A parking speed planning method, electronic device and storage medium

Abstract

The application discloses a parking speed planning method, an electronic device and a storage medium. The method comprises the following steps: acquiring a limit speed of at least one path segment of a parking path and a speed influencing factor of the at least one path segment, wherein the speed influencing factor comprises curvature information or an obstacle proportion factor, and the obstacle proportion factor represents the influence degree of obstacles on the limit speed; adjusting the limit speed of each path segment based on the speed influencing factor of the path segment, to obtain a maximum driving speed of each path segment; and determining a target driving speed of a vehicle on each path segment based on at least the maximum driving speed of each path segment. In this way, the application can improve the accuracy of the driving speed in the parking process, so as to improve the safety and user comfort in the parking process.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a parking speed planning method, electronic device, and storage medium. Background Technology

[0002] With the development of vehicles, people are paying increasing attention to autonomous driving. In the process of autonomous driving, not only driving safety but also passenger comfort must be considered. The planning and control of vehicle speed is a key factor determining passenger comfort. Therefore, speed planning and control for automatic parking is crucial in product development. Summary of the Invention

[0003] The main technical problem addressed by this application is to provide a parking speed planning method, electronic device, and storage medium that can improve the accuracy of driving speed during the parking process, thereby further enhancing parking safety and user comfort.

[0004] To address the aforementioned technical problems, the first aspect of this application provides a parking speed planning method. This method includes: obtaining the speed limit of at least one segment of a parking path, and the speed influence factor of at least one segment, wherein the speed influence factor includes curvature information or an obstacle ratio factor, and the obstacle ratio factor characterizes the degree of influence of obstacles on the speed limit; adjusting the speed limit of each segment based on the speed influence factor of each segment to obtain the maximum driving speed of each segment; and determining the target driving speed of the vehicle in each segment, based at least on the maximum driving speed of each segment.

[0005] Before obtaining the speed limit of at least one segment of the parking path, the method further includes: dividing the parking path into collision-prone and collision-free segments based on the location of obstacles; adjusting the speed limit of each segment based on the speed influence factor of each segment to obtain the maximum driving speed of each segment, including: for collision-prone segments, weighting the speed limit of the collision-prone segments based on the obstacle ratio factor to obtain the maximum driving speed of the collision-prone segments; for collision-free segments, adjusting the speed limit of the collision-free segments based on curvature information to obtain the maximum driving speed of the collision-free segments.

[0006] The adjustment of the speed limit of the collision-free path segment based on curvature information to obtain the maximum driving speed of the collision-free path segment includes: determining the influence parameter of curvature on the speed limit based on the curvature scale factor, average curvature and preset curvature threshold of the collision-free path segment; and weighting the speed limit of the collision-free path segment using the influence parameter to obtain the maximum driving speed of the collision-free path segment.

[0007] Specifically, based on the curvature scaling factor, average curvature, and preset curvature threshold of the collision-free path segment, the influence parameter of curvature on speed limitation is determined, including: obtaining a first parameter based on the curvature scaling factor and a first value; obtaining a second parameter by weighting the first parameter based on the ratio of the average curvature to the preset curvature threshold; using the difference between the second value and the second parameter as a third parameter; and selecting the largest of the curvature scaling factor and the third parameter as the influence parameter.

[0008] Based on the location of obstacles, the parking path is divided into collision-prone and collision-free segments, including: acquiring each path point on the parking path; where each path point represents the position of the vehicle on the parking path at different times; determining whether each path point is a collision point based on the distance between each path point and the obstacle; clustering the collision points to generate collision-prone segments; and taking the path segments in the parking path other than the collision-prone segments as collision-free segments.

[0009] Among them, there are at least two collision path segments; clustering each collision point to generate collision path segments includes: determining whether the number of path points between two adjacent collision points is less than a preset threshold; in response to the number of path points between two adjacent collision points being less than the preset threshold, determining that the two adjacent collision points belong to the same collision path segment; in response to the number of path points between two adjacent collision points being not less than the preset threshold, determining that the two adjacent collision points belong to different collision path segments; and splicing the collision points belonging to the same collision path segment to generate collision path segments.

[0010] The method further includes, after clustering the collision points to generate collision path segments, determining whether the length of the collision path segment is less than a preset length; in response to the length being less than the preset length, treating the collision path segment as a collision-free path segment; and / or, determining whether the collision path segment is the starting or ending path segment of a parking path; in response to the collision path segment being the starting or ending path segment of a parking path, treating the collision path segment as a collision-free path segment.

[0011] The determination of whether a collision-affected path segment is the starting or ending path segment of a parking path includes: determining the collision-affected path segment as the starting path segment of a parking path in response to the last collision point in the collision-affected path segment belonging to the first third number of path points of the parking path; or, determining the collision-affected path segment as the ending path segment of a parking path in response to the first collision point in the collision-affected path segment belonging to the last fourth number of path points of the parking path.

[0012] The parking speed planning method further includes: obtaining the endpoint speed, endpoint acceleration, and maximum acceleration of at least one path segment; determining the target driving speed of the vehicle in each path segment based at least on the maximum driving speed of each path segment, including: obtaining the acceleration curve of the path segment using Bézier curves based on the endpoint speed, maximum driving speed, endpoint acceleration, and maximum acceleration of the path segment; wherein the acceleration curve represents the relationship between the vehicle's acceleration and time in the path segment; obtaining the speed curve of the path segment based on the acceleration curve; wherein the speed curve is used to determine the target driving speed of the vehicle at each time point in the path segment.

[0013] The vehicle travels through at least one phase in each path segment, including an acceleration phase, a constant speed phase, and a deceleration phase. Based on the endpoint speed, maximum speed, endpoint acceleration, and maximum acceleration of each path segment, the acceleration curves for each path segment are obtained using Bézier curves. This includes: for each path segment, generating the acceleration curves corresponding to each travel phase using Bézier curves based on the endpoint speed, maximum speed, endpoint acceleration, and maximum acceleration of the path segment; and stitching together the acceleration curves corresponding to each travel phase to obtain the acceleration curve of the path segment.

[0014] The vehicle's travel phase within the path segment includes an acceleration phase, where endpoint acceleration includes the acceleration at the start of the path segment and endpoint speed includes the speed at the start; and / or, the vehicle's travel phase within the path segment includes a deceleration phase, where endpoint acceleration includes the acceleration at the end of the path segment and endpoint speed includes the speed at the end. Based on the endpoint speed, maximum travel speed, endpoint acceleration, and maximum acceleration, acceleration curves corresponding to each travel phase are generated using Bézier curves, including: processing the target acceleration, maximum acceleration, target speed, and maximum travel speed using a first set of objective equations to obtain intermediate control points of the Bézier curves; obtaining the start control point and end control point, and generating acceleration curves corresponding to the target travel phase based on the start control point, end control point, and intermediate control points; wherein, when the target travel phase is an acceleration phase, the first set of objective equations is the first set of equations, the target acceleration is the start acceleration, and the target speed is the start speed; when the target travel phase is a deceleration phase, the first set of objective equations is the second set of equations, the target acceleration is the end acceleration, and the target speed is the end speed.

