Cross slope bias suppression method and apparatus, electronic device, and storage medium

Abstract

This application provides a method, apparatus, electronic device, and storage medium for slope offset suppression, relating to the field of automotive technology. The method includes: calculating and acquiring multiple judgment parameters of a target vehicle, determining the real-time integral switch state according to a preset integral switch rule, and updating the compensation integral in real-time based on the target vehicle's real-time operating conditions, lateral deviation, and integral gain coefficient to determine the lane-keeping control command and thus control the target vehicle's steering mechanism for lane keeping. This method determines the real-time integral switch state of the target vehicle through judgment parameters corresponding to the target vehicle's lane-keeping control parameters, and dynamically updates the compensation integral based on the vehicle's real-time operating conditions. It then determines the lane-keeping control command based on the dynamically updated compensation integral, achieving implicit compensation for the impact of slope without relying on slope sensors or explicit estimation of the slope angle. This improves the compatibility and accuracy of slope offset suppression, better ensuring driving safety.

Description

Technical Field

[0001] This application relates to the field of automotive technology, and in particular to a method, apparatus, electronic device, and storage medium for suppressing cross slope bias. Background Technology

[0002] Lane keeping control is a type of intelligent driving assistance system that uses sensors to identify lane markings and adjust the vehicle's direction to help the driver keep the vehicle stable in the center of the current lane. Due to factors such as the vehicle's center of gravity and weight, lane keeping control on some vehicles may shift towards the lower side of the lane in cross-slope conditions; this is known as cross-slope offset.

[0003] Current slope offset mitigation schemes typically use slope sensors installed on the vehicle to measure the angle of the current slope for compensation, or use a fixed integrator to eliminate the steady-state error of lane keeping control in slope environments, thereby suppressing slope offset.

[0004] However, since some vehicles are not equipped with cross slope sensors, the angle of the current cross slope cannot be directly measured, making it impossible to compensate based on the cross slope angle. Furthermore, the fixed integrator-based scheme is prone to overcompensation when entering a cross slope from a flat road or vice versa, which can lead to reverse drifting or even serpentine oscillations. It is evident that the current cross slope offset suppression scheme has poor compatibility and insufficient accuracy, affecting driving safety. Summary of the Invention

[0005] The main objective of this application is to propose a method, apparatus, electronic device, and storage medium for suppressing cross slope offset, aiming to improve the compatibility and accuracy of cross slope offset suppression during lane keeping control and better ensure driving safety.

[0006] In a first aspect, the present invention provides a method for suppressing cross slope bias, comprising:

[0007] The lane keeping control parameters of the target vehicle are obtained, wherein the lane keeping control parameters include: lateral deviation, heading deviation, road curvature, and real-time vehicle speed;

[0008] Based on the lateral deviation and the road curvature, a preset judgment parameter algorithm is used to calculate and obtain multiple judgment parameters corresponding to the lateral deviation.

[0009] Based on the judgment parameters and the heading deviation, the real-time integral switch status is determined using a preset integral switch rule;

[0010] The compensation integral is updated in real time based on the real-time operating conditions of the target vehicle, the real-time integral switch status, the lateral deviation, and the integral gain coefficient.

[0011] The lane keeping control command is determined based on the updated compensation integral, and the lane keeping control command is used to control the steering mechanism of the target vehicle to keep in the lane.

[0012] In an optional implementation, the judgment parameters include: the moving average, moving variance, and consistency ratio corresponding to the lateral deviation;

[0013] The step involves calculating multiple judgment parameters corresponding to the lateral deviation based on the lateral deviation and the road curvature, using a preset judgment parameter algorithm, including:

[0014] Based on the lateral deviation and the preset sliding time, the preset judgment parameter algorithm is used to calculate the sliding average value and the sliding variance corresponding to the lateral deviation, respectively.

[0015] Based on the lateral deviation, the preset sliding time, and the sliding average value, the consistency ratio corresponding to the lateral deviation is calculated using the preset judgment parameter algorithm.

[0016] In an optional implementation, determining the real-time integration switch state based on the judgment parameters and the heading deviation using preset integration switch rules includes:

[0017] If the absolute value of the moving average is greater than a first preset moving average threshold, and the moving variance is less than a first preset moving variance threshold, and the absolute value of the heading deviation is less than a first preset heading deviation threshold, and the consistency ratio is greater than a first preset ratio threshold, then the real-time integration switch is determined to be in the on state, and the on state is used to indicate that the compensation integration begins to accumulate.

[0018] In an optional implementation, determining the real-time integration switch state based on the judgment parameters and the heading deviation using preset integration switch rules includes:

[0019] If the absolute value of the moving average is less than the second preset moving average threshold, or the moving variance is greater than or equal to the second preset moving variance threshold, or the absolute value of the heading deviation is greater than the second preset heading deviation threshold, or the consistency ratio is less than or equal to the second preset ratio threshold, then the real-time integration switch is determined to be in the off state, and the off state is used to indicate that the compensation integration stops accumulating.

[0020] In an optional implementation, before updating the compensation integral in real time based on the target vehicle's real-time operating conditions, the real-time integral switch status, the lateral deviation, and the integral gain coefficient, the method further includes:

[0021] The current sign status of the compensation integral and the lateral deviation is obtained by means of a preset symbol extraction function. Based on the sign status, the lateral deviation, the road curvature, and the real-time integral switch status, the real-time operating condition of the target vehicle is determined. The real-time operating condition includes: rapid error clearing condition, flat road slow release condition, curve restriction condition, cross slope candidate condition, and exception condition.

[0022] In an optional implementation, the method further includes:

[0023] Based on the target vehicle's real-time operating conditions, real-time speed, and preset leakage rate scheduling rules, the current leakage rate corresponding to the real-time operating conditions is determined.

[0024] In an optional implementation, the step of updating the compensation integral in real time based on the real-time operating conditions, the real-time integral switch status, and the lateral deviation includes:

[0025] The compensation integral is updated in real time based on the current leakage rate, the real-time integral switch status, the lateral deviation, and the integral gain coefficient corresponding to the real-time operating conditions, wherein the integral gain coefficient is determined based on the road curvature and the real-time vehicle speed.

