Vehicle control method, vehicle computer, vehicle and storage medium

Abstract

The present application relates to the field of vehicle control technology, and discloses a vehicle control method, a vehicle computer, a vehicle and a storage medium. The method is applied to the vehicle computer, and the method includes: determining the first road surface information of the first road area based on the image of the first road area where the vehicle is currently located acquired by the image acquisition device, and the road surface information includes the adhesion coefficient and the confidence of the adhesion coefficient; determining the first value corresponding to the reference index of the vehicle according to the vehicle's own state information, and determining whether the vehicle is in an understeering state based on the first value and the first reference value, and the first reference value is determined based on the first road surface information; in the case of determining that the vehicle is in an understeering state, executing the braking logic corresponding to the understeering state. Compared with the case where the first reference value is a fixed value, in this method, the first reference value can be obtained by dynamic adjustment based on the first road surface information, and the judgment of the understeering state is more timely, and the execution of the braking logic is also more timely.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a vehicle control method, a vehicle computer, a vehicle and a storage medium. Background Art

[0002] As people's requirements for vehicle safety and comfort are increasing, the electronic brake system (EBS) of vehicles, as an important part of vehicle safety systems, has developed rapidly. EBS collects vehicle's own state data such as vehicle's wheel speed, steering wheel angle and gravity based on speed sensors (such as four-wheel speed sensors), angle sensors (such as steering wheel angle sensors) and gravity sensors, determines the current value corresponding to the reference index corresponding to the abnormal state of the vehicle based on its own state data, and executes the braking logic corresponding to the abnormal state based on the current value and the reference value corresponding to the reference index, so as to make corresponding processing for the vehicle when the vehicle is in an abnormal state.

[0003] In the above method, the reference value corresponding to the reference index is obtained based on experiments and is a fixed value. However, under different road conditions, the degree of harm caused by the abnormal state of the vehicle is different. If the reference value corresponding to the above reference index is set too large or too small, it will affect the execution of the braking logic corresponding to the abnormal state of the vehicle, thereby affecting the driving safety of the user. Summary of the invention

[0004] Embodiments of the present application provide a vehicle control method, a vehicle computer, a vehicle, and a storage medium.

[0005] In a first aspect, an embodiment of the present application provides a vehicle control method, which is applied to a vehicle computer, and the method includes: determining first road surface information of the first road area based on an image of the first road area currently located by the vehicle acquired by an image acquisition device, wherein the road surface information includes an adhesion coefficient and a confidence level of the adhesion coefficient; determining a first numerical value corresponding to a reference index of the vehicle according to the vehicle's own state information, and determining whether the vehicle is in an understeering state based on the first numerical value and the first reference numerical value, wherein the reference index is used to indicate the possibility that the vehicle is currently in an understeering state, and the first reference numerical value is determined based on the first road surface information; when it is determined that the vehicle is in an understeering state, executing braking logic corresponding to the understeering state, wherein the braking logic is used to compensate for the understeering state of the vehicle.

[0006] It can be understood that the vehicle computer determines whether the vehicle is currently in an understeering state based on the first value and the first reference value, and the first reference value is obtained through dynamic adjustment based on the road surface information of the first road area where the vehicle is currently located. Compared with the case where the first reference value is a fixed value, this method adjusts the size of the first reference value based on different road surface information, and the determination of the understeering state is more timely, thereby making the execution of the braking logic more timely.

[0007] In a possible implementation of the first aspect above, the reference index includes the difference between a theoretical steering angle and an actual steering angle of the vehicle; and whether the vehicle is in an understeering state is determined based on the first numerical value and the first reference numerical value, including: when the first numerical value is greater than the first reference numerical value within a first time period, determining that the vehicle is currently in an understeering state.

[0008] In a possible implementation of the first aspect above, the first duration is determined according to first road surface information.

[0009] For example, the first duration can be obtained based on the second duration, the second duration can be the duration corresponding to the second road surface information, and the second road surface information can be the road surface information corresponding to the second road area located behind the first road area in the driving direction of the vehicle. In this case, if the vehicle computer determines that the confidence in the first road surface information is greater than the confidence threshold, and the adhesion coefficient in the first road surface information is less than the adhesion coefficient in the second road surface information, it means that the adhesion coefficient of the road is reduced, and the possibility of the vehicle producing an understeering state increases. At this time, the second duration can be reduced to the first duration, that is, the entry time for judging whether the vehicle is in an understeering state is shortened, so that the judgment of the understeering state is more timely.

[0010] Similarly, when the adhesion coefficient in the first road surface information is greater than the adhesion coefficient in the second road surface information, it means that the possibility of the vehicle understeering is reduced, and the second time duration can be increased to the first time duration.

[0011] In a possible implementation of the first aspect above, the first reference value is determined based on the first road surface information, including: obtaining a second reference value corresponding to the stored reference indicator, wherein the second reference value is determined based on the second road surface information; and updating the second reference value to the first reference value based on the first road surface information and the second road surface information.

[0012] It can be understood that the second reference value is determined based on the second road surface information, wherein the second road surface information can be the road surface information corresponding to the second road area located behind the first road area in the driving direction of the vehicle. That is to say, at this time, the second reference value is also dynamically determined based on the second road surface information. In addition, the second road surface information can also be a kind of road surface information determined in advance through experiments before the vehicle leaves the factory. In this case, the second reference value is a fixed value obtained based on the second road surface information, so as to determine whether the vehicle is in an understeering state based on the fixed second reference value during the driving process of the vehicle.

[0013] In a possible implementation of the first aspect above, the second reference value is updated to the first reference value based on the first road surface information and the second road surface information, including: when the confidence in the first road surface information is greater than the first confidence and the adhesion coefficient in the first road surface information is smaller than the adhesion coefficient in the second road surface information, the second reference value is reduced to the first reference value; when the confidence in the first road surface information is greater than the first confidence and the adhesion coefficient in the first road surface information is greater than the adhesion coefficient in the second road surface information, the second reference value is increased to the first reference value.

[0014] Taking the first reference value as the first UCL entry threshold corresponding to the first road area and the second reference value as the second UCL entry threshold corresponding to the second road area as an example, if the road adhesion coefficient decreases from the second road area to the first road area, it means that the vehicle is more likely to understeer and then slip. At this time, the size of the UCL entry threshold can be dynamically adjusted based on the first road information, such as reducing the second UCL entry threshold to the first UCL entry threshold, so that the UCL control logic is easier or earlier to be triggered.

[0015] It can be understood that the execution premise of the above process is that the confidence of the adhesion coefficient in the first road surface information is high, for example, greater than the first confidence. In this way, the accuracy of the adhesion coefficient in the first road surface information can be ensured to be high, thereby making the accuracy of the above adjustment process also high.

[0016] The formula for determining the UCL entry threshold is: UCL entry threshold = (basic brake intervention threshold - UCL offset) × correction factor. The correction factor is obtained based on the product of the road condition judgment correction factor, the lateral acceleration correction factor and the turning radius correction factor. Therefore, it can be seen from the above formula that the road condition judgment correction factor is positively correlated with the UCL entry threshold.

[0017] Therefore, if the road adhesion coefficient decreases from the second road area to the first road area, the value of the road condition judgment correction factor can be reduced, so that the UCL entry threshold value can be reduced, that is, the second UCL entry threshold value is reduced to the first UCL entry threshold value, so that the UCL control logic is easier or earlier to be triggered.

[0018] Similarly, if the road adhesion coefficient increases from the second road area to the first road area, the UCL entry threshold value can be increased by increasing the road condition judgment correction factor.

[0019] In a possible implementation of the first aspect above, the second road surface information is road surface information corresponding to a second road area behind the first road area; and the second reference value is determined based on a third reference value corresponding to the stored reference indicator and the second road surface information.

[0020] In a possible implementation of the first aspect above, the second reference value is determined based on a third reference value corresponding to a pre-stored reference indicator and the second road surface information, including: the second reference value is obtained by reducing the third reference value when the difference between the adhesion coefficient in the first road surface information and the adhesion coefficient in the second road surface information is greater than a threshold, and the adhesion coefficient in the first road surface information is smaller than the adhesion coefficient in the second road surface information; or, the second reference value is obtained by increasing the third reference value when the difference between the adhesion coefficient in the first road surface information and the adhesion coefficient in the second road surface information is greater than a threshold, and the adhesion coefficient in the first road surface information is larger than the adhesion coefficient in the second road surface information; wherein the difference between the third reference value and the second reference value is smaller than the difference between the second reference value and the first reference value.

[0021] It can be understood that the method provided in the present application can also pre-fine-tune the UCL entry threshold value by judging the road surface information when the adhesion coefficient of the road surface in front of the vehicle is about to change suddenly. Exemplarily, when the vehicle is traveling on the second road area, if it is determined that the difference between the adhesion coefficient of the first road area in front and the adhesion coefficient of the current second road area is greater than the threshold value, and the adhesion coefficient of the first road area is less than the adhesion coefficient of the second road area (that is, the adhesion coefficient is about to drop suddenly), the current third UCL entry threshold value (that is, the third reference value) can be reduced to the second UCL entry threshold value (that is, the second reference value) at this time, and preparations can be made in advance for the sudden change of the road surface information. When the vehicle is traveling on the first road area, the UCL entry threshold value can be further reduced based on the second road surface information and the first road surface information, that is, the second reference value is reduced to the first reference value.

