the control adjustment strategy can be set as the default adjustment strategy. For example, adjusting the vehicle's maximum driving speed, maximum braking deceleration, and calculating sensitivity coefficients can adjust the vehicle's operating mode to ensure more stable driving and avoid external environmental stimuli to the driver. Other methods can also be used; this is not limited to these methods.

[0037] The aforementioned data detection model can be a machine learning model or an artificial intelligence model, used to analyze real-time driving data and real-time physiological data, and output analysis results, including whether the driver's physiological state is abnormal or normal. As an example, this model can use an LSTM time series model, but this application does not limit it; other models capable of achieving the same or similar functions are also applicable. The training method of this data detection model is similar to that of existing models, and will not be elaborated upon here.

[0038] Step 103: Control the operating modules in the vehicle that match the physiological state according to the control adjustment strategy.

[0039] The operating module can be related to adjusting physiological state. For example, it may include modules that directly act on the human body, or modules that directly contact or influence the human body. Examples include: activating the seat massage / lumbar support adjustment device to physically press on the driver's back to relieve muscle tension; controlling the air conditioning system to automatically lower the cabin temperature or increase airflow to combat drowsiness; controlling the aroma generator to release invigorating or soothing scents; and controlling the ambient lighting / sound system to guide mood calming through changes in light color or the playback of music at specific frequencies.

[0040] This operating module can be a motion control module that adjusts the vehicle's motion. By adjusting the vehicle's motion through this motion control module, a more stable driving environment can be provided for the driver, thereby indirectly adjusting the driver's physiological state.

[0041] In this embodiment, real-time physiological data of the driver is collected; based on the real-time physiological data, it is determined whether the driver's physiological state meets preset state adjustment conditions; in response to the driver's physiological state meeting the preset state adjustment conditions, a control adjustment strategy suitable for the driver is determined based on the real-time physiological data and the driver's real-time driving data; and the operating modules in the vehicle that match the physiological state are controlled according to the control adjustment strategy. This application can adaptively control the vehicle based on the driver's physiological state, determine the control adjustment strategy by combining real-time physiological data and driving data, and control the vehicle's operating modules accordingly, thereby reducing the driving risks caused by abnormal driver physiological states and effectively improving driving safety.

[0042] In this embodiment, to more accurately determine whether the driver's physiological state meets the adjustment conditions, real-time physiological data can be fused with corresponding indices to obtain a safety risk score. This safety risk score allows for a more comprehensive assessment of the abnormal risk of the driver's current physiological state, thereby accurately determining whether the driver's physiological state meets the state adjustment conditions. Figure 3 As shown, the specific steps include: Step 301: Obtain the vehicle's dangerous driving behavior index.

[0043] The Dangerous Driving Behavior Index (DDI) is a quantitative indicator determined based on a driver's historical dangerous driving behavior. It characterizes a driver's inherent driving style or potential risk tendency. Dangerous driving behaviors can include events such as rapid acceleration, sudden braking, sharp turns, frequent lane changes, and speeding. The DDI can be determined based on the frequency of dangerous driving events within a historical time period. For example, data such as the number of sudden braking events and sharp turns per 100 kilometers in the past month can be weighted, summed, and then normalized to obtain the DDI. A higher DDI indicates more aggressive driving behavior and a greater risk tendency; conversely, a lower DDI indicates a lower risk tendency.

[0044] In this step, the physiological adjustment system stores a mapping relationship between vehicle identifiers and dangerous driving behavior indices, which are pre-calculated using the method described above. Based on the vehicle identifier, the corresponding dangerous driving behavior index for that vehicle can be found within the aforementioned mapping relationship.

[0045] Step 302: Determine the safety risk score based on real-time physiological data and dangerous driving behavior index.

[0046] In this step, when real-time physiological data includes real-time heart rate, real-time diastolic blood pressure, real-time oxygen saturation, and real-time systolic blood pressure, the deviation of real-time heart rate from the standard heart rate, the degree to which real-time oxygen saturation is below the lower limit of oxygen saturation, and the deviation of real-time pulse pressure from the standard pulse pressure are determined. The pulse pressure is the difference between systolic and diastolic blood pressure. Then, based on the calculated deviations and a preset formula, a safety risk score is calculated.

