Vehicle transverse control method, device, equipment, storage medium and product

Abstract

The invention discloses a vehicle transverse control method and device, equipment, a storage medium and a product, and relates to the technical field of vehicle control, and the vehicle transverse control method comprises the steps that in response to a steering control instruction, the mechanical limit angle range of a steering wheel is dispersed into a preset number of candidate steering angle sets; performing multi-dimensional cost evaluation on each candidate steering angle in the candidate steering angle set, and taking the candidate steering angle with the minimum cost in an evaluation result as a target candidate steering angle; and performing vehicle transverse control based on the target candidate steering angle. By constructing the discretized candidate steering angle set, a complex online iterative optimization process in traditional model prediction control is converted into a performance evaluation process oriented to a limited candidate set, so that the calculation complexity of an algorithm is reduced, delay is not easily caused in a scene needing high-frequency response, and the control stability is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle control, in particular to a vehicle lateral control method, device, equipment, storage medium and product. BACKGROUND

[0002] With the rapid development of assisted driving technology, vehicle lateral control as the core link to realize path tracking and trajectory following plays an increasingly key role in assisted driving scenarios such as automatic parking, lane keeping, urban navigation assistance (NOA) and high-speed automatic driving. Among many lateral control algorithms, model predictive control (MPC) has become one of the mainstream methods in the field of path tracking because it can explicitly handle multi-objective optimization, state constraints and dynamic response.

[0003] In related technologies, traditional MPC needs to solve nonlinear optimization problems online in vehicle lateral control, and its iterative calculation process requires high computing power of the vehicle-mounted controller, especially in scenarios requiring high frequency response, which can easily cause delays and lead to a decline in control stability. SUMMARY

[0004] The main purpose of the present application is to provide a vehicle lateral control method, device, equipment, storage medium and product, which aims to solve the technical problem that traditional MPC can easily cause delays in scenarios requiring high frequency response, leading to a decline in control stability.

[0005] To achieve the above purpose, the present application provides a vehicle lateral control method, which comprises: discretizing a mechanical limit angle range of a steering wheel into a preset number of candidate steering angle sets in response to a steering control instruction; performing multi-dimensional cost evaluation on each candidate steering angle in the candidate steering angle set, and taking the candidate steering angle with the minimum cost in the evaluation result as a target candidate steering angle; performing vehicle lateral control based on the target candidate steering angle.

[0006] In an embodiment, the step of performing multi-dimensional cost evaluation on each candidate steering angle in the candidate steering angle set, and taking the candidate steering angle with the minimum cost in the evaluation result as a target candidate steering angle comprises: performing multi-dimensional cost evaluation based on position tracking deviation, heading attitude deviation and steering smoothness on each candidate steering angle in the candidate steering angle set to obtain the evaluation result of each candidate steering angle; taking the candidate steering angle with the minimum cost in the evaluation result as the target candidate steering angle.

[0007] In an embodiment, the step of performing multi-dimension cost evaluation based on the position tracking deviation, the heading attitude deviation and the steering smoothness for each candidate steering angle in the candidate steering angle set comprises: calculating a preview distance for performing vehicle lateral control and a preview point corresponding to the preview distance; for each candidate steering angle in the candidate steering angle set, determining a theoretical turning radius corresponding to the candidate steering angle through a preset steering angle calibration model; calculating a heading angle change amount according to the theoretical turning radius and the preview distance; predicting a predicted pose of the vehicle at the preview point according to the heading angle change amount; determining a position tracking deviation and a heading attitude deviation according to a real pose of the preview point and the predicted pose; determining a steering smoothness based on a change gradient of the candidate steering angle; performing multi-dimension cost evaluation based on the position tracking deviation, the heading attitude deviation and the steering smoothness for each candidate steering angle, to obtain an evaluation result of each candidate steering angle.

[0008] In an embodiment, the step of calculating a preview distance for performing vehicle lateral control and a preview point corresponding to the preview distance comprises: obtaining a path point set, and preprocessing each path point in the path point set to obtain a target path point; selecting a nearest point in the target path point, the nearest point being closest to a current position of the vehicle; calculating a preview distance according to the nearest point and a path curvature corresponding to the nearest point, and determining a preview point corresponding to the preview distance in the target path point, wherein the preview distance is within a path distance of the target path point.

[0009] In an embodiment, the step of performing vehicle lateral control based on the target candidate steering angle comprises: determining a path curvature corresponding to the nearest point; determining a corresponding filtering coefficient according to the path curvature, and filtering the target candidate steering angle based on the filtering coefficient to obtain a filtered candidate steering angle, wherein the filtering coefficient comprises a strong filtering coefficient and a weak filtering coefficient, the strong filtering coefficient being used to suppress body swing, and the weak filtering coefficient being used to avoid trajectory tracking delay; performing hierarchical hardware constraint on the filtered candidate steering angle to obtain a constrained candidate steering angle; The constrained candidate steering angle is filtered by a sliding window to obtain a smoothed candidate steering angle, and vehicle lateral control is performed based on the smoothed candidate steering angle.