[0022] However, in order to avoid the UCL entry threshold value being pre-adjusted too large and affecting the current driving state of the vehicle, the value of the pre-adjusted UCL entry threshold value needs to be smaller than the adjustment value of the current UCL entry threshold value, that is, the difference between the second reference value and the third reference value needs to be smaller than the difference between the second reference value and the first reference value.

[0023] In a possible implementation of the first aspect above, when it is determined that the vehicle is in an understeering state, braking logic corresponding to the understeering state is executed, including: determining a second torque corresponding to the vehicle's own state information; corresponding to the second torque being greater than a first torque threshold corresponding to the vehicle's engine, reducing the torque output by the vehicle's engine from the first torque to the second torque; corresponding to the second torque being less than or equal to the first torque threshold corresponding to the engine, reducing the torque output by the vehicle's engine from the first torque to the first torque threshold.

[0024] In a possible implementation of the first aspect above, the first torque threshold is determined based on the following method: obtaining a second torque threshold corresponding to the stored vehicle engine, the second torque threshold being obtained based on third road surface information; updating the second torque threshold to the first torque threshold based on the first road surface information and the third road surface information, wherein the third road surface information is road surface information corresponding to the second torque threshold.

[0025] It can be understood that the third road surface information can be road surface information corresponding to the third road area located behind the first road area where the vehicle is currently located in the driving direction of the vehicle. That is to say, at this time, the second torque threshold is also dynamically determined based on the third road surface information. In addition, the third road surface information can also be a kind of road surface information that is pre-determined through experiments before the vehicle leaves the factory. In this case, the second torque threshold is a fixed value obtained based on the third road surface information, so that a specific torque reduction operation can be performed based on the fixed second torque threshold during the driving process of the vehicle.

[0026] In a possible implementation of the first aspect above, the second torque threshold is updated to the first torque threshold based on the first road surface information and the third road surface information, including: when the confidence in the first road surface information is greater than the second confidence and the adhesion coefficient in the first road surface information is smaller than the adhesion coefficient in the third road surface information, the second torque threshold is increased to the first torque threshold; when the confidence in the first road surface information is greater than the second confidence and the adhesion coefficient in the first road surface information is greater than the adhesion coefficient in the third road surface information, the second torque threshold is reduced to the first torque threshold.

[0027] Taking the first torque threshold as the first torque minimum limit value corresponding to the first road area and the second torque threshold as the second torque minimum limit value corresponding to the third road area as an example, if the road adhesion coefficient decreases from the third road area to the first road area, it means that the understeering state of the vehicle is more obvious at this time, and the engine torque needs to be further reduced. At this time, in order to avoid the torque being reduced too little, the torque minimum limit value can be dynamically adjusted, such as increasing the second torque minimum limit value to the first torque minimum limit value.

[0028] It can be understood that the execution premise of the above process is that the confidence of the adhesion coefficient in the first road surface information is high, for example, greater than the second confidence. In this way, the accuracy of the adhesion coefficient in the first road surface information can be ensured to be high, thereby making the accuracy of the above adjustment process also high. In addition, the values ​​of the first confidence and the second confidence can be the same or different.

[0029] The formula for determining the minimum torque limit value is: MMin,Friction=f(Engine_min_tq_tab,Engine_min_tq_mu_tab). MMin,Friction represents the minimum torque limit value based on the friction coefficient; f represents the friction coefficient of the engine; the Engine_min_tq_tab parameter represents the reference torque size of the four wheels of the vehicle; the Engine_min_tq_mu_tab parameter represents the reference torque adjustment coefficient of the four wheels of the vehicle. It can be seen from the above formula that the minimum torque limit value is positively correlated with Engine_min_tq_tab or Engine_min_tq_mu_tab.

[0030] Therefore, if the road adhesion coefficient decreases from the third road area to the first road area, the value of Engine_min_tq_tab or Engine_min_tq_mu_tab can be increased, so that the minimum torque limit value can be increased to avoid reducing the engine torque too much.

[0031] Similarly, if the road adhesion coefficient increases from the third road area to the first road area, the minimum torque limit value can be reduced by reducing the value of Engine_min_tq_tab or Engine_min_tq_mu_tab.

[0032] In a second aspect, the present application provides a vehicle computer, comprising: one or more processors; one or more memories; one or more memories storing one or more programs, when one or more programs are executed by one or more processors, the vehicle computer executes the first aspect and any possible vehicle control method of the first aspect.

[0033] In a third aspect, the present application provides a vehicle, and the vehicle includes the vehicle computer involved in the aforementioned second aspect.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium having instructions stored thereon, which, when executed on a computer, causes the computer to execute the first aspect and any possible vehicle control method of the first aspect.

[0035] In the fifth aspect, the present application provides a computer program product, including: execution instructions, the execution instructions are stored in a readable storage medium, at least one processor of the vehicle computer can read the execution instructions from the readable storage medium, and at least one processor executes the execution instructions so that the vehicle computer implements the first aspect and any possible vehicle control method of the first aspect.

[0036] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects:

[0037] In the embodiment of the present application, the vehicle computer determines the first reference value corresponding to the reference index based on the first road surface information (such as adhesion coefficient, confidence) of the road the vehicle is currently on, and determines the first value corresponding to the reference index based on the vehicle's own state information (such as the steering angle of the wheel), and determines whether the vehicle is currently in an understeering state based on the first value and the first reference value. If so, the braking logic corresponding to the understeering state is executed to compensate for the understeering state of the vehicle. Compared with the case where the first reference value is a fixed value, in this method, the first reference value can be obtained through dynamic adjustment based on the first road surface information, and the determination of the understeering state is more timely, thereby making the execution of the braking logic more timely. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 According to some embodiments of the present application, a data processing flow chart of a conventional electronic braking system is shown;

[0039] Figure 2 According to some embodiments of the present application, a flow chart of a vehicle control method is shown;

[0040] Figure 3 According to some embodiments of the present application, a schematic diagram of a front area in a driving direction of a vehicle is shown;

[0041] Figure 4 According to some embodiments of the present application, a schematic diagram of calibration parameters included in a brake function control module is shown;

[0042] Figure 5 According to some embodiments of the present application, a schematic diagram of parameters included in a correction coefficient is shown;

[0043] Figure 6According to some embodiments of the present application, a schematic diagram of an adjustment method of a calibration parameter mapping table is shown;

[0044] Figure 7 According to some embodiments of the present application, a flow chart for adjusting a calibration parameter mapping table in the case of a sudden change in road surface is shown;

[0045] Figure 8 According to some embodiments of the present application, a data processing flow chart of an electronic braking system corresponding to a vehicle control method is shown;

[0046] Fig. 9 According to some embodiments of the present application, a data processing flow chart of an electronic braking system corresponding to another vehicle control method is shown;

[0047] Fig.10 According to some embodiments of the present application, a system schematic diagram of a vehicle computer is shown. DETAILED DESCRIPTION

[0048] The illustrative embodiments of the present application include, but are not limited to, a vehicle control method, a vehicle computer, a vehicle, and a storage medium.

[0049] The following first briefly describes the principles of the electronic braking system inside the vehicle.

[0050] Figure 1 FIG. 1 shows a data processing flow chart of a conventional electronic brake system. It can be understood that, taking a four-wheel vehicle as an example, Figure 1 Among them, the four-wheel speed sensor is used to obtain the wheel speed signal of each of the four wheels of the vehicle; the steering wheel angle sensor is used to determine the rotation angle signal and rotation direction signal of the steering wheel when the vehicle is turning; the gravity sensor is used to determine the center of gravity signal of the vehicle based on the gravity of the vehicle, etc.

[0051] Therefore, after the four-wheel speed sensors obtain the wheel speed signals of each wheel, the steering wheel angle sensor obtains the steering wheel rotation angle signal and rotation direction signal, and the gravity sensor obtains the vehicle's center of gravity and other signals, the above signals can be input into the vehicle's motion model to obtain the vehicle's wheel speed, center of gravity position, rotation angle, and rotation direction and other result data, and the vehicle's lateral and longitudinal accelerations, yaw angular velocity and other result data can be further calculated.

[0052] The lateral acceleration of a vehicle refers to the acceleration caused by the centrifugal force generated when the vehicle turns; the longitudinal acceleration of a vehicle refers to the acceleration in the direction of travel of the vehicle. The yaw rate refers to the angular velocity of the vehicle rotating around the Z axis perpendicular to the ground.

