Method and device for controlling vehicle, vehicle and storage medium

Abstract

The embodiment of the invention provides a method and device for controlling a vehicle, the vehicle and a storage medium. The method comprises the following steps: acquiring driving state information of a vehicle; environment information of the vehicle is obtained, the environment information comprises driving state information of adjacent vehicles of the vehicle, and the adjacent vehicles of the vehicle comprise at least one of a front vehicle, a left side vehicle and a right side vehicle; processing the driving state information of the vehicle and the environment information of the vehicle based on an acceleration and deceleration intention recognition model to obtain a predicted acceleration; and executing a corresponding anti-carsickness measure at the predicted acceleration. According to the technical scheme provided by the embodiment of the invention, when the acceleration and deceleration intention recognition model predicts the acceleration, the influence of the driving state information of the adjacent vehicle on the driver of the vehicle is fully considered, so that the obtained predicted acceleration is more accurate, the anti-carsickness measures subsequently taken based on the predicted acceleration are more appropriate, and the driving experience is improved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and more particularly to a method, apparatus, vehicle, and storage medium for controlling a vehicle. Background Technology

[0002] When a vehicle suddenly accelerates or decelerates during driving, the difference between the information received by the occupants' vision and vestibular system can easily cause motion sickness.

[0003] Therefore, it is necessary to accurately predict the driver's acceleration and deceleration intentions in advance and to alert passengers to these intentions. Related technologies utilize intelligent driver models to predict the driver's acceleration and deceleration intentions, and then provide corresponding prompts based on the prediction results.

[0004] However, the predictions of the intelligent driver model were not accurate enough, resulting in poor motion sickness prevention. Summary of the Invention

[0005] This application provides a method, apparatus, vehicle, and electronic device for controlling a vehicle, aiming to improve the problem in the related art where the prediction of the driver's acceleration and deceleration intentions is not accurate enough, resulting in poor anti-motion sickness effects.

[0006] In a first aspect, embodiments of this application provide a method for controlling a vehicle, comprising: acquiring vehicle driving state information; acquiring vehicle environmental information, the environmental information including driving state information of neighboring vehicles, the neighboring vehicles including at least one of the following: a vehicle in front, a vehicle on the left, and a vehicle on the right; the vehicle on the left refers to a vehicle located in a designated space determined based on the vehicle and on the left side of the vehicle, and the vehicle on the right refers to a vehicle located in the designated space and on the right side of the vehicle; processing the vehicle driving state information and the vehicle environmental information based on an acceleration / deceleration intention recognition model to obtain a predicted acceleration; the acceleration / deceleration intention model is used to predict whether the driver of the vehicle has an acceleration intention or a deceleration intention based on the vehicle driving state information and the vehicle environmental information; and executing corresponding anti-motion sickness measures based on the predicted acceleration.

[0007] Secondly, embodiments of this application provide a device for controlling a vehicle, comprising: a status information acquisition module for acquiring vehicle driving status information; an environmental information acquisition module for acquiring vehicle environmental information, the environmental information including driving status information of neighboring vehicles, the neighboring vehicles including at least one of the following: a vehicle in front, a vehicle on the left, and a vehicle on the right; the vehicle on the left refers to a vehicle located in a designated space determined based on the vehicle and on the left side of the vehicle, and the vehicle on the right refers to a vehicle located in the designated space and on the right side of the vehicle; an acceleration prediction module for processing the vehicle driving status information and the vehicle environmental information based on an acceleration / deceleration intention recognition model to obtain a predicted acceleration; the acceleration / deceleration intention model is used to predict whether the driver of the vehicle has an acceleration intention or a deceleration intention based on the vehicle driving status information and the vehicle environmental information; and a vehicle control module for executing corresponding anti-motion sickness measures based on the predicted acceleration.

[0008] Thirdly, embodiments of this application provide a vehicle including a processor and a memory, wherein the memory is used to store a computer program; and the processor is used to execute the computer program stored in the memory to implement the method described in the first aspect.

[0009] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method described in the first aspect.

[0010] Compared to related technologies, the technical solution provided in this application embodiment is as follows: First, the driving status information and environmental information of the vehicle are obtained. The environmental information includes the driving status information of neighboring vehicles. The acceleration / deceleration intention prediction model processes the above-mentioned environmental information and the driving status information of the vehicle to obtain the predicted acceleration. Then, corresponding anti-motion sickness measures are taken based on the predicted acceleration. Since the driving status information of neighboring vehicles will affect the acceleration or deceleration intention of the driver of the vehicle during the vehicle's operation, for example, when the vehicle in front accelerates, the driver of the vehicle is likely to accelerate as well to avoid vehicles cutting in from both sides. For example, when the vehicle on the left or right accelerates, the driver of the vehicle is likely not to accelerate to avoid the safety hazards caused by vehicles driving side by side. In this application embodiment, the acceleration / deceleration intention recognition model fully considers the influence of the driving status information of neighboring vehicles on the driver of the vehicle when predicting acceleration. Therefore, the predicted acceleration is more accurate, and the subsequent anti-motion sickness measures based on the predicted acceleration are more appropriate, thereby improving the driving experience. Attached Figure Description

