WO2022160196A1 - Vehicle driving control method and apparatus, and vehicle and storage medium - Google Patents

Abstract

A vehicle driving control method, a vehicle driving control apparatus, a vehicle and a computer-readable storage medium, which belong to the technical field of vehicles. The vehicle driving control method comprises: performing path planning to acquire a tracking path; acquiring a basic preview distance according to current position information of a vehicle and the tracking path; acquiring a correction coefficient for the basic preview distance, wherein the correction coefficient comprises at least one of a speed correction coefficient, a path curvature correction coefficient and a course angle correction coefficient; acquiring a target preview distance according to the correction coefficient and the basic preview distance; and performing transverse driving control according to the target preview distance. Therefore, calculation parameters of a path following algorithm can be optimized according to the details of a driving scenario, such that the aim of optimizing a path following algorithm in a valet parking function is realized, the control accuracy during low-speed unmanned driving is improved to ensure the vehicle usage safety and the function reliability, and the usage experience of a user can thus be improved.

Description

Vehicle driving control method, device, vehicle and storage medium technical field

The present application relates to the technical field of vehicles, and in particular, to a vehicle driving control method, a vehicle driving control device, a vehicle, and a computer-readable storage medium.

Background technique

In the future, unmanned driving will gradually enter people's lives. Valet parking may be the first driverless function to be applied to mass-produced passenger cars. Valet parking is mainly to search for parking spaces autonomously in the parking lot and park the car. into the parking space.

However, in scenarios where the terrain of the parking lot is not ideal (for example, some parking lots have narrow passageways, and the parking space may also have a narrow scene), the stability of the traditional valet parking function during use is poor (for example, stable One of the reasons for the poor stability during the use of the traditional valet parking function is that the traditional valet parking function provides the path following algorithm with The calculation parameters (such as the preview distance) do not consider the detailed driving scene and cannot be adjusted according to the detailed driving scene, resulting in that the accuracy of the path following algorithm in the traditional valet parking function is not enough. Therefore, the traditional valet parking The path following algorithm in the car function has yet to be optimized.

The preceding statements are intended to provide general background information and may not constitute prior art.

technical problem

How to optimize the path following algorithm in the valet parking function is an urgent problem to be solved by those skilled in the art.

technical solutions

The technical problem to be solved by the present application is to provide a vehicle driving control method, a vehicle driving control device, a vehicle and a computer-readable storage medium in view of the above-mentioned defects of the prior art, so as to realize the optimization of the path following algorithm according to the details of the driving scene. Calculate the parameters, so as to achieve the purpose of optimizing the path following algorithm in the valet parking function, improve the control accuracy of low-speed unmanned driving to ensure the safety of the vehicle and the reliability of the function, and then improve the user experience.

The present application provides a vehicle driving control method, including: performing path planning to obtain a tracking path; obtaining a basic preview distance according to the current position information of the vehicle and the tracking path; obtaining a correction coefficient for the basic preview distance, where the correction coefficient includes a speed correction coefficient , at least one of path curvature correction coefficient and heading angle correction coefficient; obtain the target preview distance according to the correction coefficient and the basic preview distance; perform lateral driving control according to the target preview distance.

Optionally, in the step of obtaining the basic preview distance according to the current position information of the vehicle and the tracking path, the steps include: obtaining a tracking position point corresponding to the current position information of the vehicle on the tracking path; obtaining a lateral position according to the current position information of the vehicle and the tracking position point. Deviation value; obtain the basic preview distance corresponding to the lateral position deviation value from the preview distance correspondence information, wherein the preview distance correspondence information includes the correspondence between at least one lateral position deviation value and the basic preview distance.

Optionally, the step of obtaining the correction coefficient for the basic preview distance includes: obtaining the current vehicle speed, and obtaining the speed correction coefficient corresponding to the current vehicle speed from the speed correction coefficient correspondence information, wherein the speed correction coefficient correspondence information indicates that The corresponding relationship between the vehicle speed and the speed correction coefficient; the step of obtaining the target preview distance according to the correction coefficient and the basic preview distance includes: obtaining the first target preview distance according to the speed correction coefficient and the basic preview distance, wherein the speed correction coefficient It is proportional to the basic preview distance.

Optionally, in the step of obtaining the correction coefficient for the basic preview distance, the steps include: determining an initial preview point on the tracking path according to the basic preview distance; obtaining a heading deviation according to the heading of the vehicle and the heading corresponding to the initial preview point. angle; obtain the heading angle correction coefficient corresponding to the heading deviation angle and the lateral position deviation value from the heading angle correction coefficient correspondence information, wherein the heading angle correction coefficient correspondence information indicates the lateral position deviation value, heading deviation angle and heading angle correction The corresponding relationship between the coefficients; the step of obtaining the target preview distance according to the correction coefficient and the basic preview distance includes: obtaining the first target preview distance according to the heading angle correction coefficient and the basic preview distance, wherein the heading angle correction coefficient and the basic preview distance are obtained. The preview distance is proportional.

Optionally, in the step of acquiring the correction coefficient for the basic preview distance, the steps include: acquiring the mean path curvature of the tracking path; acquiring the curvature correction coefficient corresponding to the mean path curvature and the lateral position deviation value from the curvature correction coefficient correspondence information. , wherein the corresponding relationship information of the curvature correction coefficient indicates the corresponding relationship between the lateral position deviation value, the mean value of the path curvature and the curvature correction coefficient; the step of obtaining the target preview distance according to the correction coefficient and the basic preview distance includes: according to the path curvature correction coefficient and The basic preview distance obtains the first target preview distance, wherein the path curvature correction coefficient is proportional to the basic preview distance.

Optionally, in the step of obtaining the mean value of the path curvature of the tracking path, the steps include: determining an initial preview point on the tracking path according to the basic preview distance; The mean path curvature between the point and the initial preview point.

Optionally, the step of obtaining the target preview distance according to the correction coefficient and the basic preview distance includes: obtaining the target preview distance according to the first target preview distance and the optimization correction coefficient, wherein the first target preview distance and the optimized target preview distance are obtained. The correction coefficient is in a proportional relationship; wherein, the optimized correction coefficient is a correction coefficient other than the correction coefficient corresponding to the first target preview distance.

Optionally, in the step of performing lateral driving control according to the target preview distance, it includes: determining the preview point on the tracking path according to the target preview distance; The preview point obtains the vehicle preview angle; substitute the target preview distance and the vehicle preview angle into the turning radius calculation formula to calculate the vehicle turning radius; calculate the steering wheel angle according to the vehicle turning radius and the steering wheel angle calculation formula corresponding to the vehicle; controlled by the turning system.

Optionally, the turning radius calculation formula includes:

Among them, R represents the turning radius of the vehicle, L _d represents the target preview distance, and α represents the vehicle preview angle; the calculation formula of the steering wheel angle includes: StA=α ₁ ρ ⁵ +α ₂ ρ ⁴ +α ₃ ρ ³ +α ₄ ρ ² +α ₅ ρ ¹ +α ₆ ; where,

Among them, StA represents the steering wheel angle, ρ represents the turning curvature, α ₁ , α ₂ , α ₃ , α ₄ , α ₅ , and α ₆ are formula coefficients, and the formula coefficients correspond to the vehicle type.