[0047] The preset formula is D_HR(t) = (HR(t)) μ_HR_ref) / σ_HR_ref; D_SpO2(t)=max(0,SpO2_ref_min SpO2(t)); D_BP(t) = (PP(t)) μ_PP_ref) / σ_PP_ref; SRS(t)=w1·D_HR(t)+w2·D_SpO2(t)+w3·D_BP(t)+w4·I_behavior(t) Wherein, HR(t) is the real-time heart rate, μ_HR_ref is the mean of the real-time heart rate, σ_HR_ref is the standard deviation of the real-time heart rate, SpO2_ref_min is the lower limit of blood oxygenation, SpO2(t) is the real-time blood oxygen saturation, PP(t) is the real-time pulse pressure, μ_PP_ref is the mean of the real-time pulse pressure, σ_PP_ref is the standard deviation of the real-time pulse pressure, I_behavior(t) is the dangerous driving behavior index, and SRS(t) is the safety risk score. The weights w1 to w4 are dynamically adjusted according to the time period. For example, w2 is increased at night; when driving time > 2 hours, w1 is increased.

[0048] Step 303: Detect whether the driver's physiological state meets the preset state adjustment conditions based on the safety risk score.

[0049] In this step, it is detected whether the safety risk score is greater than a preset score threshold. If it is greater than the preset score, it is determined that the driver's physiological state is abnormal and meets the preset state adjustment conditions. Otherwise, it is determined that the driver's physiological state does not meet the preset state adjustment conditions.

[0050] In addition, one or more thresholds can be preset to classify risk levels. For example, a first threshold T1, a second threshold T2, and a third threshold T3 can be set. When the safety risk score is ≤ T1, it is considered a normal state and no intervention is required; when T1 < safety risk score ≤ T2, it is considered a mild abnormality, which can trigger a warning or make slight adjustments, such as turning on the seat massage; when the safety risk score > T2, it is considered a severe abnormality, and strong intervention measures must be taken immediately, such as limiting vehicle power or forcibly reminding the driver to stop and rest.

[0051] Furthermore, if the safety risk score continues to rise over multiple consecutive sampling periods, even if it does not currently exceed the threshold, it can be determined in advance that an anomaly is imminent, thereby determining whether the driver's physiological state is about to become abnormal.

[0052] In this embodiment, by analyzing the driver's historical and real-time physiological data, the trend of physiological data over a future period is predicted, thereby detecting abnormalities in the physiological state in advance before they occur, allowing sufficient response time for subsequent adjustment strategies. Therefore, this embodiment provides an anomaly detection method based on a predictive model, with specific steps including: acquiring the driver's historical physiological data; calling a pre-trained predictive model to analyze the historical and real-time physiological data to obtain future physiological data; and determining whether the driver's physiological state meets preset state conditions based on the future physiological data.

[0053] The predictive model is a machine learning or deep learning model pre-trained based on a large amount of physiological data from drivers. It is used to learn the temporal evolution of physiological parameters and predict future trends. The predictive model can be implemented using various algorithms, such as Long Short-Term Memory networks and Transformer models.

[0054] In this step, historical physiological data and real-time physiological data are input into a pre-trained prediction model, which analyzes the data to obtain future physiological data. Then, based on the future physiological data, it is determined whether the driver's physiological state meets preset conditions.

[0055] There are several ways to determine whether a driver's physiological state meets preset conditions based on future physiological data. For example, one method is to obtain the abnormal thresholds for each physiological parameter and compare the future physiological data with these thresholds. If the value at any point in the predicted data exceeds the corresponding abnormal threshold, or if it exceeds the threshold at multiple consecutive points, then the driver's physiological state is determined to meet the preset conditions. Alternatively, one can analyze the trend of future physiological data to determine if there is a tendency for rapid deterioration, thereby confirming that the driver's physiological state meets the preset conditions.