[0010] In an embodiment, the step of performing vehicle lateral control based on the target candidate steering angle comprises: An actual steering wheel steering angle and a yaw rate of the vehicle reaching the preview point are obtained, and an actual turning radius is calculated according to the steering wheel steering angle and the yaw rate; An effective data pair composed of the steering wheel steering angle and the actual turning radius is stored in a data queue; When the number of data pairs in the data queue exceeds a threshold, the initial parameters in the preset steering angle calibration model are refitted to obtain target parameters; If the target steering angle calibration model corresponding to the target parameters meets the reliability requirement, and the change amount of the target parameters compared with the initial parameters is greater than a threshold, the initial parameters in the preset steering angle calibration model are updated to the target parameters.

[0011] In addition, to achieve the above-mentioned purpose, the present application also provides a vehicle lateral control device, which comprises: A discretization module is configured to discretize a mechanical limit angle range of a steering wheel into a preset number of candidate steering angle sets in response to a steering control instruction; An evaluation module is configured to perform multi-dimensional cost evaluation on each candidate steering angle in the candidate steering angle set, and select the candidate steering angle with the minimum cost in the evaluation results as a target candidate steering angle; A control module is configured to perform vehicle lateral control based on the target candidate steering angle.

[0012] In addition, to achieve the above-mentioned purpose, the present application also provides a vehicle lateral control device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the vehicle lateral control method as described above.

[0013] In addition, to achieve the above-mentioned purpose, the present application also provides a storage medium, which is a computer readable storage medium, and a computer program is stored on the storage medium, and the computer program is executed by a processor to implement the steps of the vehicle lateral control method as described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the vehicle lateral control method as described above.

[0015] The one or more technical solutions proposed in the present application have at least the following technical effects: Compared with the related art, in which the traditional MPC needs to solve a nonlinear optimization problem online in vehicle lateral control, the iterative calculation process thereof is strict in the computing power requirement of the vehicle-mounted controller, and is prone to delay in a high-frequency response scenario, thereby causing a decrease in control stability. In response to a steering control instruction, the present application discretizes a mechanical limit angle range of a steering wheel into a preset number of candidate steering angle sets; performs multi-dimensional cost evaluation on each candidate steering angle in the candidate steering angle sets, and takes the candidate steering angle with the minimum cost in the evaluation results as a target candidate steering angle; and performs vehicle lateral control based on the target candidate steering angle. After receiving the steering control instruction, the present application discretizes the mechanical limit angle range of the steering wheel into a preset number of candidate steering angle sets, performs multi-dimensional cost evaluation on each candidate steering angle in the set, and performs vehicle lateral control according to the target candidate steering angle with the minimum cost. By constructing the discretized candidate steering angle set, the complex online iterative optimization process in the traditional model predictive control is converted into a performance evaluation process for a limited candidate set, so that the algorithm calculation complexity is reduced, and delay is not prone to occurring in a high-frequency response scenario, thereby improving the control stability. BRIEF DESCRIPTION OF DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and serve to explain the principles of the present application together with the specification.

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced here. Obviously, for those skilled in the art, other drawings can also be obtained based on these drawings without creative labor.

[0018] Figure 1 A flowchart provided for the first embodiment of the vehicle lateral control method of the present application; Figure 2 A flowchart provided for the second embodiment of the vehicle lateral control method of the present application; Figure 3 A module structure diagram of the vehicle lateral control device of the embodiment of the present application; Figure 4 A device structure diagram of the hardware running environment involved in the vehicle lateral control method in the embodiment of the present application.

[0019] The object implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are merely intended to explain the technical solutions of the present application, and are not intended to limit the present application.

[0021] In order to better understand the technical solutions of the present application, the following will be described in detail in combination with the drawings of the specification and specific embodiments.

[0022] The main solution of the embodiment of the present application is: in response to a steering control instruction, discretizing a mechanical limit angle range of a steering wheel into a preset number of candidate steering angle sets; performing multi-dimensional cost evaluation on each candidate steering angle in the candidate steering angle set, and taking the candidate steering angle with the minimum cost in the evaluation result as a target candidate steering angle; and performing vehicle lateral control based on the target candidate steering angle.

[0023] In the related art, the traditional MPC needs to solve a nonlinear optimization problem online in vehicle lateral control, and the iterative calculation process thereof has strict requirements on the computing power of the vehicle-mounted controller, and especially in the scene requiring high frequency response, it is easy to cause delay, resulting in a decline in control stability.

[0024] After receiving the steering control instruction, the present application will discretize the mechanical limit angle range of the steering wheel into a preset number of candidate steering angle sets, and perform multi-dimensional cost evaluation on each candidate steering angle in the set, and perform vehicle lateral control according to the target candidate steering angle with the minimum cost. By constructing the discretized candidate steering angle set, the complex online iterative optimization process in the traditional model predictive control is converted into a performance evaluation process for a limited candidate set, so that the algorithm calculation complexity is reduced, and in the scene requiring high frequency response, it is not easy to cause delay, and the control stability is improved.