Optionally, the target preview distance is within a limited distance range, and the limited distance range is 1 meter to 3.6 meters.

The present application also provides a vehicle driving control device, comprising a memory and a processor; the processor is configured to execute a computer program stored in the memory to implement the steps of the vehicle driving control method described above.

The present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the steps of the vehicle driving control method described above.

The present application also provides a vehicle comprising the vehicle driving control device as described above.

beneficial effect

The vehicle driving control method, vehicle driving control device, vehicle, and computer-readable storage medium provided by the present application, wherein the vehicle driving control method includes: performing path planning to obtain a tracking path; Aiming distance; obtain a correction coefficient for the basic preview distance, the correction coefficient includes at least one of a speed correction coefficient, a path curvature correction coefficient, and a heading angle correction coefficient; obtain the target preview distance according to the correction coefficient and the basic preview distance; The target preview distance is used for lateral driving control. Therefore, the present application can optimize the calculation parameters of the path following algorithm according to the details of the driving scene (for example, the vehicle speed, the path curvature of the tracked path, the heading angle deviation angle, etc.), thereby realizing the optimization of the path following algorithm in the valet parking function. The purpose is to improve the control accuracy of low-speed unmanned driving to ensure the safety of the vehicle and the reliability of its functions, thereby improving the user experience. In addition, the present application can optimize the path following algorithm, and achieve a good calculation effect with a small amount of calculation, so that the steady-state lateral deviation can be controlled to a small value in the environment of parking or fixed-point parking in low-speed automatic driving. range (for example, within ±5cm), and control the steady-state heading angle deviation within a small range (for example, within ±3°), and even when the vehicle starting position deviates greatly from the tracking path, it can be very It is good to adjust the vehicle to the tracking path, with fast convergence and small overshoot.

In addition, the application can also adaptively adjust the preview distance according to the vehicle speed, the path curvature of the tracking path, the heading angle deviation angle and the lateral deviation, so that the vehicle can quickly converge at different starting positions and angles, and can adapt to different road curvature, and meet a certain control accuracy, especially when the vehicle starting deviation is large, it has a good control effect. Some disadvantages of distance in lateral control, such as easy overshoot, slow convergence, large steady-state error, etc. The application can be adapted to different roads, such as: straight lines, right-angle bends, small S bends, large S bends, arcs with different curvatures, special-shaped bends, etc., even the path opened by the driver can be stably followed, and the steady state The deviation is small, and in the case of a large deviation, the application can quickly converge and the overshoot is small. This application can not only meet the functions of parking (valet parking, fully automatic parking, semi-automatic parking), but also meet the functions related to low-speed unmanned driving (such as autonomous wireless charging, unmanned park shuttle, unmanned park) sweeper). Since there is a nonlinear relationship between the steering wheel angle and the front wheel angle, and the nonlinear relationship between the steering wheel angle and the front wheel angle is different for different models, the present application can obtain a more accurate relationship by calibrating the relationship between the steering wheel angle and the turning radius of the vehicle, so that a more accurate relationship can be obtained. Good steady state following effect. The application has small code size, high operating efficiency, can be well embedded, and has low hardware requirements.

In order to make the above-mentioned and other objects, features and advantages of the present invention more obvious and easy to understand, the preferred embodiments are exemplified below, and are described in detail as follows in conjunction with the accompanying drawings.

Description of drawings

FIG. 1 is a schematic flowchart of a vehicle driving control method provided by a first embodiment of the present application.

FIG. 2 is a first schematic diagram of the bicycle model provided by the first embodiment of the present application.

FIG. 3 is a corresponding relationship diagram of the basic preview distance provided by the first embodiment of the present application.

FIG. 4 is a second schematic diagram of the bicycle model provided by the first embodiment of the present application.

FIG. 5A is a first simulation result diagram of position comparison provided by the first embodiment of the present application.

FIG. 5B is a simulation result diagram of the first variation of the lateral error provided by the first embodiment of the present application.

FIG. 6A is a second simulation result diagram of position comparison provided by the first embodiment of the present application.

FIG. 6B is a simulation result diagram of the second variation of the lateral error provided by the first embodiment of the present application.

FIG. 7A is a third simulation result diagram of position comparison provided by the first embodiment of the present application.

FIG. 7B is a simulation result diagram of the third variation of the lateral error provided by the first embodiment of the present application.

FIG. 8 is a corresponding relationship diagram of the speed correction coefficient provided by the first embodiment of the present application.

FIG. 9 is a corresponding relationship diagram of curvature correction coefficients provided by the first embodiment of the present application.

FIG. 10A is a simulation result diagram of path tracking before curvature correction provided by the first embodiment of the present application.

FIG. 10B is a simulation result diagram of the lateral deviation change before the curvature correction provided by the first embodiment of the present application.

Fig. 11A is a simulation result diagram of path tracking after curvature correction provided by the first embodiment of the present application.

FIG. 11B is a simulation result diagram of the lateral deviation change after curvature correction provided by the first embodiment of the present application.

FIG. 12 is a corresponding relationship diagram of the heading angle correction coefficient provided by the first embodiment of the present application.

FIG. 13A is a simulation result diagram of a curve scene before heading angle correction provided by the first embodiment of the present application.

FIG. 13B is a simulation result diagram of lateral deviation change before heading angle correction provided by the first embodiment of the present application.

FIG. 14A is a simulation result diagram of a curve scene after the heading angle correction provided by the first embodiment of the present application.

FIG. 14B is a simulation result diagram of the lateral deviation change after the heading angle correction provided by the first embodiment of the present application.

FIG. 15A is a simulation result diagram of a scene of a small S-curve provided by the first embodiment of the present application.

FIG. 15B is a simulation result diagram of the lateral deviation change of the small S-curve scene provided by the first embodiment of the present application.

FIG. 16A is a simulation result diagram of a right-angle curve scene provided by the first embodiment of the present application.

FIG. 16B is a simulation result diagram of a lateral deviation change of a right-angle curve scene provided by the first embodiment of the present application.

FIG. 17 is a comprehensive verification result diagram of a straight road scene provided by the first embodiment of the present application.

Fig. 18 is a comprehensive verification result diagram of the large S-curve scene provided by the first embodiment of the present application.

FIG. 19 is a comprehensive verification result diagram of the small S-curve scene provided by the first embodiment of the present application.

FIG. 20 is a comprehensive verification result diagram of a right-angle curve scenario provided by the first embodiment of the present application.

FIG. 21 is a comprehensive verification result diagram of the special-shaped curve scene provided by the first embodiment of the present application.

FIG. 22 is a schematic diagram of a lateral control module provided by the first embodiment of the present application.

FIG. 23 is a schematic structural diagram of a vehicle driving control device provided by the second embodiment of the present application.

FIG. 24 is a schematic diagram of a vehicle provided by the second embodiment of the present application.