[0011] 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 a method for controlling a vehicle according to an embodiment of this application; Figure 3 This is a schematic diagram of a driving scenario provided in one embodiment of this application; Figure 4 This is a flowchart of a method for controlling a vehicle according to another embodiment of this application; Figure 5 This is a flowchart of a method for controlling a vehicle according to another embodiment of this application; Figure 6 This is a flowchart of a method for controlling a vehicle according to another embodiment of this application; Figure 7 This is a structural block diagram of a vehicle control device provided in one embodiment of this application; Figure 8 This is a structural diagram of the vehicle provided in the embodiments of this application. Detailed Implementation

[0012] To make the technical problems, technical solutions, and beneficial effects solved by this application clearer, the following detailed description is provided in conjunction with embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0013] Example 1 This application provides an implementation environment, which includes a vehicle. Please refer to the embodiments described in this application. Figure 1 The vehicle is equipped with a motion sickness warning system 10, which is used to take corresponding motion sickness prevention measures when it is predicted that the driver intends to accelerate or decelerate.

[0014] Optionally, the motion sickness prevention reminder system 10 includes an acceleration / deceleration intention recognition model, a first motion sickness prevention subsystem 110, and a second motion sickness prevention system 120.

[0015] The acceleration / deceleration intention recognition model is used to output predicted acceleration based on the vehicle's state information and environmental information. A predicted acceleration greater than 0 indicates the driver intends to accelerate; a predicted acceleration less than 0 indicates the driver intends to decelerate. In this embodiment, the vehicle's environmental information includes the driving state information of neighboring vehicles, which can be at least one of the vehicle in front, the vehicle on the left, and the vehicle on the right. Since the driving state information of neighboring vehicles affects the driver's acceleration or deceleration intentions during vehicle operation—for example, if the vehicle in front accelerates, the driver is likely to accelerate as well to avoid vehicles cutting in from either side; similarly, if the vehicle on the left or right accelerates, the driver is unlikely to accelerate to avoid the safety hazards of side-by-side traffic—in this embodiment, the acceleration / deceleration intention recognition model fully considers the influence of neighboring vehicle driving state information on the driver when predicting acceleration. Therefore, the predicted acceleration is more accurate, and subsequent anti-motion sickness measures based on the predicted acceleration are more appropriate, thereby improving the driving experience.

[0016] The first motion sickness prevention subsystem 110 is used to control the air vents corresponding to the passenger's face when the acceleration indicator suggests that the driver intends to accelerate, so as to simulate the effect of wind blowing in the face from outside the vehicle during acceleration. The first motion sickness prevention subsystem 110 may include an in-vehicle air conditioner.

[0017] The second motion sickness prevention system 120 controls the tightening of the passenger's seatbelt when the driver anticipates a deceleration intention, simulating the seatbelt tightening effect felt when the body is thrown forward due to inertia during vehicle braking. The second motion sickness prevention system 120 may include a seatbelt and a seatbelt control device.

[0018] In this embodiment of the application, when it is predicted that the driver intends to accelerate or decelerate, the passenger is reminded in a reasonable way, which can effectively eliminate the information gap between the passenger's visual system and vestibular system. The passenger can know the situation when the driver is about to accelerate or decelerate, thereby effectively relieving the passenger's motion sickness.

[0019] In some embodiments, the vehicle further includes vehicle sensors and detection components. The vehicle sensors are used to collect vehicle status information, such as vehicle speed, acceleration, steering wheel angle, and driving curvature. Vehicle sensors may include speed sensors, acceleration sensors, steering wheel angle sensors, etc. The detection components are used to collect environmental information about the vehicle, such as the speed and acceleration of neighboring vehicles, the shape and speed of obstacles in the lane, etc. The detection components may include image acquisition devices and lidar.

[0020] Example 2 This application provides a method for controlling a vehicle. Please refer to the embodiments provided. Figure 2The method includes the following steps.

[0021] S10, obtain vehicle driving status information.

[0022] The vehicle's status information includes its speed. The vehicle includes a speed sensor, through which the vehicle's speed is acquired. The vehicle's status information may also include acceleration, curvature, steering wheel angle, etc., but this application embodiment does not limit this.

[0023] S20, obtains environmental information about the vehicle.

[0024] The vehicle's environmental information includes the driving status information of its neighboring vehicles. Neighboring vehicles include at least one of the following: the vehicle in front, the vehicle on the left, and the vehicle on the right.

