Memory parking path generation method and device, vehicle and storage medium

Abstract

The application relates to a memory parking path generation method and device, a vehicle and a storage medium, wherein the method comprises the following steps: in a parking mode, an initial parking path for parking into a current destination is generated, two-side lane line information of the initial parking path is perceived, and a point cloud sequence of the two-side lane lines is generated according to the two-side lane line information; redundant points in the point cloud sequence of the two-side lane lines are screened out, and the remaining points of the point cloud sequence are equidistantly screened to obtain a smooth point cloud sequence of the two-side lane lines; and a final parking path of the current destination is generated based on the smooth point cloud sequence of the two-side lane lines, so as to control the vehicle to park out of the current destination or park into the current destination again according to the final parking path. According to the embodiment of the application, the final parking path can be generated through screening and smoothing processing of the point cloud sequence of the two-side lane lines of the initial parking path, and the path can be adjusted automatically when the obstacle on the path changes, so that the parking-in and parking-out efficiency of the vehicle is improved, and the use experience of the user is improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a method, apparatus, vehicle, and storage medium for generating a memory parking path. Background Technology

[0002] Autonomous driving is a crucial part of vehicle intelligence. It refers to a vehicle's ability to autonomously perceive its surroundings, plan its own path, and control itself without human intervention, enabling it to complete tasks assigned by the user. Examples include driving autonomously from a parking lot entrance to a parking space or from a parking space to a designated destination. Memory parking is part of autonomous driving functionality; this feature can receive user commands and enable autonomous valet parking and pick-up services along a fixed route within a parking lot.

[0003] In related technologies, when a user plans to use the memory parking function, the parking entry and exit routes of the user's past parking can be recorded. The user needs to drive along a certain route to a certain target point in advance. When the vehicle arrives at this environment again, the vehicle can be controlled to automatically park or exit based on the historical parking entry and exit routes.

[0004] However, in related technologies, when a vehicle first enters or exits a parking space, due to dynamic situations on the route, such as temporary road construction on the right or vehicles blocking the way ahead, the vehicle will perform actions such as maneuvering around obstacles or reversing. However, when the environment returns to normal, the vehicle will still perform unnecessary actions such as maneuvering around obstacles and reversing again. This technology has poor versatility, low parking efficiency, and affects the user experience, and needs to be improved. Summary of the Invention

[0005] This application provides a method, apparatus, vehicle, and storage medium for generating parking paths, in order to solve the technical problem in related technologies that only remembering and recalling historical parking and exit paths cannot be applied to dynamically changing paths, thus reducing the efficiency of vehicle parking and exiting and affecting the user experience.

[0006] The first aspect of this application provides a method for generating a memory parking path, comprising the following steps: in a parking mode, generating an initial parking path to the current destination; sensing lane line information on both sides of the initial parking path; generating a point cloud sequence of the lane lines on both sides based on the lane line information; filtering out redundant points in the point cloud sequence of the lane lines on both sides; and performing equidistant filtering on the remaining points in the point cloud sequence to obtain a smooth point cloud sequence of the lane lines on both sides; and generating a final parking path to the current destination based on the smooth point cloud sequence of the lane lines on both sides, so as to control the vehicle to park out of the current destination or park back into the current destination according to the final parking path.

[0007] Based on the above technical means, the embodiments of this application can process the lane lines on both sides of the initial parking path separately, filter out redundant points in the point cloud sequence of the lane lines on both sides, and perform equidistant processing on the remaining points to obtain a smooth point cloud sequence of the lane lines on both sides, thereby generating the final parking path of the current destination. This facilitates the vehicle to park or exit based on the final parking path, and can automatically adjust the path when obstacles on the path change, thereby improving the parking efficiency of the vehicle and enhancing the user experience.

[0008] Optionally, in one embodiment of this application, before filtering out redundant points in the point cloud sequence of the two lane lines, the method further includes: selecting any window on the initial parking path, wherein the window contains at least one initial path point; determining a plane equation based on the position information of the at least one path point in the window; selecting any initial path point in the window and substituting the any initial path point into the plane equation; dividing the at least one initial path point in the window into the two lane lines based on the calculation result of the plane equation, until all initial path points in the window are divided, thereby determining the path points of each lane line.

[0009] Based on the above technical means, the embodiments of this application can divide all the acquired initial path points by plane equations to determine which side of the lane line each initial path point belongs to, thereby facilitating subsequent point cloud processing for each side of the lane line.