Glossary of attached drawings:

Current Point: The tracking position point corresponding to the center of the rear axle of the vehicle;

Preview Point: preview point;

Preview Distance: Preview distance;

Path: trace path;

PathCurvature: The road curvature refers to the mean path curvature from the current point (Current Point) to the preview point (Preview Point);

Lateral Deviation (or Lateral Deviation Error): lateral position deviation (the distance from the center of the rear axle of the vehicle to the vertical line on the tracked path);

Target Position: the target path tracked by the vehicle;

Real Position: It is the actual position in the process of vehicle path tracking;

Distance error: The lateral position deviation refers to the vertical distance from the center of the rear axle of the vehicle to the tracked path, see e _y in Figure 2 for details;

Velocity: the speed of the vehicle;

Y Error: lateral position deviation;

Odemetry: moving distance;

Location Comparison: location comparison;

Yaw Comparison: heading angle comparison;

Yaw Error: Heading angle deviation.

Embodiments of the present invention

In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

The embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

First embodiment:

For a clear description of the vehicle driving control method provided by the first embodiment of the present application, please refer to FIG. 1 to FIG. 22 .

The vehicle driving control method provided by the first embodiment of the present application includes:

S11: Perform path planning to obtain a tracking path.

In an optional implementation manner, in step S11: performing path planning to acquire the tracking path, it may include: acquiring the current position information of the vehicle through the positioning module, and performing path planning to acquire the tracking path.

In an optional embodiment, the positioning module may use RTK differential positioning technology and/or IMU to perform dead reckoning to provide vehicle current position information (or real-time vehicle position information) and/or track paths, and it may provide vehicle The horizontal and vertical coordinates of .

Among them, RTK differential positioning technology (Real-time kinematic, RTK), also known as carrier phase differential technology, is a new and commonly used GPS measurement method. The previous static, fast static and dynamic measurements need to be solved after the fact. It can obtain centimeter-level accuracy, and RTK is a measurement method that can obtain centimeter-level positioning accuracy in real time in the field. It can provide the three-dimensional coordinates of the observation point in real time and achieve centimeter-level high precision; the same as the principle of pseudorange difference, it is determined by the reference station. The carrier observation value and the station coordinate information are transmitted to the user station in real time through the data link; the user station receives the carrier phase of the GPS satellite and the carrier phase from the base station, and forms the phase difference observation value for real-time processing, which can give centimeters in real time. There are two types of methods for realizing carrier phase differential GPS: the correction method and the differential method. The former is the same as the pseudorange difference. The base station sends the carrier phase correction amount to the user station to correct its carrier phase, and then solves the problem. Coordinates, the latter sends the carrier phase collected by the base station to the subscriber station for difference calculation of coordinates. The former is the quasi-RTK technology, and the latter is the real RTK technology.

Among them, IMU, the full name is inner measurement unit, that is, inertial measurement unit, usually composed of gyroscope, accelerometer and algorithm processing unit, through the measurement of acceleration and rotation angle to obtain its own motion trajectory, which is very important in navigation. Application value: We call the system that combines the traditional IMU with the algorithm of information fusion such as body and GPS as a generalized IMU for autonomous driving. GPS/IMU sensing system can help autonomous driving to complete positioning through global positioning and inertial update data up to 100Hz frequency. GPS is a relatively accurate positioning sensor, but its update frequency is too low, only 10Hz, which is not enough to provide enough real-time position updates. The IMU has the real-time performance that GPS lacks, and the update frequency of the IMU can reach 100Hz or higher. By integrating GPS and IMU, we can provide both accurate and sufficiently real-time position updates for vehicle positioning. The combination of GPS and IMU is to integrate the heading velocity, angular velocity and acceleration information of IMU to improve the accuracy and anti-interference ability of GPS. Compared with GPS, IMU can not only provide some information, but also provide supplementary navigation information, because GPS itself only provides location information, IMU can also provide heading and attitude information, which is also encountered in vehicle control and even the most basic vehicle control. to the information. Because the IMU will provide different angles, we can monitor the changes in the vehicle attitude very keenly in real time, and can more accurately identify some more complex road conditions. The relative and absolute position deduction of the IMU does not depend on any external equipment and is a complete system like a black box in an aircraft. Since the IMU does not require any external signal, it can be installed in a concealed location such as the chassis of a car, thus avoiding electronic or mechanical attack.

S12: Obtain the basic preview distance according to the current position information of the vehicle and the tracking path.

In an optional embodiment, in step S12: obtaining the basic preview distance according to the current position information of the vehicle and the tracking path, may include: obtaining the tracking position point corresponding to the current position information of the vehicle on the tracking path; and the tracking position point to obtain the lateral position deviation value; match the basic preview distance corresponding to the lateral position deviation value.

In an optional embodiment, in the step of obtaining the lateral position deviation value according to the current position information of the vehicle and the tracking position point, it may include: based on the basic principle of the pure tracking algorithm, establishing a coordinate system according to the current position information of the vehicle, the origin of the coordinate system. Corresponding to the center of the rear axle of the vehicle, the positive X-axis of the coordinate system is the forward direction of the vehicle, and the Y-axis of the coordinate system is the lateral direction of the vehicle; and/or the lateral position deviation value is obtained according to the coordinate system and the tracking position point.

In an optional implementation, the basic principle of the pure tracking algorithm in this embodiment can refer to the article Myungwook Park, Sangwoo Lee, and Wooyong Han. Development of Steering Control System for Autonomous Vehicle Using Geometry-Based Path Tracking Algorithm [J] . Rationale in ETRI Journal, 2015, 37(3):617-625.

In one embodiment, based on the basic principle of pure tracking algorithm, the coordinate system is established according to the current position information of the vehicle, and the lateral position deviation value is obtained according to the coordinate system and the tracking position point. (or the center of the rear wheel axle) to establish a coordinate system, the forward direction is the positive X axis, the lateral direction is the Y axis, and the vehicle is simplified as a bicycle model, where T1 is the simplification of the two rear wheels, and T2 is the simplification of the two front wheels; According to the global coordinate system provided by the positioning module (such as the coordinates of the left side of the entire parking lot or the current position of the vehicle in the parking lot, not shown in the figure) and the above coordinate system, the relative position of the tracking path Path is obtained, thereby obtaining the tracking path Path The tracking position point Current Point corresponding to the center of the rear axle of the vehicle can be obtained, and the distance e _y (that is, the lateral position deviation value) from the center of the rear axle of the vehicle to the tracking position point Current Point can be obtained.

In an optional embodiment, the step of matching the basic preview distance corresponding to the lateral position deviation value may include: acquiring the basic preview distance corresponding to the lateral position deviation value from the preview distance correspondence information. The preview distance correspondence information includes the correspondence between at least one lateral position deviation value and the basic preview distance, and the preview distance correspondence information may be preset and stored by the user or the system according to actual needs. The use of the preview distance correspondence information provided in this embodiment can ensure that the vehicle has no overshoot phenomenon as much as possible when the vehicle converges from a large lateral position deviation value to the tracking path, and improves the stability of the vehicle tracking to the tracking path. .

In an optional embodiment, wherein, the correspondence relationship information of the preview distance includes the corresponding relationship between the lateral position deviation value and the basic preview distance, which can be represented by the formula l=f(e _y ) (wherein, l represents the basic preview distance. , e _y represents the lateral position deviation value). For example, the corresponding relationship information of the preview distance is as shown in Figure 3, wherein, the minimum lateral position deviation value (Lateral Deviation, or e _y for short) is 0 to 0.1 meters, corresponding to the shortest basic preview distance (Preview Distance) is 1 meter, and the lateral position deviation value exceeds 0.5 meters, which corresponds to the longest basic preview distance of about 2.7 meters.