[0025] It should be noted that the execution subject of the present embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a vehicle lateral control device, etc. The present embodiment and each of the following embodiments will be described below taking the vehicle lateral control device as an example.

[0026] Based on this, the present embodiment provides a vehicle lateral control method, which refers to Figure 1 , Figure 1 is a flowchart of the first embodiment of the vehicle lateral control method of the present application.

[0027] In the present embodiment, the vehicle lateral control method comprises steps S10-S30: Step S10, in response to a steering control instruction, discretizing a mechanical limit angle range of a steering wheel into a preset number of candidate steering angle sets; It should be noted that the execution subject of the embodiment is a vehicle lateral control device. The steering control instruction refers to a steering operation signal generated by the vehicle lateral control device according to path tracking requirements, which is used to guide the rotation of the steering wheel. The mechanical limit angle range of the steering wheel refers to the maximum angle range that the steering wheel can rotate under the hardware structure limit, and a typical value is ±540°. When the vehicle lateral control device receives the steering control instruction, it will divide the continuous mechanical limit angle range into a limited number of discrete angle values according to a predetermined strategy. By discretizing the continuous steering angle space into a limited candidate set, the online iterative optimization process of the traditional model predictive control is replaced, the calculation complexity is reduced from cubic to linear, and the vehicle lateral control device can complete the solution within milliseconds, meeting the real-time requirements of high-speed control scenarios.

[0028] Step S20, multi-dimensional cost evaluation is performed on each candidate steering angle in the candidate steering angle set, and the candidate steering angle with the minimum cost in the evaluation result is taken as the target candidate steering angle; It can be understood that the vehicle lateral control device performs multi-dimensional evaluation on each candidate steering angle in the discrete candidate set, and takes the candidate steering angle with the minimum cost in the evaluation result as the target candidate steering angle for vehicle lateral control.

[0029] Step S30, vehicle lateral control is performed based on the target candidate steering angle.

[0030] It should be noted that after the vehicle lateral control device selects the target candidate steering angle, it generates a final steering wheel rotation angle instruction according to the target candidate steering angle and outputs it to the EPS, completing the lateral control of this control cycle.

[0031] In a possible implementation, step S20 can include the following steps: Multi-dimensional cost evaluation based on position tracking deviation, heading attitude deviation and steering smoothness is performed on each candidate steering angle in the candidate steering angle set, and the evaluation result of each candidate steering angle is obtained; It can be understood that the position tracking deviation refers to the difference between the lateral position of the vehicle when it reaches the preview point after executing the candidate steering angle and the expected position of the preview point on the reference path, which is predicted by the vehicle lateral control device. The heading attitude deviation refers to the absolute difference between the heading angle of the vehicle when it reaches the preview point after executing the candidate steering angle and the expected heading angle of the preview point on the reference path, which is predicted by the vehicle lateral control device. The steering smoothness refers to the absolute value of the difference between the value of the candidate steering angle and the actual output steering wheel rotation angle value in the last control cycle, which is used to quantify the change amplitude of the control instruction. The vehicle lateral control device uniformly integrates the deviation amounts of the position tracking deviation, the heading attitude deviation and the steering smoothness into a cost value through weighted summation, and then obtains the evaluation result.

[0032] The candidate with the minimum cost in the evaluation result is taken as the target candidate steering angle.

[0033] It should be noted that the evaluation result refers to the comprehensive cost value calculated for each candidate steering angle through multi-dimensional cost evaluation. The vehicle lateral control device selects the candidate steering angle with the minimum comprehensive cost as the final decision, enabling the vehicle lateral control device to achieve the optimal balance of multiple control objectives (tracking accuracy, heading matching, smoothness) under limited computing resources.

[0034] In a possible implementation, the step of performing multi-dimensional cost evaluation based on position tracking deviation, heading attitude deviation, and steering smoothness for each candidate steering angle in the candidate steering angle set to obtain the evaluation result of each candidate steering angle includes: The preview distance for vehicle lateral control is calculated, and the preview point corresponding to the preview distance is calculated. It can be understood that the preview distance refers to the look-ahead distance that is adaptively adjusted according to the driving condition during lateral control. The preview distance is increased at high speed or in a large-curvature path to maintain stability, and the preview distance is shortened at low speed or in a small-curvature path to improve tracking accuracy. The preview point refers to a path point on the reference path, which has a cumulative distance equal to the preview distance from the current position of the vehicle. The vehicle lateral control device calculates the preview distance required for current lateral control, and takes the trajectory point corresponding to the current preview distance on the reference path as the preview point.

[0035] For each candidate steering angle in the candidate steering angle set, a theoretical turning radius corresponding to the candidate steering angle is determined through a preset steering angle calibration model. It should be noted that the preset steering angle calibration model refers to the mapping relationship between the steering wheel steering angle and the vehicle turning radius pre-stored in the vehicle lateral control device. The theoretical turning radius refers to the turning radius value corresponding to the vehicle steady-state turning under ideal conditions, which is obtained by querying or calculating the steering angle calibration model based on the current candidate steering angle. The vehicle lateral control device maps the theoretical turning radius corresponding to each candidate steering angle through the preset steering angle calibration model representing the mapping relationship between the steering wheel steering angle and the vehicle turning radius.