[0010] Optionally, in one embodiment of this application, the step of filtering redundant points in the point cloud sequence of the lane lines on both sides includes: selecting any consecutive multiple initial path points in the point cloud sequence of each lane line; connecting the consecutive multiple initial path points to generate corresponding path polylines, and measuring all angles of the path polylines; determining whether the initial path points meet preset filtering conditions based on the angles, and deleting the initial path points when the preset filtering conditions are met, until the filtering of the point cloud sequence of each lane line is completed, obtaining all intermediate path points.

[0011] Based on the above technical means, the embodiments of this application can filter out redundant points in the point cloud sequence of lane lines on both sides and transform the obstacle avoidance path into a general path.

[0012] Optionally, in one embodiment of this application, the step of equidistantly filtering the remaining points of the point cloud sequence to obtain the smooth point cloud sequence of the lane lines on both sides includes: selecting the starting point of the point cloud sequence of each lane line, selecting the next intermediate path point at preset distances based on the starting point, until the selection of the intermediate path points of each lane line is completed, thereby obtaining all the smooth path points.

[0013] Based on the above technical means, the embodiments of this application can perform equidistant filtering on the remaining points to obtain a smooth point cloud sequence of lane lines on both sides, so as to generate the final parking path.

[0014] Optionally, in one embodiment of this application, generating the final parking path to the current destination based on the smooth point cloud sequence of the lane lines on both sides includes: calculating the shortest distance between two corresponding smooth path points in the smooth point cloud sequence of the lane lines on both sides in sequence; calculating the final path point based on the shortest distance using a preset point selection strategy; and concatenating the final path points to generate the final parking path.

[0015] Based on the above-mentioned technical means, the embodiments of this application can calculate and generate the final parking path, and automatically adjust the path for dynamically changing paths, thereby improving the efficiency of vehicle parking and exiting, and enhancing the user experience.

[0016] A second aspect of this application provides a device for generating a parking path, comprising: a generation module, configured to generate an initial parking path to the current destination in a parking mode, sense lane line information on both sides of the initial parking path, and generate a point cloud sequence of the lane lines on both sides based on the lane line information; a processing module, configured to filter out redundant points in the point cloud sequence of the lane lines on both sides, and perform equidistant filtering on the remaining points in the point cloud sequence to obtain a smooth point cloud sequence of the lane lines on both sides; and a control module, configured to generate a final parking path to the current destination based on the smooth point cloud sequence of the lane lines on both sides, so as to control the vehicle to park out of the current destination or park back into the current destination according to the final parking path.

[0017] Optionally, in one embodiment of this application, it further includes: a selection module, configured to select any window on the initial parking path, wherein the window contains at least one initial path point; a determination module, configured to determine a plane equation based on the position information of the at least one path point in the window; and a calculation module, configured to select any initial path point in the window, substitute the any initial path point into the plane equation, and divide the at least one initial path point in the window into the lane lines on both sides based on the calculation result of the plane equation, until all initial path points in the window are divided, thereby determining the path points of each lane line.

[0018] Optionally, in one embodiment of this application, the processing module includes: a first selection unit, configured to select any consecutive multiple initial path points in the point cloud sequence of each lane line; a measurement unit, configured to connect the consecutive multiple initial path points to generate corresponding path polylines, and measure all angles of the path polylines; and a judgment unit, configured to judge whether the initial path points meet preset screening conditions based on the angles, and delete the initial path points when the preset screening conditions are met, until the screening of the point cloud sequence of each lane line is completed, and all intermediate path points are obtained.

[0019] Optionally, in one embodiment of this application, the processing module includes: a second selection unit, used to select the starting point of the point cloud sequence of each lane line, and select the next intermediate path point at preset distances based on the starting point, until the selection of the intermediate path points of each lane line is completed, thereby obtaining all smooth path points.

[0020] Optionally, in one embodiment of this application, the control module includes: a first calculation unit, configured to calculate, based on the smooth point cloud sequence of the lane lines on both sides, the shortest distance between two corresponding smooth path points in the smooth point cloud sequence of the lane lines on both sides; a second calculation unit, configured to calculate the final path point based on the shortest distance using a preset point selection strategy; and a generation unit, configured to concatenate the final path points to generate the final parking path.

[0021] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the memory parking path generation method as described in the above embodiments.

[0022] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for generating a memory parking path.