In an optional embodiment, referring to FIG. 4 , after obtaining the basic preview distance, the initial preview point P1 may be determined according to the basic preview distance, and the included angle of the heading corresponding to the initial preview point P1 according to the forward direction of the vehicle is determined. (ie the heading deviation angle β _μ ), to determine the included angle between the forward direction of the vehicle and the heading corresponding to the tracking position point (ie the initial heading deviation angle β _c ).

In an optional embodiment, the setting principle of the preview distance correspondence information is that since the preview distance plays a decisive role in the control effect of the pure tracking algorithm, in the case of a large lateral position deviation of the vehicle, if a smaller value is used. Although the preview distance can quickly pull the vehicle back to the tracked path, it is easy to overshoot. If the preview distance is too large, it is not easy to overshoot, but the steady-state error after stabilizing to the tracking path is relatively low. Therefore, it is necessary to match the appropriate preview distance according to the lateral position deviation, so as to avoid the problems of overshoot and large steady-state error after stabilizing to the tracking path.

Experiments have proved that when the initial lateral position deviation value e _y =1m and the initial heading deviation angle β _c =0° (refer to the initial heading deviation angle in Figure 4, it is the angle between the forward direction of the vehicle and the heading corresponding to the tracking position point) , under this kind of deviation, when the preview distance is 1m, see the Carsim simulation results in Figure 5A, it can be found that there is an overshoot (the overshoot of the vehicle lateral deviation value is about 0.3m). Therefore, it is proved that the initial lateral position deviation When the value of e _y = 1m, the selected preview distance (1m) is not enough, resulting in overshoot phenomenon, but referring to the Matlab simulation results in Figure 5B, it is found that the steady-state error after stabilizing to the tracking path in the above situation is small (at ± within 5cm). In the follow-up experiments, in the case of this deviation, the preview distance was gradually increased, and the experiment found that the overshoot phenomenon was improved, but in this case, when the preview distance increased to a certain value, a stable to tracking path appeared. After that, the steady-state error begins to increase. For example, in the case of the same deviation, after increasing the preview distance to 2m, referring to the Carsim simulation results in Figure 6A, it can be seen that although the vehicle overshoot is small, refer to the Matlab simulation results in Figure 6B. It can be seen that the steady-state error after stabilizing to the tracking path is relatively large (for example, when the tracking path in FIG. 6A has a continuous curve condition, the steady-state error is relatively large).

After proving the influence of the preview distance on the lateral tracking error through a large number of experiments, it is found that when the lateral position deviation value is large, it corresponds to a relatively long preview distance, and when the lateral position deviation value is small, it corresponds to a relatively short distance. The preview distance can not only reduce the vehicle overshoot, but also reduce the steady-state error after stabilizing to the tracking path.

In an optional embodiment, for example, using the preview distance correspondence information corresponding to FIG. 3 to conduct an experiment, the initial lateral position deviation value e _y is set to 1 m, and the initial heading deviation angle β _c is set to 10 °, this In the case of this deviation, the selected initial preview distance is 2.7m. Refer to the Carsim simulation results in Figure 7A to see that there is no overshoot, and refer to the Matlab simulation results in Figure 7B to see the steady state after the tracking path is stabilized. The error is very small. Therefore, it is proved by experimental data that the use of the preview distance correspondence information provided in this embodiment can make the vehicle converge from a large lateral position deviation value to the tracking path, as much as possible to ensure that the vehicle does not have an overshoot phenomenon, and at the same time greatly reduce the The steady-state error after settling to the tracking path.

S13: Obtain a correction coefficient for the basic preview distance, where the correction coefficient includes at least one of a speed correction coefficient, a path curvature correction coefficient, and a heading angle correction coefficient.

In an optional embodiment, in step S13: obtaining the correction system for the basic preview distance, it may include: obtaining the current vehicle speed, and obtaining the speed correction coefficient corresponding to the current vehicle speed from the speed correction coefficient correspondence information (wherein, The corresponding relationship information of the speed correction coefficient indicates the corresponding relationship between the vehicle speed and the speed correction coefficient); and/or, the mean value of the path curvature of the tracked path is obtained, and the mean value of the path curvature and the obtained lateral position deviation value are obtained from the information on the corresponding relationship of the curvature correction coefficients. and/or, determine the initial preview point on the tracking path according to the basic preview distance, and determine the initial preview point on the tracking path according to the forward direction of the vehicle and the initial The heading corresponding to the preview point is obtained to obtain the heading deviation angle, and the heading angle correction coefficient corresponding to the heading deviation angle and the obtained lateral position deviation value is obtained from the heading angle correction coefficient correspondence information (wherein, the heading angle correction coefficient correspondence information indicates that the horizontal Corresponding relationship between position deviation value, heading deviation angle and heading angle correction coefficient).

In an optional embodiment, the current vehicle speed is obtained, and in the step of obtaining the speed correction coefficient corresponding to the current vehicle speed from the speed correction coefficient correspondence information, the speed correction coefficient correspondence information includes the corresponding relationship between the vehicle speed and the speed correction coefficient, It can be expressed by the relational formula ψ _v =f(v) (ψ _v represents the speed correction coefficient, and v represents the vehicle degree).

In an optional embodiment, the setting principle of the corresponding relationship information of the speed correction coefficient may be, due to the delay of the steering system, when the vehicle speed increases, the preview distance should be correspondingly increased, so it needs to be based on the basic preview distance. Increase the speed correction coefficient ψ _v . The corresponding relationship between the vehicle speed and the speed correction coefficient ψ _v in the corresponding relationship information of the speed correction coefficient can refer to Figure 8. When the vehicle speed is less than 2.5Km/h, no correction is required. At this time, the speed correction coefficient ψ _v is set to 1; when the vehicle speed is greater than 2.5Km /h, the correction needs to be performed at the beginning, and the speed correction coefficient ψ _v greater than 1 is selected for correction at this time.

In an optional embodiment, the path curvature mean value of the tracking path is obtained, and in the step of obtaining the curvature correction coefficient corresponding to the path curvature mean value and the obtained lateral position deviation value from the curvature correction coefficient correspondence information, the curvature correction coefficient correspondence The information includes the corresponding relationship between the lateral position deviation value, the path curvature mean value and the curvature correction coefficient, which can be expressed by the relational formula ψ _c =f(C _a , e _y ) (C _a means the path curvature mean value, e _y means the lateral position deviation value, ψ _c represents the curvature correction coefficient).

In an optional embodiment, the setting principle of the curvature correction coefficient correspondence information may be, in order to allow the vehicle to quickly converge to the tracking path at the starting vehicle position with a larger lateral position deviation value without excessive When the tracking path curvature is small, the preview distance should be shorter, so that the vehicle can return to the path as soon as possible. When it is larger, the preview distance should be longer to prevent overshoot in some cases, so it is necessary to increase the curvature correction coefficient ψ _C on the basis of the above. Since the vehicle does not need to have a certain relationship with the path curvature after stable tracking, Therefore, the curvature correction coefficient ψ _C should be set to 1 after the vehicle is tracked stably. According to the above characteristics, the relationship between the path curvature C, the lateral position deviation value e _y and the coefficient ψ _C can be obtained, as shown in Figure 9.