[0026] In a second aspect, the present invention provides a cross slope offset suppression device, comprising:

[0027] The acquisition module is used to acquire the lane keeping control parameters of the target vehicle, wherein the lane keeping control parameters include: lateral deviation, heading deviation, road curvature, and real-time vehicle speed;

[0028] The calculation module is used to calculate and obtain multiple judgment parameters corresponding to the lateral deviation based on the lateral deviation and the road curvature using a preset judgment parameter algorithm;

[0029] The determination module is used to determine the real-time integral switch status based on the judgment parameters and the heading deviation, using a preset integral switch rule;

[0030] The update module is used to update the compensation integral in real time based on the real-time operating conditions of the target vehicle, the real-time integral switch status, the lateral deviation, and the integral gain coefficient.

[0031] A control module is used to determine a lane keeping control command based on the updated compensation integral, the lane keeping control command being used to control the steering mechanism of the target vehicle to maintain the lane.

[0032] Thirdly, the present invention provides an electronic device, comprising: a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of any of the methods described in the foregoing embodiments.

[0033] Fourthly, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the method as described in any of the foregoing embodiments.

[0034] The beneficial effects of this application are:

[0035] The cross slope offset suppression method provided in this application includes: acquiring lane keeping control parameters of a target vehicle, wherein the lane keeping control parameters include: lateral deviation, heading deviation, road curvature, and real-time vehicle speed; calculating and acquiring multiple judgment parameters corresponding to the lateral deviation using a preset judgment parameter algorithm based on the lateral deviation and the road curvature; determining the real-time integral switch state using a preset integral switch rule based on the judgment parameters and the heading deviation; updating the compensation integral in real time based on the real-time operating conditions of the target vehicle, the real-time integral switch state, the lateral deviation, and the integral gain coefficient; and determining a lane keeping control command based on the updated compensation integral, wherein the lane keeping control command is used to control the steering mechanism of the target vehicle to maintain the lane. In this embodiment, the real-time integral switch state of the target vehicle is determined by calculating and obtaining multiple judgment parameters corresponding to the lane keeping control parameters of the target vehicle. The compensation integral is dynamically updated in combination with the real-time operating conditions of the vehicle, lateral deviation, and integral gain coefficient. Then, based on the dynamically updated compensation integral, the lane keeping control command is determined to control the steering mechanism of the target vehicle to maintain the lane. This achieves implicit compensation for the cross slope effect through dynamically updated compensation integral without relying on the data collection results of the cross slope sensor or explicit estimation of the cross slope angle. This avoids the problem of overcompensation that may occur in certain situations with the scheme of cross slope offset suppression through a fixed integrator, thereby improving the compatibility and accuracy of cross slope offset suppression and better ensuring driving safety. Attached Figure Description

[0036] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a schematic flowchart of a cross slope offset suppression method provided in an embodiment of this application;

[0038] Figure 2 This is a schematic diagram of a cross slope offset suppression method provided in another embodiment of this application;

[0039] Figure 3 This is a schematic diagram of the structure of a cross slope offset suppression device provided in an embodiment of this application;

[0040] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0042] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0043] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0044] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0045] Current slope offset mitigation solutions typically use slope sensors installed on the vehicle to measure the angle of the current slope for compensation, or use fixed integrators to eliminate steady-state errors in lane keeping control under slope conditions, thus suppressing slope offset. However, since some vehicles are not equipped with slope sensors, the angle of the current slope cannot be directly measured for compensation. Therefore, slope offset mitigation solutions based on fixed integrators are more commonly used. However, because the integration process of fixed integrators is not dynamically adjusted based on vehicle operating conditions, the accumulation or leakage process is relatively fixed. Therefore, overcompensation is prone to occur when entering a slope from a flat road or vice versa, leading to reverse drift or even serpentine oscillation. It is evident that current slope offset mitigation solutions have poor compatibility and insufficient accuracy, affecting driving safety.

[0046] To address the aforementioned issues, the main objective of this application is to propose a method, apparatus, electronic device, and storage medium for suppressing cross slope offset, aiming to improve the compatibility and accuracy of cross slope offset suppression during lane keeping control and better ensure driving safety.

[0047] Figure 1 This is a schematic flowchart of a cross slope offset suppression method provided in an embodiment of this application. The executing entity of this method can be, for example, a vehicle infotainment system, a VCU (Vehicle Control Unit), or other devices with computing capabilities, but is not limited thereto. Figure 1 As shown, the method includes:

[0048] S101. Obtain the lane keeping control parameters of the target vehicle, wherein the lane keeping control parameters include: lateral deviation, heading deviation, road curvature, and real-time vehicle speed.

[0049] For example, the aforementioned lateral deviation, heading deviation, and road curvature can be calculated using vehicle positioning data and image data collected by cameras, sensors, etc., located at the front of the vehicle. Specifically, for example, the structured lane line cubic polynomial coefficients can be obtained based on the image data collected by the cameras, sensors, etc., located at the front of the vehicle. The road curvature can then be calculated based on these structured lane line cubic polynomial coefficients. The lateral deviation and heading deviation can then be calculated by combining the vehicle positioning data and preset vehicle coordinates. However, the above is only one possible example, and the actual methods for calculating and obtaining lateral deviation, heading deviation, and road curvature are not limited to the examples described above.

[0050] The real-time vehicle speed mentioned above can be obtained directly from the aforementioned speed sensor or similar device through a communication connection between the speed sensor and the vehicle's infotainment system, VCU, etc., but is not limited thereto.

[0051] The lane keeping control parameters mentioned above can be linear continuous data acquired in real time, or data acquired periodically at a preset frequency. Assuming that the lane keeping control parameters are acquired periodically at a preset frequency, the preset frequency could be, for example, 50Hz, meaning that the real-time vehicle speed is collected once every 0.02s, and the lateral deviation, heading deviation, and road curvature are calculated once. Each time the real-time vehicle speed is collected and the lateral deviation, heading deviation, and road curvature are calculated once, that is, one cycle. Of course, the preset frequency mentioned above is only a possible example, and the actual preset frequency can be adjusted and determined according to the actual situation, and is not limited to 50Hz.