[0015] The parking speed planning method further includes the following steps for constructing the first set of objective equations: obtaining the acceleration function corresponding to each driving stage; wherein the acceleration function is obtained based on the Bézier curve formula; integrating each acceleration function to obtain the velocity function; wherein the velocity function represents the relationship between velocity, endpoint acceleration, acceleration corresponding to intermediate control points, and time; based on the velocity function, obtaining the expression for the vehicle's velocity at the end time of the driving stage; based on the velocity expression, determining the first set of objective equations; wherein, when the endpoint acceleration is the starting acceleration, the velocity expression is set to equal the maximum driving speed, and the acceleration corresponding to the intermediate control point is set to the maximum acceleration, to obtain the first set of equations; when the endpoint acceleration is the ending acceleration, the velocity expression is set to equal the ending speed, and the acceleration corresponding to the intermediate control point is set to the maximum acceleration, to obtain the second set of equations.

[0016] The process includes, after generating the acceleration curve corresponding to the target driving stage based on the starting control point, ending control point, and intermediate control point, the following steps: determining whether the maximum jerk in the acceleration curve is greater than a preset jerk based on the acceleration curve corresponding to the target driving stage; in response to the maximum jerk being greater than the preset jerk, processing the target acceleration, target speed, maximum driving speed, and preset jerk using the second objective equation set to re-obtain the intermediate control point of the Bézier curve, and regenerating the acceleration curve corresponding to the target driving stage based on the starting control point, ending control point, and intermediate control point; wherein, when the target driving stage is an acceleration stage, the second objective equation set is the third equation set, the target acceleration is the starting acceleration, and the target speed is the starting speed; when the target driving stage is a deceleration stage, the second objective equation set is the fourth equation set, the target acceleration is the ending acceleration, and the target speed is the ending speed.

[0017] The parking speed planning method further includes the following steps for constructing the second objective equation set: obtaining the acceleration function corresponding to each driving stage; wherein the acceleration function is obtained based on the Bézier curve formula; integrating each acceleration function to obtain the velocity function; wherein the velocity function represents the relationship between velocity, endpoint acceleration, acceleration corresponding to intermediate control points, and time; based on the velocity function, obtaining the expression for the vehicle's velocity at the end of the driving stage; based on the velocity expression, determining the second objective equation set; wherein, when the endpoint acceleration is the starting acceleration, the velocity expression is set to equal the maximum driving speed, and the acceleration corresponding to the intermediate control point is set to a preset jerk, to obtain the third objective equation set; when the endpoint acceleration is the ending acceleration, the velocity expression is set to equal the ending speed, and the acceleration corresponding to the intermediate control point is set to a preset jerk, to obtain the fourth objective equation set.

[0018] The vehicle's travel phase within the path segment includes a constant speed phase. After generating the acceleration curve corresponding to the target travel phase based on the starting control point, ending control point, and intermediate control points, the process further includes: determining the distance traveled in the target travel phase based on the acceleration curve; using the difference between the length of the parking path and the distance traveled in the target travel phase as the distance traveled in the constant speed phase; determining the travel time in the constant speed phase based on the distance traveled in the constant speed phase and the speed in the constant speed phase; wherein the speed in the constant speed phase is the speed at the end of the previous stage in the constant speed phase; and obtaining the acceleration curve for the constant speed phase based on the acceleration and travel time in the constant speed phase.

[0019] The path segment includes collision path segments, and the endpoint speed includes the starting speed and the ending speed. Obtaining the endpoint speed of at least one path segment includes: for a collision path segment, determining whether the target collision point of the collision path segment is a target location point in the parking path corresponding to the target collision point; in response to the target collision point not being a target location point in the parking path corresponding to the target collision point, setting the speed of the target location point corresponding to the target collision point to the maximum driving speed; in response to the target collision point being a target location point in the parking path corresponding to the target collision point, setting the speed of the target location point corresponding to the target collision point to a preset speed; wherein the target collision point is at least one of the first collision point and the last collision point, the target location point corresponding to the first collision point is the starting point, the speed of the target location point corresponding to the first collision point is the starting speed, the target location point corresponding to the last collision point is the ending point, and the speed of the target location point corresponding to the last collision point is the ending speed.

[0020] To address the aforementioned technical problems, a second aspect of this application provides an electronic device comprising a memory and a processor coupled to each other, wherein the memory stores program instructions; and the processor executes the program instructions stored in the memory to implement the method provided in the first aspect.

[0021] To address the aforementioned technical problems, a third aspect of this application provides a computer-readable storage medium for storing program instructions that can be executed to implement the method provided in the first aspect.

[0022] The beneficial effects of this application are as follows: Unlike existing technologies, this application obtains the speed limit of at least one segment of a parking path, and the speed influence factor of at least one segment. The speed influence factor includes curvature information or an obstacle proportion factor, where the obstacle proportion factor characterizes the degree of influence of obstacles on the speed limit. Based on the speed influence factor of each segment, the speed limit of each segment is adjusted to obtain the maximum driving speed for each segment. At least based on the maximum driving speed of each segment, the target driving speed of the vehicle in each segment is determined. By adjusting the speed limit using the speed influence factor, the speed limit can be controlled within a reasonable speed range, thereby improving the accuracy of the target driving speed and avoiding situations where the speed limit is too high, resulting in an excessively high target driving speed. Improving the accuracy of the target driving speed enhances the safety and user comfort of the parking process. Attached Figure Description

[0023] Figure 1 This is a flowchart illustrating one implementation method of the parking speed planning method provided in this application;

[0024] Figure 2 This is a flowchart illustrating one implementation method for constructing the first set of objective equations provided in this application;

[0025] Figure 3 This is a schematic diagram of one embodiment of the acceleration function in the acceleration phase provided in this application;

[0026] Figure 4 This is a schematic diagram of one embodiment of the acceleration function during the deceleration phase provided in this application;

[0027] Figure 5 This is a schematic diagram of one embodiment of the acceleration curve of the collision-free path segment provided in this application;

[0028] Figure 6 This is a schematic diagram of one embodiment of the speed curve of the collision-free path segment provided in this application;

[0029] Figure 7 This is a schematic diagram of one embodiment of the acceleration curve of the collision-free path segment provided in this application;

[0030] Figure 8 This is a schematic diagram of one embodiment of the acceleration curve of the collision path segment provided in this application;

[0031] Figure 9 This is a schematic diagram of one embodiment of the velocity curve of the collision path segment provided in this application;

[0032] Figure 10 This is a schematic diagram of one embodiment of the acceleration curve of the collision path segment provided in this application;

[0033] Figure 11 This is a schematic diagram of the framework of one embodiment of the electronic device provided in this application;

[0034] Figure 12 This is a schematic diagram of a framework of one embodiment of the computer-readable storage medium provided in this application. Detailed Implementation

[0035] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0036] It should be noted that the embodiments of this application contain descriptions involving "first," "second," etc., which are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0037] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0038] Please see Figure 1 , Figure 1 This is a flowchart illustrating one embodiment of the parking speed planning method provided in this application. The method includes:

[0039] S11: Obtain the speed limit of at least one segment of the parking path, and the speed influence factor of at least one segment.