In an optional embodiment, the path curvature mean value of the tracking path is obtained, and the step of obtaining the curvature correction coefficient corresponding to the path curvature mean value and the obtained lateral position deviation value from the curvature correction coefficient correspondence information may include: The preview distance determines the initial preview point on the tracking path; according to the tracking position point on the tracking path and the initial preview point, the mean value of the path curvature from the tracking position point to the initial preview point is calculated.

In an optional implementation manner, according to the tracking position point and the initial preview point on the tracking path, in the step of calculating the mean value of the path curvature between the tracking position point and the initial preview point, it may include: acquiring the mean value of the path curvature on the tracking path. The number of position points between the tracking position point and the initial preview point and the curvature of each position point; the average curvature of the path is calculated according to the number of position points and the curvature of each position point through the curvature mean calculation formula (that is, the path The curvature can be the mean path curvature from the tracked position point to the initial preview point).

In an optional embodiment, the formula for calculating the mean value of path curvature includes:

Wherein, C ₁ , C ₂ . . . C _n all represent the curvature of a certain position point on the path, and n represents the number of position points between the tracking position point and the initial preview point.

In an optional embodiment, taking the right-angle curved path tracked by the vehicle as an example, the convergence distance before and after the curvature correction is compared, for example, the vehicle lateral control is performed with the same initial lateral position deviation value of the vehicle and the same vehicle speed, According to the simulation results of the path tracking before the curvature correction in Figure 10A and the simulation results of the path tracking after the curvature correction Figure 11A, it can be seen that the curvature correction shows a faster convergence speed, and the simulation results according to the lateral deviation change before the curvature correction are shown in Figure 11A. 10B and the simulation results of the lateral deviation change before the curvature correction, it can be seen from Figure 11B that before the curvature correction, the mileage is about 7.5m, and the mileage is about 5.5m after the curvature correction. It is about 2m shorter than the distance to stability before curvature correction, so it is faster to achieve stable path tracking after curvature correction.

In an optional embodiment, the initial preview point is determined according to the basic preview distance, the heading deviation angle is obtained according to the heading direction of the vehicle and the heading corresponding to the initial preview point, and the heading deviation is obtained from the corresponding relationship information of the heading angle correction coefficient. In the step of the angle and the heading angle correction coefficient corresponding to the obtained lateral position deviation value, the corresponding relationship information of the heading angle correction coefficient includes the corresponding relationship between the lateral position deviation value, the heading deviation angle and the heading angle correction coefficient, and the relational formula ψ _a = f(β _p , e _y ) represents (where e _y represents the lateral position deviation value, β _p represents the heading deviation angle, and ψ _a represents the heading angle correction coefficient). For the relationship diagram corresponding to the corresponding relationship information of the heading angle correction coefficient, please refer to FIG. 12 .

In an optional embodiment, the principle of setting the corresponding relationship information of the heading angle correction coefficient may be that, since the starting position of the vehicle is sometimes at a curve, at this time, when the heading angle of the vehicle deviates from the heading angle of the preview point on the path, When β _μ is too large, overshoot is easy to occur, so it is necessary to set the heading angle correction coefficient for debugging to avoid overshoot when the heading angle deviation β _μ is too large. Taking a right-angle bend as an example, see Fig. 13A of the curve simulation results, the lateral position deviation is (13, 1), and the initial heading deviation angle β _c is [10, -10, 5, -5, 0] degrees respectively. From the variation of the lateral position deviation in Figure 13B, the overshoot phenomenon appears in these working conditions. These working conditions are mainly caused by the excessively large heading deviation angle β _p formed by the heading of the vehicle and the heading corresponding to the initial preview point. Different initial heading deviation angles) and different curvatures at the adjacent points of the tracked path can be stably converged without overshoot, and the heading angle correction coefficient ψ _a is added. This heading angle correction coefficient ψ _a not only corresponds to the initial preview point. The heading deviation angle β _p is related, and it is also related to whether the vehicle is on the inside of the curve or the outside of the curve. When the initial preview point is on the inside of the curve, the larger the heading deviation angle β _p is, the larger the vehicle preview distance should be, so that The vehicle turns in advance without overshooting. The larger the heading deviation angle β _μ corresponding to the initial preview point on the outside of the curve, the smaller the vehicle preview distance should be, so that the vehicle can converge to the tracked path as soon as possible. Since the vehicle does not need to adjust the preview distance according to the heading deviation angle β _p corresponding to the initial preview point after stable tracking, the heading angle correction coefficient ψ _a should be set to 1 at this time. Based on the above characteristics, β _p , e _y , ψ _a relationship in Figure 12. Among them, the positive or negative of the heading deviation angle β _p corresponding to the initial preview point depends on whether the vehicle is on the inside of the curve or on the outside of the curve, and the positive or negative of the included angle between the vehicle heading angle and the heading angle of the preview point.

See Figure 13A and Figure 13B for the vehicle control effect diagram before correction, and Figure 14A and Figure 15B for the vehicle control effect after correction. It can be seen from the figure that the overshoot amount before correction is more than 10cm but less than 20cm. The overshoot is all below 5cm, which can meet the control requirements that the industry desires to control the steady-state lateral deviation within ±5cm.

S14: Obtain the target preview distance according to the correction coefficient and the basic preview distance.

In a first optional embodiment, in step S14: obtaining the target preview distance according to the correction coefficient and the basic preview distance, it may include: obtaining the first target preview according to the speed correction coefficient and the basic preview distance distance, wherein the speed correction coefficient is proportional to the basic preview distance. The formula for obtaining the first target preview distance is for example: L _d ′=ψ _v l; wherein, L _d ′ represents the first target preview distance, ψ _v represents the speed correction coefficient, and l represents the basic preview distance.

In a second optional embodiment, in step S14: obtaining the target preview distance according to the correction coefficient and the basic preview distance, it may include: obtaining the first target preview distance according to the heading angle correction coefficient and the basic preview distance, wherein , the heading angle correction coefficient is proportional to the basic preview distance. The formula for obtaining the first target preview distance is for example: L _d ′=ψ _a l; wherein, L _d ′ represents the first target preview distance, ψ _a represents the heading angle correction coefficient, and l represents the basic preview distance.

In a third optional embodiment, in step S14: obtaining the target preview distance according to the correction coefficient and the basic preview distance, it may include: obtaining the first target preview distance according to the path curvature correction coefficient and the basic preview distance The aiming distance, wherein the path curvature correction coefficient is proportional to the basic preview distance. The formula for obtaining the first target preview distance is for example: L _d ′=ψ _C l; wherein, L _d ′ represents the first target preview distance, ψ _C represents the path curvature correction coefficient, and l represents the basic preview distance.

In an optional embodiment, in step S14: obtaining the target preview distance according to the correction coefficient and the basic preview distance, it may include: obtaining the target preview distance according to the first target preview distance and the optimization correction coefficient, wherein the first target preview distance is obtained. A target preview distance is proportional to the optimization correction coefficient; wherein, the optimization correction coefficient is a correction coefficient other than the correction coefficient corresponding to the first target preview distance. For example, the first target preview distance acquisition formula is L _d ′=ψ _v l, where ψ _v is a correction coefficient, and the optimized correction coefficient may include at least one of ψ _C and ψ _a . Therefore, the preview distance correction formula Including: L _d =ψ _C L _d ', or L _d =ψ _a L _d ', or L _d =ψ _c ψ _a L _d '.