[0056] In this embodiment, by analyzing driver driving data and combining it with physiological data, the driver is categorized into a specific target group type, and then the most suitable adjustment strategy for that group is matched from a preset strategy library. Therefore, this embodiment provides a method for selecting control adjustment strategies, the specific steps of which include: analyzing real-time driving data and real-time physiological data to determine the target group type to which the driver belongs; and determining a control strategy suitable for the driver from a preset control adjustment strategy based on the target group type.

[0057] In this step, real-time physiological data is a sequence of physiological data over a period of time, and real-time driving data is also a sequence of formal data over a period of time. Therefore, the real-time physiological data and real-time driving data are first aligned in the time dimension to calculate the typical characteristics corresponding to the driver, such as "the increase in heart rate after emergency braking" and "blood oxygen fluctuations during continuous lane changes." The typical characteristics corresponding to the driver are compared with the typical characteristics corresponding to each group type. The group type that matches the comparison is determined as the target group type, and the control adjustment strategy corresponding to the target group type is determined as the control adjustment strategy to be used.

[0058] In practice, physiological data corresponding to each group type were collected and analyzed to extract their typical characteristics, such as: high stress type: HR rises by >20 bpm after immobilization; hypoxia-sensitive type: SpO2 <63%.

[0059] In this embodiment, to indirectly adjust the driver's physiological state, it is necessary to record the speed parameters corresponding to each historical driving event and the change in the physiological disturbance index caused by that event, and use these to constitute sample data. Using this sample data, the target speed parameters are solved through mathematical fitting. Subsequently, based on these sensitivity coefficients and a preset maximum change in physiological disturbance, the limit value of vehicle motion control is derived in reverse, and this limit is used to constrain the motion control module, ensuring that the stimuli generated by subsequent driving events never exceed the driver's physiological tolerance range. Therefore, this embodiment provides a control adjustment method, such as... Figure 4 As shown, the specific steps include: 401, retrieve the historical driving event data corresponding to the historical driving event.

[0060] Driving events refer to typical driving operations that occur during vehicle operation. These events are usually accompanied by significant changes in longitudinal or lateral acceleration, which may affect the driver's physiological state. Common driving events include, but are not limited to, braking events, turning events, and lane-changing events. Driving event data includes the change in the physiological disturbance index corresponding to the driving event and vehicle-related speed parameters. The change in the physiological disturbance index is used to quantify the additional physiological disturbance caused by the driving event itself and is the target variable (dependent variable) for fitting. The speed parameters include the maximum braking deceleration, maximum yaw rate, and maximum lateral velocity change in the current driving event. The maximum braking deceleration is the maximum absolute value of the braking deceleration recorded in this event, corresponding to the longitudinal impact stimulus. The maximum yaw rate is the maximum absolute value of the yaw rate recorded in this event, corresponding to the lateral sway stimulus. The maximum lateral velocity change is the maximum absolute value of the lateral velocity change recorded in this event, corresponding to the lateral disturbance stimulus.

[0061] During vehicle operation, each driving event is recorded along with its corresponding physiological disturbance index change and speed parameters, forming driving event data for that specific event. This allows for direct access to pre-stored driving event data for subsequent processing when needed. 402. Based on the real-time driving event data corresponding to the driver's real-time driving events and each historical driving event data, fit the sensitivity coefficient corresponding to the speed parameter.

[0062] In this step, parameter fitting is performed based on a preset linear model, the basic form of which is: ΔPDIk=θ1 ∣ak∣+θ2 |ωk|+θ3 ∣Δvk∣+ , Where θ1, θ2, and θ3 are the first, second, and third sensitivity coefficients to be fitted, respectively; ak is the braking deceleration; ωk is the yaw rate; Δvk is the change in lateral velocity; and ΔPDIk is the change in the physiological disturbance index. This represents the fitting error.

[0063] The goal of fitting the above model is to find a set of θ1, θ2, θ3 such that for all driving events, the sum of squared errors between the model-predicted ΔPDI (physiological perturbation index change) and the measured value is minimized.

[0064] In practice, commonly used fitting methods include least squares method, gradient descent method, regularization method, etc.

[0065] 403. Determine the target speed parameters of the vehicle based on the sensitivity coefficient corresponding to the speed parameters.