[0053] In addition, based on the vehicle's motion model, the vehicle's pedal status data (for example, determined by the displacement of the pedal) and the hydraulic pressure data of each connected pump inside the vehicle can be obtained according to the pedal status signals and hydraulic pressure signals collected by the pedal sensors, hydraulic pressure sensors, etc. inside the vehicle, and other result data.

[0054] Then, the result data output by the vehicle motion model and the vehicle calibration parameter mapping table (hereinafter referred to as the mapping table) are input into the input signal preprocessing module for data preprocessing to obtain preprocessed data. The preprocessing operation may, for example, be to adjust the format of the data to a data type that can be called by the brake function module in the electronic brake system, and to remove noise data from the data.

[0055] The calibration parameter mapping table is used to indicate the one-to-one correspondence between each control logic and the corresponding parameter size in the input signal preprocessing module, the brake function control module and the arbitration algorithm module. The preprocessing module, the brake function control module and the arbitration algorithm module can all assist in implementing their respective algorithms and functions by searching the mapping table.

[0056] Taking the braking function control module as an example, the braking function control module includes multiple systems, such as the active yaw control (AYC) system, the anti-lock brake system, etc. These systems can calculate their respective functional requirements based on the data obtained after the above preprocessing. For example, the AYC system can actively brake the wheels to generate additional yaw torque, thereby controlling the yaw rate and yaw angular velocity of the vehicle and improving the stability and handling performance of the vehicle. The system has judgment logics such as understeer control logic (UCL), and the parameters corresponding to the understeer control logic further include UCL entry threshold value (UCL_THRESHOLD_IN), UCL exit threshold value (UCL_THRESHOLD_OUT), confirmation time for entering UCL, and confirmation time for exiting UCL. For example, the UCL entry threshold value corresponds to the first value, the UCL exit threshold value corresponds to the second value, the confirmation time for entering UCL corresponds to the first time period, and the confirmation time for exiting UCL corresponds to the second time period. The UCL entry threshold value and the first value may constitute a calibration parameter mapping table.

[0057] It should be understood that the understeering state means that when the steering wheel angle of the vehicle is fixed, if the vehicle's driving speed is changed, the vehicle's actual turning radius is larger than the theoretical turning radius, and the vehicle cannot steer according to the theoretical turning radius based on the steering wheel angle, that is, the vehicle slides outward when turning.

[0058] For example, if the first relevant parameter is determined to be greater than the first value based on the vehicle's own state data (steering wheel steering angle, wheel steering angle, etc.) and lasts for a first time period, it means that the current state of the vehicle is an understeering state, and the braking logic needs to be executed, such as calculating the target speed to which the vehicle needs to decelerate to compensate for the understeering state of the vehicle by decelerating, or reducing the torque of the vehicle's engine to ensure the driving safety of the vehicle. Similarly, if the second relevant parameter is determined to be greater than the second value based on the vehicle's own state data and lasts for a second time period, it means that the current vehicle is not in an understeering state, that is, there is no need to execute the braking logic.

[0059] When the vehicle is in an understeering state, the brake function control module calculates the target speed or target torque, issues a deceleration request or a torque reduction request (i.e., a function request), and submits it to the arbitration algorithm module for processing.

[0060] The arbitration algorithm module performs arbitration based on the functional requirements of each system and the preprocessed data output by the input signal preprocessing module to obtain an arbitration conclusion. For example, if the anti-lock braking system of the vehicle determines that the functional requirement of the anti-lock braking system is to request a larger wheel-end pressure based on the current vehicle state, and the active yaw control module determines that its functional requirement is to request a smaller wheel-end pressure, and because only one wheel-end pressure can be output to the same wheel of the vehicle at the same time, the arbitration algorithm module is required to arbitrate the different wheel-end pressures requested by the anti-lock braking system and the active yaw control module to obtain the final wheel-end pressure.

[0061] Based on the above content, after the arbitration algorithm module obtains the arbitration conclusion, it will hand over the arbitration conclusion to the lower-level execution module for execution. For example, if the arbitration conclusion is to set the wheel end pressure of the left front wheel of the vehicle to M Newtons, the lower-level execution module can apply the wheel end pressure of M Newtons to the left front wheel of the vehicle based on the arbitration conclusion. At this point, the data processing process of the electronic brake system ends.

[0062] Based on the above process, it can be known that the reference value corresponding to the reference index corresponding to the abnormal state of the vehicle is fixed, but under different road conditions, the degree of harm of the abnormal state of the vehicle is different. If the reference value corresponding to the reference index is set too large or too small, it will affect the execution of the braking logic corresponding to the abnormal state of the vehicle, and thus affect the driving safety of the user. Taking the current value corresponding to the reference index as the first related parameter mentioned above as an example, after the vehicle computer determines the first related parameter based on the vehicle's own state data, if it is determined that the first related parameter is greater than the first value (UCL entry threshold value), it can be determined that the vehicle is in an understeering state, and then the understeering state is processed. However, if the first value is set too large, it will be determined that the vehicle is in an understeering state only when the vehicle is in a more serious understeering state, and then the understeering state will be processed. At this time, the driving safety of the user cannot be guaranteed.

[0063] To solve the above technical problems, an embodiment of the present application provides a vehicle control method. In this method, the vehicle computer can determine the road surface conditions (for example, the adhesion coefficient of the road surface, the confidence of the adhesion coefficient, etc.) based on the image of the road surface on which the vehicle is currently located captured by the image acquisition device. Then, the vehicle computer can determine the reference value (i.e., the first reference value) corresponding to the reference index of the abnormal state of the vehicle based on the road surface conditions, and determine the current value (i.e., the first value) corresponding to the reference index based on the vehicle's own state data (e.g., the steering angle of the steering wheel, the steering angle of the wheels, etc.), and then execute the braking logic corresponding to the abnormal state based on the current value and the reference value (for example, when the current value is greater than the reference value, it is determined that the vehicle is in an abnormal state, and the corresponding braking logic is executed, such as reducing the torque of the vehicle engine, etc.), so as to intervene in the abnormal state of the vehicle and ensure the driving safety of the vehicle.

[0064] In some embodiments, the vehicle computer can input at least one image of the road surface on which the vehicle is currently located, obtained by an image acquisition device, into a pre-trained adhesion determination model to obtain the road conditions of the road surface on which the vehicle is currently located, such as the adhesion coefficient and the confidence level of the adhesion coefficient.

[0065] It should be understood that the adhesion determination model can be any neural network model that can process images, such as a convolutional neural network model (CNN). Taking the adhesion determination model as a convolutional neural network model as an example, after the vehicle computer inputs at least one image into the convolutional neural network, the convolutional neural network model determines the adhesion coefficient of the road surface by extracting road surface features in the image, and outputs the relevant confidence level. Among them, the confidence level is used to indicate the reliability of the adhesion coefficient, which can be expressed as a percentage.

[0066] It can be understood that a low road adhesion coefficient means that the road surface is relatively smooth, such as an icy or snowy road; a high road adhesion coefficient means that the road surface is relatively rough, such as an ordinary asphalt road or a gravel road.

[0067] In some embodiments, the vehicle computer may input the obtained vehicle state data into an algorithm of a current value corresponding to a specific reference index to obtain the current value corresponding to the reference index. It should be understood that the algorithm of the current value corresponding to the reference index may be any algorithm that can determine the current value.

[0068] In some embodiments, the vehicle computer may determine the reference value corresponding to the reference indicator of the abnormal state of the vehicle based on the road conditions by adjusting the reference value of the road behind the current road corresponding to the reference indicator inside the vehicle in real time according to the road conditions to obtain the reference value of the current road corresponding to the reference indicator.

[0069] For example, taking the understeer state as an example, when it is determined that the adhesion coefficient of the road on which the vehicle is traveling is reduced, it means that the possibility of the vehicle understeer and then skidding increases. At this time, the UCL entry threshold value can be lowered, and the understeer state of the vehicle can be determined earlier, thereby making the handling of the abnormal state of the vehicle more timely.

[0070] In some embodiments, when the image acquisition device determines that the adhesion has suddenly changed, for example, the road surface in front of the vehicle changes from a high-adhesion road surface to a low-adhesion road surface, the reference value corresponding to the reference indicator can be pre-adjusted, for example, the UCL entry threshold can be pre-lowered. In addition, the confirmation time for entering the UCL can be pre-adjusted, for example, the confirmation time for entering the UCL can be reduced to further speed up the intervention of the understeering logic. In this way, the abnormal state of the vehicle can be processed in time by pre-adjusting the reference value corresponding to the reference indicator, thereby reducing the severity of the abnormal state of the vehicle caused by the sudden change in the road adhesion.

[0071] It is understood that the vehicle control method provided in the embodiment of the present application can be applied to a vehicle computer. It is understood that the vehicle computer is any device in a vehicle that can execute the method provided in the present application, such as a processor of the vehicle.