[0023] The beneficial effects of the embodiments of this application are as follows:

[0024] (1) The embodiments of this application can process the lane lines on both sides of the initial parking path separately, filter out redundant points in the point cloud sequence of the lane lines on both sides, and perform equidistant processing on the remaining points to obtain a smooth point cloud sequence of the lane lines on both sides, thereby optimizing the obstacle avoidance path into a general path.

[0025] (2) The embodiments of this application can generate the final parking path of the current destination based on the smooth point cloud sequence, which makes it easier for vehicles to park or exit based on the final parking path. When obstacles on the path change, the path can be adjusted automatically, thereby improving the parking efficiency of vehicles and improving the user experience.

[0026] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0027] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0028] Figure 1 This is a flowchart of a method for generating a memory parking path according to an embodiment of this application;

[0029] Figure 2 This is a schematic diagram of the initial parking path of a method for generating a memory parking path according to an embodiment of this application;

[0030] Figure 3 This is a schematic diagram of lane line point cloud filtering in a method for generating a memory parking path according to an embodiment of this application;

[0031] Figure 4 This is a schematic diagram of lane line point cloud smoothing for a method of generating a memory parking path according to an embodiment of this application;

[0032] Figure 5 This is a schematic diagram comparing the initial parking path and the final parking path in a memory parking path generation method according to an embodiment of this application;

[0033] Figure 6 This is a flowchart of a method for generating a memory parking path according to an embodiment of this application;

[0034] Figure 7 This is a schematic diagram of a memory parking path generation device provided according to an embodiment of this application;

[0035] Figure 8 This is a structural schematic diagram of a vehicle provided according to an embodiment of this application.

[0036] Among them, 10 is a device for generating parking paths; 100 is a generation module; 200 is a processing module; and 300 is a control module. Detailed Implementation

[0037] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0038] The following description, with reference to the accompanying drawings, outlines a method, apparatus, vehicle, and storage medium for generating a memorized parking path according to embodiments of this application. Addressing the technical problem mentioned in the background section that simply memorizing and recalling historical parking entry and exit paths is unsuitable for dynamically changing paths, leading to reduced parking entry and exit efficiency and impacting user experience, this application provides a method for generating a memorized parking path. This method processes the lane lines on both sides of the initial parking path separately, filtering out redundant points in the point cloud sequence of the lane lines and performing equidistant processing on the remaining points to obtain a smooth point cloud sequence of the lane lines. This generates the final parking path for the current destination, facilitating vehicle parking or exiting based on the final parking path. The method can automatically adjust the path when obstacles on the path change, thereby improving parking entry and exit efficiency and enhancing user experience. This solves the technical problem in the related art where simply memorizing and recalling historical parking entry and exit paths is unsuitable for dynamically changing paths, resulting in reduced parking entry and exit efficiency and impacting user experience.

[0039] Specifically, Figure 1 This is a flowchart illustrating a method for generating a memory parking path, as provided in an embodiment of this application.

[0040] like Figure 1 As shown, the method for generating the memory parking path includes the following steps:

[0041] In step S101, in parking mode, an initial parking path is generated to park at the current destination, the lane line information on both sides of the initial parking path is sensed, and a point cloud sequence of the lane lines on both sides is generated based on the lane line information on both sides.

[0042] In actual implementation, this embodiment can first determine whether the vehicle is in parking mode. When the vehicle is not in parking mode, the vehicle's driving path is not recorded. When the vehicle is in parking mode, this embodiment can record the initial parking path when first parking at the current destination, and based on sensing devices such as radar, cameras, and other sensors, perceive the lane line information on both sides of the initial parking path, and perform point cloud mapping based on the perceived lane line information on both sides to generate a point cloud sequence of lane lines on both sides.

[0043] In step S102, redundant points in the point cloud sequence of the lane lines on both sides are filtered out, and the remaining points in the point cloud sequence are filtered at equal intervals to obtain a smooth point cloud sequence of the lane lines on both sides.

[0044] As one possible implementation, embodiments of this application can filter out redundant points in the allowed column of lane line points on both sides and perform equidistant processing on the remaining points to obtain a smooth point cloud sequence, optimize the obstacle avoidance path into a general path, and eliminate the influence of obstacles in the path on the parking path.

[0045] Optionally, in one embodiment of this application, before filtering out redundant points in the point cloud sequence of the lane lines on both sides, the method further includes: selecting any window on the initial parking path, wherein the window contains at least one initial path point; determining a plane equation based on the position information of at least one path point in the window; selecting any initial path point in the window and substituting the arbitrary initial path point into the plane equation; dividing at least one initial path point in the window into the lane lines on both sides based on the calculation result of the plane equation, until all initial path points in the window are divided, thereby determining the path points of each lane line.