[0025] The vehicle in front refers to the vehicle traveling in front of the vehicle and the one closest to it. The vehicle on the left refers to the vehicle located within a designated space determined by the vehicle and to its left. The designated space determined by the vehicle is set according to actual driving needs. For example, the designated space is a rectangular space centered on the vehicle's center point, with a length of a specified distance and a width equal to the vehicle's lane width plus the width of adjacent lanes. The specified distance can be set according to road type; for example, the specified distance is larger on highways and smaller on urban roads. For example, the specified distance is 100 meters. The vehicle on the right refers to the vehicle located within the designated space determined by the vehicle and to its right.

[0026] Reference Figure 3 This diagram illustrates a driving scenario 30 provided in one embodiment of this application. The vehicle 310 is surrounded by a preceding vehicle 320, a left-side vehicle 330, and a right-side vehicle 340. The left-side vehicle 330 is located in the left lane of the vehicle and is situated within a designated space 350 centered on the center point of the vehicle 310, with a length of 100 meters and a width covering three lanes. The right-side vehicle is located in the right lane of the vehicle and is also situated within the designated space 350 centered on the center point of the vehicle 310, with a length of 100 meters and a width covering three lanes.

[0027] In this embodiment, the driving status information of the neighboring vehicle includes the acceleration of the neighboring vehicle. Optionally, the driving status information of the neighboring vehicle also includes the speed of the neighboring vehicle.

[0028] In some embodiments, the vehicle's environmental information also includes the distance between the vehicle and adjacent vehicles. The distance between the vehicle and the vehicle in front refers to the vertical distance between the front of the vehicle and the rear of the vehicle in front. If the vehicle on the left is in front of the vehicle in the direction of travel, the distance between the vehicle and the vehicle on the left can be the vertical distance between the front of the vehicle and the rear of the vehicle on the left; if the vehicle on the left is behind the vehicle in the direction of travel, the distance between the vehicle and the vehicle on the left can be the vertical distance between the rear of the vehicle and the front of the vehicle on the left; the distance between the vehicle and the vehicle on the left can also be the straight-line distance between the center point of the vehicle and the center point of the vehicle on the left. If the vehicle on the right is in front of the vehicle in the direction of travel, the distance between the vehicle and the vehicle on the right can be the vertical distance between the front of the vehicle and the rear of the vehicle on the right; if the vehicle on the right is behind the vehicle in the direction of travel, the distance between the vehicle and the vehicle on the right can be the vertical distance between the rear of the vehicle and the front of the vehicle on the right; the distance between the vehicle and the vehicle on the right can also be the straight-line distance between the center point of the vehicle and the center point of the vehicle on the right.

[0029] The driving status information of the neighboring vehicles and the distance between the vehicle and the neighboring vehicles are obtained by detection components installed on the vehicle, such as lidar.

[0030] The vehicle's environmental information may also include the speed limit information of the road on which the vehicle is currently traveling, environmental images captured by the image acquisition device on the vehicle, etc., but this application embodiment does not limit this.

[0031] S30 uses an acceleration / deceleration intention recognition model to process the vehicle's driving status information and environmental information to obtain predicted acceleration.

[0032] The acceleration / deceleration intention recognition model is used to identify the driver's acceleration / deceleration intentions. This model describes the relationship between predicted acceleration, vehicle driving status information, and vehicle environmental information, and can output predicted acceleration based on both the vehicle's driving status information and its environmental information.

[0033] In this embodiment of the application, the acceleration / deceleration intention recognition model includes, in addition to the first component, at least one of the second component, the third component, and the fourth component.

[0034] The predicted acceleration is determined by four components: The first component reflects the impact of the difference between the current vehicle speed and the driver's expected speed, and the difference between the current headway and the driver's expected headway, on the predicted acceleration. Headway refers to the distance between the front of the current vehicle and the rear of the vehicle in front. The second component reflects the impact of the acceleration of the vehicle in front on the predicted acceleration. The predicted acceleration is positively correlated with the acceleration of the vehicle in front; that is, the greater the acceleration of the vehicle in front, the greater the predicted acceleration, and vice versa. The third component reflects the impact of the acceleration of the vehicle on the left side on the predicted acceleration. The predicted acceleration is negatively correlated with the acceleration of the vehicle on the left side; that is, the greater the acceleration of the vehicle on the left side, the greater the predicted acceleration, and vice versa. The fourth component reflects the impact of the acceleration of the vehicle on the right side on the predicted acceleration. The predicted acceleration is also negatively correlated with the acceleration of the vehicle on the right side; that is, the greater the acceleration of the vehicle on the right side, the greater the predicted acceleration, and vice versa.