[0066] In this step, the correspondence between the sensitivity coefficient range and the speed parameter is preset. In this way, the sensitivity coefficient range in which the sensitivity coefficient is located can be determined, and the speed parameter corresponding to the sensitivity coefficient range can be determined as the target speed parameter.

[0067] For example, if the speed parameter is braking deceleration, by pre-setting the range of sensitivity coefficients corresponding to braking deceleration and the correspondence between the maximum braking deceleration, the maximum braking deceleration can be found based on the range of sensitivity coefficients corresponding to braking deceleration, thus obtaining the target speed parameter.

[0068] 404, The vehicle's motion control module is controlled according to the target speed parameters.

[0069] In this step, the target speed parameters are sent to the motion control module so that the motion control module can perform control based on the target speed parameters.

[0070] For example, when the speed parameters include maximum braking deceleration, maximum yaw rate, and maximum lateral velocity change, the maximum braking deceleration, maximum yaw rate, and maximum lateral velocity change can be sent to the corresponding motion control module so that the motion control module controls the vehicle movement according to the maximum braking deceleration, maximum yaw rate, and maximum lateral velocity change.

[0071] The motion control module includes, but is not limited to, operational modules such as the vehicle controller, chassis domain controller, and steer-by-wire system. The vehicle controller limits the torque output corresponding to the accelerator pedal opening, ensuring that longitudinal acceleration does not exceed the maximum braking deceleration. The chassis domain controller monitors the yaw rate during steering, applying braking intervention or adjusting steering assist as necessary to ensure that the yaw rate does not exceed the maximum yaw rate. The steer-by-wire system limits the rate of change of steering wheel angle, preventing sudden changes in lateral velocity from exceeding the maximum lateral velocity change.

[0072] It should be noted that the above adjustment method can be triggered periodically, or when the driver's physiological state meets preset conditions, or it can be triggered in step 103 by triggering the default adjustment strategy. This application does not limit this.

[0073] In this embodiment, when the speed parameters include maximum braking deceleration, maximum yaw rate, and maximum lateral velocity change, the maximum vehicle motion limit that the driver can withstand in the current state is calculated in reverse using a pre-set maximum physiological disturbance change and a fitted sensitivity coefficient. This serves as the basis for subsequent vehicle motion control module limitations. This method of inverse derivation based on sensitivity coefficients ensures that any stimulus to the vehicle does not exceed the driver's physiological tolerance range, thereby fundamentally avoiding physiological discomfort caused by excessive driving. Therefore, this embodiment provides a method for determining vehicle motion limit values, specifically including: obtaining a preset maximum value for the physiological disturbance index change; determining the ratio of the preset maximum value to a first sensitivity coefficient as the vehicle's maximum braking deceleration; determining the ratio of the preset maximum value to a second sensitivity coefficient as the vehicle's maximum yaw rate; determining the ratio of the preset maximum value to a third sensitivity coefficient as the vehicle's maximum lateral velocity change; and constructing the vehicle's target speed parameters from the vehicle's maximum braking deceleration, maximum yaw rate, and maximum lateral velocity change.

[0074] The preset maximum value of the physiological disturbance index change is used to characterize the maximum instantaneous discomfort increment that a driver can tolerate under normal conditions. This value can be a general fixed value (such as a default threshold set based on a large amount of driver experimental data), or it can be personalized according to individual characteristics—that is, the system parameters are dynamically adjusted according to the driver's age, gender, health status and other information to obtain a preset maximum value that is more suitable for the driver.

[0075] For example, the maximum braking deceleration is limited to: |a | = PDI max / θ1, where PDI max The preset maximum value of the physiological disturbance change is θ1, which is the first sensitivity coefficient, i.e., the sensitivity coefficient corresponding to the braking deceleration. The maximum yaw rate during a turn is: |ω | = PDI max / θ2, where θ2 is the second sensitivity coefficient, i.e., the sensitivity coefficient corresponding to the yaw rate; The maximum lateral velocity change during a lane change is: Δv ≤ PDI max / θ3, where θ3 is the third sensitivity coefficient, i.e., the sensitivity coefficient corresponding to the change in lateral velocity.