[0036] The heading angle change amount is calculated according to the theoretical turning radius and the preview distance. It can be understood that the heading angle change amount refers to the angle change value of the heading angle of the vehicle after driving the preview distance along the circle with the radius of the theoretical turning radius, with the front wheel steering center of the vehicle as the reference. The vehicle lateral control device converts the key parameters (theoretical turning radius and preview distance) of steering control into the heading angle change amount that can be directly used for state prediction.

[0037] Specifically, the vehicle lateral control device obtains a corresponding theoretical turning radius for each candidate angle through a predefined steering geometry mapping relationship , and predicts a change in the heading angle:

[0038] wherein the above formula represents a change in the heading angle of the vehicle when driving a preview distance along a circle with a radius of .

[0039] According to the change in the heading angle, a predicted pose of the vehicle at the preview point is predicted; It should be noted that the predicted pose refers to the predicted state of the vehicle when driving the preview distance and reaching the preview point, including the predicted position and the predicted heading angle. The vehicle lateral control device first calculates the theoretical turning radius according to the candidate steering angle, determines the change in the heading angle in combination with the preview distance; then deduces the planar offset component from the vehicle to the preview point based on the central angle-chord length relationship; finally, through coordinate system rotation transformation, the local offset is converted into the predicted position in the global coordinate system, and the predicted heading angle is calculated in combination with the current heading angle of the vehicle and the change in the heading angle.

[0040] According to the true pose of the preview point and the predicted pose, a position tracking deviation and a heading attitude deviation are determined; It can be understood that the vehicle lateral control device quantifies and compares the difference between the predicted vehicle state and the expected path state to obtain the position tracking deviation and the heading attitude deviation.

[0041] Based on the change gradient of the candidate steering angle, a steering smoothness is determined; It should be noted that the change gradient of the candidate steering angle refers to the absolute value of the difference between the currently evaluated candidate steering angle and the steering wheel steering angle actually output in the last control cycle. The vehicle lateral control device quantifies the measurement value of the degree of change in the control instruction according to the change gradient of the candidate steering angle, and the size of the value directly reflects the smoothness of the steering wheel steering angle instruction. The smaller the value, the more gentle the change in the control instruction.

[0042] A multi-dimensional cost evaluation of the candidate steering angle based on the position tracking deviation, the heading attitude deviation, and the steering smoothness is performed to obtain an evaluation result of each candidate steering angle.

[0043] It can be understood that the vehicle lateral control device integrates the evaluation indexes of the position tracking deviation, the heading attitude deviation, and the steering smoothness into a cost value, and further obtains the evaluation result of each candidate steering angle.

[0044] ​In an implementable embodiment, the step of calculating a preview distance for vehicle lateral control and a preview point corresponding to the preview distance comprises: Obtaining a path point set, preprocessing each path point in the path point set to obtain a preprocessed target path point; It should be noted that the vehicle lateral control device is also provided with a path planning module, and the path point set refers to an original data set containing a plurality of path points output by the path planning module, which usually exists in the form of a one-dimensional array. The vehicle lateral control device pre-processes the original path point data to obtain a preprocessed target path point, so that the vehicle lateral control device can ensure the quality and integrity of the input data, effectively eliminate the risk of control instability caused by abnormal or sparse planning data, and provide an accurate and reliable data basis for subsequent preview point calculation and steering optimization.

[0045] Specifically, the vehicle lateral control device will receive a reference path containing a plurality of path points in advance, and the path points are one-dimensional input arrays that need to be reorganized into a two-dimensional matrix structure.

[0046] The core operations include: Heading angle validity check: verify that the heading angle of each point is within a reasonable angle range, and mark the abnormal points as invalid; Coordinate unit standardization: convert the position coordinates to standard international units; Path point adaptive expansion: when the number of valid points is lower than a set threshold, based on the motion state of the last valid point, supplement path points in the direction indicated by the gear with a fixed spatial step, and the new points inherit the kinematic properties of the original last point.

[0047] Select the nearest point in the target path point set that is closest to the current position of the vehicle; It can be understood that the nearest point refers to the path point in the preprocessed target path point set that has the shortest Euclidean distance in the two-dimensional plane with the current position of the vehicle (usually taking the front axle center or the center of mass of the vehicle as the reference point). After obtaining the preprocessed target path point set, the vehicle lateral control device traverses all valid path points to find the path point with the smallest distance, which is the nearest point.

[0048] Specifically, the nearest point search: passing through the vehicle position point Draw a straight line perpendicular to the vehicle heading angle , calculate the distance , the nearest point is , the minimum value in , that is . According to the closest point and the path curvature corresponding to the closest point, a preview distance is calculated, and a preview point corresponding to the preview distance is determined in the target path point, wherein the preview distance is within the path distance of the target path point.