[0040] In one embodiment, the speed limit for a path segment can be the maximum driving speed stipulated by the state for that path segment, such as 30 km / h. The speed influence factor of the path segment is used to limit the maximum driving speed of the vehicle on that path segment. The speed influence factor may include curvature information or obstacle ratio factor. The obstacle ratio factor characterizes the degree of influence of obstacles on the speed limit. The obstacle ratio factor has a greater degree of restriction on the maximum driving speed than curvature information. That is, the maximum driving speed obtained using the obstacle ratio factor is less than the maximum driving speed obtained using curvature information.

[0041] In one implementation, the parking path can be calculated directly without segmentation. In other implementations, the parking path can be divided into at least two segments. For example, based on the location of obstacles, the parking path can be divided into collision-prone and collision-free segments. A collision-prone segment indicates that the vehicle is traveling on that segment and there is a high probability of colliding with an obstacle, while a collision-free segment indicates that the vehicle is traveling on that segment and there is a high probability of not colliding with an obstacle. It is understood that a parking path may contain only collision-prone segments or only collision-free segments.

[0042] In one embodiment, based on the location of obstacles, the parking path is divided into collision-prone and non-collision-prone segments, including: acquiring each path point on the parking path; wherein each path point represents the position of the vehicle on the parking path at different times; for example, the position of the vehicle's center point at different times can be used as the position of each path point, or the position of the vehicle's rear axle center can be used as the position of each path point. Based on the distance between each path point and the obstacle, it is determined whether each path point is a collision point; in one specific embodiment, it can be determined whether the distance between each path point and the obstacle is greater than a first preset distance, and if so, the path point is considered a collision point; in another specific embodiment, after determining the path points, the vehicle body outline can be generated at the path points, and the generated body outline can be larger than the actual body outline. It is determined whether the distance between the body outline and the obstacle is less than a second preset distance, and if so, the corresponding path point is considered a collision point. It is understood that the first and second preset distances can be set according to the actual situation, and are not limited here. After determining each collision point, the collision points are clustered to generate collision-prone path segments; at this time, the obtained collision-prone path segments can be one or multiple. The parking path segments other than those with collision risks are considered collision-free segments.

[0043] In one specific implementation, if there are at least two collision path segments, clustering is performed on each collision point to generate a collision path segment. The method can be determined by checking if the number of path points between two adjacent collision points is less than a preset threshold. If the number of path points between two adjacent collision points is less than the preset threshold, the two collision points are determined to belong to the same collision path segment. If the number of path points between two adjacent collision points is not less than the preset threshold, the two collision points are determined to belong to different collision path segments. The collision points belonging to the same collision path segment are then concatenated to generate the collision path segment. In another specific implementation, path points in the parking path are numbered according to the vehicle's forward movement order. To determine if the number of path points between two adjacent collision points is less than a preset threshold, the difference between the indexes of two adjacent collision points can be checked. For example, if the preset threshold is 10, and the indexes of two adjacent collision points are 10 and 11, then these two collision points belong to the same collision path segment; if the indexes of two adjacent collision points are 11 and 25, then these two collision points do not belong to the same collision path segment.

[0044] After obtaining the collision-prone path segment using the above method, at least one of the following judgments can be performed on the collision-prone path segment. Specifically, it can be determined whether the length of the collision-prone path segment is less than a preset length; in response to the length being less than the preset length, the collision-prone path segment is treated as a collision-free path segment; by setting a preset length, collision-prone path segments that are too short can be avoided. It can also be determined whether the collision-prone path segment is the starting or ending path segment of a parking path; in response to the collision-prone path segment being the starting or ending path segment of a parking path, the collision-prone path segment is treated as a collision-free path segment.

[0045] In one specific implementation, the starting or ending point of a parking path can be determined by the first and last collision points within the collision path segment. Specifically, in response to the last collision point in the collision path segment belonging to the third-order number of path points in the parking path, the collision path segment is determined to be the starting point of the parking path. These third-order number of path points are path points within the starting point of the parking path. For example, if the starting point of the parking path contains 10 path points, it can be determined whether the last collision point in the collision path segment is any one of these 10 path points. If so, it indicates that the collision path segment belongs to the starting point of the parking path. In response to the first collision point in a collision-prone path segment belonging to the last fourth-number path points of the parking path, the collision-prone path segment is determined to be the termination path segment of the parking path. Similarly, if the last fourth-number path points are path points in the termination path segment of the parking path, it is determined whether the first collision point in the collision-prone path segment is any of the path points in the termination path segment. If so, it indicates that the collision-prone path segment belongs to the termination path segment of the parking path. In one specific embodiment, it can be determined whether the index of the last collision point in the collision-prone path segment is less than the index of the last path point in the starting path segment. For example, the index of the last path point in the starting path segment can be 10. If so, the collision-prone path segment is determined to be the starting path segment. Alternatively, it can be determined whether the index of the first collision point in the collision-prone path segment is greater than the index of the first path point in the termination path segment. For example, the index of the first path point in the termination path segment can be 90. If so, the collision-prone path segment is determined to be the termination path segment.

[0046] S12: Adjust the speed limit of each path segment based on the speed influence factor of each path segment to obtain the maximum driving speed of each path segment.

[0047] In one specific implementation, for collision-prone path segments, the speed limit of these segments can be weighted based on an obstacle scale factor to obtain the maximum driving speed. This is achieved by multiplying the obstacle scale factor by the speed limit. The obstacle scale factor is set empirically and is not limited here. For collision-free path segments, the speed limit can be adjusted based on curvature information to obtain the maximum driving speed. Specifically, the curvature scale factor, average curvature, and a preset curvature threshold of the collision-free path segment are used to determine the curvature influence parameter on the speed limit. This influence parameter is then used to weight the speed limit of the collision-free path segment to obtain the maximum driving speed. In one specific implementation, a first parameter is obtained based on the curvature scale factor and a first value. A second parameter is obtained by weighting the first parameter based on the ratio of the average curvature to the preset curvature threshold. The difference between the second value and the second parameter is used as a third parameter. The larger of the curvature scale factor and the third parameter is selected as the influence parameter. The first and second values ​​can both be set to 1. The maximum driving speed of the collision-free path segment is determined as shown in Formula 1 below.

[0048]

[0049] in, The maximum driving speed on a collision-free path segment, 1-γ curvature As the first parameter, For the mean curvature, The preset curvature threshold, For the second parameter, β is the third parameter. curvature v is the curvature scaling factor. max The speed limit for collision-free path segments.

[0050] S13: Determine the target speed of the vehicle on each path segment, based at least on the maximum speed of each path segment.

[0051] In one implementation, after determining the maximum driving speed for each path segment, the target driving speed for each path segment can be directly made less than or equal to the maximum driving speed. For example, if a certain path segment is a collision-free path segment, the vehicle can travel at a constant speed at the maximum driving speed, or accelerate at a target driving speed less than the maximum driving speed, as long as the target driving speed of that path segment does not exceed the maximum driving speed of that path segment.