[0072] In order to make the purpose and technical solution of the present application clearer, the technical solution in the embodiments of the present application will be clearly and comprehensively described below with reference to the accompanying drawings. Figure 2 According to the embodiment of the present application, a flow chart of a vehicle control method is shown. In addition, the execution subject of each of the following steps is the vehicle computer, and for the convenience of description, they are not shown one by one. Figure 2 As shown, the process includes but is not limited to the following steps:

[0073] 201: Determine first road surface information of a first road area based on an image of a first road area currently located by a vehicle acquired by an image acquisition device.

[0074] In the embodiment of the present application, the first road surface information includes but is not limited to the adhesion coefficient of the road surface (used to indicate the adhesion of the road surface) and the confidence (or certainty) of the adhesion coefficient. It can be understood that the confidence is used to indicate the reliability of the adhesion coefficient.

[0075] In an exemplary embodiment, if the vehicle computer wants to obtain the road surface information of the first road area where the vehicle is currently located, it can first obtain the road surface information of the front area in the direction of vehicle travel (i.e., the front area of ​​the first road area) based on the image acquisition device. Then, based on the road surface information of the front area, the distance between the front area and the current position of the vehicle, the current speed of the vehicle, etc., the vehicle computer can determine when the vehicle is in the aforementioned front area, and store the above information in the database inside the vehicle computer. Therefore, when the vehicle travels to the aforementioned front area, the road surface information of the road surface where the vehicle is currently located can be obtained by querying the database.

[0076] Among them, the way in which the vehicle computer obtains road surface information of the front area in the driving direction of the vehicle based on the image acquisition device includes but is not limited to: after the vehicle computer obtains at least one image of the road surface in the front area in the driving direction of the vehicle based on the image acquisition device located on the vehicle, the at least one image can be input into a pre-trained adhesion determination model, and the adhesion determination model can output the adhesion coefficient of the road surface corresponding to the front area in the driving direction of the vehicle and the confidence of the adhesion coefficient (which can also be understood as the confidence of the adhesion determination model) based on the at least one input image.

[0077] The adhesion determination model can be any neural network model that can process images, such as a convolutional neural network model (CNN). Taking the adhesion determination model as a convolutional neural network model as an example, after the vehicle computer inputs at least one image into the convolutional neural network, the convolutional neural network model determines the adhesion coefficient of the road surface by extracting road surface features in the image, and outputs the relevant confidence level.

[0078] It can be understood that the front area mentioned above can be directly in front of the vehicle in the direction of travel, or it can be diagonally in front of the vehicle in the direction of travel. The range of the front area can be set based on experience and can also be flexibly adjusted according to actual application scenarios.

[0079] Figure 3 Schematic diagram of the front area in the direction of vehicle travel is shown. Figure 3As shown, the front area in the direction of vehicle travel is divided into multiple different sub-areas. Among them, sub-areas A1, A2 and A3 can be regarded as different areas directly in front of the right wheel in the direction of vehicle travel; similarly, sub-areas B1, B2 and B3 can be regarded as different areas diagonally in front of the right wheel in the direction of vehicle travel. The area directly in front of the left wheel in the direction of vehicle travel and the area diagonally in front of the left wheel in the direction of vehicle travel are the same, and will not be described here one by one.

[0080] based on Figure 3 After the vehicle computer obtains at least one image of the front area in the direction of vehicle travel based on the image acquisition device, the at least one image is input into the adhesion determination model, and the adhesion determination model can output the adhesion coefficient of the road surface corresponding to each sub-area in the direction of vehicle travel and the confidence of the adhesion coefficient. It can be understood that the adhesion determination model can also output the reference distance between each sub-area and the current position of the vehicle based on at least one image.

[0081] After the vehicle computer determines the time when the vehicle arrives at each sub-area based on the reference distance and the current speed of the vehicle, the adhesion coefficient and confidence of the road surface corresponding to each time and each sub-area can be stored in the database. When the vehicle is determined to have traveled to the corresponding sub-area based on each time, the road surface information of the vehicle's current road surface can be obtained by querying the database.

[0082] In an exemplary embodiment, the distance range of the sub-area, the adhesion coefficient of the road surface, and the magnitude of the confidence (certainty) can be seen in the following Table 1.

[0083] Table 1

[0084]

[0085]

[0086] It can be seen from Table 1 above that for the distance range of the sub-areas, the area directly in front of the left and right wheels of the vehicle and the area diagonally in front of the vehicle are divided into three sub-areas, with 5 meters, 15 meters and 25 meters as boundaries respectively. For the road adhesion coefficient, if the road surface is a dry new road made of concrete, then this type of road surface corresponds to a reference adhesion coefficient; if the road surface is a dry old road made of concrete, then it corresponds to another reference adhesion coefficient. The same is true for other situations, which will not be repeated here. For the degree of certainty, taking the determination of the degree of certainty through the adhesion determination model as an example, the adhesion determination model can output a visual reference weight ratio, that is, the degree of certainty, according to the complexity of the information in the image input to the model. It can be understood that in the embodiment of the present application, because the road surface information obtained based on the adhesion determination model only serves to assist in determining the driving state of the vehicle, the value range of the degree of certainty can be 0%-50%.

[0087] It can be understood that the relevant data involved in the above Table 1 are only exemplary and do not constitute all limitations of the present application. In other words, data such as confidence can be flexibly adjusted according to actual application conditions.

[0088] 202: Determine a first value corresponding to a reference index of the vehicle based on the vehicle's own state information, and determine whether the vehicle is in an understeering state based on the first value and the first reference value, wherein the reference index is used to indicate the possibility that the vehicle is currently in an understeering state, and the first reference value is determined based on the first road surface information.

[0089] It can be understood that the reference index can refer to the calibration parameters mentioned above (such as the difference between the theoretical steering angle and the actual steering angle of the vehicle). In this case, the reference index and the first reference value corresponding to the reference index can constitute a calibration parameter mapping table. In an embodiment of the present application, the calibration parameter mapping table includes all calibration parameters inside the vehicle and the reference values ​​corresponding to each calibration parameter. Taking the electronic braking system in the vehicle as an example, the input signal preprocessing module, the braking function control module and the arbitration algorithm module in the electronic braking system, each module corresponds to a plurality of calibration parameters, and these calibration parameters can assist each module in executing its own braking logic for realizing the braking function of the vehicle.

[0090] Taking the brake function control module as an example, Figure 4 FIG. 1 shows a schematic diagram of the calibration parameters included in the brake function control module. Figure 4 As shown, the brake function control module includes multiple control systems, such as anti-lock brake system (ABS), active yaw control (AYC) system, traction control system (TCS), diesel injection electronic control (EDC) system, hill start assist (HAS) system, intelligent integrated brake (IPB) system, steep slope descent control (Hill Descent Control) system, etc.

[0091] Take the Active Yaw Control (AYC) system in multiple control systems as an example. The system includes multiple control logics, such as BetaP, DpsiP, Dstangle, LCL, SESP, ARP, UCL, TSA, DTV, etc. Take UCL control logic as an example. UCL control logic is usually triggered only when the vehicle has obvious understeer. The logic includes multiple calibration parameters, such as UCL entry threshold (UCL_THRESHOLD_IN), UCL exit threshold (UCL_THRESHOLD_OUT), confirmation time for entering UCL, and confirmation time for exiting UCL.

[0092] It should be understood that in the embodiment of the present application, the reference index may include the difference between the theoretical steering angle (e.g., the front wheel steering angle) and the actual steering angle (front wheel steady-state steering angle) of the vehicle in the first road area. In this case, the first reference value may be the value corresponding to the UCL entry threshold value mentioned above.

[0093] Among them, the measurement value of the front wheel steering angle is obtained by measuring the steering wheel angle and dividing it by the steering ratio of the steering system, which can also be understood as the turning angle of the vehicle's steel rim; the front wheel steady-state steering angle is a system calculated value, which can be understood as the angle of rotation of the vehicle tire tread in contact with the road surface.

[0094] When the reference indicator includes the difference between a theoretical steering angle and an actual steering angle of the vehicle, determining whether the vehicle is in an understeering state is based on a first numerical value and a first reference numerical value, including: when the first numerical value is greater than the first reference numerical value within a first time period, determining that the vehicle is currently in an understeering state.

[0095] The first duration may refer to the confirmation duration of entering the UCL. It can be understood that if the first value is greater than the first reference value and lasts for the first duration, it can be determined that the vehicle is currently in an understeering state.

[0096] Normally, the reference values ​​corresponding to the above calibration parameters are fixed values. However, in the embodiment of the present application, the reference values ​​corresponding to the calibration parameters can be dynamically adjusted based on the road surface information to change the triggering or execution conditions of each braking logic.

[0097] Therefore, in one possible implementation, the method for determining the first reference value includes but is not limited to: obtaining a second reference value corresponding to a stored reference indicator, wherein the second reference value is determined based on second road surface information; and updating the second reference value to the first reference value based on the first road surface information and the second road surface information.