[0049] It should be noted that the path curvature refers to the bending degree of the reference path at the closest point, and is a scalar value with a positive or negative sign, and the absolute value reflects the bending degree. The vehicle lateral control device dynamically calculates the preview distance and the preview distance corresponding to the preview point through the closest point and the path curvature corresponding to the closest point, and ensures that the preview point is located within the effective path point range through the index protection mechanism, thereby providing accurate target states for subsequent steering optimization control.

[0050] Specifically, based on the vehicle speed, the path curvature and the adjustable parameter, the dynamic preview distance is calculated through a composite formula:

[0051] wherein, represents the real-time speed of the vehicle, reflects the motion inertia effect, and the higher the speed, the longer the preview distance; represents an adjustable time reference parameter, controls the preview time length, and together with the vehicle speed constitutes a basic preview amount; represents a basic distance compensation term, which guarantees the minimum preview distance in low-speed working conditions; is the absolute value of the curvature of the closest point.

[0052] In this embodiment, a predefined discrete steering angle candidate set is used instead of traditional online optimization, which greatly reduces the calculation complexity, ensures that the system meets the real-time requirements of high-speed control scenarios on the vehicle embedded controller, and solves the problem of calculation power bottleneck of traditional MPC.

[0053] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as the above embodiment one can refer to the above introduction, and the following will not be repeated. On this basis, please refer to Figure 2 , step S30, the vehicle lateral control method further comprises steps S01-S04: Step S01, determining the path curvature corresponding to the closest point; It should be noted that the vehicle lateral control device directly obtains the preset path curvature value at the closest point, which provides key path shape information for subsequent preview distance calculation, so that the vehicle lateral control device can accurately perceive the bending characteristics of the current path segment.

[0054] Step S02, determining a corresponding filter coefficient according to the path curvature, and filtering the target candidate steering angle based on the filter coefficient to obtain a filtered candidate steering angle, wherein the filter coefficient includes a strong filter coefficient and a weak filter coefficient, the strong filter coefficient is used to suppress body swing, and the weak filter coefficient is used to avoid trajectory tracking delay; It can be understood that the filter coefficient refers to a smoothing factor for a first-order low-pass filter algorithm, and the value range thereof is between 0 and 1. The strong filter coefficient refers to a larger value (for example, 0.8), which can deeply smooth the input signal and effectively suppress high-frequency noise and body swing. The weak filter coefficient refers to a smaller value (for example, 0.3), which can retain the high-frequency component of the input signal and avoid trajectory tracking delay caused by excessive smoothing. The vehicle lateral control device directly associates the path curvature with the filtering strength, so that the vehicle lateral control device can intelligently adjust the smoothing strategy, such as the strong filter coefficient and the weak filter coefficient: the strong filter is used in the low-curvature straight road scene to ensure driving smoothness, and the weak filter is used in the high-curvature curve scene to ensure timeliness of tracking, thereby achieving dynamic optimal balance between control smoothness and tracking rapidity.

[0055] Specifically, the vehicle lateral control device adjusts the filtering strength based on the path curvature . That is, when is less than a set threshold, the strong filter coefficient is used to suppress body swing, otherwise the weak filter coefficient is used to retain high-frequency steering instructions and avoid trajectory tracking delay. The filtering formula is as follows:

[0056] Step S03, performing layered hardware constraint on the filtered candidate steering angle to obtain a constrained candidate steering angle. It should be noted that the vehicle lateral control device applies a multi-stage angle limiting strategy in sequence, which includes at least three levels of constraints: the first level is a hardware limit constraint, which limits the angle within the mechanical limit range of the steering wheel (a typical value is ±540°); the second level is an actuator performance constraint, which considers the tracking ability of the electric power steering system (EPS) and limits the maximum allowed deviation of the steering angle instruction between adjacent control periods; the third level is a motion state constraint, which limits the rate of change of the steering wheel angle based on the real-time kinematic state of the vehicle. After the above three levels of constraint processing, the final output candidate steering angle is obtained, which meets all hardware and performance constraints.

[0057] Specifically, the filtered steering wheel angle is subjected to layered constraint, and first, the assignment limit is performed according to the hardware constraint:

[0058] Then according to the EPS performance to limit the deviation:

[0059]

[0060] Finally according to the motion state to change the rate limit:

[0061]

[0062]

[0063] Step S04, the candidate steering angle after the constraint is filtered through the sliding window, the smooth candidate steering angle is obtained, and the vehicle lateral control device is based on the candidate steering angle of the flat vehicle lateral control device. The vehicle lateral control is carried out.

[0064] It can be understood that the vehicle lateral control device carries out the last smoothing processing on the control command through the sliding window filtering, effectively suppresses the high frequency jitter of the control signal, enables the vehicle lateral control device to output stable and smooth steering command, and finally ensures the smoothness and ride comfort of the vehicle lateral movement.

[0065] In a feasible implementation mode, step S30 comprises: The actual steering wheel steering angle and the yaw rate of the vehicle reaching the preview point are obtained, and the actual turning radius is calculated according to the steering wheel steering angle and the yaw rate; It should be noted that the actual steering wheel steering angle refers to the steering wheel rotation angle collected in real time through the electric power steering system (EPS) sensor. The yaw rate refers to the angular velocity of the vehicle rotating around the vertical axis measured by the inertial measurement unit (IMU). The vehicle lateral control device directly reads the steering wheel steering angle fed back by the EPS And the yaw rate fed back by the IMU And the actual turning radius of the vehicle is calculated through the vehicle kinematics model.