[0052] In another embodiment, the endpoint speed, endpoint acceleration, and maximum acceleration of at least one path segment can also be obtained. The endpoint speed may include at least one of the starting speed and the ending speed. In one specific embodiment, the endpoint speeds of a collision-prone path segment and a collision-free path segment may be different. For a collision-prone path segment, it is determined whether the target collision point of the collision-prone path segment is a target position point in the parking path corresponding to the target collision point. If the target collision point is not a target position point in the parking path corresponding to the target collision point, the speed of the target position point corresponding to the target collision point is set to the maximum driving speed. If the target collision point is a target position point in the parking path corresponding to the target collision point, the speed of the target position point corresponding to the target collision point is set to a preset speed. The target collision point can be at least one of the first collision point and the last collision point of the collision-prone path segment. The target position point corresponding to the first collision point is the starting point, and the speed of the target position point corresponding to the first collision point is the starting speed. The target position point corresponding to the last collision point is the ending point, and the speed of the target position point corresponding to the last collision point is the ending speed. Specifically, it determines whether the first collision point of a collision path segment is the starting point of the parking path; if not, the starting speed is set to the maximum driving speed. It also determines whether the last collision point of a collision path segment is the ending point of the parking path; if not, the ending speed is set to the maximum driving speed. If the first collision point is the starting point of the parking path, the starting speed is set to a preset speed; similarly, if the last collision point is the ending point of the parking path, the ending speed is set to a preset speed. The preset speed can be 0 or a value close to 0.

[0053] For collision-free path segments, determine whether the first collision point of the collision-free path segment is the starting point of the parking path. If not, set the starting speed of the collision-free path segment to the speed of the end point of the adjacent previous path segment; if so, set the starting speed of the collision-free path segment to a preset speed. Similarly, determine whether the last collision point of the collision-free path segment is the end point of the parking path. If not, set the ending speed of the collision-free path segment to the speed of the starting point of the adjacent next path segment; if so, set the ending speed of the collision-free path segment to a preset speed.

[0054] After obtaining the endpoint speed, endpoint acceleration, and maximum acceleration of at least one path segment, the acceleration curve of each path segment can be obtained using Bézier curves based on the endpoint speed, maximum speed, endpoint acceleration, and maximum acceleration of each path segment. The acceleration curve represents the relationship between the vehicle's acceleration and time in the path segment. Based on each acceleration curve, the speed curve of each path segment is obtained. The speed curve is used to determine the target speed of the vehicle at each time point in the path segment.

[0055] In one embodiment, the vehicle includes at least one driving stage in each path segment. The driving stage includes an acceleration stage, a constant speed stage, and a deceleration stage. For each path segment, an acceleration curve corresponding to each driving stage can be generated using Bézier curves based on the endpoint speed, maximum driving speed, endpoint acceleration, and maximum acceleration of the path segment. The acceleration curves corresponding to each driving stage are then spliced ​​together to obtain the acceleration curve of the path segment.

[0056] In one specific implementation, for a certain path segment, this path segment may only contain an acceleration phase, i.e., the vehicle accelerates within this path segment. This path segment may be a collision-prone or collision-free path segment. In this case, the endpoint speed of the path segment may include the starting speed, and the endpoint acceleration of the path segment may include the starting acceleration. Based on the endpoint speed, maximum speed, endpoint acceleration, and maximum acceleration, an acceleration curve corresponding to the acceleration phase is generated using a Bézier curve. This includes: processing the starting speed, starting acceleration, maximum speed, and maximum acceleration using a first set of equations to obtain the intermediate control points of the Bézier curve; wherein, the first set of equations is shown in Formula 2 below, and the exact method of implementing the first set of equations is described below. Substituting the starting speed, starting acceleration, maximum speed, and maximum acceleration into the first set of equations yields the intermediate control points of the acceleration phase.

[0057]

[0058] Among them, a m Let Δt be the ordinate of the intermediate control point during the acceleration phase on the acceleration curve. accel Let a be the x-coordinate of the intermediate control point during the acceleration phase on the acceleration curve. start Let a be the initial acceleration. max For maximum acceleration, v start v is the initial velocity. max This is the maximum driving speed.

[0059] After obtaining the intermediate control point of the acceleration phase, the starting control point and the ending control point of the acceleration phase are acquired. Based on these three control points, the acceleration curve corresponding to the acceleration phase is generated. The starting control point represents the acceleration at the beginning of the acceleration phase; its ordinate can be the acceleration value of the vehicle entering the acceleration phase (which can be 0 or not). The abscissa represents the time taken for the vehicle to enter the acceleration phase. In one specific implementation, the time of each driving phase is quantified, meaning the time of each driving phase is between [0,1]. Therefore, the abscissa of the starting control point is 0. The ending control point represents the acceleration at the end of the acceleration phase. In one specific implementation, since the acceleration phase is followed by a deceleration phase, a constant speed phase, or a stop, to ensure the continuity of each driving phase, the acceleration value at the end of the acceleration phase is set to 0 or a value close to 0, resulting in the coordinates of the ending control point being (1,0). After obtaining the coordinates of the starting control point, intermediate control point, and ending control point of the acceleration phase, the Bézier curve can be obtained using the Bézier formula, and this Bézier curve can be used as the acceleration curve for that acceleration phase. In this embodiment, the intermediate control point can be the point between the starting control point and the intermediate control point, that is, the x-coordinate of the intermediate control point is located between the x-coordinates of the starting control point and the ending control point. In other embodiments, the intermediate control point may not be the point between the starting control point and the intermediate control point.

[0060] In another specific implementation, for a certain path segment, the path segment may only contain a deceleration phase, that is, the vehicle decelerates within this path segment. In this case, the endpoint speed of the path segment may include the final speed, and the endpoint acceleration of the path segment may include the final acceleration. Based on the endpoint speed, maximum speed, endpoint acceleration, and maximum acceleration, an acceleration curve corresponding to the deceleration phase is generated using a Bézier curve. This includes: processing the final speed, final acceleration, maximum speed, and maximum acceleration using a second set of equations to obtain the intermediate control points of the Bézier curve; wherein the second set of equations is shown in Formula 3 below, and the exact method of using the second set of equations is described below. Substituting the final speed, final acceleration, maximum speed, and maximum acceleration into the second set of equations yields the intermediate control points of the deceleration phase.

[0061]

[0062] Among them, a n Let Δt be the ordinate of the intermediate control point during the deceleration phase on the acceleration curve. decelLet a be the x-coordinate of the intermediate control point during the deceleration phase on the acceleration curve. end Let a be the final acceleration. max v is the maximum acceleration, v2(1) is the velocity at the end of the previous stage before the deceleration stage, v end The final speed.

[0063] After obtaining the intermediate control point of the deceleration phase, the starting control point and the ending control point of the deceleration phase are acquired. Based on these three control points, an acceleration curve corresponding to the deceleration phase is generated. The starting control point represents the acceleration at the beginning of the deceleration phase; its ordinate can be the acceleration value when the vehicle enters the acceleration phase (which can be 0 or non-zero). The abscissa represents the time taken for the vehicle to enter the deceleration phase. In one specific implementation, the time for each driving phase is quantified, meaning the time for each phase is between [0,1], so the abscissa of the starting control point is 0. The ending control point represents the acceleration at the end of the deceleration phase; its value can be 0 or non-zero. After obtaining the coordinates of the starting, intermediate, and ending control points, a Bézier curve can be obtained using the Bézier formula, and this curve serves as the acceleration curve for the deceleration phase. In this embodiment, the intermediate control point can be the point between the starting control point and the intermediate control point, that is, the x-coordinate of the intermediate control point is located between the x-coordinate of the starting control point and the x-coordinate of the ending control point. In other embodiments, the intermediate control point may not be the point between the starting control point and the intermediate control point.