In the fourth optional embodiment, in step S14: obtaining the target preview distance according to the correction coefficient and the basic preview distance, it may include: combining the speed correction coefficient, the path curvature correction coefficient, the heading angle correction coefficient and the basic preview distance Substitute into the preview distance correction formula to obtain the target preview distance; the preview distance correction formula includes: L _d =ψ _v ψ _C ψ _a l; Wherein, L _d represents the target preview distance, ψ _v represents the speed correction coefficient, ψ _C Represents the path curvature correction coefficient, ψ _a represents the heading angle correction coefficient, and l represents the basic preview distance.

In an optional embodiment, the target preview distance obtained by the preview distance correction formula is within a limited distance range, and the limited distance range is 1 meter to 3.6 meters. The target preview distance obtained by the preview distance correction formula is within the limited distance range, which enables the vehicle to stably track to the tracking path when performing lateral control, and has almost no overshoot when converging to the tracking path.

S15: Perform lateral driving control according to the target preview distance.

In an optional embodiment, in step S15: performing the lateral driving control according to the target preview distance, it may include: performing the operation according to the first target preview distance or the target preview distance obtained by optimizing the first target preview distance. Lateral driving controls.

In an optional embodiment, in step S15: performing lateral driving control according to the target preview distance, it may include: determining a preview point on the tracking path according to the target preview distance; The vehicle preview angle is obtained from the coordinate system and the preview point on the tracking path (for example, the vehicle preview angle is obtained according to the origin of the coordinate system and the preview point on the positive X-axis tracking path); the target preview distance and the vehicle preview angle are obtained. The aiming angle is substituted into the turning radius calculation formula to calculate the vehicle turning radius; the steering wheel angle is calculated according to the vehicle turning radius and the steering wheel angle calculation formula corresponding to the vehicle; the turning system of the vehicle is controlled according to the steering wheel angle.

In an optional embodiment, the calculation formula of the turning radius includes:

Among them, R represents the turning radius of the vehicle, L _d represents the target preview distance, and α represents the vehicle preview angle; the calculation formula of the steering wheel angle includes: StA=α ₁ ρ ⁵ +α ₂ ρ ⁴ +α ₃ ρ ³ +α ₄ ρ ² +α ₅ ρ ¹ +α ₆ ; where,

Among them, StA represents the steering wheel angle, ρ represents the turning curvature, α ₁ , α ₂ , α ₃ , α ₄ , α ₅ , and α ₆ are formula coefficients, and the formula coefficients correspond to the vehicle type. Formula coefficients with the model of the vehicle, for example, model X, α1 is _38102.13 , _α2 is _813.06 , α3 is _-10202.81 , α4 is _-39.63 , α5 is _2472.84 , and α6 is -0.29.

In an optional implementation manner, after the vehicle driving control method provided in this embodiment is applied to a vehicle, referring to FIG. 15A and FIG. 15B , when the tracking path is a small S curve path, the vehicle has different starting position deviations, different The initial heading deviation angle and different road curvatures can be stably converged, and there is almost no overshoot, achieving the desired goal of the industry that the steady-state lateral deviation is controlled within ±5cm and the steady-state heading angle deviation is controlled within ±3°. Control requirements. Referring to Fig. 16A and Fig. 16B, when the tracking path is a right-angle curve path, the vehicle can stably converge at different starting position deviations, different starting heading deviation angles, and different road curvatures, and there is almost no overshoot. The steady-state lateral deviation is controlled within ±5cm, and the steady-state heading angle deviation is controlled within ±3°.

After the vehicle driving control method provided in this embodiment is applied to a vehicle, real-vehicle verification is performed on straight roads, large S curves, small S curves, right-angle curves, and special-shaped curves. For the real vehicle verification results of the straight road, please refer to Figure 17, for the real vehicle verification results of the big S curve, please refer to Figure 18, for the real vehicle verification results of the small S curve, please refer to Figure 19, for the real vehicle verification results of the right angle curve For the verification results, please refer to Figure 20. For the real vehicle verification results of special-shaped curves, please refer to Figure 21. According to Figures 17 to 21, it can be seen that on straight roads, large S curves, small S curves, right-angle curves or special-shaped curves , Different starting deviations, the lateral position error after stable tracking is less than ±5cm, and the heading angle deviation is also within ±3°. Therefore, after the vehicle driving control method provided in this embodiment is applied to a vehicle, it can adapt to different roads and different starting deviations, and ensure that the lateral position errors after stable tracking are all less than ±5cm, and the heading angle deviation is also ±3° To meet the control requirements that the industry aspires to achieve.

In an optional implementation manner, the vehicle driving control method provided in this embodiment may be applied to a lateral control module in a vehicle, and optionally, the lateral control module may execute steps S12 to S15. Referring to Figure 22, the lateral control module obtains information such as the tracking path, the current position of the vehicle, and the speed of the vehicle, and then performs lateral position deviation calculation, curvature calculation, and vehicle heading angle calculation, and matches the basic preview distance and its correction coefficient according to the aforementioned calculation results, and Obtain the target preview distance to realize the self-response preview distance, transmit the obtained target preview distance to the pure tracking unit in the lateral control module, and calculate the control parameters (such as steering wheel angle information) through the pure tracking unit and send it to the vehicle for execution The device realizes lateral driving control.

The vehicle driving control method provided by the first embodiment of the present application includes: S11: Perform path planning to obtain a tracking path. S12: Obtain the basic preview distance according to the current position information of the vehicle and the tracking path. S13: Obtain a correction coefficient for the basic preview distance, where the correction coefficient includes at least one of a speed correction coefficient, a path curvature correction coefficient, and a heading angle correction coefficient. S14: Obtain the target preview distance according to the correction coefficient and the basic preview distance. S15: Perform lateral driving control according to the target preview distance. Therefore, the vehicle driving control method provided by the first embodiment of the application can optimize the calculation parameters of the path following algorithm according to the details of the driving scene (such as the vehicle speed, the path curvature of the tracked path, the heading angle deviation angle, etc.), thereby realizing the optimization of the valet. The purpose of the path following algorithm in the parking function is to improve the control accuracy of low-speed unmanned driving to ensure vehicle safety and functional reliability, thereby enhancing the user experience. In addition, the vehicle driving control method provided in the first embodiment of the application can optimize the path following algorithm and achieve a good calculation effect with a small amount of calculation, so that in the environment of low-speed automatic driving for parking or fixed-point parking, the Steady-state lateral deviation is controlled within a small range (for example, within ±5cm), and steady-state heading angle deviation is controlled within a small range (for example, within ±3°), and even if the vehicle starting position and tracking When the path has a large deviation, the vehicle can be well adjusted to the tracking path, and the convergence speed is fast and the overshoot is small.