[0035] Optionally, the acceleration / deceleration recognition model can be represented by the following calculation formula: (1) in, This indicates the predicted acceleration. The maximum acceleration desired by the driver of the vehicle can be obtained through parameter calibration. The speed of the vehicle. The driver's desired vehicle speed can be obtained through parameter calibration. The acceleration exponent is a parameter used to describe the relationship between vehicle acceleration and desired speed. Its core function is to compare the current vehicle speed with the desired vehicle speed, and to influence acceleration calculation through an exponential decay function. The value range is 2-4, in the context of highways. A smaller value, such as 2, is typically used in urban road scenarios. A larger value, such as 4, is typically used. In the embodiments of this application, The value is also obtained based on the parameter calibration. This item reflects the gap between the current vehicle speed and the driver's desired speed, and is used to encourage the driver to accelerate.

[0036] The minimum headroom desired by the driver; headroom refers to the distance between the front of one vehicle and the rear of the vehicle in front. Similarly, it is obtained based on parameter calibration. The expected following distance is the driver's desired following distance. The expected following distance refers to the ideal following time interval calculated by the model based on the vehicle's current speed and the status of the vehicle ahead during operation. It is also obtained through parameter calibration. The actual headway is the distance between the front of the vehicle and the rear of the vehicle in front, which is obtained by the vehicle's detection components. This represents the speed difference between the vehicle and the vehicle in front. Comfort deceleration refers to the upper limit of deceleration set during vehicle deceleration to improve ride comfort; it is also obtained through parameter calibration. The item reflects the difference between the current front-end distance and the desired front-end distance, and is used to encourage the driver's braking behavior.

[0037] This is the first component.

[0038] This is the sensitivity coefficient of the driver of the vehicle to the acceleration of the vehicle in front, in the absence of a vehicle in front. The value of is 0, in the presence of a vehicle ahead. The value is obtained based on the parameter calibration. This represents the acceleration of the vehicle in front. This is the second component.

[0039] This is the sensitivity coefficient for the driver of the vehicle to the acceleration of the vehicle on the left. In the absence of the vehicle on the left, The value of is 0, in the case of a car on the left. The value is obtained based on the parameter calibration. This represents the acceleration of the car on the left. This is the third component.

[0040] This represents the driver's sensitivity coefficient to the acceleration of the vehicle on their right. In the absence of a vehicle on the right, The value of is 0, in the case of a vehicle on the right. The value is obtained based on the parameter calibration. This represents the acceleration of the vehicle on the right. This is the fourth component.

[0041] S40, implements corresponding motion sickness prevention measures based on predicted acceleration.

[0042] The vehicle determines whether the driver intends to accelerate or decelerate based on predicted acceleration. If the driver intends to accelerate, anti-motion sickness measures corresponding to that acceleration intention are implemented. If the driver intends to decelerate, anti-motion sickness measures corresponding to that deceleration intention are implemented. The anti-motion sickness measures for acceleration and deceleration intentions will be described in the following examples.

[0043] When predicting acceleration, the acceleration / deceleration intention recognition model fully considers the impact of the driving status information of neighboring vehicles on the driver of the vehicle itself. Therefore, the predicted acceleration is more accurate, and the subsequent anti-motion sickness measures based on the predicted acceleration are more appropriate, thereby improving the driving experience.

[0044] In summary, the technical solution provided in this application first obtains the driving status information and environmental information of the vehicle itself, including the driving status information of neighboring vehicles. An acceleration / deceleration intention prediction model processes this environmental information and the driving status information of the vehicle itself to obtain a predicted acceleration. Then, corresponding anti-motion sickness measures are taken based on the predicted acceleration. Since the driving status information of neighboring vehicles affects the driver's acceleration or deceleration intentions during vehicle operation—for example, if the vehicle in front accelerates, the driver is likely to accelerate as well to avoid vehicles cutting in from either side; conversely, if the vehicle on the left or right accelerates, the driver is unlikely to accelerate to avoid the safety hazards of driving side-by-side—in this application embodiment, the acceleration / deceleration intention recognition model fully considers the influence of the driving status information of neighboring vehicles on the driver when predicting acceleration. Therefore, the predicted acceleration is more accurate, and the subsequent anti-motion sickness measures based on the predicted acceleration are more appropriate, thereby improving the driving experience.

[0045] In some embodiments, execution begins from S10 when the vehicle's intelligent anti-motion sickness function is activated and it is detected that there are passengers in seats other than the driver's seat.

[0046] The intelligent motion sickness prevention function can be enabled by default in the vehicle or manually activated by passengers. In some embodiments, the vehicle's central control screen includes controls corresponding to the intelligent motion sickness prevention function, which the driver or passenger can trigger to enable or disable the function. In other embodiments, the user interface of the vehicle control software includes controls corresponding to the intelligent motion sickness prevention function, which users can trigger to enable or disable the function.

[0047] Optionally, the vehicle cabin is equipped with an image acquisition device to capture images of the vehicle interior and identify whether passengers are present in seats other than the driver's seat. Optionally, each seat in the vehicle is equipped with a seat sensor to detect whether a passenger is present in the corresponding seat based on the sensor's detection value.