[0098] It can be understood that in the embodiment of the present application, the second reference value can be updated to the first reference value based on the first road surface information and the second road surface information, that is, the process of determining the first reference value corresponding to the reference indicator based on the first road surface information and the second road surface information is a dynamic adjustment process. Further, the methods of updating the second reference value to the first reference value based on the first road surface information and the second road surface information include the following two methods:

[0099] Method 1: When the confidence in the first road surface information is greater than the first confidence and the adhesion coefficient in the first road surface information is less than the adhesion coefficient in the second road surface information, the second reference value is reduced to the first reference value.

[0100] Method 2: When the confidence in the first road surface information is greater than the first confidence and the adhesion coefficient in the first road surface information is greater than the adhesion coefficient in the second road surface information, the second reference value is increased to the first reference value.

[0101] The second road surface information is road surface information corresponding to a second road area behind the first road area; and the second reference value is determined based on a third reference value corresponding to the stored reference index and the second road surface information.

[0102] For the above-mentioned method 1, in the embodiment of the present application, taking the first reference value as the first UCL entry threshold value corresponding to the first road area and the second reference value as the second UCL entry threshold value corresponding to the second road area as an example, if the road adhesion coefficient decreases from the second road area to the first road area, it means that the vehicle is more likely to understeer and then slip. At this time, the size of the UCL entry threshold value can be dynamically adjusted based on the first road information, such as reducing the second UCL entry threshold value to the first UCL entry threshold value, so that the UCL control logic is easier or earlier to be triggered.

[0103] In addition, the execution premise of the above process is that the confidence of the adhesion coefficient in the first road surface information is high, for example, greater than the first confidence. In this way, the accuracy of the adhesion coefficient in the first road surface information can be ensured to be high, thereby making the accuracy of the above adjustment process also high.

[0104] In an exemplary embodiment, the UCL entry threshold value is determined by the following formula:

[0105] UCL entry threshold value = (brake intervention basic threshold value - UCL offset value) × correction coefficient formula (1)

[0106] In the traditional method of determining the UCL entry threshold value, the parameters such as the basic threshold value of brake intervention, the UCL bias value and the correction coefficient in the above formula (1) are all fixed values, and each parameter can be obtained based on experiments. Among them, the basic threshold value of brake intervention is determined based on the difference between the theoretical steering angle and the actual steering angle of the vehicle, and the correction coefficient includes two aspects: a lateral acceleration correction factor and a turning radius correction factor. Exemplarily, the correction coefficient can be the product of the lateral acceleration correction factor and the turning radius correction factor.

[0107] However, if Figure 5 As shown, in the embodiment of the present application, the UCL entry threshold is adjusted based on the first road surface information, so the parameter of the road condition judgment correction factor can be added to the correction coefficient. That is, in the embodiment of the present application, the correction coefficient in the above formula (1) is obtained based on the product of the road condition judgment correction factor, the lateral acceleration correction factor and the turning radius correction factor. Therefore, the embodiment of the present application can determine the road condition judgment correction factor based on the first road surface information (such as increasing or decreasing the road condition judgment correction factor), and then multiply the determined road condition judgment correction factor with the lateral acceleration correction factor and the turning radius correction factor to obtain the correction coefficient, and then obtain the first UCL entry threshold based on the above formula (1). It can be understood that when the basic threshold value of the braking intervention, the UCL bias value, the lateral acceleration correction factor and the turning radius correction factor are fixed, the road condition judgment correction factor is positively correlated with the UCL entry threshold. Therefore, in this way, the road condition judgment correction factor can be dynamically adjusted based on the first road surface information, thereby achieving the purpose of adjusting the UCL entry threshold (i.e. determining the first UCL entry threshold).

[0108] Exemplarily, the correspondence between road surface information (such as the first road surface information) and the road condition judgment correction factor can be seen in the following Table 2.

[0109] Table 2

[0110]

[0111] Based on the above table, it can be understood that if the current road surface has a low adhesion coefficient and the adhesion coefficients of the roads where the two front tires of the vehicle are located are roughly the same, it means that the vehicle may have understeering. The road condition judgment correction factor can be adjusted to 90%-100%, that is, the road condition judgment correction factor can be reduced to reduce the UCL entry threshold. In addition, in this case, as long as the adhesion coefficient of the road surface is smaller, the selected value of the road condition judgment correction factor will be smaller. In this way, when the adhesion of the road surface decreases and the possibility of understeering increases, the UCL entry threshold can be reduced, making it easier for the UCL control logic to enter.

[0112] Similarly, for the second method mentioned above, if the adhesion coefficient of the road surface increases, the value of the road condition judgment correction factor can be appropriately increased. In this way, the UCL entry threshold value can be appropriately increased when the possibility of the vehicle understeering is reduced.

[0113] If the current road surface has a low adhesion coefficient, and the road adhesion corresponding to the wheel in the direction of the vehicle's current request for steering is lower than the road adhesion corresponding to the wheel on the other side, it means that the vehicle is more likely to understeer. At this time, the road condition judgment correction factor can be adjusted to 80%-90%, and the road condition judgment correction factor can be reduced by a larger margin to reduce the UCL entry threshold. If the current road surface has a low adhesion coefficient, but the road adhesion corresponding to the wheel in the direction of the vehicle's current request for steering is higher than the road adhesion corresponding to the wheel on the other side, it means that the vehicle is less likely to understeer. At this time, the road condition judgment correction factor can be adjusted to 100%-105%, and the road condition judgment correction factor can be increased to increase the UCL entry threshold.

[0114] The above table is only an exemplary illustration of the relationship between different road surface information and the road condition judgment correction factor, and is only for the purpose of clearly indicating the relationship between the road surface adhesion (which can indicate the degree of difficulty of understeering of the vehicle) and the adjustment trend of the UCL entry threshold value, and does not constitute all restrictions on the embodiments of the present application. It can be understood that the specific value of the road condition judgment correction factor can be determined based on the specific adhesion coefficient and confidence level. For example, the road surface information such as adhesion coefficient and confidence level can be input into a pre-trained correction factor determination model to output the specific selected value of the road condition judgment correction factor.

[0115] Understandably, based on Figure 3In the situation shown, in an embodiment of the present application, the vehicle computer can adjust the road condition judgment correction factors corresponding to all sub-areas in the above manner, and then adjust the UCL entry threshold value (that is, each time the vehicle is in a sub-area, the road condition judgment correction factor is adjusted based on the road surface information of the current sub-area, and then the UCL entry threshold value is adjusted). In addition, the vehicle computer can also determine the target sub-area where the vehicle is most likely to understeer during driving based on road surface information, the current vehicle's wheel speed, the steering theoretical value, and the difference between the actual value, and only when the vehicle is driving in the target sub-area, the road condition judgment correction factor is adjusted based on the road surface information of the target sub-area, and then the UCL entry threshold value is adjusted. Compared with the method of adjusting the road condition judgment correction factors corresponding to each sub-area, this method can reduce the amount of calculation, and can also reduce the storage amount of road surface information, etc., saving storage space.

[0116] Figure 6 A schematic diagram of a calibration parameter mapping table adjustment method is shown. Figure 6 As shown, taking the UCL control logic as an example, based on the traditional calibration parameter mapping table, no matter the adhesion coefficient of the current road surface is low or high, as long as the confidence of the adhesion coefficient is high and the vehicle is prone to understeering, the UCL entry threshold value can be reduced, the UCL exit threshold value can be increased, and the confirmation time for entering the UCL can be correspondingly reduced, or the confirmation time for exiting the UCL can be increased. Then, based on the above adjustment process, the adjusted calibration parameter mapping table is obtained.

[0117] In some other embodiments, the present application may also pre-fine-tune the calibration parameter mapping table by judging the road surface information when the adhesion coefficient of the road surface in front of the vehicle is about to change suddenly.

[0118] In this case, the method for determining the aforementioned second reference value includes but is not limited to: when the difference between the adhesion coefficient in the first road surface information and the adhesion coefficient in the second road surface information is greater than a threshold value, and the adhesion coefficient in the first road surface information is smaller than the adhesion coefficient in the second road surface information, the second reference value is obtained by reducing the third reference value; or, when the difference between the adhesion coefficient in the first road surface information and the adhesion coefficient in the second road surface information is greater than a threshold value, and the adhesion coefficient in the first road surface information is larger than the adhesion coefficient in the second road surface information, the second reference value is obtained by increasing the third reference value; wherein, the difference between the third reference value and the second reference value is smaller than the difference between the second reference value and the first reference value.

[0119] For example, in the understeering control logic, when the vehicle computer determines that there is a sudden change in road surface information ahead of the vehicle, for example, the road ahead of the vehicle is about to suddenly change from a high-adhesion road surface to a low-adhesion road surface, the calibration parameter mapping table can be fine-tuned in advance, that is, the understeering entry threshold value (UCL entry threshold value) is adjusted at the current moment, and the third reference value is reduced to the second reference value. It can be understood that the UCL entry threshold value can still be fine-tuned by changing the road condition judgment correction factor.

[0120] The corresponding relationship between the sudden change of the road surface and the road condition judgment correction factor can be seen in the following Table 3.