[0046] In some embodiments, the present application may distinguish the point clouds of the two lane lines before filtering out redundant points in the point cloud sequence of the two lane lines.

[0047] Specifically, in this embodiment, a window can be pre-selected on the initial parking path, and the window includes at least one initial path point. This embodiment can determine a plane equation based on the position information of multiple initial path points in the currently selected window, such as Mx+Ny+Lz+K=0, where M, N, L, and K represent parameters, indicating a plane in the three-dimensional coordinate system where these points are located. This embodiment can arbitrarily substitute any point in the current window into the plane equation, placing points where Mx+Ny+Lz+K<0 in a left lane line point cloud sequence, and points where Mx+Ny+Lz+K>0 in a right lane line point cloud sequence. Windows on the initial parking path are selected sequentially to distinguish the point clouds of the lane lines on both sides.

[0048] Furthermore, this embodiment can pre-select a window on the initial parking path, and the window includes at least one initial path point, defining the current path point as the starting point of the initial parking path. This embodiment can determine a plane equation based on the position information of multiple initial path points in the currently selected window, such as Mx+Ny+Lz+K=0, where M, N, L, and K represent parameters, indicating a plane in the three-dimensional coordinate system where these points are located. This embodiment can sequentially calculate the points on the path closest to the starting point on the initial parking path, starting from the starting point. If this point is within the current window, the position information of the selected lane line points is substituted into the plane equation. Points with calculated Mx+Ny+Lz+K<0 are placed in a left lane line point cloud sequence, and points with calculated Mx+Ny+Lz+K>0 are placed in a right lane line point cloud sequence. The above steps are repeated by sequentially selecting windows on the initial parking path until all initial path points are divided, and the lane lines on both sides are denoted as p_left_lane and p_right_lane, respectively.

[0049] Optionally, in one embodiment of this application, filtering out redundant points in the point cloud sequence of lane lines on both sides includes: selecting any consecutive multiple initial path points in the point cloud sequence of each lane line; connecting the consecutive multiple initial path points to generate corresponding path polylines, and measuring all angles of the path polylines; determining whether the initial path points meet the preset filtering conditions based on the angles, and deleting the initial path points when the preset filtering conditions are met, until the filtering of the point cloud sequence of each lane line is completed, and all intermediate path points are obtained.

[0050] For example, such as Figure 2 As shown in the embodiment of this application, five points ABCDE, including the current lane line point, can be selected from the lane line point cloud sequence on one side. The angles between the four line segments formed by these five points and the distances between the five points and their nearest initial path points can be calculated.

[0051] like Figure 3 As shown, if ∠ABC is greater than 120°, ∠BCD is less than 120°, and ∠CDE is greater than 120°, and the distances from points C, D, and E to the initial path point gradually increase, then points D and E are discarded at this point.

[0052] Take the points after DE in this lane line point cloud sequence, calculate ∠ABC and angle ∠BCD until the difference between the two is within 10°. At this point, the embodiment of this application can obtain point F. This filtering process filters out all lane line point cloud points after C and before F.

[0053] Take F as the current lane line point, repeat the above steps, and finally obtain the intermediate path points after filtering.

[0054] Repeat the above steps for the other lane line to obtain the middle path point of the other lane line.

[0055] Optionally, in one embodiment of this application, the remaining points of the point cloud sequence are filtered at equal intervals to obtain a smooth point cloud sequence of lane lines on both sides, including: selecting the starting point of the point cloud sequence of each lane line, selecting the next intermediate path point at preset intervals based on the starting point, until the selection of intermediate path points of each lane line is completed, and obtaining all smooth path points.

[0056] In actual implementation, after the filtering is completed, for the lane line point cloud sequence on one side, the current middle path point is selected as the first point, denoted as point A, and the next point is selected as the second point, denoted as point B. Points at a certain distance from A along the AB direction are calculated: if this point is inside the AB line segment, then this point is set as A, and this point is stored in a new lane line point cloud sequence, and then points at a certain distance from A along the AB direction are calculated; if this point is outside the AB line segment, then the next point after B in the initial lane line point cloud sequence is selected as B, and points at a certain distance from A along the AB direction are calculated.