[0052] S102. Based on the above lateral deviation and the above road curvature, a preset judgment parameter algorithm is used to calculate and obtain multiple judgment parameters corresponding to the above lateral deviation.

[0053] For example, based on the aforementioned lateral deviation and road curvature, the aforementioned algorithm for calculating and obtaining multiple judgment parameters corresponding to the aforementioned lateral deviation can be, for example, by performing calculations, including but not limited to averaging algorithms and variance algorithms, on the values ​​of multiple lateral deviations within a preset time or preset quantity range. The results obtained can be, for example, the multiple judgment parameters corresponding to the aforementioned lateral deviation.

[0054] Of course, the above is just one possible example. The actual preset judgment parameter algorithm is not limited to the average algorithm or the variance algorithm. The actual multiple judgment parameters corresponding to the lateral deviation are not limited to the calculation results obtained by averaging or calculating the variance of multiple lateral deviations within a preset time or preset quantity range. The specific types, quantities and calculation methods of the judgment parameters can be selected and determined according to the actual situation, and are not limited here.

[0055] S103. Based on the above judgment parameters and the above heading deviation, the real-time integral switch status is determined using the preset integral switch rules.

[0056] For example, the aforementioned preset integral switching rules may include comparison rules for each judgment parameter and heading deviation being greater than or less than a certain preset threshold. Multiple preset integral switching rules may be included, each setting different preset thresholds and comparison rules for each judgment parameter and heading deviation. However, the specific types of preset integral switching rules are not limited to comparison rules, and the number of preset integral switching rules can be adjusted and determined according to actual circumstances. It is understood that when multiple preset integral switching rules are included, the real-time integral switching status can be determined by methods such as multiple preset integral switching rules being simultaneously true, multiple preset integral switching rules being partially true, or any one of multiple preset integral switching rules being true; specific methods are not limited here.

[0057] The aforementioned real-time integral switch status can be used, for example, to indicate whether the integrator's compensation integral has started accumulating. However, the specific data format and content of the real-time integral switch status can be adjusted and determined according to actual needs, and no specific restrictions are imposed here.

[0058] S104. Based on the real-time operating conditions of the target vehicle, the real-time integral switch status, the lateral deviation, and the integral gain coefficient, update the compensation integral in real time.

[0059] For example, the real-time operating condition of the target vehicle can be determined by combining the lateral deviation, road curvature, and other preset operating condition judgment rules. The real-time operating condition of the target vehicle can include a variety of different operating conditions, and each real-time operating condition can correspond to one or more preset operating condition judgment rules. Based on this, when the lateral deviation, road curvature, and other data satisfy one or more preset operating condition judgment rules corresponding to a certain operating condition, the operating condition of the target vehicle can be determined as that operating condition.

[0060] The compensation integral is updated in real time based on the real-time operating conditions of the target vehicle, the real-time integral switch status, the lateral deviation, and the integral gain coefficient. This can be achieved, for example, through the following formula:

[0061] ,

[0062] Among them, the above For example, the update amount (or change) of the compensation integral can be the value to be calculated. It can be understood that when this value is positive, the compensation integral increases; when this value is negative, the compensation integral decreases. The current compensation integral is an integral memory term used to eliminate steady-state deviation. The larger the value of the compensation integral, the greater the degree of control the lane keeping control takes to suppress cross slope deviation. For example, it can be greater, but the specific relationship is not limited here. Based on this, the updated compensation integral is: + For periodic updates, it can also be understood as the compensation integral of the (n+1)th period. = + , For the compensation integral of the nth period, The update amount of the compensation integral for the nth period is obtained by calculating using the above formula. The sum of the update amounts of the compensation integral for the nth period and the compensation integral for the nth period is the compensation integral for the next period, i.e., the (n+1)th period.

[0063] The above For example, it could be the aforementioned real-time integral switch state, which could be a value of 0 or 1, when... When the integral is 0, the integral does not accumulate, as shown in the formula above. A result must be 0, when When the value is 1, the points accumulate, but the final update value of the compensation points still needs to be determined based on... and The size relationship is determined.

[0064] The above The integral gain coefficient mentioned above can be dynamically determined based on the road curvature and real-time vehicle speed, for example, by dynamically calculating it using a preset integral gain coefficient algorithm, or by dynamically looking up the table based on a preset integral gain coefficient calibration table combined with the road curvature and real-time vehicle speed. However, the specific method of determining the integral gain coefficient is not limited to the examples mentioned above.

[0065] The above To compensate for the leakage rate of the compensation points, this compensation point leakage rate is used to represent the rate at which the compensation points are forgotten / cleared (or the rate of decline). That is, the larger the value of the compensation point leakage rate, the faster the rate of decline of the compensation points within the same period. The specific value of the compensation point leakage rate can be determined according to the real-time operating conditions of the target vehicle, etc., and is not limited here.

[0066] It is understandable that the formula used above to achieve real-time updates of compensation points is only one possible method for real-time updates of compensation points, but the actual method for real-time updates of compensation points is not limited to the above formula.

[0067] S105. Determine the lane keeping control command based on the updated compensation integral, the lane keeping control command being used to control the steering mechanism of the target vehicle to keep in the lane.

[0068] For example, during lane keeping, in order to suppress cross slope deviation, the vehicle's position in the lane can be adjusted or corrected by rotating the vehicle's steering mechanism. The lane keeping control command is used to control the steering mechanism of the target vehicle to keep the vehicle in the lane, that is, for example, the vehicle's steering mechanism can be rotated by the lane keeping control command to adjust or correct the vehicle's position in the lane, thereby achieving lane keeping.

[0069] The aforementioned compensation integral can, for example, be used to indicate the amount of adjustment or correction of the steering mechanism of the target vehicle by the lane keeping control command when determining the lane keeping control command.