[0121] Table 3

[0122] Sudden changes in road surface Road condition judgment correction factor Sudden change from high adhesion road to low adhesion road 95％-100％ Sudden change from low adhesion road to high adhesion road 100％-105％

[0123] It can be understood that if the vehicle is about to enter a low-adhesion road from a high-adhesion road, it means that the vehicle is likely to understeer. At this time, the value of the road condition judgment correction factor can be selected to be 95%-100%. That is, by pre-fine-tuning the UCL entry threshold value in this way and the aforementioned formula (1), the vehicle can be prevented from suddenly entering a low-adhesion road from a high-adhesion road to a certain extent, and the serious understeer phenomenon that occurs when turning. Then, after the vehicle completely enters the low-adhesion road, the road condition judgment correction factor can be further reduced according to the corresponding relationship in Table 2 above, the UCL entry threshold value can be reduced, and the UCL control logic can be executed in time.

[0124] In addition, if the vehicle is about to enter a high-adhesion road from a low-adhesion road, it means that the vehicle is less likely to understeer when entering the high-adhesion road. At this time, the road condition judgment correction factor can be selected as 100%-105%, that is, the UCL entry threshold value is slightly increased. This can not only prepare for the sudden change of road surface information in advance, but also try to avoid affecting the current driving state of the vehicle.

[0125] In the embodiment of the present application, when the road surface ahead of the vehicle has a sudden change, for example, when the vehicle is about to enter a low-adhesion road surface from a high-adhesion road surface, the confirmation time for entering the UCL (i.e., the first duration) can be reduced in advance. In other words, the first duration can also be obtained by adjustment based on the first road surface information.

[0126] For example, if it is determined based on the current speed of the vehicle that the road surface on which the vehicle is traveling will suddenly change from a high-adhesion road surface to a low-adhesion road surface in 200 milliseconds, and if the confirmation time for entering the UCL is originally 500 milliseconds, then the confirmation time for entering the UCL can be reduced to 300 milliseconds. In this way, the confirmation time for entering the UCL is reduced, and the vehicle can be confirmed to be in an understeering state earlier, and then the corresponding braking logic can be executed. In addition, the confirmation time for entering the UCL can be increased in advance when the vehicle is about to enter a high-adhesion road surface from a low-adhesion road surface.

[0127] Figure 7 FIG. 1 shows a flow chart for adjusting a calibration parameter mapping table in the case of a sudden change in road surface. Figure 7 As shown, the vehicle computer can mark the pre-correction enable on the auxiliary correction interface, wherein the auxiliary correction interface is used to input the road surface information to the braking module (such as the preprocessing module) of the vehicle computer. Exemplarily, when a sudden change in the road surface occurs in front of the vehicle in the direction of travel, the value of the pre-correction enable identified by the auxiliary correction interface can be set to 1, and when there is no sudden change in the road surface in front of the vehicle in the direction of travel, the value of the pre-correction enable can be set to 0. In this way, when a sudden change in the road surface occurs, the vehicle computer can determine whether the change in the adhesion coefficient exceeds the threshold based on each braking module. If so, each braking module can set a risk identification bit (or risk identification position bit) to indicate that the vehicle has a risk of understeering, and then adjust the calibration parameter mapping table, such as the UCL entry threshold value, etc. If not, the risk identification bit is cleared, and there is no need to adjust the calibration parameter mapping table.

[0128] The embodiment of the present application only explains the adjustment method of the UCL entry threshold and the confirmation time for entering the UCL, but this does not constitute all limitations of the present application. For example, the UCL exit threshold and the confirmation time for exiting the UCL can also be adjusted accordingly.

[0129] In this method, when there is a sudden change in the road surface information ahead of the vehicle, the UCL entry threshold value can be pre-fine-tuned to prepare for the sudden change in road surface information in advance while trying to avoid affecting the current driving state of the vehicle. This can, to a certain extent, avoid sudden changes in the road conditions on which the vehicle is driving, which may lead to severe understeer when turning.

[0130] 203: When it is determined that the vehicle is in an understeering state, executing a braking logic corresponding to the understeering state, wherein the braking logic is used to compensate for the understeering state of the vehicle.

[0131] It can be understood that when it is determined that the vehicle is in an understeering state, the torque reduction braking logic corresponding to the understeering state can be executed, wherein the execution method of the torque reduction braking logic includes: determining the second torque corresponding to the vehicle's own state information; corresponding to the second torque being greater than the first torque threshold corresponding to the vehicle's engine, reducing the torque output by the vehicle's engine from the first torque to the second torque; corresponding to the second torque being less than or equal to the first torque threshold corresponding to the engine, reducing the torque output by the vehicle's engine from the first torque to the first torque threshold.

[0132] It can be understood that the vehicle computer can determine the second torque based on the vehicle's own state information, such as the steering wheel angle, the wheel angle, etc., wherein the second torque is the torque of the engine requested by the vehicle computer and can compensate for the understeering state of the vehicle, and the second torque is less than the first torque, wherein the first torque can be the torque of the engine when the vehicle is in a non-understeering state. However, no matter how large the second torque requested by the vehicle computer is, the torque reduction braking logic itself will impose certain restrictions on the minimum value of the final torque output by the engine to prevent the final torque from being too small.

[0133] Therefore, the final torque requested by the torque reduction braking logic is equal to the maximum value of the calculated second torque and the torque minimum limit value (first torque threshold), which can also be expressed as MReq_1=Max(MReq_2, MMin). Among them, MReq_1 represents the final torque of the final request, MReq_2 represents the second torque, and MMin represents the torque minimum limit value (first torque threshold). Among them, the embodiment of the present application does not limit the calculation method of the second torque, as long as the second torque of the engine that can compensate for the current understeering state of the vehicle can be obtained based on the vehicle's own state data.

[0134] For example, the calculation method of the minimum torque limit value can refer to the following formula (2).

[0135] MMin,Friction = f (Engine_min_tq_tab, Engine_min_tq_mu_tab) Formula (2)

[0136] Among them, MMin,Friction represents the minimum torque limit value obtained based on the friction coefficient; f represents the friction coefficient of the engine; the Engine_min_tq_tab parameter represents the reference torque size of the four wheels of the vehicle, and is the calibration parameter corresponding to the torque reduction braking logic; the Engine_min_tq_mu_tab parameter represents the reference torque adjustment coefficient of the four wheels of the vehicle, and is also the calibration parameter corresponding to the torque reduction braking logic. It can be seen from the above formula that when the friction coefficient f remains unchanged, the Engine_min_tq_tab parameter and the Engine_min_tq_mu_tab parameter are positively correlated with the minimum torque limit value MMin,Friction.

[0137] Therefore, the Engine_min_tq_tab parameter or the Engine_min_tq_mu_tab parameter can be adjusted in real time based on the first road surface information, thereby achieving the purpose of adjusting the minimum torque limit value. Therefore, in a possible implementation, the first torque threshold is determined based on the following method: obtaining the second torque threshold corresponding to the stored engine of the vehicle; updating the second torque threshold to the first torque threshold based on the first road surface information and the third road surface information, and the third road surface information is the road surface information corresponding to the second torque threshold.

[0138] Among them, when the confidence in the first road surface information is greater than the second confidence and the adhesion coefficient in the first road surface information is smaller than the adhesion coefficient in the third road surface information, the second torque threshold is increased to the first torque threshold; when the confidence in the first road surface information is greater than the second confidence and the adhesion coefficient in the first road surface information is greater than the adhesion coefficient in the third road surface information, the second torque threshold is reduced to the first torque threshold.

[0139] It can be understood that if the adhesion coefficient of the first road area where the vehicle is currently located is less than the adhesion coefficient of the third road area of ​​the vehicle, it means that the vehicle is more likely to experience understeering and needs to reduce the torque. However, in order to avoid the torque being too small, the reference value of the Engine_min_tq_tab parameter or the Engine_min_tq_mu_tab parameter can be increased, thereby increasing the minimum torque limit value based on the above formula (2).

[0140] Taking the modification of only the Engine_min_tq_tab parameter as an example, since this formula pays more attention to high adhesion road surfaces, the Engine_min_tq_tab correction factor can be designed as shown in Table 4:

[0141] Table 4

[0142] Road surface information Engine_min_tq_tab correction factor The current road surface has a high adhesion coefficient 100％-120％ Other road conditions 100％

[0143] As shown in Table 4, if the current road surface has a high adhesion coefficient, the value of the Engine_min_tq_tab correction factor can be 100%-120%. It is also possible to increase the reference value of the Engine_min_tq_tab parameter by increasing the correction factor of Engine_min_tq_tab, and then increase the minimum torque limit value based on the above formula (2). For example, it can be understood that the traditional value of the Engine_min_tq_tab parameter can be: (60, 80, 100, 120). Taking the correction factor of 110% as an example, the correction factor is multiplied by the traditional Engine_min_tq_tab parameter size, that is, (60, 80, 100, 120), and the corrected Engine_min_tq_tab parameter size can be (66, 88, 110, 132). In this case, the parameter size of Engine_min_tq_tab increases, and based on formula (2), it can be seen that the parameter size of Engine_min_tq_tab is positively correlated with the minimum torque limit value, so the minimum torque limit value is also increased. This calibration parameter adjustment method can avoid excessive engine torque reduction when understeering occurs on high-adhesion roads.