[0057] Based on the above steps, the embodiments of this application can obtain a complete smooth point cloud sequence, in which the spacing between each point is the same and the direction is the same as the initial lane line.

[0058] By performing the same actions on the original lane line sequence on the other side, the embodiments of this application can obtain a smoothed lane line sequence on the other side.

[0059] Thus, as Figure 4 As shown, in this embodiment of the application, a point cloud sequence of equally spaced left and right lane lines can be obtained, denoted as p_left_lane_smooth and p_right_lane_smooth.

[0060] In step S103, a final parking path for the current destination is generated based on a smooth point cloud sequence of lane lines on both sides, so as to control the vehicle to park out of the current destination or park back into the current destination according to the final parking path.

[0061] As one possible implementation, embodiments of this application can generate and memorize the final parking path of the current destination based on the smooth point cloud sequence of the lane lines on both sides. When the vehicle leaves the current destination or parks back into the current destination, embodiments of this application can extract the corresponding memorized path, i.e., the final parking path, and control the vehicle to leave or park.

[0062] Optionally, in one embodiment of this application, generating the final parking path to the current destination based on the smooth point cloud sequence of the lane lines on both sides includes: calculating the shortest distance between two corresponding smooth path points in the smooth point cloud sequence of the lane lines on both sides in sequence; calculating the final path point based on the shortest distance using a preset point selection strategy; and concatenating the final path points to generate the final parking path.

[0063] As one possible implementation method, this application embodiment can calculate the shortest distance between two corresponding smooth path points in the smooth point cloud sequence of the lane lines on both sides after smoothing processing, and then calculate the final path point based on the shortest distance using a preset point selection strategy, thereby obtaining the final parking path.

[0064] Among them, the preset point selection strategy can select a point as the final path point according to a specific pattern on the shortest distance between two corresponding smooth path points, such as selecting one-quarter of the shortest distance.

[0065] For example, in this embodiment of the application, the point closest to the starting point of the initial parking path in the smoothed point cloud sequence of the smoothed connected lane lines can be selected as the first point of the lane lines on both sides.

[0066] In this embodiment of the application, the point cloud of the lane lines on both sides can be numbered sequentially, starting from the first point determined in the previous step and numbering them sequentially downwards.

[0067] Furthermore, in this embodiment of the application, for points A and B, numbered N on both sides of the lane lines, the distance L between them can be calculated, and a point on the line connecting the two points with a distance of L / 4 from point B can be selected. This point is the Nth point of the reference path, and finally all the final path points are obtained.

[0068] Following the steps described above, the final waypoints are processed at equal intervals to obtain the optimized final parking path, p_final_path. This path can be compared with the original memorized waypoint information as follows: Figure 5 As shown.

[0069] Combination Figures 2 to 6 As shown, the working principle of the memory parking path generation method of this application embodiment is explained in detail with an example.

[0070] like Figure 6 As shown, embodiments of this application may include the following steps:

[0071] Step S601: Perceive the initial parking path. This embodiment of the application can first determine whether the vehicle is in parking mode. When the vehicle is not in parking mode, the vehicle's driving path is not recorded. When the vehicle is in parking mode, this embodiment of the application can record the initial parking path when first parking at the current destination, and based on sensing devices such as radar, cameras, and other sensors, perceive the lane line information on both sides of the initial parking path, and perform point cloud mapping based on the perceived lane line information on both sides to generate a point cloud sequence of lane lines on both sides.

[0072] Step S602: Differentiate the lane lines on both sides. In this embodiment, a window can be pre-selected on the initial parking path, and the window includes at least one initial path point. This embodiment can determine a plane equation based on the position information of multiple initial path points in the currently selected window, such as Mx+Ny+Lz+K=0, where M, N, L, and K represent parameters, indicating a plane in the three-dimensional coordinate system where these points are located. This embodiment can arbitrarily substitute any point in the current window into the plane equation, placing points where Mx+Ny+Lz+K<0 in a left lane line point cloud sequence, and points where Mx+Ny+Lz+K>0 in a right lane line point cloud sequence. Windows on the initial parking path are selected sequentially to achieve differentiation of the point clouds of the lane lines on both sides.