[0070] The cross slope offset suppression method provided in this application includes: acquiring lane keeping control parameters of a target vehicle, wherein the lane keeping control parameters include: lateral deviation, heading deviation, road curvature, and real-time vehicle speed. Based on the lateral deviation and road curvature, a preset judgment parameter algorithm is used to calculate and acquire multiple judgment parameters corresponding to the lateral deviation. Based on the judgment parameters and heading deviation, a preset integral switch rule is used to determine the real-time integral switch state. Based on the real-time operating conditions of the target vehicle, the real-time integral switch state, the lateral deviation, and the integral gain coefficient, the compensation integral is updated in real time. Based on the updated compensation integral, a lane keeping control command is determined, which is used to control the steering mechanism of the target vehicle to maintain lane position. In this embodiment, the real-time integral switch state of the target vehicle is determined by calculating and obtaining multiple judgment parameters corresponding to the lane keeping control parameters of the target vehicle. The compensation integral is dynamically updated in combination with the real-time operating conditions of the vehicle, lateral deviation, and integral gain coefficient. Then, based on the dynamically updated compensation integral, the lane keeping control command is determined to control the steering mechanism of the target vehicle to maintain the lane. This achieves implicit compensation for the cross slope effect through dynamically updated compensation integral without relying on the data collection results of the cross slope sensor or explicit estimation of the cross slope angle. This avoids the problem of overcompensation that may occur in certain situations with the scheme of cross slope offset suppression through a fixed integrator, thereby improving the compatibility and accuracy of cross slope offset suppression and better ensuring driving safety.

[0071] Figure 2 This is a schematic flowchart of a cross slope offset suppression method provided in another embodiment of this application. Optionally, in the above... Figure 1 Based on the embodiments, the above-mentioned judgment parameters include: the moving average, moving variance, and consistency ratio corresponding to the above-mentioned lateral deviation.

[0072] Based on the aforementioned lateral deviation and road curvature, a preset judgment parameter algorithm is used to calculate and obtain multiple judgment parameters corresponding to the aforementioned lateral deviation, including:

[0073] S201. Based on the above-mentioned lateral deviation and preset sliding time, the above-mentioned preset judgment parameter algorithm is used to calculate the above-mentioned sliding average value and the above-mentioned sliding variance corresponding to the above-mentioned lateral deviation.

[0074] For example, the aforementioned preset sliding duration may refer to a preset sliding time window, such as a 2-second sliding time window, but is not limited thereto. This preset sliding time window may slide as the lane keeping control parameters are acquired, so that the latest acquired lane keeping control parameters are always kept within the preset sliding time window.

[0075] Assuming that the lane keeping control parameters are acquired periodically at a preset frequency of 50Hz (i.e., once every 0.02s), the 2s sliding time window can slide as the lane keeping control parameters are acquired, so as to always keep the latest acquired lane keeping control parameters (each lane keeping control parameter has 100 values) within the 2s sliding time window.

[0076] The above-mentioned calculation of the sliding average and sliding variance corresponding to the lateral deviation, based on the lateral deviation and preset sliding time, using the preset judgment parameter algorithm, can, for example, refer to calculating the sliding average and sliding variance corresponding to 100 lateral deviations within the 2-second sliding time window using the preset judgment parameter algorithm. For instance, assuming the lateral deviation is... The moving average value corresponding to the aforementioned lateral deviation can be calculated using, for example, the following formula:

[0077] ,

[0078] Among them, the above This refers to the sliding average value corresponding to the aforementioned lateral deviation, where N is the number of lateral deviation samples collected within the preset sliding time. Taking the example above, N = 100. Let k be the current period number. Taking 100 lateral deviations collected so far as an example, then k=100, and the 100 lateral deviations corresponding to 100 periods are as follows: ~ ,Right now ~ The above. This is a loop index used to indicate the number of iterations or the range of summation.

[0079] Based on this, the sliding variance corresponding to the aforementioned lateral deviation can be calculated using, for example, the following formula:

[0080] ,

[0081] Among them, the above This is the sliding variance corresponding to the aforementioned lateral deviation.

[0082] S202. Based on the aforementioned lateral deviation, preset sliding time, and the aforementioned sliding average value, the aforementioned preset judgment parameter algorithm is used to calculate and obtain the aforementioned consistency ratio corresponding to the aforementioned lateral deviation.

[0083] Continuing with the example above, the consistency ratio corresponding to the aforementioned lateral deviation can be calculated using the following formula:

[0084] ,

[0085] Among them, the above This refers to the consistency ratio corresponding to the aforementioned deviation, which is a percentage value ranging from 0% to 100%. This is an indicator function used to determine whether a condition is true or false. When the condition is true (i.e., ...), the function returns true. hour), =1, when the condition is not met (i.e. hour), =0.

[0086] It is understood that the formulas used above to calculate the moving average, moving variance, and consistency ratio corresponding to lateral deviation are all possible examples, and the actual calculation methods for the moving average, moving variance, and consistency ratio corresponding to lateral deviation are not limited to those using the formulas in the examples above.

[0087] Furthermore, in the above Figure 2 Based on the embodiments, the above-mentioned determination of the real-time integral switch state according to the above-mentioned judgment parameters and the above-mentioned heading deviation, using preset integral switch rules, includes:

[0088] If the absolute value of the above-mentioned moving average is greater than the first preset moving average threshold, and the above-mentioned moving variance is less than the first preset moving variance threshold, and the absolute value of the above-mentioned heading deviation is less than the first preset heading deviation threshold, and the above-mentioned consistency ratio is greater than the first preset ratio threshold, then the above-mentioned real-time integration switch state is determined to be on, and the above-mentioned on state is used to indicate that the above-mentioned compensation integration begins to accumulate.