[0076] In this embodiment, simply comparing absolute physiological values ​​before and after an event may not accurately reflect the intensity of the disturbance, as physiological states naturally fluctuate. Therefore, the rate of change of physiological data before and after an event is introduced as a benchmark. By comparing the difference in the rate of change before and after the event, the incremental physiological disturbance caused by the driving event itself can be extracted more accurately. Therefore, this embodiment provides a method for determining the change in physiological disturbance index, specifically including: for each historical driving event, obtaining a first rate of change and a second rate of change corresponding to the historical driving event; determining a first physiological disturbance index based on the first rate of change; determining a second physiological disturbance index based on the second rate of change; and determining the change in physiological disturbance index corresponding to the historical driving event based on the first and second physiological disturbance indices.

[0077] The first rate of change is the rate of change in the driver's physiological data before the historical driving event, such as the rate of change in the driver's heart rate, blood oxygen saturation, and systolic blood pressure before the historical driving event. The second rate of change is the rate of change in the driver's physiological data after the historical driving event, such as the rate of change in the driver's heart rate, blood oxygen saturation, and systolic blood pressure after the historical driving event.

[0078] In this step, for each historical driving event, the driver's heart rate change rate, blood oxygen saturation change rate, and systolic blood pressure change rate before the historical driving event occurred are obtained. Based on the heart rate change rate, blood oxygen saturation change rate, and systolic blood pressure change rate and a preset formula, a first physiological disturbance index is calculated. After the historical driving event occurred, the driver's heart rate change rate, blood oxygen saturation change rate, and systolic blood pressure change rate are obtained. Based on the heart rate change rate, blood oxygen saturation change rate, and systolic blood pressure change rate and a preset formula, a second physiological disturbance index is calculated. The first physiological disturbance index is subtracted from the second physiological disturbance index to obtain the physiological disturbance index change corresponding to the historical driving event.

[0079] For example, the preset formula is PDI(t) = α·|dHR / dt| + β·|dSpO2 / dt| + γ·|dSBP / dt| Where: HR is heart rate, SpO2 is blood oxygen saturation, SBP is systolic blood pressure; dHR / dt represents the rate of change of heart rate, dSpO2 / dt represents the rate of change of blood oxygen saturation, dSBP / dt represents the rate of change of systolic blood pressure, PDI(t) is the physiological disturbance index; α, β, and γ are weighting coefficients.

[0080] In addition, α, β, and γ can be pre-configured according to the user's age and health condition. For example, middle-aged and elderly people have higher β values, which emphasizes blood oxygen stability.

[0081] like Figure 5 As shown, this application provides a vehicle control device, which corresponds to the method embodiment, and specifically includes: The data acquisition unit 501 is used to collect real-time physiological data of the vehicle's driver. The detection unit 502 is used to determine whether the driver's physiological state meets the preset state adjustment conditions based on the real-time physiological data. The first determining unit 503 is used to determine a control adjustment strategy that conforms to the driver based on the real-time physiological data and the driver's real-time driving data in response to the driver's physiological state meeting the preset state adjustment conditions. The adjustment unit 504 is used to control the operating module in the vehicle that matches the physiological state according to the control adjustment strategy.

[0082] Optionally, the detection unit 502 is used for: Obtain the dangerous driving behavior index of the vehicle, which is determined based on the driver's historical dangerous driving behavior; A safety risk score is determined based on the real-time physiological data and the dangerous driving behavior index; The driver's physiological state is determined based on the safety risk score to see if it meets the preset state adjustment conditions.

[0083] Optionally, the detection unit 502 is used for: Obtain the driver's historical physiological data; By analyzing the historical physiological data and the real-time physiological data through a pre-trained prediction model, future physiological data can be obtained. Based on the future physiological data, determine whether the driver's physiological state meets the preset state adjustment conditions.

[0084] Optionally, the detection unit 502 is used for: The real-time driving data and the real-time physiological data are analyzed to determine the target group type to which the driver belongs; Based on the target group type, a control strategy that suits the driver is determined from the preset control adjustment strategy.