[0064] In another specific implementation, for a certain path segment, this path segment may include an acceleration phase and a deceleration phase. For example, a vehicle accelerates and then decelerates in this path segment. Then, the first objective equation set can be used to process the target acceleration, maximum acceleration, target speed, and maximum speed to obtain the intermediate control points of the Bézier curve. The starting control point and ending control point are then obtained, and based on these, the acceleration curve corresponding to the target driving phase is generated. Specifically, when the target driving phase is an acceleration phase, the first objective equation set is the first equation set, the target acceleration is the starting acceleration, and the target speed is the starting speed; when the target driving phase is a deceleration phase, the first objective equation set is the second equation set, the target acceleration is the ending acceleration, and the target speed is the ending speed. That is, the acceleration curves corresponding to the acceleration and deceleration phases are obtained separately, and then concatenated to obtain the acceleration curve of the path segment.

[0065] In other embodiments, a path segment may include a constant speed phase. Understandably, the path segment may include only a constant speed phase, or it may include both an acceleration and a constant speed phase, or both a deceleration and a constant speed phase, or it may include acceleration, constant speed, and deceleration phases. Taking a path segment including acceleration, constant speed, and deceleration phases as an example, the vehicle first accelerates on this path segment, then travels at a constant speed, and finally decelerates. In this case, the acceleration curves for the acceleration and constant speed phases can still be obtained using the methods described above, which will not be elaborated further here. The acceleration and deceleration phases are each considered as target driving phases. The acceleration curves corresponding to these target driving phases are integrated to obtain the distance curves for each phase. The driving time for each target driving phase is then substituted into these distance curves to obtain the distance traveled in each target driving phase. The difference between the parking path length and the distance traveled in each target driving phase is taken as the distance traveled in the constant-speed phase. Based on the distance traveled in the constant-speed phase and the speed in that phase, the driving time in the constant-speed phase is determined. The speed in the constant-speed phase is the speed at the end of the previous phase. Once the driving time in the constant-speed phase is determined, the acceleration curve for that phase can be obtained based on the acceleration and driving time. It is understandable that the acceleration in the constant-speed phase can be 0 or close to 0.

[0066] In the above implementation, for schemes where the path segment includes acceleration and / or deceleration phases, after generating the acceleration curves corresponding to the acceleration and / or deceleration phases, the acceleration curves can be verified. Specifically, the acceleration and deceleration phases are respectively taken as target driving phases, and the acceleration curves of the target driving phases are obtained. The derivative of the acceleration curves of the target driving phases is calculated to obtain the jerk curves of the target driving phases. The jerk curves represent the rate of change of acceleration. Based on the jerk curves, the maximum jerk is obtained, and it is determined whether the maximum jerk is greater than a preset jerk. If not, it is determined that the acceleration curves of the target driving phases obtained using the first set of objective equations meet the conditions.

[0067] If the maximum jerk is greater than the preset jerk, the second objective equation set is used to process the target acceleration, target speed, maximum driving speed, and preset jerk, and to obtain the intermediate control point of the Bézier curve again. Based on the starting control point, ending control point, and intermediate control point, the acceleration curve corresponding to the target driving stage is regenerated. When the target driving stage is the acceleration stage, the second objective equation set is the third equation set, the target acceleration is the starting acceleration, and the target speed is the starting speed. The third equation set is shown in Formula 4.

[0068]

[0069] In formula (4), a mThe ordinate of the intermediate control point redefined during the acceleration phase on the acceleration curve, Δt accel a is the x-coordinate of the intermediate control point redefined during the acceleration phase on the acceleration curve. start For the initial acceleration, jerk max For maximum jerk, v start v is the initial velocity. max This is the maximum driving speed.

[0070] When the target travel phase is a deceleration phase, the second set of objective equations becomes the fourth set of equations, where the target acceleration is the final acceleration and the target velocity is the final velocity. The fourth set of equations is shown in Formula 5.

[0071]

[0072] Among them, a n The ordinate of the intermediate control point redefined during the deceleration phase on the acceleration curve is Δt. aecel a is the x-coordinate of the intermediate control point redefined during the deceleration phase on the acceleration curve. end For the final acceleration, jerk max v is the maximum acceleration, v2(1) is the velocity at the end of the previous stage before the deceleration stage, v end The final speed.

[0073] The above method obtains the speed limit of at least one segment of the parking path and the speed influence factor of at least one segment. The speed influence factor includes curvature information or obstacle ratio factor, whereby the obstacle ratio factor characterizes the degree of influence of obstacles on the speed limit. Based on the speed influence factor of each segment, the speed limit of each segment is adjusted to obtain the maximum driving speed for each segment. At least based on the maximum driving speed of each segment, the target driving speed of the vehicle in each segment is determined. By adjusting the speed limit using the speed influence factor, the speed limit can be controlled within a reasonable speed range, improving the accuracy of the target driving speed and avoiding situations where the speed limit is too high, resulting in an excessively high target driving speed. Improving the accuracy of the target driving speed enhances parking safety and user comfort.

[0074] In the above embodiments, the first objective equation set can be a first equation set or a second equation set, and the second objective equation set can be a third equation set or a fourth equation set. Therefore, this application also provides embodiments for constructing each equation set.

[0075] Please refer to the following: Figure 2-4 , Figure 2 This is a flowchart illustrating an implementation method for constructing the first set of objective equations provided in this application. Figure 3This is a schematic diagram of one embodiment of the acceleration function during the acceleration phase provided in this application. Figure 4 This is a schematic diagram of one embodiment of the acceleration function during the deceleration phase provided in this application; the first set of equations can be determined using the following steps.

[0076] S21: Obtain the acceleration function corresponding to each driving stage; where the acceleration function is obtained based on the Bézier curve formula.

[0077] In one embodiment, for the acceleration phase, it is assumed that the acceleration phase is divided into a positive acceleration growth phase and a positive acceleration decrease phase, and let the time of the positive acceleration growth phase be Δt1, and the time of the positive acceleration decrease phase be Δt2, such that Δt1 = Δt2 = Δt accel Using the Bézier curve formula P i For the i-th control point, B i (s) is the i-th Bernstein basis function, where s is the time normalization factor (0 ≤ s ≤ 1). It includes four control points for both the positive acceleration growth phase and the positive acceleration decrease phase. The first control point P0 and the second control point P1 for the positive acceleration growth phase are both (O, a). start During the positive acceleration growth phase, both the third control point P2 and the fourth control point P3 are (Δt). accel a m Using four control points and the Bézier curve formula, the acceleration function a1(s) = a1(s) during the positive acceleration growth phase is obtained. start *(1-3s 2 +2s 3 )+a m *(3s 2 -2s 3 Furthermore, it was determined that the first control point P0 and the second control point P1 during the positive acceleration decreasing phase were both (Δt). accel a m During the positive acceleration decreasing phase, the third control point P2 and the fourth control point P3 are both (t, 0). Using the four control points and the Bézier curve formula, the acceleration function a2(s) = a2(t) during the positive acceleration decreasing phase is obtained. m *(1-3s 2 +2s 3 Finally, the acceleration function during the positive acceleration growth phase is concatenated with the acceleration function during the positive acceleration decrease phase to obtain the acceleration function during the acceleration phase. The acceleration function during the acceleration phase obtained in this embodiment is as follows: Figure 3 As shown, it can be understood that in other embodiments, other control points may be used to determine the acceleration function.