[0089] For example, the aforementioned preset integral switch rule can be expressed as the following formula:

[0090] ,

[0091] ,

[0092] ,

[0093] ，

[0094] Among them, the above For example, the first preset moving average threshold could be 0.5m, but it is not limited to this. For example, the first preset sliding variance threshold could be 0.0064. However, this is not the only limitation. The above. For example, the first preset heading deviation threshold can be used, which can be, for example, 3°, but is not limited to this. For example, it can be the first preset ratio threshold mentioned above, which can be 80% for example, but is not limited to this.

[0095] When the preset integral switch rules corresponding to the above four formulas are all true, that is, when the absolute value of the above sliding average is greater than the first preset sliding average threshold, and the above sliding variance is less than the first preset sliding variance threshold, and the absolute value of the above heading deviation is less than the first preset heading deviation threshold, and the above consistency ratio is greater than the first preset ratio threshold, then the above real-time integral switch state is determined to be in the open state. The above open state is used to indicate that the above compensation integral begins to accumulate.

[0096] It is understood that, in addition to the aforementioned preset integral switch rules, the determination of the real-time integral switch state as open may also include other preset integral switch rules, and is not limited to the above four rules. Furthermore, the determination of the real-time integral switch state as open is not limited to the simultaneous fulfillment of all preset integral switch rules. Moreover, the aforementioned first preset moving average threshold, first preset moving variance threshold, first preset heading deviation threshold, first preset proportional threshold, and other thresholds can all be adjusted and determined according to the actual situation.

[0097] In addition, in the above Figure 2 Based on the embodiments, the above-mentioned determination of the real-time integral switch state according to the above-mentioned judgment parameters and the above-mentioned heading deviation, using preset integral switch rules, includes:

[0098] If the absolute value of the above-mentioned moving average is less than the second preset moving average threshold, or the above-mentioned moving variance is greater than or equal to the second preset moving variance threshold, or the absolute value of the above-mentioned heading deviation is greater than the second preset heading deviation threshold, or the above-mentioned consistency ratio is less than or equal to the second preset ratio threshold, then the above-mentioned real-time integration switch state is determined to be off. The off state is used to indicate that the above-mentioned compensation integration stops accumulating.

[0099] Similar to the above embodiments, the preset integral switch rule can be expressed as, for example, the following formula:

[0100] ,

[0101] ,

[0102] ,

[0103] ，

[0104] Among them, the above For example, the second preset moving average threshold could be used, which could be, for example, 0.3m, but is not limited to this. For example, the second preset sliding variance threshold could be used, and this second preset sliding variance threshold could be, for example, 0.01. However, this is not the only limitation. The above. For example, the second preset heading deviation threshold could be used, which could be, for example, 4°, but is not limited to this. For example, it can be the second preset ratio threshold mentioned above, which can be 70% for example, but is not limited to this.

[0105] When any of the preset integral switch rules corresponding to the above four formulas are met, that is, the absolute value of the above sliding average is less than the second preset sliding average threshold, or the above sliding variance is greater than or equal to the second preset sliding variance threshold, or the absolute value of the above heading deviation is greater than the second preset heading deviation threshold, or the above consistency ratio is less than or equal to the second preset ratio threshold, then the above real-time integral switch state is determined to be off. The off state is used to indicate that the above compensation integral stops accumulating.

[0106] It should be noted that the first preset moving average threshold and the second preset moving average threshold, the first preset moving variance threshold and the second preset moving variance threshold, the first preset heading deviation threshold and the second preset heading deviation threshold, and the first preset proportional threshold and the second preset proportional threshold may be equal or unequal. For example:

[0107] Taking the first preset moving average threshold value as 0.5m and the second preset moving average threshold value as 0.3m, and determining the real-time integral switch state based on the absolute value of the above moving average, without considering other preset integral switch rules, when the absolute value of the above moving average... At m time, If the absolute value of the moving average is greater than the first preset moving average threshold, then the real-time integral switch is determined to be in the "on" state, and the compensation integral begins to accumulate. In a subsequent acquisition cycle, the absolute value of the moving average... m, although 0.4m is no longer satisfied ,but 0.4m was not met. If the preset integral switch rule corresponds to the off state, then the above real-time integral switch state will remain on, and the above compensation integral will continue to accumulate until the absolute value of the above sliding average value in a certain acquisition period is reached. Only when the above real-time integral switch state is determined to be the off state, the above compensation integral stops accumulating. That is, the compensation integral starts to accumulate after the absolute value of the sliding average satisfies the preset integral switch rule corresponding to the on state, and stops accumulating only after the absolute value of the sliding average satisfies the preset integral switch rule corresponding to the off state. The threshold ranges of the preset integral switch rules corresponding to the on state and the off state do not necessarily constitute a complementary relationship.

[0108] It is understood that, in addition to the aforementioned preset integral switch rules, the determination of the real-time integral switch state as off may also include other preset integral switch rules, and is not limited to the above four rules. Furthermore, the determination of the real-time integral switch state as off is not limited to any one of the preset integral switch rules being met. Moreover, the aforementioned second preset moving average threshold, second preset moving variance threshold, second preset heading deviation threshold, second preset proportional threshold, and other thresholds can all be adjusted and determined according to the actual situation.

[0109] Optionally, in the foregoing Figure 1 Based on the embodiments, before updating the compensation integral in real time according to the real-time operating conditions of the target vehicle, the real-time integral switch status, the lateral deviation, and the integral gain coefficient, the following is also included:

[0110] The current sign status of the compensation integral and the lateral deviation is obtained by a preset symbol extraction function. Based on the sign status, the lateral deviation, the road curvature, and the real-time integral switch status, the real-time operating conditions of the target vehicle are determined. The real-time operating conditions include: rapid error clearing condition, flat road slow release condition, curve restriction condition, cross slope candidate condition, and exception condition.

[0111] For example, the conditions corresponding to the above-mentioned rapid error clearing process can be determined by the following formula:

[0112] ,

[0113] ,

[0114] Among them, the above This is a sign extraction function that returns a value based on whether the input value is positive or negative. Specifically, it could return -1 for a negative input, 1 for a positive input, and 0 for a zero input. (Example provided). , , The above. The current compensation integral is an integral memory term used to eliminate steady-state deviation. The larger the value of the compensation integral, the greater the degree of control the lane keeping control makes to suppress cross slope deviation; for example, it can be greater, but the specific relationship is not limited here. To quickly clear the lateral deviation threshold of the error clearing condition, the lateral deviation threshold of the quick error clearing condition can be, for example, 0.15, but is not limited to this.