[0085] Optionally, when the operating module includes a motion control module, the adjustment unit 504 is used for: Acquire historical driving event data corresponding to historical driving events, wherein the historical driving event data includes the change in physiological disturbance index and speed parameters related to vehicle driving corresponding to the historical driving events; Based on the real-time driving event data corresponding to the driver's real-time driving events and each historical driving event data, fit the sensitivity coefficient corresponding to the speed parameter; The target speed parameters of the vehicle are determined based on the sensitivity coefficient corresponding to the speed parameters. The vehicle's motion control module is controlled according to the target speed parameters.

[0086] Optionally, the speed parameters include maximum braking deceleration, maximum yaw rate, and maximum lateral velocity change; the sensitivity coefficients corresponding to the speed parameters include a first sensitivity coefficient corresponding to the maximum braking deceleration, a second sensitivity coefficient corresponding to the maximum yaw rate, and a third sensitivity coefficient corresponding to the maximum lateral velocity change; the adjustment unit 504 is used for: Obtain the preset maximum value of the change in the physiological disturbance index; The ratio of the preset maximum value to the first sensitivity coefficient is determined as the maximum braking deceleration of the vehicle; The ratio of the preset maximum value to the second sensitivity coefficient is determined as the maximum yaw rate of the vehicle; The ratio of the preset maximum value to the third sensitivity coefficient is determined as the maximum lateral speed change of the vehicle; The target speed parameters of the vehicle are composed of the vehicle's maximum braking deceleration, the vehicle's maximum yaw rate, and the vehicle's maximum lateral speed change.

[0087] Optionally, the device further includes a second determining unit 505, used for: For each historical driving event, a first rate of change and a second rate of change corresponding to the historical driving event are obtained, wherein the first rate of change is the rate of change of the driver's physiological data before the occurrence of the historical driving event, and the second rate of change is the rate of change of the driver's physiological data after the occurrence of the historical driving event. Based on the first rate of change, determine the first physiological disturbance index; The second physiological disturbance index is determined based on the second rate of change; The change in physiological disturbance index corresponding to the historical driving event is determined based on the first physiological disturbance index and the second physiological disturbance index.

[0088] like Figure 6 As shown in the figure, this application provides a vehicle control device, including a processor 601, a communication interface 602, a memory 603, and a communication bus 604, wherein the processor 601, the communication interface 602, and the memory 603 communicate with each other through the communication bus 604. Memory 603 is used to store computer programs; In one embodiment of this application, when the processor 601 executes the program stored in the memory 603, it implements the vehicle control method provided in any of the foregoing method embodiments, including: Collect real-time physiological data of the vehicle's driver; Based on the real-time physiological data, determine whether the driver's physiological state meets the preset state adjustment conditions; In response to the driver's physiological state meeting preset state adjustment conditions, a control adjustment strategy that conforms to the driver is determined based on the real-time physiological data and the driver's real-time driving data. According to the control adjustment strategy, the operating modules in the vehicle that match the physiological state are controlled.

[0089] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the vehicle control method provided in any of the foregoing method embodiments.

[0090] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0091] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0092] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0093] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A vehicle control method, characterized in that, The method further includes: Collect real-time physiological data of the vehicle's driver; Based on the real-time physiological data, determine whether the driver's physiological state meets the preset state adjustment conditions; In response to the driver's physiological state meeting preset state adjustment conditions, a control adjustment strategy that conforms to the driver is determined based on the real-time physiological data and the driver's real-time driving data. According to the control adjustment strategy, the operating modules in the vehicle that match the physiological state are controlled.

2. The method according to claim 1, characterized in that, The step of determining whether the driver's physiological state meets the preset state adjustment conditions based on the real-time physiological data includes: Obtain the dangerous driving behavior index of the vehicle, which is determined based on the driver's historical dangerous driving behavior; A safety risk score is determined based on the real-time physiological data and the dangerous driving behavior index; The driver's physiological state is determined based on the safety risk score to see if it meets the preset state adjustment conditions.