[0066] Specifically, the turning radius formula, in order to ensure that the data is collected under dynamic working conditions, when the vehicle speed And the yaw rate Both are greater than the set threshold, the actual turning radius of the vehicle is calculated : The effective data pair composed of the steering wheel steering angle and the actual turning radius is stored in the data queue; It can be understood that the data queue is a first-in first-out queue with a capacity of N, and the effective data The vehicle lateral control device systematically collects the steering response data of the vehicle in actual operation, such as the steering wheel angle and the actual turning radius, by establishing a data queue.

[0067] When the number of data pairs in the data queue exceeds a threshold value, the initial parameters in the preset steering angle calibration model are refitted to obtain target parameters. It should be noted that the threshold value is a preset integer M (M

[0068] Specifically, when the number of data pairs in the queue is greater than M, the linear model is fitted by the least square method: The parameter solving formula is:

[0069] Wherein: If the reliability of the target steering angle calibration model corresponding to the target parameters meets the standard, and the change amount of the target parameters compared with the initial parameters is greater than a threshold value, the initial parameters in the preset steering angle calibration model are updated to the target parameters.

[0070] It can be understood that when the vehicle lateral control device completes parameter refitting to obtain target parameters, it will be judged whether the update condition is met through a double judgment mechanism of reliability test and parameter significance change. If the update condition is met, the target parameters are used to replace the initial parameters, the online optimization of the steering angle calibration model is completed, the subsequent turning radius prediction is more in line with the actual steering characteristics of the vehicle, the steering model parameters are continuously corrected based on the dynamic calibration mechanism, the steering characteristics drift caused by vehicle aging, tire wear and load change is effectively adapted, and the tracking accuracy and stability of the system during long-term operation are significantly improved.

[0071] Specifically, the reliability test is determined based on the determination coefficient, and the determination coefficient is calculated as follows: (the value range is 0-1):

[0072] Wherein,

[0073] If is greater than a set threshold value, it means that the model reliability meets the standard; is greater than a set threshold value, it means that the parameter changes significantly, and if both conditions are met, the new parameters replace the existing calibration table.

[0074] In this embodiment, the control robustness of the path curvature mutation scene is enhanced, the ride comfort and system safety are improved through the cooperation of the curvature adaptive preview strategy and the multi-stage smoothing filter.

[0075] It should be noted that the above examples are only used for understanding the present application and do not constitute a limitation on the vehicle lateral control method of the present application. More forms of simple transformation based on this technical concept are within the protection scope of the present application.

[0076] The present application also provides a vehicle lateral control device, please refer to Figure 3 , the vehicle lateral control device comprises: a discrete module 10 for discretizing a mechanical limit angle range of a steering wheel into a preset number of candidate steering angle sets in response to a steering control instruction; an evaluation module 20 for performing multi-dimensional cost evaluation on each candidate steering angle in the candidate steering angle set, and taking the candidate steering angle with the minimum cost in the evaluation result as a target candidate steering angle; a control module 30 for performing vehicle lateral control based on the target candidate steering angle.

[0077] Optionally, the evaluation module comprises: an evaluation sub-module for performing multi-dimensional cost evaluation based on position tracking deviation, heading attitude deviation and steering smoothness on each candidate steering angle in the candidate steering angle set to obtain an evaluation result of each candidate steering angle; and taking the candidate steering angle with the minimum cost in the evaluation result as a target candidate steering angle.

[0078] Optionally, the evaluation sub-module comprises: an evaluation unit for calculating a preview distance for performing vehicle lateral control and a preview point corresponding to the preview distance; determining a theoretical turning radius corresponding to each candidate steering angle in the candidate steering angle set through a preset steering angle calibration model; calculating a heading angle change amount according to the theoretical turning radius and the preview distance; predicting a predicted pose of the vehicle at the preview point according to the heading angle change amount; determining a position tracking deviation and a heading attitude deviation according to a real pose of the preview point and the predicted pose; determining a steering smoothness based on a change gradient of the candidate steering angle; and performing multi-dimensional cost evaluation on the candidate steering angle based on the position tracking deviation, the heading attitude deviation and the steering smoothness to obtain an evaluation result of each candidate steering angle.

[0079] Optionally, the evaluation unit comprises: The computing subunit is configured to obtain a path point set, pre-process each path point in the path point set to obtain a target path point after pre-processing, select a nearest point closest to a current position of the vehicle from the target path points, calculate a preview distance according to the nearest point and a path curvature corresponding to the nearest point, and determine a preview point corresponding to the preview distance in the target path points, wherein the preview distance is within a path distance of the target path point.