[0048] Furthermore, if the vehicle's intelligent anti-motion sickness function is activated and a designated passenger is identified in a seat other than the driver's seat, execution begins from S10. The user can record the identity information and corresponding biometric information (such as facial features, voiceprint features, etc.) of the designated passenger for whom intelligent anti-motion sickness is activated. Subsequently, with the intelligent anti-motion sickness function activated and the vehicle in motion, the in-cabin image acquisition device captures images of the vehicle interior. If the in-cabin image includes the designated passenger's facial features, execution begins from S10. Alternatively, the in-cabin sound acquisition device collects voice information, and if the designated passenger's voiceprint features are extracted from the voice information, execution begins from S10.

[0049] Furthermore, starting from S10, the process begins when the vehicle's intelligent anti-motion sickness function is activated, passengers are detected in seats other than the driver's seat, and the vehicle is traveling on designated road conditions. These designated road conditions are set based on actual conditions and include bumpy roads, mountain roads, traffic congestion, etc.

[0050] Example 3 This application describes a method for controlling a vehicle. Please refer to the embodiments described herein. Figure 4 Prior to S30, the method also includes S50-S80.

[0051] S10, obtain vehicle driving status information.

[0052] S20, obtains environmental information about the vehicle.

[0053] S50 collects the driver's biometric information.

[0054] Biometric information refers to sensitive data used for identity verification based on an individual's physiological or behavioral characteristics. Biometric information includes, but is not limited to, facial features, voiceprint features, iris features, fingerprint features, palm print features, etc. In this embodiment, only facial features are used as an example of biometric information. Optionally, an image acquisition device is installed in the vehicle's cabin to capture images of the vehicle interior. The facial features of the driver are extracted from these images as the driver's biometric information.

[0055] S60 determines the driver's identity information based on the driver's biometric information.

[0056] The driver's identity information is used to uniquely identify the driver; it can be the driver's name or a pre-determined unique number. The vehicle can store the correspondence between different users' identity information and different biometric information. By querying these comparison relationships, the driver's identity information can be determined.

[0057] S70 determines the parameter values ​​of specified parameters in the acceleration / deceleration intention recognition model based on the driver's identity information.

[0058] The specified parameters include at least one of the following: the driver's maximum desired acceleration. Driver's desired speed Acceleration index Minimum headway expected by the driver Driver's expected following distance Comfort deceleration The driver's sensitivity coefficient to the acceleration of the vehicle in front. The driver's sensitivity coefficient to the acceleration of the vehicle on the left. The driver's sensitivity coefficient to the acceleration of the vehicle on the right. .

[0059] The aforementioned specified parameters are related to individual drivers. Different drivers have different driving habits and varying sensitivities to safety margins, resulting in different values. Therefore, parameter calibration is required to obtain the parameter values ​​corresponding to each driver. These parameter values ​​are then stored in association with the driver's identity information. Subsequently, when driving, the driver can directly read the parameter values ​​corresponding to the driver's identity information. The calibration process for the specified parameter values ​​will be described in the following examples.

[0060] S80 initializes the acceleration / deceleration intention recognition model based on the parameter values ​​of the specified parameters.

[0061] Replace the values ​​of the specified parameters in the acceleration / deceleration intent recognition model with the specified parameter values, and then initialize the acceleration / deceleration intent recognition model so that the specified parameter values ​​take effect.

[0062] In some embodiments, the calibration process for the parameter value of the specified parameter includes S90-S100.

[0063] S90, obtain the driver's driving trajectory dataset.

[0064] The driving trajectory dataset includes multiple driving trajectories. These trajectories were obtained by the vehicle's onboard sensors and detection components while the driver was driving the vehicle within a preset time period. The preset time period is set based on experiments or experience and is denoted as k-time.

[0065] Set the collection The actual acceleration trajectory of the vehicle over the specified time period is as follows , Based on the collected environmental data trajectory Combined with parameters The predicted vehicle acceleration trajectory can be obtained using the above acceleration / deceleration recognition model (Formula (1)). The calculation formula is expressed as: (2) Where the function This is the matrix operation form of the acceleration / deceleration intention recognition model, where x represents environmental parameter variables. . The parameters to be calibrated .

[0066] S100, calibrate the parameters of the initial acceleration / deceleration intention recognition model based on the driving trajectory dataset, so that the difference between the predicted acceleration output by the acceleration / deceleration intention recognition model and the vehicle's acceleration is less than a preset difference.

[0067] The purpose of parameter calibration is to find a suitable set of parameters. This allows the acceleration trajectory predicted by the acceleration / deceleration intention recognition model to be displayed. Compared with the actual collected acceleration trajectory To approximate the two, the formula for calculating the mean square error between them is as follows: (3) The genetic algorithm is used to optimize the model parameters. The expression for solving the parameter optimization problem is as follows: (4) In the formula: The parameter that minimizes the mean square error between the predicted and actual accelerations; and , where represents the upper and lower limits of the parameter value, and represents the range of possible values ​​for optimization.