[0115] When the conditions corresponding to the two formulas above are met simultaneously, the real-time operating condition of the target vehicle can be determined as a rapid error clearing condition, for example. However, it should be understood that the above is only a possible example and is not actually limited to the case where the real-time operating condition of the target vehicle is determined as a rapid error clearing condition when the conditions corresponding to the two formulas above are met simultaneously.

[0116] For the above-mentioned level road slow-release conditions, the following formula can be used to determine the conditions:

[0117] ,

[0118] ,

[0119] Wherein, Q represents the curvature of the road, and the aforementioned... The road curvature threshold for the smooth road mitigation condition is defined as follows: This threshold can be, for example, 0.0002, but is not limited to this value. The lateral deviation threshold for the slow-release operation on flat roads can be, for example, 0.25, but is not limited to this.

[0120] When the conditions corresponding to the two formulas above are met simultaneously, the real-time operating condition of the target vehicle can be determined as a flat road slow-release condition, for example. However, it should be understood that the above is only a possible example and is not actually limited to the real-time operating condition of the target vehicle being determined as a flat road slow-release condition when the conditions corresponding to the two formulas above are met simultaneously.

[0121] For the aforementioned curve-restricted conditions, the conditions can be determined, for example, by the following formula:

[0122] ,

[0123] Among them, the above The curvature threshold for road curvature under curve restriction conditions can be, for example, 0.001, but is not limited to this value.

[0124] When the conditions corresponding to the above formula are met, the real-time operating condition of the target vehicle can be determined as a curve-restricted operating condition, for example. However, it should be understood that the above content is only a possible example and is not actually limited to the real-time operating condition of the target vehicle being determined as a curve-restricted operating condition when the conditions corresponding to the above formula are met.

[0125] Additionally, once the target vehicle's real-time operating condition is determined to be a curve-restricted condition, if the road curvature changes and the conditions corresponding to the following formula are met, then the target vehicle's real-time operating condition is determined to exit the curve-restricted condition to avoid control jitter between straight and curved roads due to lane keeping:

[0126] ,

[0127] Among them, the above To exit the curvature threshold for road curvature under curve restriction conditions, the curvature threshold for exiting curve restriction conditions can be, for example, 0.0008, but is not limited to this.

[0128] For the aforementioned cross-slope candidate operating condition, the determination conditions can be the same as those for determining the real-time integral switch state to be on, that is, the absolute value of the aforementioned sliding average is greater than the first preset sliding average threshold, and the aforementioned sliding variance is less than the first preset sliding variance threshold, and the absolute value of the aforementioned heading deviation is less than the first preset heading deviation threshold, and the aforementioned consistency ratio is greater than the first preset ratio threshold, then the real-time operating condition of the target vehicle is determined to be the cross-slope candidate operating condition.

[0129] If none of the conditions corresponding to the above four operating conditions are met, then the real-time operating condition of the target vehicle is determined to be an exceptional operating condition.

[0130] In addition, based on any of the foregoing embodiments, the method further includes:

[0131] Based on the aforementioned real-time operating conditions, real-time vehicle speed, and preset leakage rate scheduling rules of the target vehicle, the current leakage rate corresponding to the aforementioned real-time operating conditions is determined.

[0132] For example, the current leakage rates corresponding to the above-mentioned rapid error clearing condition, flat road slow-release condition, curve restriction condition, cross slope candidate condition, and exception condition can be determined sequentially by the following formulas:

[0133] ,

[0134] ,

[0135] ,

[0136] ,

[0137] ,

[0138] Among them, the above is the current leakage rate corresponding to the above-mentioned fast error-clearing working condition, and the above is the current leakage rate corresponding to the above-mentioned flat-road slow-release working condition, and the above is the current leakage rate corresponding to the above-mentioned curve-limiting working condition, and the above is the current leakage rate corresponding to the above-mentioned cross-slope candidate working condition, and the above is the current leakage rate corresponding to the above-mentioned exception working condition. The above is the above-mentioned real-time vehicle speed, and the above is a limited-range output function, which limits the output value a within the interval [b, c]. Assuming b < c, then when a < b, and when a > c, and when b ≤ a ≤ c, .

[0139] It can be understood that the above formula for determining the current leakage rate corresponding to the real-time working condition is only a possible example, and the actual method for determining the current leakage rate corresponding to the real-time working condition is not limited to the formula in the above example. Moreover, even if the current leakage rate corresponding to the real-time working condition is determined by the above formula, the parameters in the above formula are adjustable. For example 0.60, 0.0288, and 1.0 in the formula are not used as fixed parameters.

[0140] Furthermore, on the basis of the above embodiment, the above-mentioned real-time update of the compensation integral according to the above-mentioned real-time working condition, the above-mentioned real-time integral switch state, and the above-mentioned lateral deviation includes:

[0141] Real-time update of the compensation integral according to the above-mentioned current leakage rate corresponding to the real-time working condition, the above-mentioned real-time integral switch state, the above-mentioned lateral deviation, and the integral gain coefficient, where the above-mentioned integral gain coefficient is determined according to the above-mentioned road curvature and the above-mentioned real-time vehicle speed.

[0142] Exemplarily, the above-mentioned real-time update of the compensation integral according to the above-mentioned current leakage rate corresponding to the real-time working condition, the above-mentioned real-time integral switch state, the above-mentioned lateral deviation, and the integral gain coefficient is to update the compensation integral in real time through the following formula:

[0143] ,

[0144] The compensation integral of the n + 1th cycle = + , For the compensation integral of the nth period, This is the update amount of the compensation integral for the nth period, calculated using the formula above.