[0073] Furthermore, this embodiment can pre-select a window on the initial parking path, and the window includes at least one initial path point, defining the current path point as the starting point of the initial parking path. This embodiment can determine a plane equation based on the position information of multiple initial path points in the currently selected window, such as Mx+Ny+Lz+K=0, where M, N, L, and K represent parameters, indicating a plane in the three-dimensional coordinate system where these points are located. This embodiment can sequentially calculate the points on the path closest to the starting point on the initial parking path, starting from the starting point. If this point is within the current window, the position information of the selected lane line points is substituted into the plane equation. Points with calculated Mx+Ny+Lz+K<0 are placed in a left lane line point cloud sequence, and points with calculated Mx+Ny+Lz+K>0 are placed in a right lane line point cloud sequence. The above steps are repeated by sequentially selecting windows on the initial parking path until all initial path points are divided, and the lane lines on both sides are denoted as p_left_lane and p_right_lane, respectively.

[0074] Step S603: Screen out the point clouds of lane lines on both sides. For example, such as Figure 2 As shown in the embodiment of this application, five points ABCDE, including the current lane line point, can be selected from the lane line point cloud sequence on one side. The angles between the four line segments formed by these five points and the distances between the five points and their nearest initial path points can be calculated.

[0075] like Figure 3 As shown, if ∠ABC is greater than 120°, ∠BCD is less than 120°, and ∠CDE is greater than 120°, and the distances from points C, D, and E to the initial path point gradually increase, then points D and E are discarded at this point.

[0076] Take the points after DE in this lane line point cloud sequence, calculate ∠ABC and angle ∠BCD until the difference between the two is within 10°. At this point, the embodiment of this application can obtain point F. This filtering process filters out all lane line point cloud points after C and before F.

[0077] Take F as the current lane line point, repeat the above steps, and finally obtain the intermediate path points after filtering.

[0078] Repeat the above steps for the other lane line to obtain the middle path point of the other lane line.

[0079] Step S604: Smooth the lane line point clouds on both sides. In this embodiment of the application, after the filtering is completed, for the lane line point cloud sequence on one side, select the current middle path point as the first point, let's call it point A, and the next point as the second point, let's call it point B. Calculate the points along the AB direction that are a certain distance from A: if this point is inside the AB line segment, then set this point as A, and store this point in a new lane line point cloud sequence, and then continue to calculate the points along the AB direction that are a certain distance from A; if this point is outside the AB line segment, then select the next point of B in the initial lane line point cloud sequence as B, and continue to calculate the points along the AB direction that are a certain distance from A.

[0080] Based on the above steps, the embodiments of this application can obtain a complete smooth point cloud sequence, in which the spacing between each point is the same and the direction is the same as the initial lane line.

[0081] By performing the same actions on the original lane line sequence on the other side, the embodiments of this application can obtain a smoothed lane line sequence on the other side.

[0082] Thus, as Figure 4 As shown, in this embodiment of the application, a point cloud sequence of equally spaced left and right lane lines can be obtained, denoted as p_left_lane_smooth and p_right_lane_smooth.

[0083] Step S605: Generate the final reference path. For example, in this embodiment of the application, the point closest to the starting point of the initial parking path in the smoothed point cloud sequence of the smoothed connected lane lines can be selected as the first point of the lane lines on both sides.

[0084] In this embodiment of the application, the point cloud of the lane lines on both sides can be numbered sequentially, starting from the first point determined in the previous step and numbering them sequentially downwards.

[0085] Furthermore, in this embodiment of the application, for points A and B, numbered N on both sides of the lane lines, the distance L between them can be calculated, and a point on the line connecting the two points with a distance of L / 4 from point B can be selected. This point is the Nth point of the reference path, and finally all the final path points are obtained.

[0086] Following the steps described above, the final waypoints are processed at equal intervals to obtain the optimized final parking path, p_final_path. This path can be compared with the original memorized waypoint information as follows: Figure 5 As shown.

[0087] The method for generating a parking path according to the embodiments of this application can process the lane lines on both sides of the initial parking path separately, filter out redundant points in the point cloud sequence of the lane lines on both sides, and perform equidistant processing on the remaining points to obtain a smooth point cloud sequence of the lane lines on both sides, thereby generating the final parking path for the current destination. This facilitates the vehicle to park or exit based on the final parking path, and can automatically adjust the path when obstacles on the path change, thereby improving the parking efficiency of the vehicle and enhancing the user experience. This solves the technical problem in related technologies where simply memorizing and recalling historical parking paths is not applicable to dynamically changing paths, resulting in reduced parking efficiency and impacting the user experience.

[0088] Next, with reference to the accompanying drawings, a memory parking path generation apparatus according to an embodiment of this application is described.