[0068] In summary, the technical solution provided in this application uses parameter values ​​for specified parameters in the acceleration / deceleration intention recognition model that are calibrated based on the driver's historical driving conditions, thus enabling it to more accurately predict the driver's acceleration / deceleration intentions.

[0069] Example 4 This application describes a method for controlling a vehicle, based on... Figure 2 or Figure 4 In the optional embodiments provided, S40 is replaced by S410. Please refer to... Figure 5 The method includes the following steps.

[0070] S10, obtain vehicle driving status information.

[0071] S20, obtains environmental information about the vehicle.

[0072] Environmental information includes the driving status information of the vehicle's neighboring vehicles. The vehicle's neighboring vehicles include at least one of the following: the vehicle in front, the vehicle on the left, and the vehicle on the right. The vehicle on the left refers to the vehicle located in the designated space determined based on the vehicle and on the left side of the vehicle. The vehicle on the right refers to the vehicle located in the designated space and on the right side of the vehicle.

[0073] S30 processes the vehicle's driving status information and environmental information based on the acceleration / deceleration intention recognition model to obtain the predicted acceleration.

[0074] Acceleration / deceleration intention models are used to predict whether a driver intends to accelerate or decelerate based on the vehicle's driving status information and environmental information.

[0075] S410 controls the air vents corresponding to the passengers in the vehicle to blow air when the acceleration indicator suggests that the driver intends to accelerate.

[0076] A predicted acceleration greater than 0 indicates that the driver intends to accelerate.

[0077] When the predicted acceleration indicates the driver's intention to accelerate, the system first identifies whether there are passengers in seats other than the driver's seat. In some embodiments, the vehicle cabin is equipped with an image acquisition device that captures images of the vehicle interior and identifies whether passengers are in seats other than the driver's seat. In other embodiments, each seat in the vehicle is equipped with a seat sensor, and the presence of passengers in the corresponding seat is detected by the detection values ​​of the seat sensors.

[0078] The target air vent for the passenger refers to the air vent opposite the passenger's face. When air is emitted from the target air vent, the passenger's face can feel the wind. When the driver is predicted to accelerate, the air vent corresponding to the passenger's face is controlled to simulate the effect of wind blowing directly into the passenger's face during acceleration. This effectively eliminates the information gap between the passenger's visual and vestibular systems, allowing the passenger to be aware of the driver's impending acceleration or deceleration, thus effectively alleviating motion sickness.

[0079] In some embodiments, when the predicted acceleration indicates that the driver intends to accelerate, the vehicle controls the airflow from the target air vent corresponding to the passenger if the predicted acceleration is greater than a first acceleration. The first acceleration is set based on experiments or experience, and this application embodiment does not limit it. When the predicted acceleration is relatively small, the passenger's perception is not obvious, and in this case, the corresponding anti-motion sickness measures are not implemented, which can save vehicle energy consumption.

[0080] In some embodiments, S410 includes S411-S412.

[0081] S411 determines the airflow rate of the target air outlet based on predicted acceleration.

[0082] The airflow rate at the target outlet is positively correlated with the predicted acceleration. That is, the greater the predicted acceleration, the greater the airflow rate at the target outlet, and the smaller the predicted acceleration, the smaller the airflow rate at the target outlet.

[0083] Optionally, the airflow rate of the target air outlet is the product of the airflow rate acceleration proportionality coefficient and the predicted acceleration, plus the base airflow rate. The base airflow rate is determined by the vehicle's air conditioning system. The airflow rate acceleration proportionality coefficient is set based on experiments or experience. Optionally, the airflow rate of the target air outlet is determined according to the following formula.

[0084] (5) in, The airflow rate at the target air outlet. Based on the airflow rate, The proportionality coefficient of the airflow acceleration. To predict acceleration.

[0085] By determining the airflow rate of the target air outlet based on the predicted acceleration, the effect of the wind blowing in front of the vehicle during acceleration can be simulated more realistically.

[0086] S412 controls the target air outlet to discharge air according to the airflow rate.

[0087] In summary, the technical solution provided in this application, by controlling the airflow from the target air vent corresponding to the passenger when the driver's intention to accelerate is detected, simulates the effect of wind blowing directly into the passenger's face during acceleration. This effectively eliminates the information gap between the passenger's visual and vestibular systems, allowing the passenger to be aware of the driver's impending acceleration or deceleration, thereby effectively alleviating motion sickness. Furthermore, by determining the airflow from the target air vent based on the predicted acceleration, the effect of wind blowing directly into the passenger's face during acceleration can be simulated more realistically.