[0080] Optionally, the control module comprises: The filtering sub-module is configured to determine a path curvature corresponding to the nearest point, determine a corresponding filtering coefficient according to the path curvature, filter the target candidate steering angle based on the filtering coefficient to obtain a filtered candidate steering angle, wherein the filtering coefficient comprises a strong filtering coefficient and a weak filtering coefficient, the strong filtering coefficient is used to suppress body swing, and the weak filtering coefficient is used to avoid trajectory tracking hysteresis, perform hierarchical hardware constraint on the filtered candidate steering angle to obtain a constrained candidate steering angle, perform sliding window filtering on the constrained candidate steering angle to obtain a smoothed candidate steering angle, and perform vehicle lateral control based on the smoothed candidate steering angle.

[0081] The updating sub-module is configured to obtain an actual steering wheel steering angle and a yaw rate of the vehicle when the vehicle reaches the preview point, calculate an actual turning radius according to the steering wheel steering angle and the yaw rate, store an effective data pair composed of the steering wheel steering angle and the actual turning radius in a data queue, when the number of data pairs in the data queue exceeds a threshold value, re-fit initial parameters in the preset steering angle calibration model to obtain target parameters, if a target steering angle calibration model corresponding to the target parameters is reliable, and a change amount of the target parameters compared with the initial parameters is greater than a threshold value, update the initial parameters in the preset steering angle calibration model to the target parameters.

[0082] The vehicle lateral control device provided in the application adopts the vehicle lateral control method in the above embodiments, and can solve the technical problem of vehicle lateral control. Compared with the prior art, the vehicle lateral control device provided in the application has the same beneficial effects as the vehicle lateral control method provided in the above embodiments, and other technical features in the vehicle lateral control device are the same as the features disclosed in the above embodiments, which will not be repeated here.

[0083] The application provides a vehicle lateral control device, which comprises at least one processor and a memory in communication connection with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the vehicle lateral control method in the above embodiment one.

[0084] Reference will now be made to Figure 4 which shows a structural diagram of a vehicle lateral control apparatus suitable for use in implementing embodiments of the present application. The vehicle lateral control apparatus in embodiments of the present application can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, tablet computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, as well as stationary terminals such as digital TVs, desktop computers, and the like. Figure 4 The illustrated vehicle lateral control apparatus is merely an example and should not impose any limitation on the functions and the range of use of embodiments of the present application.

[0085] As Figure 4 shown, the vehicle lateral control apparatus can include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, or the like) that can perform various appropriate actions and processes in accordance with a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. Various programs and data required for operation of the vehicle lateral control apparatus are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. In general, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, and the like; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, and the like; the storage device 1003 including, for example, a magnetic tape, a hard disk, and the like; and a communication device 1009. The communication device 1009 can allow the vehicle lateral control apparatus to communicate wirelessly or by wire with other devices to exchange data. Although the vehicle lateral control apparatus is shown as having various systems, it should be understood that all of the illustrated systems are not required to be implemented or provided. More or fewer systems can alternatively be implemented or provided.

[0086] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program codes for executing the method shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiments disclosed in the present application are executed.

[0087] The vehicle lateral control device provided by the present application adopts the vehicle lateral control method in the above-mentioned embodiments, and can solve the technical problem of vehicle lateral control. Compared with the prior art, the vehicle lateral control device provided by the present application has the same beneficial effects as the vehicle lateral control method provided by the above-mentioned embodiments, and other technical features in the vehicle lateral control device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0088] It should be understood that various parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the description of the above-mentioned embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0089] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0090] The present application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e. computer program) for executing the vehicle lateral control method in the above-mentioned embodiments.

[0091] The computer readable storage medium provided in the present application may, for example, be a U disk, but is not limited to an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples of the computer readable storage medium can include, but are not limited to, an electric connection with one or more conductive wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present embodiment, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer readable storage medium can be transmitted by any suitable medium, including but not limited to an electric wire, an optical cable, an RF (Radio Frequency), and the like, or any suitable combination thereof.

[0092] The above computer readable storage medium can be included in the vehicle lateral control device, or can exist separately without being assembled into the vehicle lateral control device.

[0093] The above computer readable storage medium carries one or more programs, which, when executed by the vehicle lateral control device, cause the vehicle lateral control device to: discretize a mechanical limit angle range of a steering wheel into a preset number of candidate steering angle sets in response to a steering control instruction; perform multi-dimensional cost evaluation for each candidate steering angle in the candidate steering angle set, and select a candidate steering angle with the minimum cost in the evaluation results as a target candidate steering angle; and perform vehicle lateral control based on the target candidate steering angle.

[0094] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0095] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0096] The modules involved in the embodiments of the present application can be implemented in the form of software or in the form of hardware. In some cases, the name of the module does not constitute a limitation on the module itself.

[0097] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e., a computer program) for executing the vehicle lateral control method, and can solve the technical problem of vehicle lateral control. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the vehicle lateral control method provided by the above-mentioned embodiments, which will not be described here.

[0098] The application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the vehicle lateral control method as described above.

[0099] The computer program product provided by the application can solve the technical problem of vehicle lateral control. Compared with the prior art, the beneficial effects of the computer program product provided by the application are the same as those of the vehicle lateral control method provided by the above-mentioned embodiments, which will not be repeated here.