[0145] The specific calculation method for the integral gain coefficient, determined based on the aforementioned road curvature and real-time vehicle speed, is not limited here. For the nth cycle, the integral gain coefficient determined based on the aforementioned road curvature and real-time vehicle speed can also be expressed as... , that is:

[0146] ,

[0147] Among them, the above For the real-time integral switch state of the nth cycle, the above For the lateral deviation of the nth period, the above The current leakage rate in the nth cycle.

[0148] Figure 3 This is a schematic diagram of a cross slope offset suppression device provided in an embodiment of this application. This cross slope offset suppression device can perform the aforementioned cross slope offset suppression method. The device can be integrated into devices with computing capabilities, such as vehicle infotainment systems and VCUs. Figure 3 As shown, the device may include:

[0149] The acquisition module 310 is used to acquire the lane keeping control parameters of the target vehicle, wherein the lane keeping control parameters include: lateral deviation, heading deviation, road curvature, and real-time vehicle speed.

[0150] The calculation module 320 is used to calculate and obtain multiple judgment parameters corresponding to the lateral deviation based on the lateral deviation and the road curvature, using a preset judgment parameter algorithm.

[0151] The determination module 330 is used to determine the real-time integral switch status based on the above judgment parameters and the above heading deviation, using a preset integral switch rule.

[0152] The update module 340 is used to update the compensation integral in real time based on the real-time operating conditions of the target vehicle, the real-time integral switch status, the lateral deviation, and the integral gain coefficient.

[0153] The control module 350 is used to determine the lane keeping control command based on the updated compensation integral, and the lane keeping control command is used to control the steering mechanism of the target vehicle to keep in the lane.

[0154] The cross slope offset suppression method provided in this application includes: acquiring lane keeping control parameters of a target vehicle, wherein the lane keeping control parameters include: lateral deviation, heading deviation, road curvature, and real-time vehicle speed. Based on the lateral deviation and road curvature, a preset judgment parameter algorithm is used to calculate and acquire multiple judgment parameters corresponding to the lateral deviation. Based on the judgment parameters and heading deviation, a preset integral switch rule is used to determine the real-time integral switch state. Based on the real-time operating conditions of the target vehicle, the real-time integral switch state, the lateral deviation, and the integral gain coefficient, the compensation integral is updated in real time. Based on the updated compensation integral, a lane keeping control command is determined, which is used to control the steering mechanism of the target vehicle to maintain lane position. In this embodiment, the real-time integral switch state of the target vehicle is determined by calculating and obtaining multiple judgment parameters corresponding to the lane keeping control parameters of the target vehicle. The compensation integral is dynamically updated in combination with the real-time operating conditions of the vehicle, lateral deviation, and integral gain coefficient. Then, based on the dynamically updated compensation integral, the lane keeping control command is determined to control the steering mechanism of the target vehicle to maintain the lane. This achieves implicit compensation for the cross slope effect through dynamically updated compensation integral without relying on the data collection results of the cross slope sensor or explicit estimation of the cross slope angle. This avoids the problem of overcompensation that may occur in certain situations with the scheme of cross slope offset suppression through a fixed integrator, thereby improving the compatibility and accuracy of cross slope offset suppression and better ensuring driving safety.

[0155] Optionally, the above-mentioned judgment parameters include: the moving average, moving variance, and consistency ratio corresponding to the above-mentioned lateral deviation.

[0156] The aforementioned calculation module 320 is specifically used to calculate the sliding average and sliding variance corresponding to the lateral deviation based on the aforementioned lateral deviation and the preset sliding duration, using the aforementioned preset judgment parameter algorithm. Based on the aforementioned lateral deviation, the preset sliding duration, the aforementioned road curvature, and the aforementioned sliding average, and using the aforementioned preset judgment parameter algorithm, the consistency ratio corresponding to the aforementioned lateral deviation is calculated and obtained.

[0157] Optionally, the determining module 330 is specifically configured to determine the real-time integration switch state to be in the open state if the absolute value of the sliding average is greater than the first preset sliding average threshold, and the sliding variance is less than the first preset sliding variance threshold, and the absolute value of the heading deviation is less than the first preset heading deviation threshold, and the consistency ratio is greater than the first preset ratio threshold. The open state is used to indicate that the compensation integration starts to accumulate.

[0158] Optionally, the determining module 330 is specifically used to determine the real-time integration switch state to be off if the absolute value of the sliding average is less than the second preset sliding average threshold, or the sliding variance is greater than or equal to the second preset sliding variance threshold, or the absolute value of the heading deviation is greater than the second preset heading deviation threshold, or the consistency ratio is less than or equal to the second preset ratio threshold. The off state is used to indicate that the compensation integration stops accumulating.

[0159] Optionally, the determination module 330 can also be used to obtain the current sign status of the compensation integral and the lateral deviation through a preset symbol extraction function, and determine the real-time operating condition of the target vehicle based on the symbol status, the lateral deviation, the road curvature, and the real-time integral switch status. The real-time operating condition includes: rapid error clearing condition, flat road slow release condition, curve restriction condition, cross slope candidate condition, and exception condition.

[0160] Optionally, the determining module 330 can also be used to determine the current leakage rate corresponding to the real-time operating conditions based on the real-time operating conditions, real-time vehicle speed, and preset leakage rate scheduling rules of the target vehicle.

[0161] Optionally, the update module 340 is specifically used to update the compensation integral in real time according to the current leakage rate, the real-time integral switch status, the lateral deviation and the integral gain coefficient corresponding to the real-time operating conditions, wherein the integral gain coefficient is determined according to the road curvature and the real-time vehicle speed.

[0162] The above-described device is used to execute the method provided in the foregoing embodiments, and its implementation principle and technical effect are similar, so they will not be described again here.

[0163] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device can be a device with computing capabilities, such as the aforementioned vehicle infotainment system or VCU. Figure 4 As shown, the device 400 includes:

[0164] The processor 410, storage medium 420, and bus 430 are connected and communicate with each other via bus 430.

[0165] The storage medium 420 stores machine-readable instructions that can be executed by the processor 410. When the electronic device is running, the processor 410 executes the machine-readable instructions to perform the cross slope bias suppression method.