[0088] Example 5 This application describes a method for controlling a vehicle, based on... Figure 2 or Figure 4 In the optional embodiment provided by the example, S40 is replaced by S420. Please refer to... Figure 6 The method includes the following steps.

[0089] S10, obtain vehicle driving status information.

[0090] Environmental information includes the driving status information of the vehicle's neighboring vehicles. The vehicle's neighboring vehicles include at least one of the following: the vehicle in front, the vehicle on the left, and the vehicle on the right. The vehicle on the left refers to the vehicle located in the designated space determined based on the vehicle and on the left side of the vehicle. The vehicle on the right refers to the vehicle located in the designated space and on the right side of the vehicle.

[0091] S30 processes the vehicle's driving status information and environmental information based on the acceleration / deceleration intention recognition model to obtain the predicted acceleration.

[0092] Acceleration / deceleration intention models are used to predict whether a driver intends to accelerate or decelerate based on the vehicle's driving status information and environmental information.

[0093] S420, when the driver is predicted to have a deceleration intention, tightens the target seat belts for the passengers in control of the vehicle.

[0094] A predicted acceleration less than 0 indicates that the driver intends to decelerate. The target seatbelt for the passenger is the seatbelt strapped to the passenger's body.

[0095] In some embodiments, when the predicted acceleration indicates that the driver intends to decelerate, the vehicle controls the tightening of the target seatbelt corresponding to the passenger if the predicted acceleration is less than a second acceleration. The second acceleration is set based on experiments or experience, and this application embodiment does not limit it. When the second acceleration is less than the first acceleration, and the predicted acceleration is relatively small, the passenger's perception is not obvious. In this case, not implementing the corresponding anti-motion sickness measures can save vehicle energy consumption.

[0096] In some embodiments, S420 includes S421-S422.

[0097] S421 determines the tightening force of the target seat belt based on predicted acceleration.

[0098] The tightening force of the target seat belt is negatively correlated with the predicted acceleration. That is, the smaller the predicted acceleration, the greater the tightening force of the target seat belt, and vice versa.

[0099] Optionally, the target seatbelt's tension force is the product of the tension force deceleration proportionality coefficient and the predicted acceleration, plus the base pretension force. The pretension force is determined by the seatbelt system. The tension force deceleration proportionality coefficient is obtained from actual vehicle calibration. Optionally, the target seatbelt's tension force is determined according to the following formula.

[0100] (6) in, The tightening force of the target seat belt, For pre-tightening force, This is the proportionality coefficient for the tightening force deceleration. To predict acceleration.

[0101] By determining the tightening force of the target seat belt based on the predicted acceleration, the effect of the seat belt tightening felt by the human body due to inertia when the vehicle brakes during deceleration can be simulated more realistically.

[0102] S422, control the target seat belt to tighten according to the tightening force.

[0103] In summary, the technical solution provided in this application, by controlling the tightening of the target seatbelt corresponding to the passenger when the driver's intention to accelerate is detected, simulates the seatbelt tightening effect felt by the human body due to inertia when the vehicle brakes during deceleration. This effectively eliminates the information gap between the passenger's visual and vestibular systems, allowing the passenger to be aware of the situation when the driver is about to accelerate or decelerate, thereby effectively alleviating motion sickness. Furthermore, by determining the tightening force of the target seatbelt based on the predicted acceleration, the seatbelt tightening effect felt by the human body due to inertia when the vehicle brakes during deceleration can be simulated more realistically.

[0104] Example 6 This application also provides a device 700 for controlling a vehicle, please refer to... Figure 7 It includes: a status information acquisition module 710, used to execute step S10; an environmental information acquisition module 720, used to execute step S20; an acceleration prediction module 730, used to execute step S30; and a vehicle control module 740, used to execute step S40.

[0105] In some embodiments, the device 700 further includes a model initialization module (not shown) for performing S50-S80.

[0106] In some embodiments, the device 700 further includes a parameter calibration module (not shown) for performing S90-S100.

[0107] This application also provides a vehicle 800, please refer to... Figure 8 It includes a processor 810 and a memory 820, wherein the memory 810 is used to store computer programs; and the processor 820 is used to execute the programs stored in the memory 810 to implement the method for controlling a vehicle described in any embodiment of this application.

[0108] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for controlling a vehicle as described in any embodiment of this application.

[0109] In this application, "multiple" refers to two or more.

[0110] In this application, unless otherwise expressly defined, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0111] The terms “first,” “second,” “third,” “fourth,” etc., in this application (if present) are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0112] In this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, in this application, the character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0113] Unless otherwise specified, all steps in this application may be performed sequentially or randomly. For example, if the method includes steps A and B, it means that the method may include steps A and B performed sequentially, or it may include steps B and A performed sequentially. For example, if the method may also include step C, it means that step C may be added to the method in any order. For example, the method may include steps A, B, and C, or it may include steps A, C, and B, or it may include steps C, A, and B, etc.