In addition, the vehicle driving control method provided in the first embodiment of the application can also adaptively adjust the preview distance according to the vehicle speed, the path curvature of the tracked path, the heading angle deviation angle, and the lateral deviation, so that the vehicle starts at different positions and starts at different angles. It can quickly converge in different situations, and can adapt to different road curvatures, and meet a certain control accuracy, especially when the vehicle initial deviation is large, it has a good control effect, and solves the problem of fixed preview when the vehicle initial deviation is large. Some disadvantages of the distance or the preview distance adjusted only according to the vehicle speed in the lateral control, such as easy overshoot, slow convergence speed, large steady-state error, etc. The vehicle driving control method provided by the first embodiment of the application can be adapted to different roads, such as: straight lines, right-angle bends, small S bends, large S bends, arcs with different curvatures, special-shaped bends, etc., even if the driver arbitrarily drives The path can also be followed stably, and the steady-state deviation is small, and the vehicle driving control method provided by the first embodiment of the application can quickly converge with a small overshoot in the case of a large deviation. The vehicle driving control method provided by the first embodiment of the application can not only meet the functions of parking (valet parking, fully automatic parking, semi-automatic parking) but also meet the functions related to low-speed unmanned driving (such as autonomous wireless charging, Park shuttle bus, unmanned park sweeper). Since there is a nonlinear relationship between the steering wheel angle and the front wheel angle, and the nonlinear relationship between the steering wheel angle and the front wheel angle is different for different vehicle models, the vehicle driving control method provided by the first embodiment of the application can be obtained by calibrating the relationship between the steering wheel angle and the vehicle turning radius. A more accurate relationship, so that a better steady-state following effect can be achieved. When the vehicle driving control method provided by the first embodiment of the application is executed by a computer, the amount of code is small, the operation efficiency is high, it can be well embedded, and the hardware requirements are low.

Second embodiment:

FIG. 23 is a schematic structural diagram of a vehicle driving control device provided by the second embodiment of the present application. For a clear description of the vehicle driving control device 1 provided by the second embodiment of the present application, please refer to FIG. 23 .

The vehicle driving control device 1 provided in the second embodiment of the present application includes: a processor A101 and a memory A201, wherein the processor A101 is configured to execute the computer program A6 stored in the memory A201 to realize the vehicle as described in the first embodiment The steps of the driving control method.

In one embodiment, the vehicle driving control device 1 provided in this embodiment may include at least one processor A101 and at least one memory A201. Wherein, at least one processor A101 may be referred to as a processing unit A1, and at least one memory A201 may be referred to as a storage unit A2. Specifically, the storage unit A2 stores a computer program A6. When the computer program A6 is executed by the processing unit A1, the vehicle driving control device 1 provided in this embodiment realizes the steps of the vehicle driving control method described in the first embodiment. , for example, S11 shown in Fig. 1: carry out path planning to obtain the tracking path; S12: obtain the basic preview distance according to the current position information of the vehicle and the tracking path; S13: obtain the correction coefficient for the basic preview distance, and the correction coefficient includes At least one of the speed correction coefficient, the path curvature correction coefficient, and the heading angle correction coefficient; S14: Obtain the target preview distance according to the correction coefficient and the basic preview distance; S15: Perform lateral driving control according to the target preview distance.

In one embodiment, the vehicle driving control device 1 provided in this embodiment may include a plurality of memories A201 (referred to as storage units A2 for short).

The storage unit A2 may be a volatile memory or a non-volatile memory, and may also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM, Read Only Memory), a programmable read-only memory (PROM, Programmable Read-Only Memory), an erasable programmable read-only memory (EPROM, Erasable Programmable Read-only memory) Only Memory), Electrically Erasable Programmable Read-Only Memory (EEPROM, Electrically Erasable Programmable Read-Only Memory), Magnetic Random Access Memory (FRAM, ferromagnetic random access memory), Flash Memory (Flash Memory), Magnetic Surface Memory , CD-ROM, or CD-ROM (Compact Disc Read-Only Memory); magnetic surface memory can be disk memory or tape memory. Volatile memory may be Random Access Memory (RAM), which acts as an external cache. By way of example and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory Memory (DRAM, Dynamic Random Access Memory), Synchronous Dynamic Random Access Memory (SDRAM, Synchronous Dynamic Random Access Memory), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM, Double Data Rate Synchronous Dynamic Random Access Memory), Enhanced Type Synchronous Dynamic Random Access Memory (ESDRAM, Enhanced Synchronous Dynamic Random Access Memory), Synchronous Link Dynamic Random Access Memory (SLDRAM, SyncLink Dynamic Random Access Memory), Direct Memory Bus Random Access Memory (DRRAM, Direct Rambus Random Access Memory) ). The storage unit A2 described in the embodiments of the present application is intended to include but not limited to these and any other suitable types of memories.

In one embodiment, the vehicle driving control device 1 also includes a bus connecting different components (eg, the processor A101 and the memory A201, etc.).

In one embodiment, the vehicle driving control device 1 in this embodiment may further include a communication interface (eg, I/O interface A3), which may be used to communicate with external devices.

In an embodiment, the terminal 1 provided in this embodiment may further include a communication apparatus A5.

The vehicle driving control device 1 provided by the second embodiment of the present application includes a memory A101 and a processor A201, and the processor A101 is configured to execute the computer program A6 stored in the memory A201 to realize the vehicle driving control described in the first embodiment Therefore, the vehicle driving control device 1 provided in this embodiment can optimize the calculation parameters of the path following algorithm according to the details of the driving scene, so as to achieve the purpose of optimizing the path following algorithm in the valet parking function, and improve low-speed The control accuracy of the human driver ensures the safety of the vehicle and the reliability of the function, which in turn can improve the user experience.

The second embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program A6, and when the computer program A6 is executed by the processor A101, implements the vehicle driving control as in the first embodiment The steps of the method are, for example, steps S11 to S15 shown in FIG. 1 .

In one embodiment, the computer-readable storage medium provided by this embodiment may include any entity or device capable of carrying computer program code, a recording medium, such as ROM, RAM, magnetic disk, optical disk, flash memory, and the like.

When the computer program A6 stored in the computer-readable storage medium provided by the second embodiment of the present application is executed by the processor A101, the calculation parameters of the path following algorithm can be optimized according to the details of the driving scene, thereby realizing the optimization of the valet parking function. The purpose of the path following algorithm is to improve the control accuracy of low-speed unmanned driving to ensure vehicle safety and functional reliability, thereby enhancing the user experience.

The second embodiment of the present application also provides a vehicle, see FIG. 24 , the vehicle includes the vehicle classroom control device or the lateral control module as described above, so that the vehicle provided by the second embodiment of the present application can be based on the details of the driving scene. Optimize the calculation parameters of the path following algorithm, so as to achieve the purpose of optimizing the path following algorithm in the valet parking function, improve the control accuracy of low-speed unmanned driving to ensure the safety of the vehicle and the reliability of the function, thereby improving the user's experience. Use experience.

The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity, all possible combinations of the technical features in the above-described embodiments are not described. However, as long as there is no contradiction between the combinations of these technical features, All should be regarded as the scope described in this specification.

It should be noted that, herein, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements, It also includes other elements not expressly listed or inherent to such a process, method, article or apparatus. Without further limitation, an element defined by the phrase "comprises a..." does not preclude the presence of additional identical elements in the process, method, article, or device that includes the element, and further, different implementations of the present application Components, features and elements with the same names in the examples may have the same meaning or may have different meanings, and their specific meanings need to be determined by their explanations in this specific embodiment or further combined with the context in this specific embodiment.