[0078] For the deceleration phase, we also assume that the deceleration phase is divided into a negative acceleration growth phase and a negative acceleration decrease phase, and let the time of the negative acceleration growth phase be Δt3 and the time of the negative acceleration decrease phase be Δt4, such that Δt3 = Δt4 = Δt decel The first and second control points P0 and P1 of the negative acceleration growth phase are both (0, 0), and the third and fourth control points P2 and P3 of the negative acceleration growth phase are both (Δt). decel， a n Using four control points and the Bézier curve formula, the acceleration function a3(s) = a3(s) during the negative acceleration growth phase is obtained. n *(3s 2 -2s 3 Furthermore, it was determined that the first control point P0 and the second control point P1 during the negative acceleration reduction phase were both (Δt). decel a n During the negative acceleration reduction phase, the third control point P2 and the fourth control point P3 are both (t, a). end Using four control points and the Bézier curve formula, the acceleration function a4(s) = a4(s) during the negative decreasing phase of acceleration is obtained. n *(1-3s 2 +2s 3 )+a end *(3s 2 -2s 3 Finally, the acceleration function of the negative acceleration growth phase is concatenated with the acceleration function of the negative acceleration decrease phase to obtain the acceleration function of the deceleration phase. The acceleration function of the deceleration phase obtained in this embodiment is as follows: Figure 4 As shown, it can be understood that in other embodiments, other control points may be used to determine the acceleration function.

[0079] The acceleration function for each stage of driving can be obtained using the above method.

[0080] S22: Integrate each acceleration function to obtain the velocity function for each driving stage.

[0081] In one implementation, the velocity function can characterize the relationship between velocity, endpoint acceleration, acceleration at intermediate control points, and time. For example, the acceleration function a1(s) = a1(s) during the positive growth phase of acceleration. start *(1-3s 2 +2s 3 )+a m *(3s 2 -2s 3 Integrate to obtain The acceleration function a2(s) = a during the acceleration phase when the acceleration is decreasing. m *(1-3s 2 +2s 3 Integrate to obtain Here, v1(1) represents the vehicle's velocity at the end of the positive acceleration growth phase; for the negative acceleration growth phase of the deceleration phase, the acceleration function a3(s) = a n *(3s 2 -2S 3 Integrate to obtain Here, v2(1) represents the velocity at the end of the acceleration phase, meaning that the phase preceding the deceleration phase is the acceleration phase. In other implementations, if the phase preceding the deceleration phase is not the acceleration phase, v2(1) can be replaced with the velocity at the beginning of the deceleration phase. The acceleration function a4(s) = a... n *(1-3s 2 +2s 3 )+a end *(3s 2 -2s 3 Integrate to obtain

[0082] S23: Based on the speed function, obtain the expression for the vehicle's speed at the end of the driving phase.

[0083] Since the acceleration phase includes a phase of positive acceleration increase and a phase of positive acceleration decrease, and because time has been quantified as mentioned above, the speed obtained when time s equals 1 during the positive acceleration increase and decrease phases is the speed at the end of the corresponding phase. Therefore, the expression for the vehicle's speed at the end of the acceleration phase can be derived. The expression for the vehicle's speed at the end of the deceleration phase.

[0084] S24: Determine the first set of objective equations based on the expression for velocity.

[0085] In one implementation, when the endpoint acceleration is the same as the starting acceleration, the expression for the velocity is set to be equal to the maximum speed, i.e., let... The acceleration a corresponding to the intermediate control point m The maximum acceleration a max To obtain the first set of equations; when the acceleration at the endpoint is the acceleration at the destination, let the expression for the velocity be equal to the velocity at the destination, that is, let The acceleration a corresponding to the intermediate control point n For maximum acceleration -a maxThis leads to the second system of equations.

[0086] In other implementations, when the endpoint acceleration is the same as the starting acceleration, the expression for the velocity is set to equal the maximum speed, i.e., let... The acceleration a corresponding to the intermediate control point m For maximum jerk max To obtain the third-party program group; when the endpoint acceleration is the endpoint acceleration, let the expression for velocity be equal to the endpoint velocity, that is, let The acceleration a corresponding to the intermediate control point n For maximum jerk max This leads to the fourth set of equations. The maximum jerk can be obtained from the acceleration curve, and the slope of the acceleration curve characterizes the jerk.

[0087] In one embodiment, if the driving path during the acceleration and deceleration phases is greater than the total length of the parking path, the coordinates of intermediate control points during the acceleration and deceleration phases can be constrained using the total length of the parking path. Specifically, the distance function can be obtained by integrating the acceleration function; for example, the acceleration function a1(s) = a during the positive acceleration growth phase of the acceleration phase. start *(1-3s 2 +2s 3 )+a m *(3s 2 -2s 3 Integrate to obtain The acceleration function a2(s) = a during the acceleration phase when the acceleration is decreasing. m *(1-3s 2 +2s 3 Integrate to obtain Here, l1(1) represents the distance traveled by the vehicle at the end of the positive acceleration growth phase; for the negative acceleration growth phase of the deceleration phase, the acceleration function a3(s) = a n *(3s 2 -2s 3 Integrate to obtain Here, v2(1) represents the velocity at the end of the acceleration phase; the acceleration function a4(s) = a during the deceleration phase is negatively decreasing. n *(1-3s 2 +2s 3 )+a end *(3s 2 -2s 3 Integrate to obtain Here, l3(1) represents the distance traveled by the vehicle at the end of the negative acceleration growth phase. Therefore, the expression for the distance traveled by the vehicle at the end of the acceleration phase can be derived. The expression for the distance traveled by the vehicle at the end of the deceleration phase can be found. Let the sum of l2(1) and l4(1) equal the total length L of the parking path, that is... The following formula can be obtained, which can be used to determine the new intermediate control points during the acceleration and deceleration phases.

[0088]

[0089] In this embodiment, by using at least one of the maximum driving speed, maximum acceleration, maximum jerk and the total length of the parking path to constrain the intermediate control point of the deceleration phase and / or acceleration phase, the peak value of the speed curve on the path segment can be appropriately reduced without changing the time required for the acceleration and deceleration phases. Furthermore, the acceleration and jerk of the speed curve after reducing the peak speed are also less than the maximum acceleration and jerk values.