[0114] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for controlling a vehicle, characterized in that, The method includes: Obtain vehicle driving status information; The environmental information of the vehicle is obtained, including the driving status information of the neighboring vehicles of the vehicle. The neighboring vehicles of the vehicle include at least one of the following: the vehicle in front, the vehicle on the left, and the vehicle on the right. The vehicle on the left refers to the vehicle located in the designated space determined based on the vehicle and on the left side of the vehicle. The vehicle on the right refers to the vehicle located in the designated space and on the right side of the vehicle. The vehicle's driving state information and environmental information are processed based on the acceleration / deceleration intention recognition model to obtain the predicted acceleration; the acceleration / deceleration intention model is used to predict whether the driver of the vehicle has an intention to accelerate or decelerate based on the vehicle's driving state information and environmental information. Based on the predicted acceleration, corresponding motion sickness prevention measures will be implemented.

2. The method according to claim 1, characterized in that, The driving status information of the neighboring vehicle includes the acceleration of the neighboring vehicle; When the neighboring vehicle includes the vehicle in front, the predicted acceleration is positively correlated with the acceleration of the vehicle in front; or / and when the neighboring vehicle includes the vehicle on the left, the predicted acceleration is negatively correlated with the acceleration of the vehicle on the left; or / and when the neighboring vehicle includes the vehicle on the right, the predicted acceleration is negatively correlated with the acceleration of the vehicle on the right.

3. The method according to claim 1, characterized in that, Before processing the vehicle's driving state information and environmental information based on the acceleration / deceleration intention recognition model to obtain the predicted acceleration, the method further includes: Collect the driver's biometric information; The driver's identity information is determined based on the driver's biometric information; The parameter values ​​of the specified parameters in the acceleration / deceleration intention recognition model are determined based on the driver's identity information; The acceleration / deceleration intention recognition model is initialized based on the parameter values ​​of the specified parameters.

4. The method according to claim 3, characterized in that, The calibration process for the specified parameter value includes: Obtain the driver's driving trajectory dataset, which includes multiple driving trajectories. Each driving trajectory includes the driving status information of the vehicle itself, the driving status information of neighboring vehicles, and the acceleration of the vehicle itself. The parameters of the initial acceleration / deceleration intention recognition model are calibrated based on the driving trajectory dataset so that the difference between the predicted acceleration output by the acceleration / deceleration intention recognition model and the acceleration of the vehicle is less than a preset difference.

5. The method according to any one of claims 1 to 4, characterized in that, The measures to prevent motion sickness based on the predicted acceleration include: When the predicted acceleration indicates that the driver intends to accelerate, the airflow from the target air vents corresponding to the passengers in the vehicle is controlled.

6. The method according to claim 5, characterized in that, The control of airflow from the passenger-specific vents of the vehicle includes: The airflow rate of the target air outlet is determined based on the predicted acceleration, and the airflow rate of the target air outlet is positively correlated with the predicted acceleration. Control the target air outlet to discharge air according to the specified airflow rate.

7. The method according to any one of claims 1 to 4, characterized in that, The measures to prevent motion sickness based on the predicted acceleration include: When the predicted acceleration indicates that the driver intends to decelerate, the target seat belts for the passengers in the vehicle are tightened.

8. The method according to claim 7, characterized in that, The tightening of the target seat belt corresponding to the passenger in the vehicle includes: The tightening force of the target seat belt is determined based on the predicted acceleration, and the tightening force of the target seat belt is negatively correlated with the predicted acceleration. The target seat belt is controlled to tighten according to the tightening force.

9. A device for controlling a vehicle, characterized in that, The device includes: The status information acquisition module is used to acquire the vehicle's driving status information; An environmental information acquisition module is used to acquire the environmental information of the vehicle. The environmental information includes the driving status information of the vehicle's neighboring vehicles. The vehicle's neighboring vehicles include at least one of the following: the vehicle in front, the vehicle on the left, and the vehicle on the right. The vehicle on the left refers to the vehicle located in a designated space determined based on the vehicle and on the left side of the vehicle. The vehicle on the right refers to the vehicle located in the designated space and on the right side of the vehicle. An acceleration prediction module is used to process the vehicle's driving state information and the vehicle's environmental information based on an acceleration / deceleration intention recognition model to obtain a predicted acceleration; the acceleration / deceleration intention model is used to predict whether the driver of the vehicle has an intention to accelerate or decelerate based on the vehicle's driving state information and the vehicle's environmental information. The vehicle control module is used to execute corresponding motion sickness prevention measures based on the predicted acceleration.

10. A vehicle, characterized in that, Including processor and memory, among which, The memory is used to store computer programs; The processor is configured to execute the computer program stored in the memory to implement the method described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-8.

Images