[0144] Figure 8 The data processing flow chart of the electronic brake system corresponding to the method provided in the embodiment of the present application is shown. After the vehicle computer obtains at least one image of the road surface based on the image acquisition device, the at least one image is input into the adhesion determination model (which can also be understood as after machine vision analysis), and the road surface information of the current road surface of the left front wheel and the right front wheel of the vehicle is obtained respectively (for example, it may include the adhesion coefficient of the road surface, the confidence of the adhesion coefficient, etc.), and then the road surface information is sent to the input signal preprocessing module for preprocessing based on the auxiliary correction interface.

[0145] In addition, the vehicle computer can also input the wheel speed signals of each wheel obtained by the four-wheel speed sensor, the steering wheel rotation angle signal and rotation direction signal obtained by the steering wheel angle sensor, and the vehicle's center of gravity obtained by the gravity sensor into the vehicle's motion model to obtain the vehicle's own state information such as the vehicle's wheel speed, center of gravity position, rotation angle, and rotation direction. Then, the vehicle's own state information is input into the input signal preprocessing module for preprocessing. The input signal preprocessing module can also receive bus signals sent to the network by other controllers, such as engine information, gear information, steering drive information, etc.

[0146] In an embodiment of the present application, the vehicle computer can also dynamically adjust relevant parameters in the calibration parameter mapping table based on road information to obtain an adjusted calibration parameter mapping table, and then input the adjusted calibration parameter mapping table into the input signal preprocessing module for preprocessing.

[0147] Then, the vehicle computer sends the preprocessed data to the braking function control module based on the input signal preprocessing module. The braking function control module calculates the function request based on the preprocessed data. For example, when the vehicle is in an understeering state, it requests to reduce the speed of the vehicle, or increase the minimum required torque in the torque reduction braking logic, etc., and then outputs the function request to the arbitration algorithm module for arbitration.

[0148] Among them, in addition to receiving the function request sent by the brake function control module, the arbitration algorithm module can also receive various requests based on the preprocessed data output by the input signal preprocessing module and the bus signal of the vehicle, such as engine control request, gear control request, torque distribution request, steering execution request, motor control request, etc. After the arbitration algorithm module arbitrates the above information, it obtains the arbitration result and sends the arbitration structure to the lower-level execution module for execution.

[0149] Fig. 9 Another data processing flow chart of an electronic brake system corresponding to the method provided in another embodiment of the present application is shown. It can be understood that Fig. 9 In the process, the vehicle computer sends the acquired road surface information to the input signal preprocessing module based on the auxiliary correction interface. The information input to the input signal preprocessing module also includes the adjusted calibration parameter mapping table and the vehicle's own state information (data) obtained based on the vehicle's wheel speed sensor, steering wheel angle sensor, gravity sensor and vehicle motion model. After the input signal preprocessing module performs preprocessing operations on the received information, it submits the preprocessed information to each system in the brake function control module, such as the anti-lock braking system. Each system determines the function request of each system based on the preprocessed information, and then submits the function request to the brake system function arbitration module (that is, the arbitration algorithm module mentioned above) for arbitration to obtain the arbitration result, and finally submits the arbitration result to the lower-level execution module for execution.

[0150] It can be understood that the above embodiment only describes the method provided by the present application by taking the example of determining whether the vehicle is in an understeering state and taking the torque reduction braking logic to compensate for the understeering state when the vehicle is in an understeering state. However, it should be understood that the method provided by the present application is not limited to determining whether the vehicle is in an understeering state, for example, it can also determine whether the vehicle is in an abnormal state such as oversteering, and in both cases, the reference value corresponding to the reference indicator of the abnormal state (for example, determining the threshold value for entering the abnormal state, etc.) can be reduced when the adhesion coefficient is reduced, so that the judgment of the abnormal state is more timely.

[0151] In the embodiment of the present application, the vehicle computer determines the first reference value corresponding to the reference index based on the first road surface information (such as adhesion coefficient, confidence) of the road the vehicle is currently on, and determines the first value corresponding to the reference index based on the vehicle's own state information (such as the steering angle of the wheel), and determines whether the vehicle is currently in an understeering state based on the first value and the first reference value. If so, the braking logic corresponding to the understeering state is executed to compensate for the understeering state of the vehicle. Compared with the case where the first reference value is a fixed value, in this method, the first reference value can be obtained through dynamic adjustment based on the first road surface information, and the determination of the understeering state is more timely, thereby making the execution of the braking logic more timely.

[0152] Fig.10 A block diagram of a vehicle computer 1400 involved in an embodiment of the present application is shown. In one embodiment, the vehicle computer 1400 may include one or more processors 1404, a system control logic 1408 connected to at least one of the processors 1404, a system memory 1412 connected to the system control logic 1408, a non-volatile memory (NVM) 1416 connected to the system control logic 1408, and a communication interface 1420 connected to the system control logic 1408.

[0153] In some embodiments, the processor 1404 may include one or more single-core or multi-core processors. In some embodiments, the processor 1404 may include any combination of general-purpose processors and special-purpose processors (e.g., graphics processors, application processors, baseband processors, etc.). In an embodiment where the vehicle machine 1400 uses an eNB (Evolved Node B) or RAN (Radio Access Network) controller, the processor 1404 may be configured to execute various embodiments, such as Figure 2 One or more of the multiple embodiments shown.

[0154] In some embodiments, system control logic 1408 may include any suitable interface controller to provide any suitable interface to at least one of processors 1404 and / or any suitable device or component in communication with system control logic 1408 .

[0155] In some embodiments, the system control logic 1408 may include one or more memory controllers to provide an interface to the system memory 1412. The system memory 1412 may be used to load and store data and / or instructions. In some embodiments, the memory 1412 of the vehicle computer 1400 may include any suitable volatile memory, such as a suitable dynamic random access memory (DRAM).

[0156] NVM / memory 1416 may include one or more tangible, non-transitory computer-readable media for storing data and / or instructions. In some embodiments, NVM / memory 1416 may include any suitable non-volatile memory such as flash memory and / or any suitable non-volatile storage device, such as a hard disk drive (HDD), a compact disc (CD) drive, and a digital versatile disc (DVD) drive.

[0157] NVM / storage 1416 may include a portion of storage resources on a device on which vehicle machine 1400 is installed, or it may be accessible by a device but not necessarily a portion of the device. For example, NVM / storage 1416 may be accessed over a network via communication interface 1420 .

[0158] In particular, the system memory 1412 and the NVM / storage 1416 may include a temporary copy and a permanent copy of the instructions 1424, respectively. The instructions 1424 may include: when executed by at least one of the processors 1404, causing the vehicle computer 1400 to implement the following Figure 2 In some embodiments, instructions 1424, hardware, firmware, and / or software components thereof may additionally / alternatively be placed in system control logic 1408, communication interface 1420, and / or processor 1404.

[0159] The communication interface 1420 may include a transceiver for providing a radio interface for the vehicle computer 1400, and then communicating with any other suitable device (such as a front-end module, an antenna, etc.) through one or more networks. Exemplarily, the communication interface 1420 may be the auxiliary correction interface mentioned above. The communication interface 1420 can be connected to an image acquisition device to receive an image of the road surface on which the vehicle is currently located captured by the image acquisition device, and send the received image to a subsequent processing module, etc. In some embodiments, the communication interface 1420 can be integrated with other components of the vehicle computer 1400. For example, the communication interface 1420 can be integrated with at least one of the processor 1404, the system memory 1412, the NVM / storage 1416, and a firmware device (not shown) with instructions. When at least one of the processors 1404 executes the instructions, the vehicle computer 1400 implements the following. Figure 2 The method shown.

[0160] The image acquisition device may be a vehicle-mounted camera, a vehicle-mounted video camera, a vehicle-mounted scanner or other devices with a shooting function, such as a mobile phone, a tablet computer, etc.

[0161] In one embodiment, at least one of the processors 1404 may be packaged together with logic for one or more controllers of the system control logic 1408 to form a system in package (SiP). In one embodiment, at least one of the processors 1404 may be integrated on the same die with logic for one or more controllers of the system control logic 1408 to form a system on a chip (SoC).

[0162] The vehicle computer 1400 may further include: an input / output (I / O) device 1432. The I / O device 1432 may include a user interface to enable a user to interact with the vehicle computer 1400; the design of the peripheral component interface enables the peripheral component to also interact with the vehicle computer 1400. In some embodiments, the vehicle computer 1400 further includes a sensor for determining at least one of an environmental condition and location information related to the vehicle computer 1400.