[0090] To illustrate the beneficial effects of the parking speed planning method provided in this application, an example is given below: the maximum driving speed is set to 1 m / s, and the maximum acceleration is 0.5 m / s². 2 The maximum jerk is 0.5 m / s². 3 The obstacle scale factor is 0.3, and the curvature scale factor is 0.9. Assuming the parking path consists of a collision-prone segment and a collision-free segment, the acceleration, velocity, and jerk curves for these two segments are obtained using the parking speed planning method described above. Please refer to [link to relevant documentation]. Figure 5-7 , Figure 5 This is a schematic diagram of one embodiment of the acceleration curve of the collision-free path segment provided in this application. Figure 6 This is a schematic diagram of one embodiment of the velocity curve of the collision-free path segment provided in this application. Figure 7 This is a schematic diagram of one embodiment of the acceleration curve for a collision-free path segment provided in this application. Figure 5 It can be seen that the maximum actual acceleration of the vehicle on the collision-free path section is 0.5 m / s². 2 , equal to the set maximum acceleration, by Figure 6 It can be seen that the maximum actual driving speed of the vehicle on the collision-free path section is greater than 0.9 m / s and less than 1 m / s, meaning that the actual driving speed of the vehicle on the collision-free path section is less than the set maximum driving speed. Figure 7 It can be seen that the maximum actual acceleration of the vehicle on the collision-free path section is less than 0.4 m / s². 3Therefore, the actual acceleration value is less than the set maximum acceleration. Thus, by using the above parking speed planning method, the speed, acceleration, and jerk of the barrier-free path segment all meet the set constraints.

[0091] Please see Figure 8-10 , Figure 8 This is a schematic diagram of one embodiment of the acceleration curve of the collision path segment provided in this application. Figure 9 This is a schematic diagram of one embodiment of the velocity curve of a collision path segment provided in this application. Figure 10 This is a schematic diagram of one embodiment of the acceleration curve for a collision path segment provided in this application. Figure 8 It can be seen that the maximum actual acceleration of the vehicle in the collision-prone section is less than 0.5 m / s². 2 ,Depend on Figure 9 It can be seen that the maximum actual driving speed of the vehicle in the collision-prone section is greater than 0.9 m / s and less than 1 m / s, meaning that the actual driving speed of the vehicle in the collision-prone section is less than the set maximum driving speed. Figure 10 It can be seen that the maximum actual acceleration of the vehicle on the collision path segment is less than 0.5 m / s². 3 That is, the actual acceleration value is less than the set maximum acceleration. Therefore, by using the above parking speed planning method, the speed, acceleration and jerk of the obstacle path segment all meet the set constraints.

[0092] Please see Figure 11 , Figure 11 This is a schematic diagram of one embodiment of the electronic device provided in this application.

[0093] The electronic device 110 includes a memory 111 and a processor 112 coupled to each other. The memory 111 stores program instructions, and the processor 112 executes the program instructions to implement the steps in any of the above method embodiments. Specifically, the electronic device 110 may include, but is not limited to, desktop computers, laptops, servers, mobile phones, tablets, etc., and is not limited thereto.

[0094] Specifically, processor 112 controls itself and memory 111 to implement the steps in any of the above method embodiments. Processor 112 may also be referred to as a CPU (Central Processing Unit). Processor 112 may be an integrated circuit chip with signal processing capabilities. Processor 112 may also be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component. A general-purpose processor may be a microprocessor or any conventional processor. Furthermore, processor 112 may be implemented using integrated circuit chips.

[0095] Please see Figure 12 , Figure 12 This is a schematic diagram of an embodiment of the computer-readable storage medium provided in this application. The computer-readable storage medium 120 stores program instructions 121, which, when executed by a processor, are used to implement the steps in any of the above method embodiments.

[0096] The computer-readable storage medium 120 can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or a medium that can store computer programs. Alternatively, it can be a server that stores the computer program, which can send the stored computer program to other devices for execution or can also run the stored computer program itself.

[0097] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, with clear signs / information informing users of the personal information processing rules, authorization is obtained from the individual through pop-up information or by asking the individual to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

[0098] The above are merely embodiments of this application and do not limit the scope of this patent application. Any equivalent structural or procedural changes made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of this application.

Claims

1. A parking speed planning method, characterized in that, include: Based on the location of obstacles, the parking path is divided into collision-prone and non-collision-prone segments. Obtain the speed limit of at least one segment of the parking path and the speed influence factor of the at least one segment, wherein the speed influence factor includes curvature information or obstacle scale factor, and the obstacle scale factor characterizes the degree of influence of obstacles on the speed limit. Based on the speed influence factor of each path segment, the speed limit of each path segment is adjusted to obtain the maximum driving speed of each path segment; The target speed of the vehicle in each of the aforementioned path segments is determined based at least on the maximum speed of the vehicle in each of the aforementioned path segments. The step of adjusting the speed limit of each path segment based on the speed influence factor of each path segment to obtain the maximum driving speed of each path segment includes: For the collision-prone path segment, the speed limit of the collision-prone path segment is weighted based on the obstacle ratio factor to obtain the maximum driving speed of the collision-prone path segment. For the collision-free path segment, the curvature scale factor, average curvature, and preset curvature threshold of the collision-free path segment are used to determine the curvature influence parameter on the speed limit; the speed limit of the collision-free path segment is weighted using the influence parameter to obtain the maximum driving speed of the collision-free path segment.

2. The method according to claim 1, characterized in that, The method for determining the influence parameters of curvature on the speed limit based on the curvature scaling factor, average curvature, and preset curvature threshold of the collision-free path segment includes: Based on the curvature scaling factor and the first value, the first parameter is obtained; The first parameter is weighted based on the ratio of the average curvature to the preset curvature threshold to obtain the second parameter; The difference between the second value and the second parameter is used as the third parameter; The larger of the curvature scaling factor and the third parameter is selected as the influence parameter.

3. The method according to claim 1, characterized in that, Based on the location of obstacles, the parking path is divided into collision-prone and non-collision-prone segments, including: Obtain each path point on the parking path; wherein each path point represents the position of the vehicle on the parking path at different times; Based on the distance between each path point and the obstacle, determine whether each path point is a collision point; Cluster the collision points to generate the collision path segments; The path segments in the parking path other than the collision-prone path segments are designated as the collision-free path segments.

4. The method according to claim 3, characterized in that, There are at least two collision path segments; The step of clustering the collision points to generate the collision path segments includes: Determine whether the number of path points between two adjacent collision points is less than a preset threshold; In response to the fact that the number of path points between two adjacent collision points is less than a preset threshold, it is determined that the two adjacent collision points belong to the same collision path segment; In response to the fact that the number of path points between two adjacent collision points is not less than a preset threshold, it is determined that the two adjacent collision points belong to different collision path segments. The collision points belonging to the same collision path segment are spliced ​​together to generate the collision path segment.

5. The method according to claim 3, characterized in that, After clustering the collision points to generate the collision path segments, the method further includes: Determine whether the length of the collision-prone path segment is less than a preset length; in response to the length being less than the preset length, treat the collision-prone path segment as a collision-free path segment; And / or, determine whether the collision-prone path segment is the starting or ending path segment of the parking path; in response to the collision-prone path segment being the starting or ending path segment of the parking path, treat the collision-prone path segment as a collision-free path segment.

6. The method according to claim 5, characterized in that, The determination of whether the collision-affected path segment is the starting or ending path segment of the parking path includes: In response to the fact that the last collision point in the collision path segment belongs to the third number of path points in the parking path, the collision path segment is determined to be the starting path segment of the parking path. Alternatively, in response to the fact that the first collision point in the collision path segment belongs to the last fourth number of path points of the parking path, the collision path segment is determined to be the termination path segment of the parking path.