[0100] The above only describes some embodiments of the application, and does not limit the protection scope of the application. Any equivalent structure transformation made by using the content of the application specification and drawings, or direct / indirect application in other related technical fields is included in the protection scope of the application.

Claims

1. A vehicle lateral control method, characterized in that, The vehicle lateral control method includes: In response to steering control commands, the mechanical limit angle range of the steering wheel is discretized into a preset set of candidate steering angles; For each candidate steering angle in the candidate steering angle set, a multi-dimensional cost evaluation is performed, and the candidate steering angle with the lowest cost in the evaluation results is taken as the target candidate steering angle. Based on the target candidate steering angle, lateral vehicle control is performed.

2. The vehicle lateral control method as described in claim 1, characterized in that, The step of performing a multi-dimensional cost evaluation for each candidate steering angle in the candidate steering angle set, and selecting the candidate steering angle with the lowest cost in the evaluation results as the target candidate steering angle, includes: For each candidate steering angle in the candidate steering angle set, a multi-dimensional cost evaluation based on position tracking deviation, heading attitude deviation, and steering smoothness is performed to obtain the evaluation result for each candidate steering angle; The candidate steering angle with the lowest cost in the evaluation results is taken as the target candidate steering angle.

3. The vehicle lateral control method as described in claim 2, characterized in that, The step of performing a multi-dimensional cost evaluation based on position tracking deviation, heading attitude deviation, and steering smoothness for each candidate steering angle in the candidate steering angle set, to obtain the evaluation result for each candidate steering angle, includes: The aiming distance for lateral vehicle control and the aiming point corresponding to the aiming distance are calculated. For each candidate steering angle in the candidate steering angle set, the theoretical turning radius corresponding to the candidate steering angle is determined by a preset steering angle calibration model; Based on the theoretical turning radius and the pre-aiming distance, the change in heading angle is calculated. Based on the change in heading angle, the predicted pose of the vehicle at the pre-aiming point is predicted; Based on the actual pose of the pre-aiming point and the predicted pose, determine the position tracking deviation and the heading attitude deviation; The steering smoothness is determined based on the gradient of the change in the candidate steering angle; A multi-dimensional cost evaluation based on the position tracking deviation, the heading attitude deviation, and the steering smoothness is performed on the candidate steering angles to obtain the evaluation result for each candidate steering angle.

4. The vehicle lateral control method as described in claim 3, characterized in that, The steps of calculating the aiming distance for vehicle lateral control and the aiming point corresponding to the aiming distance include: Obtain a path point set, and preprocess each path point in the path point set to obtain the preprocessed target path point; Select the nearest point from the target path points that is closest to the vehicle's current position; Based on the nearest point and the path curvature corresponding to the nearest point, the aiming distance is calculated, and the aiming point corresponding to the aiming distance is determined in the target path point, wherein the aiming distance is within the path distance of the target path point.

5. The vehicle lateral control method as described in claim 1, characterized in that, The steps for performing vehicle lateral control based on the target candidate steering angle include: Determine the path curvature corresponding to the nearest point; Based on the path curvature, the corresponding filtering coefficients are determined, and the target candidate steering angle is filtered based on the filtering coefficients to obtain the filtered candidate steering angle. The filtering coefficients include strong filtering coefficients and weak filtering coefficients. The strong filtering coefficients are used to suppress vehicle body sway, and the weak filtering coefficients are used to avoid trajectory tracking lag. The filtered candidate steering angles are subjected to hierarchical hardware constraints to obtain constrained candidate steering angles. The constrained candidate steering angle is filtered by a sliding window to obtain a smooth candidate steering angle, and vehicle lateral control is performed based on the smooth candidate steering angle.

6. The vehicle lateral control method as described in claim 1, characterized in that, The step of performing vehicle lateral control based on the target candidate steering angle is followed by: The actual steering wheel angle and yaw rate of the vehicle when it reaches the pre-aiming point are obtained, and the actual turning radius is calculated based on the steering wheel angle and the yaw rate. The effective data pair consisting of the steering wheel angle and the actual turning radius is stored in the data queue; When the number of data pairs in the data queue exceeds the threshold, the initial parameters in the preset steering angle calibration model are refitted to obtain the target parameters; If the target steering angle calibration model corresponding to the target parameter meets the reliability standard, and the change of the target parameter compared to the initial parameter is greater than a threshold, then the initial parameter in the preset steering angle calibration model is updated to the target parameter.

7. A vehicle lateral control device, characterized in that, The device includes: The discrete module is used to discretize the mechanical limit angle range of the steering wheel into a preset set of candidate steering angles in response to steering control commands; The evaluation module is used to perform multi-dimensional cost evaluation for each candidate steering angle in the candidate steering angle set, and to take the candidate steering angle with the lowest cost in the evaluation results as the target candidate steering angle. The control module is used to perform lateral control of the vehicle based on the target candidate steering angle.

8. A vehicle lateral control device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the vehicle lateral control method as claimed in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the vehicle lateral control method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the vehicle lateral control method as described in any one of claims 1 to 6.

Images