[0163] In some embodiments, the sensor may include, but is not limited to, a gyroscope sensor, an accelerometer, a proximity sensor, an ambient light sensor, and a positioning unit. The positioning unit may also be part of the communication interface 1420 or interact with the communication interface 1420 to communicate with components of a positioning network (e.g., a global positioning system (GPS) satellite). It is understood that the sensor may be used to collect the vehicle's own state data such as the wheel speed signal of the wheel, the rotation angle signal of the steering wheel, and the rotation direction signal mentioned above.

[0164] It can be understood that the structure of the vehicle computer involved in the above content is only an exemplary structure. This application does not specifically limit the structure of the vehicle computer. As long as the method provided by this application can be executed, for example, the vehicle computer can also be a vehicle processor, etc.

[0165] It will be understood that, as used herein, the term "module" may refer to or include an application specific integrated circuit (ASIC), an electronic circuit, a processor (shared, dedicated, or group) and / or memory that executes one or more software or firmware programs, a combinational logic circuit, and / or other appropriate hardware components that provide the described functionality, or may be part of these hardware components.

[0166] It is understood that in each embodiment of the present application, the processor may be a microprocessor, a digital signal processor, a microcontroller, etc., and / or any combination thereof. According to another aspect, the processor may be a single-core processor, a multi-core processor, etc., and / or any combination thereof.

[0167] The various embodiments disclosed in the present application may be implemented in hardware, software, firmware, or a combination of these implementation methods. The embodiments of the present application may be implemented as a computer program or program code executed on a programmable system, the programmable system including at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device.

[0168] Program code can be applied to input instructions to perform the functions described in this application and generate output information. The output information can be applied to one or more output devices in a known manner. For the purposes of this application, a processing system includes any system having a processor such as, for example, a digital signal processor (DSP), a microcontroller, an application specific integrated circuit (ASIC), or a microprocessor.

[0169] Program code can be implemented with high-level programming language or object-oriented programming language to communicate with the processing system. When necessary, program code can also be implemented with assembly language or machine language. In fact, the mechanism described in this application is not limited to the scope of any specific programming language. In either case, the language can be a compiled language or an interpreted language.

[0170] In some cases, the disclosed embodiments may be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments may also be implemented as instructions carried or stored on one or more temporary or non-temporary machine-readable (e.g., computer-readable) storage media, which may be read and executed by one or more processors. For example, instructions may be distributed over a network or through other computer-readable media. Therefore, machine-readable media may include any mechanism for storing or transmitting information in a machine (e.g., computer) readable form, including, but not limited to, floppy disks, optical disks, optical disks, read-only memories (CD-ROMs), magneto-optical disks, read-only memories (ROMs), random access memories (RAMs), erasable programmable read-only memories (EPROMs), electrically erasable programmable read-only memories (EEPROMs), magnetic or optical cards, flash memory, or a tangible machine-readable memory for transmitting information (e.g., carrier waves, infrared signals, digital signals, etc.) using the Internet in electrical, optical, acoustic, or other forms of propagation signals. Therefore, machine-readable media include any type of machine-readable media suitable for storing or transmitting electronic instructions or information in a machine (e.g., computer) readable form.

[0171] In the accompanying drawings, some structural or method features may be shown in a specific arrangement and / or order. However, it should be understood that such a specific arrangement and / or order may not be required. Instead, in some embodiments, these features may be arranged in a manner and / or order different from that shown in the illustrative drawings. In addition, the inclusion of structural or method features in a particular figure does not mean that such features are required in all embodiments, and in some embodiments, these features may not be included or may be combined with other features.

[0172] It should be noted that the units / modules mentioned in the various device embodiments of the present application are all logical units / modules. Physically, a logical unit / module can be a physical unit / module, or a part of a physical unit / module, or can be implemented as a combination of multiple physical units / modules. The physical implementation method of these logical units / modules themselves is not the most important. The combination of functions implemented by these logical units / modules is the key to solving the technical problems proposed by the present application. In addition, in order to highlight the innovative part of the present application, the above-mentioned device embodiments of the present application do not introduce units / modules that are not closely related to solving the technical problems proposed by the present application, which does not mean that there are no other units / modules in the above-mentioned device embodiments.

[0173] It should be noted that, in the examples and description of the present application, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or equipment. In the absence of further restrictions, the elements defined by the statement "comprise one" do not exclude the presence of other identical elements in the process, method, article or equipment including the elements.

[0174] Although the present application has been illustrated and described with reference to certain preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the scope of the present application.

Claims

1. A vehicle control method, applied to a vehicle computer, characterized in that: The method comprises: Determining first road surface information of a first road area based on an image of a first road area where the vehicle is currently located acquired by an image acquisition device, wherein the road surface information includes an adhesion coefficient and a confidence level of the adhesion coefficient; determining a first value corresponding to a reference index of the vehicle according to the vehicle's own state information, and determining whether the vehicle is in an understeering state based on the first value and a first reference value, wherein the reference index is used to indicate the possibility that the vehicle is currently in the understeering state, and the first reference value is determined based on the first road surface information; In a case where it is determined that the vehicle is in the understeering state, executing a braking logic corresponding to the understeering state, wherein the braking logic is used to compensate for the understeering state of the vehicle; Wherein, determining the first reference value based on the first road surface information includes: Acquire a second reference value corresponding to the stored reference index, wherein the second reference value is determined based on second road surface information; The second reference value is updated to the first reference value based on the first road surface information and the second road surface information.

2. The method according to claim 1, characterized in that The reference index includes a difference between a theoretical steering angle and an actual steering angle of the vehicle; and, The determining whether the vehicle is in an understeering state based on the first value and a first reference value includes: When the first value is greater than the first reference value within a first time period, it is determined that the vehicle is currently in the understeering state.

3. The method according to claim 2, characterized in that The first duration is determined according to the first road surface information.

4. The method according to claim 2, characterized in that: The updating the second reference value to the first reference value based on the first road surface information and the second road surface information includes: When the confidence level in the first road surface information is greater than the first confidence level, and the adhesion coefficient in the first road surface information is less than the adhesion coefficient in the second road surface information, reducing the second reference value to the first reference value; When the confidence level in the first road surface information is greater than the first confidence level, and the adhesion coefficient in the first road surface information is greater than the adhesion coefficient in the second road surface information, the second reference value is increased to the first reference value.

5. The method according to claim 4, characterized in that The second road surface information is road surface information corresponding to a second road area behind the first road area; and The second reference value is determined based on a third reference value corresponding to the stored reference index and the second road surface information.

6. The method according to claim 5, characterized in that The second reference value is determined based on a pre-stored third reference value corresponding to the reference index and the second road surface information, including: The second reference value is obtained by reducing the third reference value when the difference between the adhesion coefficient in the first road surface information and the adhesion coefficient in the second road surface information is greater than a threshold value, and the adhesion coefficient in the first road surface information is less than the adhesion coefficient in the second road surface information; or, The second reference value is obtained by adding the third reference value when a difference between the adhesion coefficient in the first road surface information and the adhesion coefficient in the second road surface information is greater than a threshold value, and the adhesion coefficient in the first road surface information is greater than the adhesion coefficient in the second road surface information; The difference between the third reference value and the second reference value is smaller than the difference between the second reference value and the first reference value.

7. The method according to any one of claims 1 to 6, characterized in that When determining that the vehicle is in the understeering state, executing a braking logic corresponding to the understeering state includes: Determining a second torque corresponding to the vehicle's own state information; Corresponding to the second torque being greater than a first torque threshold corresponding to the engine of the vehicle, reducing the torque output by the engine of the vehicle from the first torque to the second torque; Corresponding to the second torque being less than or equal to a first torque threshold corresponding to the engine, the torque output by the engine of the vehicle is reduced from the first torque to the first torque threshold.

8. The method according to claim 7, characterized in that The first torque threshold is determined based on the following method: Acquire a stored second torque threshold corresponding to the engine of the vehicle; The second torque threshold is updated to the first torque threshold based on the first road surface information and third road surface information, wherein the third road surface information is road surface information corresponding to the second torque threshold.

9. The method according to claim 8, characterized in that The updating the second torque threshold to the first torque threshold based on the first road surface information and the third road surface information includes: In a case where the confidence level in the first road surface information is greater than the second confidence level, and the adhesion coefficient in the first road surface information is less than the adhesion coefficient in the third road surface information, increasing the second torque threshold to the first torque threshold; When the confidence level in the first road surface information is greater than the second confidence level, and the adhesion coefficient in the first road surface information is greater than the adhesion coefficient in the third road surface information, the second torque threshold is reduced to the first torque threshold.

10. A vehicle computer, characterized in that: include: one or more processors; One or more memories; the one or more memories store one or more programs, and when the one or more programs are executed by the one or more processors, the vehicle computer executes the vehicle control method described in any one of claims 1 to 9.

11. A vehicle, characterized in that: The vehicle comprises the vehicle computer according to claim 10.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, which, when executed on a computer, cause the computer to execute the vehicle control method according to any one of claims 1 to 9.

Images