[0089] Figure 7 This is a block diagram of a memory parking path generation device according to an embodiment of this application.

[0090] like Figure 7 As shown, the memory parking path generation device 10 includes: a generation module 100, a processing module 200, and a control module 300.

[0091] Specifically, the generation module 100 is used to generate an initial parking path to the current destination in parking mode, perceive the lane line information on both sides of the initial parking path, and generate a point cloud sequence of lane lines on both sides based on the lane line information on both sides.

[0092] The processing module 200 is used to filter out redundant points in the point cloud sequence of the lane lines on both sides, and to perform equidistant filtering on the remaining points in the point cloud sequence to obtain a smooth point cloud sequence of the lane lines on both sides.

[0093] The control module 300 is used to generate the final parking path for the current destination based on the smooth point cloud sequence of the lane lines on both sides, so as to control the vehicle to park out of the current destination or park back into the current destination according to the final parking path.

[0094] Optionally, in one embodiment of this application, the memory parking path generation device 10 further includes: a selection module, a determination module, and a calculation module.

[0095] The selection module is used to select any window on the initial parking path, wherein the window contains at least one initial path point.

[0096] The determination module is used to determine the plane equation based on the position information of at least one path point within the window.

[0097] The calculation module is used to select any initial path point within the window, substitute any initial path point into the plane equation, and divide at least one initial path point within the window into the lane lines on both sides based on the calculation result of the plane equation, until all initial path points within the window are divided, thus determining the path points of each lane line.

[0098] Optionally, in one embodiment of this application, the processing module 200 includes: a first selection unit, a measurement unit, and a judgment unit.

[0099] The first selection unit is used to select any number of consecutive initial path points in the point cloud sequence of each lane line.

[0100] The measurement unit is used to connect multiple consecutive initial path points to generate a corresponding path polyline and to measure all angles of the path polyline.

[0101] The judgment unit is used to determine whether the initial path point meets the preset screening conditions based on the angle, and delete the initial path point when the preset screening conditions are met, until the screening of the point cloud sequence of each lane line is completed, and all intermediate path points are obtained.

[0102] Optionally, in one embodiment of this application, the processing module 200 includes a second selection unit.

[0103] The second selection unit is used to select the starting point of the point cloud sequence of each lane line, and select the next intermediate path point at preset distances based on the starting point until the selection of intermediate path points of each lane line is completed, thus obtaining all smooth path points.

[0104] Optionally, in one embodiment of this application, the control module 300 includes: a first calculation unit, a second calculation unit, and a generation unit.

[0105] The first calculation unit is used to calculate the shortest distance between two corresponding smooth path points in the smooth point cloud sequence of the lane lines on both sides, based on the smooth point cloud sequence of the lane lines on both sides.

[0106] The second calculation unit is used to calculate the final path point based on the shortest distance using a preset point selection strategy.

[0107] The generation unit is used to connect the final waypoints to generate the final parking path.

[0108] It should be noted that the foregoing explanation of the method for generating memory parking paths also applies to the memory parking path generation apparatus of this embodiment, and will not be repeated here.

[0109] The parking path generation device proposed in this application can process the lane lines on both sides of the initial parking path separately, filter out redundant points in the point cloud sequence of the lane lines on both sides, and perform equidistant processing on the remaining points to obtain a smooth point cloud sequence of the lane lines on both sides, thereby generating the final parking path for the current destination. This facilitates the vehicle to park or exit based on the final parking path. It can automatically adjust the path when obstacles on the path change, thereby improving the parking efficiency of the vehicle and enhancing the user experience. This solves the technical problem in related technologies where simply memorizing and recalling historical parking paths is not applicable to dynamically changing paths, resulting in reduced parking efficiency and impacting the user experience.

[0110] Figure 8 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0111] The memory 801, the processor 802, and the computer program stored on the memory 801 and capable of running on the processor 802.

[0112] When the processor 802 executes the program, it implements the memory parking path generation method provided in the above embodiments.

[0113] Furthermore, the vehicle also includes:

[0114] Communication interface 803 is used for communication between memory 801 and processor 802.

[0115] The memory 801 is used to store computer programs that can run on the processor 802.

[0116] The memory 801 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0117] If the memory 801, processor 802, and communication interface 803 are implemented independently, then the communication interface 803, memory 801, and processor 802 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 8 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0118] Optionally, in a specific implementation, if the memory 801, processor 802, and communication interface 803 are integrated on a single chip, then the memory 801, processor 802, and communication interface 803 can communicate with each other through an internal interface.