[0166] It should be understood that, Figure 4 The structure shown is only a schematic diagram of an electronic device; the electronic device may also include components that are larger than those shown. Figure 4The more or fewer components shown, or having the same Figure 4 The different configurations shown. Figure 4 The components shown can be implemented using hardware, software, or a combination thereof.

[0167] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the cross slope bias suppression method described in the above method embodiments.

[0168] Computer-readable storage media can be electronic storage devices such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, computer-readable storage media includes non-transitory computer-readable storage medium. The computer-readable storage medium has storage space for program code that performs any of the method steps described above. This program code can be read from or written to one or more computer program exhibits. The program code can be compressed, for example, in a suitable form.

[0169] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program exhibits according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0170] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0171] If the functionality is implemented as a software module and sold or used as an independent exhibit, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software exhibit. This computer software exhibit is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0172] The above description is merely a preferred embodiment of this application and does not limit the patent scope of this application. Any equivalent structural transformations made based on the inventive concept of this application and the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included within the patent protection scope of this application.

Claims

1. A method for suppressing cross slope bias, characterized in that, include: The lane keeping control parameters of the target vehicle are obtained, wherein the lane keeping control parameters include: lateral deviation, heading deviation, road curvature, and real-time vehicle speed; Based on the lateral deviation and the road curvature, a preset judgment parameter algorithm is used to calculate and obtain multiple judgment parameters corresponding to the lateral deviation. Based on the judgment parameters and the heading deviation, the real-time integral switch status is determined using a preset integral switch rule; The compensation integral is updated in real time based on the real-time operating conditions of the target vehicle, the real-time integral switch status, the lateral deviation, and the integral gain coefficient. The lane keeping control command is determined based on the updated compensation integral, and the lane keeping control command is used to control the steering mechanism of the target vehicle to keep the vehicle in the lane. The judgment parameters include: the moving average, moving variance, and consistency ratio corresponding to the lateral deviation; The step involves calculating multiple judgment parameters corresponding to the lateral deviation based on the lateral deviation and the road curvature, using a preset judgment parameter algorithm, including: Based on the lateral deviation and the preset sliding time, the preset judgment parameter algorithm is used to calculate the sliding average value and the sliding variance corresponding to the lateral deviation, respectively. Based on the lateral deviation, the preset sliding time, and the sliding average value, the consistency ratio corresponding to the lateral deviation is calculated using the preset judgment parameter algorithm.

2. The method according to claim 1, characterized in that, The step of determining the real-time integral switch state based on the judgment parameters and the heading deviation, using preset integral switch rules, includes: If the absolute value of the moving average is greater than a first preset moving average threshold, and the moving variance is less than a first preset moving variance threshold, and the absolute value of the heading deviation is less than a first preset heading deviation threshold, and the consistency ratio is greater than a first preset ratio threshold, then the real-time integration switch is determined to be in the on state, and the on state is used to indicate that the compensation integration begins to accumulate.

3. The method according to claim 1, characterized in that, The step of determining the real-time integral switch state based on the judgment parameters and the heading deviation, using preset integral switch rules, includes: If the absolute value of the moving average is less than the second preset moving average threshold, or the moving variance is greater than or equal to the second preset moving variance threshold, or the absolute value of the heading deviation is greater than the second preset heading deviation threshold, or the consistency ratio is less than or equal to the second preset ratio threshold, then the real-time integration switch is determined to be in the off state, and the off state is used to indicate that the compensation integration stops accumulating.

4. The method according to claim 1, characterized in that, Before updating the compensation integral in real time based on the target vehicle's real-time operating conditions, the real-time integral switch status, the lateral deviation, and the integral gain coefficient, the method further includes: The current sign status of the compensation integral and the lateral deviation is obtained by means of a preset symbol extraction function. Based on the sign status, the lateral deviation, the road curvature, and the real-time integral switch status, the real-time operating condition of the target vehicle is determined. The real-time operating condition includes: rapid error clearing condition, flat road slow release condition, curve restriction condition, cross slope candidate condition, and exception condition.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: Based on the target vehicle's real-time operating conditions, real-time speed, and preset leakage rate scheduling rules, the current leakage rate corresponding to the real-time operating conditions is determined.

6. The method according to claim 5, characterized in that, The step of updating the compensation integral in real time based on the real-time operating conditions, the real-time integral switch status, and the lateral deviation includes: The compensation integral is updated in real time based on the current leakage rate, the real-time integral switch status, the lateral deviation, and the integral gain coefficient corresponding to the real-time operating conditions, wherein the integral gain coefficient is determined based on the road curvature and the real-time vehicle speed.

7. A cross slope offset suppression device, characterized in that, include: The acquisition module is used to acquire the lane keeping control parameters of the target vehicle, wherein the lane keeping control parameters include: lateral deviation, heading deviation, road curvature, and real-time vehicle speed; The calculation module is used to calculate and obtain multiple judgment parameters corresponding to the lateral deviation based on the lateral deviation and the road curvature using a preset judgment parameter algorithm; The determination module is used to determine the real-time integral switch status based on the judgment parameters and the heading deviation, using a preset integral switch rule; The update module is used to update the compensation integral in real time based on the real-time operating conditions of the target vehicle, the real-time integral switch status, the lateral deviation, and the integral gain coefficient. A control module is used to determine a lane keeping control command based on the updated compensation integral, the lane keeping control command being used to control the steering mechanism of the target vehicle to maintain its lane. The judgment parameters include: the moving average, moving variance, and consistency ratio corresponding to the lateral deviation; The calculation module is specifically used to calculate the sliding average and sliding variance corresponding to the lateral deviation based on the lateral deviation and the preset sliding duration, using the preset judgment parameter algorithm; and to calculate the consistency ratio corresponding to the lateral deviation based on the lateral deviation, the preset sliding duration, the sliding average, and the preset judgment parameter algorithm.

8. An electronic device, characterized in that, include: The device includes a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is in operation, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the method as described in any one of claims 1-6.

Images