It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited by these terms. These terms are only used to distinguish the same type of information from each other. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of this document. The word "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determining", depending on the context. Also, as used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context dictates otherwise. It should be further understood that the terms "comprising", "comprising" indicate the presence of stated features, steps, operations, elements, components, items, kinds, and/or groups, but do not exclude one or more other features, steps, operations, The existence, appearance or addition of elements, assemblies, items, categories, and/or groups. The terms "or" and "and/or" as used herein are to be construed to be inclusive or to mean any one or any combination. Thus, "A, B or C" or "A, B and/or C" means "any of the following: A; B; C; A and B; A and C; B and C; A, B and C" . Exceptions to this definition arise only when combinations of elements, functions, steps, or operations are inherently mutually exclusive in some way.

It should be understood that, although the steps in the flowcharts in the embodiments of the present application are displayed in sequence according to the arrows, these steps are not necessarily executed in the sequence indicated by the arrows. Unless explicitly stated herein, the execution of these steps is not strictly limited to the order and may be performed in other orders. Moreover, at least a part of the steps in the figure may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but may be executed at different times, and the execution order is not necessarily sequential. Instead, it may be performed in turn or alternately with other steps or at least a portion of sub-steps or stages of other steps.

The above are only preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements or improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application. Inside.

Claims (13)

1. A vehicle driving control method, comprising:

   Perform path planning to obtain tracking paths;

   Obtain the basic preview distance according to the current position information of the vehicle and the tracking path;

   obtaining a correction coefficient for the basic preview distance, where the correction coefficient includes at least one of a speed correction coefficient, a path curvature correction coefficient, and a heading angle correction coefficient;

   Obtain the target preview distance according to the correction coefficient and the basic preview distance;

   The lateral driving control is performed according to the target preview distance.
2. The vehicle driving control method according to claim 1, wherein the step of obtaining the basic preview distance according to the current position information of the vehicle and the tracking path comprises:

   obtaining a tracking position point corresponding to the current position information of the vehicle on the tracking path;

   Obtain a lateral position deviation value according to the current position information of the vehicle and the tracking position point;

   The basic preview distance corresponding to the lateral position deviation value is obtained from the preview distance corresponding relationship information, wherein the preview distance corresponding relationship information includes the correspondence between at least one lateral position deviation value and the basic preview distance relation.
3. The vehicle driving control method according to claim 2, wherein the step of acquiring the correction coefficient for the basic preview distance comprises:

   Obtaining the current vehicle speed, and obtaining the speed correction coefficient corresponding to the current vehicle speed from the speed correction coefficient correspondence information, wherein the speed correction coefficient correspondence information indicates the corresponding relationship between the vehicle speed and the speed correction coefficient;

   The step of obtaining the target preview distance according to the correction coefficient and the basic preview distance includes:

   The first target preview distance is obtained according to the speed correction coefficient and the basic preview distance, wherein the speed correction coefficient and the basic preview distance are in a proportional relationship.
4. The vehicle driving control method according to claim 2, wherein the step of acquiring the correction coefficient for the basic preview distance comprises:

   determining an initial preview point on the tracking path according to the basic preview distance;

   Obtain the heading deviation angle according to the heading direction of the vehicle and the heading corresponding to the initial preview point;

   The heading angle correction coefficient corresponding to the heading deviation angle and the lateral position deviation value is obtained from the heading angle correction coefficient correspondence information, wherein the heading angle correction coefficient correspondence information indicates the lateral position deviation value, the heading Corresponding relationship between deviation angle and heading angle correction coefficient;

   The step of obtaining the target preview distance according to the correction coefficient and the basic preview distance includes:

   The first target preview distance is obtained according to the heading angle correction coefficient and the basic preview distance, wherein the heading angle correction coefficient and the basic preview distance are in a proportional relationship.
5. The vehicle driving control method according to claim 2, wherein the step of acquiring the correction coefficient for the basic preview distance comprises:

   obtaining the mean path curvature of the tracking path;

   The curvature correction coefficient corresponding to the path curvature mean value and the lateral position deviation value is obtained from the curvature correction coefficient correspondence information, wherein the curvature correction coefficient correspondence information indicates the lateral position deviation value, the path curvature mean value and the Corresponding relationship of curvature correction coefficient;

   The step of obtaining the target preview distance according to the correction coefficient and the basic preview distance includes:

   The first target preview distance is obtained according to the path curvature correction coefficient and the basic preview distance, wherein the path curvature correction coefficient and the basic preview distance are in a proportional relationship.
6. The vehicle driving control method according to claim 5, wherein the step of acquiring the mean value of the path curvature of the tracking path comprises:

   determining an initial preview point on the tracking path according to the basic preview distance;

   According to the tracking position point and the initial preview point on the tracking path, the mean value of the path curvature from the tracking position point to the initial preview point is calculated.
7. The vehicle driving control method according to any one of claims 3 to 6, wherein the step of obtaining the target preview distance according to the correction coefficient and the basic preview distance includes:

   Obtain the target preview distance according to the first target preview distance and the optimization correction coefficient, wherein the first target preview distance and the optimization correction coefficient are in a proportional relationship;

   Wherein, the optimization correction coefficient is a correction coefficient other than the correction coefficient corresponding to the first target preview distance.
8. The vehicle driving control method according to claim 1, wherein the step of performing lateral driving control according to the target preview distance comprises:

   determining a preview point on the tracking path according to the target preview distance;

   Obtain the vehicle preview angle according to the coordinate system established based on the basic principle of the pure tracking algorithm and the preview point on the tracking path;

   Substitute the target preview distance and the vehicle preview angle into the turning radius calculation formula to calculate the vehicle turning radius;

   Calculate the steering wheel angle according to the vehicle turning radius and the steering wheel angle calculation formula corresponding to the vehicle;

   The steering system of the vehicle is controlled according to the steering wheel angle.
9. The vehicle driving control method according to claim 8, wherein the calculation formula of the turning radius comprises:

   

   Wherein, R represents the turning radius of the vehicle, L _d represents the target preview distance, and α represents the vehicle preview angle;

   The steering wheel angle calculation formula includes:

   StA=α ₁ ρ ⁵ +α ₂ ρ ⁴ +α ₃ ρ ³ +α ₄ ρ ² +α ₅ ρ ¹ +α ₆ ;

   in,

   

   Wherein, StA represents the steering wheel angle, ρ represents the turning curvature, α ₁ , α ₂ , α ₃ , α ₄ , α ₅ , and α ₆ are formula coefficients, and the formula coefficients correspond to the vehicle type.
10. The vehicle driving control method according to claim 1, wherein the target preview distance is within a limited distance range, and the limited distance range is 1 meter to 3.6 meters.
11. A vehicle driving control device, characterized in that it includes a memory and a processor;

    The processor is configured to execute the computer program stored in the memory to implement the steps of the vehicle driving control method as claimed in any one of claims 1 to 10.
12. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the vehicle driving according to any one of claims 1 to 10 is implemented The steps of the control method.
13. A vehicle, characterized in that the vehicle includes the vehicle driving control device of claim 11 .

Images