[0119] The processor 802 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0120] This embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for generating a memory parking path.

[0121] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0122] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0123] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0124] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0125] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0126] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0127] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0128] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for generating a memory parking path, characterized in that, Includes the following steps: In parking mode, an initial parking path is generated to park at the current destination, the lane line information on both sides of the initial parking path is perceived, and a point cloud sequence of the lane lines on both sides is generated based on the lane line information on both sides. Redundant points in the point cloud sequence of the lane lines on both sides are removed, and the remaining points in the point cloud sequence are filtered at equal intervals to obtain a smooth point cloud sequence of the lane lines on both sides; and The final parking path to the current destination is generated based on the smooth point cloud sequence of the lane lines on both sides, so as to control the vehicle to park out of the current destination or park back into the current destination according to the final parking path.

2. The method according to claim 1, characterized in that, Before filtering out redundant points in the point cloud sequence of the lane lines on both sides, the process also includes: Select any window on the initial parking path, wherein the window contains at least one initial path point; Determine the plane equation based on the position information of at least one initial path point within the window; Select any initial path point within the window and substitute it into the plane equation. Based on the calculation result of the plane equation, assign at least one initial path point within the window to the lane lines on both sides until all initial path points within the window are assigned, thus determining the path points for each lane line.

3. The method according to claim 2, characterized in that, The process of filtering out redundant points in the point cloud sequence of the lane lines on both sides includes: Select any number of consecutive initial path points from the point cloud sequence of each lane line; Connect the consecutive initial path points to generate a corresponding path polyline, and measure all angles of the path polyline; Based on the angle, determine whether the initial path point meets the preset screening conditions, and delete the initial path point when the preset screening conditions are met, until the screening of the point cloud sequence of each lane line is completed, and obtain all intermediate path points.

4. The method according to claim 3, characterized in that, The step of isometrically filtering the remaining points in the point cloud sequence to obtain a smooth point cloud sequence for the lane lines on both sides includes: The starting point of the point cloud sequence of each lane line is selected, and the next intermediate path point is selected at preset intervals based on the starting point until the selection of intermediate path points of each lane line is completed, thus obtaining all smooth path points.

5. The method according to claim 4, characterized in that, The generation of the final parking path to the current destination based on the smooth point cloud sequence of the lane lines on both sides includes: Based on the smooth point cloud sequence of the lane lines on both sides, the shortest distance between two corresponding smooth path points in the smooth point cloud sequence of the lane lines on both sides is calculated sequentially. Based on the shortest distance, the final path point is calculated using a preset point selection strategy; The final path points are connected in series to generate the final parking path.

6. A vehicle memory parking device, characterized in that, include: The generation module is used to generate an initial parking path to the current destination in parking mode, perceive the lane line information on both sides of the initial parking path, and generate a point cloud sequence of the lane lines on both sides based on the lane line information on both sides. The processing module is used to filter out redundant points in the point cloud sequence of the lane lines on both sides, and to perform equidistant filtering on the remaining points in the point cloud sequence to obtain a smooth point cloud sequence of the lane lines on both sides. as well as The control module is used to generate a final parking path for the current destination based on the smooth point cloud sequence of the lane lines on both sides, so as to control the vehicle to park out of the current destination or park back into the current destination according to the final parking path.

7. The apparatus according to claim 6, characterized in that, Also includes: A selection module is used to select any window on the initial parking path, wherein the window contains at least one initial path point; The determination module is used to determine the plane equation based on the position information of the at least one initial path point within the window; The calculation module is used to select any initial path point within the window, substitute the arbitrary initial path point into the plane equation, and divide at least one initial path point within the window into the lane lines on both sides based on the calculation result of the plane equation, until all initial path points within the window are divided, thereby determining the path points of each lane line.

8. The apparatus according to claim 7, characterized in that, The processing module includes: The selection unit is used to select any number of consecutive initial path points in the point cloud sequence of each lane line; A measurement unit is used to connect the multiple consecutive initial path points to generate a corresponding path polyline, and to measure all angles of the path polyline; The judgment unit is used to determine whether the initial path point meets the preset screening conditions based on the angle, and delete the initial path point when the preset screening conditions are met, until the screening of the point cloud sequence of each lane line is completed, and all intermediate path points are obtained.

9. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the method for generating a memory parking path as described in any one of claims 1-5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the method for generating memory parking paths as described in any one of claims 1-5.

Images