3. The method according to claim 1, characterized in that, The step of determining whether the driver's physiological state meets the preset state adjustment conditions based on the real-time physiological data includes: Obtain the driver's historical physiological data; By analyzing the historical physiological data and the real-time physiological data through a pre-trained prediction model, future physiological data can be obtained. Based on the future physiological data, determine whether the driver's physiological state meets the preset state adjustment conditions.

4. The method according to claim 2 or 3, characterized in that, The step of determining a control adjustment strategy that matches the driver's real-time physiological data and the driver's real-time driving data includes: The real-time driving data and the real-time physiological data are analyzed to determine the target group type to which the driver belongs; Based on the target group type, a control strategy that suits the driver is determined from the preset control adjustment strategy.

5. The method according to claim 3, characterized in that, When the operating module includes a motion control module, controlling the vehicle's operating module according to the control adjustment strategy includes: Acquire historical driving event data corresponding to historical driving events, wherein the historical driving event data includes the change in physiological disturbance index and speed parameters related to vehicle driving corresponding to the historical driving events; Based on the real-time driving event data corresponding to the driver's real-time driving events and each historical driving event data, fit the sensitivity coefficient corresponding to the speed parameter; The target speed parameters of the vehicle are determined based on the sensitivity coefficient corresponding to the speed parameters. The vehicle's motion control module is controlled according to the target speed parameters.

6. The method according to claim 5, characterized in that, The speed parameters include maximum braking deceleration, maximum yaw rate, and maximum lateral velocity change; the sensitivity coefficients corresponding to the speed parameters include a first sensitivity coefficient corresponding to the maximum braking deceleration, a second sensitivity coefficient corresponding to the maximum yaw rate, and a third sensitivity coefficient corresponding to the maximum lateral velocity change; determining the target speed parameters of the vehicle based on the sensitivity coefficients corresponding to the speed parameters includes: Obtain the preset maximum value of the physiological disturbance index change; The ratio of the preset maximum value to the first sensitivity coefficient is determined as the maximum braking deceleration of the vehicle; The ratio of the preset maximum value to the second sensitivity coefficient is determined as the maximum yaw rate of the vehicle; The ratio of the preset maximum value to the third sensitivity coefficient is determined as the maximum lateral speed change of the vehicle; The target speed parameters of the vehicle are composed of the vehicle's maximum braking deceleration, the vehicle's maximum yaw rate, and the vehicle's maximum lateral speed change.

7. The method according to claim 5, characterized in that, The method further includes: For each historical driving event, a first rate of change and a second rate of change corresponding to the historical driving event are obtained, wherein the first rate of change is the rate of change of the driver's physiological data before the occurrence of the historical driving event, and the second rate of change is the rate of change of the driver's physiological data after the occurrence of the historical driving event. Based on the first rate of change, determine the first physiological disturbance index; The second physiological disturbance index is determined based on the second rate of change; The change in physiological disturbance index corresponding to the historical driving event is determined based on the first physiological disturbance index and the second physiological disturbance index.

8. A vehicle control device, characterized in that, The device includes: The data acquisition unit is used to collect real-time physiological data of the vehicle's driver. The detection unit is used to determine whether the driver's physiological state meets the preset state adjustment conditions based on the real-time physiological data. The first determining unit is configured to determine a control adjustment strategy that conforms to the driver based on the real-time physiological data and the driver's real-time driving data, in response to the driver's physiological state meeting the preset state adjustment conditions. An adjustment unit is used to control the operating modules in the vehicle that are matched with the physiological state according to the control adjustment strategy.

9. A vehicle control device, characterized in that, include: At least one communication interface; At least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; At least one memory connected to the at least one bus, wherein the processor is configured to: Collect real-time physiological data of the vehicle's driver; Based on the real-time physiological data, determine whether the driver's physiological state meets the preset state adjustment conditions; In response to the driver's physiological state meeting preset state adjustment conditions, a control adjustment strategy that conforms to the driver is determined based on the real-time physiological data and the driver's real-time driving data. According to the control adjustment strategy, the operating modules in the vehicle that match the physiological state are controlled.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the vehicle control method according to any one of claims 1 to 7.

Images