7. The method according to claim 1, characterized in that, The method further includes: Obtain the endpoint velocity, endpoint acceleration, and maximum acceleration of at least one of the path segments; Determining the target driving speed of the vehicle in each of the path segments, based at least on the maximum driving speed of each of the path segments, includes: Based on the endpoint speed, maximum driving speed, endpoint acceleration, and maximum acceleration of the path segment, an acceleration curve for the path segment is obtained using a Bézier curve; wherein, the acceleration curve characterizes the relationship between the vehicle's acceleration and time in the path segment. Based on the acceleration curve, the speed curve of the path segment is obtained; wherein, the speed curve is used to determine the target driving speed of the vehicle at each time point in the path segment.

8. The method according to claim 7, characterized in that, The vehicle includes at least one driving phase in each of the aforementioned path segments, and the driving phase includes an acceleration phase, a constant speed phase, and a deceleration phase. Based on the endpoint speed, maximum driving speed, endpoint acceleration, and maximum acceleration of each path segment, the acceleration curve of each path segment is obtained using Bézier curves, including: For each of the path segments, an acceleration curve corresponding to each of the driving stages is generated using Bézier curves based on the endpoint speed, the maximum driving speed, the endpoint acceleration, and the maximum acceleration of the path segment. The acceleration curves corresponding to each of the aforementioned driving stages are spliced ​​together to obtain the acceleration curve of the path segment.

9. The method according to claim 8, characterized in that, The vehicle's travel phase in the path segment includes an acceleration phase, the endpoint acceleration includes the starting acceleration of the path segment, and the endpoint speed includes the starting speed; and / or, the vehicle's travel phase in the path segment includes a deceleration phase, the endpoint acceleration includes the ending acceleration of the path segment, and the endpoint speed includes the ending speed. The step of generating acceleration curves corresponding to each driving stage using Bézier curves based on the endpoint speed, the maximum driving speed, the endpoint acceleration, and the maximum acceleration includes: Using the first set of objective equations, the target acceleration, the maximum acceleration, the target velocity, and the maximum driving speed are processed to obtain the intermediate control point of the Bézier curve; Obtain the starting control point and the ending control point, and generate the acceleration curve corresponding to the target driving stage based on the starting control point, the ending control point and the intermediate control point; Wherein, when the target driving stage is an acceleration stage, the first target equation set is the first equation set, the target acceleration is the starting acceleration, and the target speed is the starting speed; when the target driving stage is a deceleration stage, the first target equation set is the second equation set, the target acceleration is the ending acceleration, and the target speed is the ending speed.

10. The method according to claim 9, characterized in that, The method further includes the following steps for constructing the first set of objective equations: Obtain the acceleration function corresponding to each driving stage; wherein, the acceleration function is obtained based on the Bézier curve formula; Integrating each of the acceleration functions yields a velocity function; wherein the velocity function characterizes the relationship between velocity, endpoint acceleration, acceleration at intermediate control points, and time. Based on the speed function, obtain an expression for the speed of the vehicle at the end time of the driving phase; Based on the expression for the velocity, the first set of target equations is determined; wherein, when the endpoint acceleration is the starting acceleration, the expression for the velocity is set to be equal to the maximum driving speed, and the acceleration corresponding to the intermediate control point is set to be the maximum acceleration, so as to obtain the first set of equations; when the endpoint acceleration is the ending acceleration, the expression for the velocity is set to be equal to the ending velocity, and the acceleration corresponding to the intermediate control point is set to be the maximum acceleration, so as to obtain the second set of equations.

11. The method according to claim 9, characterized in that, After generating the acceleration curve corresponding to the target driving stage based on the starting control point, the ending control point, and the intermediate control point, the method further includes: Based on the acceleration curve corresponding to the target driving stage, determine whether the maximum jerk in the acceleration curve is greater than the preset jerk; In response to the maximum jerk being greater than the preset jerk, the target acceleration, target speed, maximum driving speed, and preset jerk are processed using the second objective equation set to obtain the intermediate control point of the Bézier curve again. Based on the starting control point, the ending control point, and the intermediate control point, the acceleration curve corresponding to the target driving stage is regenerated. Wherein, when the target driving stage is the acceleration stage, the second target equation set is the third equation set, the target acceleration is the starting acceleration, and the target speed is the starting speed; when the target driving stage is the deceleration stage, the second target equation set is the fourth equation set, the target acceleration is the ending acceleration, and the target speed is the ending speed.

12. The method according to claim 11, characterized in that, The method further includes the following steps for constructing a second set of objective equations: Obtain the acceleration function corresponding to each driving stage; wherein, the acceleration function is obtained based on the Bézier curve formula; Integrating each of the acceleration functions yields a velocity function; wherein the velocity function characterizes the relationship between velocity, endpoint acceleration, acceleration at intermediate control points, and time. Based on the speed function, obtain an expression for the vehicle's speed at the end of the driving phase; Based on the expression for the speed, the second set of objective equations is determined; wherein, when the endpoint acceleration is the starting acceleration, the expression for the speed is set to be equal to the maximum driving speed, and the acceleration corresponding to the intermediate control point is set to the preset jerk, to obtain the third set of equations; when the endpoint acceleration is the ending acceleration, the expression for the speed is set to be equal to the ending speed, and the acceleration corresponding to the intermediate control point is set to the preset jerk, to obtain the fourth set of equations.

13. The method according to claim 9, characterized in that, The vehicle's travel phase in the path segment also includes a constant speed phase. After generating the acceleration curve corresponding to the target driving stage based on the starting control point, the ending control point, and the intermediate control point, the method further includes: Based on the acceleration curve corresponding to the target driving stage, determine the distance traveled in the target driving stage; The difference between the length of the parking path and the distance traveled in the target driving phase is taken as the distance traveled in the constant speed phase. Based on the distance traveled during the constant speed phase and the speed during the constant speed phase, the travel time of the constant speed phase is determined; wherein, the travel speed during the constant speed phase is the speed at the end of the previous constant speed phase. Based on the acceleration during the constant speed phase and the travel time during the constant speed phase, the acceleration curve for the constant speed phase is obtained.

14. The method according to claim 7, characterized in that, The path segment includes a collision path segment, and the endpoint velocity includes the starting velocity and the ending velocity; The step of obtaining the endpoint speed of at least one of the path segments includes: For the collision path segment, determine whether the target collision point of the collision path segment is the target location point in the parking path that corresponds to the target collision point; In response to the fact that the target collision point is not a target location point in the parking path corresponding to the target collision point, the speed of the target location point corresponding to the target collision point is set to the maximum driving speed; In response to the fact that the target collision point is a target location point in the parking path corresponding to the target collision point, the speed of the target location point corresponding to the target collision point is set to a preset speed; Wherein, the target collision point is at least one of the first collision point and the last collision point, the target position point corresponding to the first collision point is the starting point, the velocity of the target position point corresponding to the first collision point is the starting velocity, the target position point corresponding to the last collision point is the ending point, and the velocity of the target position point corresponding to the last collision point is the ending velocity.

15. An electronic device, characterized in that, Including interconnected memory and processor, The memory stores program instructions; The processor is configured to execute program instructions stored in the memory to implement the method according to any one of claims 1-14.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program instructions that can be executed to implement the method as described in any one of claims 1-4.

Images