Parking path planning method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a parking path planning method and device, electronic equipment and a storage medium. The method comprises the steps that a ground image of a ground area where a vehicle is located is acquired, and material information in the ground area where the vehicle is located is determined according to the ground image; wherein the material information represents a ground material contained in a ground area where the vehicle is located; dividing the ground area where the vehicle is located into at least one sub-area according to the material information in the ground area where the vehicle is located; wherein one kind of material information corresponds to one or more sub-regions; according to the material information corresponding to each sub-region in the ground region where the vehicle is located, determining a target parking path of the vehicle from a starting point to an ending point; wherein the target parking path is used for indicating the vehicle to perform automatic parking. According to the method, the vehicle can be prevented from rolling the area which is not suitable for driving, and the personalized capability and safety of parking are improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving, and particularly to a method, apparatus, electronic device, and storage medium for planning a parking path. Background Art

[0002] With the rapid development of intelligent vehicle technology, the automatic parking function has become one of the important configurations of modern vehicles. Currently, the automatic parking system mainly senses the surrounding obstacles through sensors and then plans the path by combining preset rules or traditional algorithms.

[0003] However, this method cannot comprehensively and meticulously detect the vehicle's environment, cannot meet the personalized requirements of users for automatic parking, and affects the safety of automatic parking. Summary of the Invention

[0004] Embodiments of this application provide a method, apparatus, electronic device, and storage medium for planning a parking path to improve the personalization ability and safety of parking.

[0005] In a first aspect, embodiments of this application provide a method for planning a parking path, including:

[0006] Obtain a ground image of the ground area where the vehicle is located, and determine the material information in the ground area where the vehicle is located according to the ground image; wherein, the material information characterizes the ground materials contained in the ground area where the vehicle is located;

[0007] Divide the ground area where the vehicle is located into at least one sub-area according to the material information in the ground area where the vehicle is located; wherein, one type of material information corresponds to one or more sub-areas;

[0008] Determine a target parking path for the vehicle from the starting point to the ending point according to the material information corresponding to each sub-area in the ground area where the vehicle is located; wherein, the target parking path is used to instruct the vehicle to perform automatic parking.

[0009] In a possible implementation manner, determining the target parking path for the vehicle from the starting point to the ending point according to the material information corresponding to each sub-area in the ground area where the vehicle is located includes:

[0010] Determine a target area from the ground area where the vehicle is located according to the material information corresponding to the sub-areas in the ground area where the vehicle is located; wherein, the target area includes one or more sub-areas;

[0011] Based on a preset path planning algorithm, determine a candidate parking path for the vehicle from the starting point to the ending point from the target area;

[0012] Determine a target parking path from each of the candidate parking paths according to the path information of each candidate parking path; wherein, the path information characterizes the driving condition of the vehicle when driving along the candidate parking path.

[0013] In a possible implementation manner, determining a target area from the ground area where the vehicle is located according to the material information corresponding to the sub-areas in the ground area where the vehicle is located includes:

[0014] Determine the driving priority of the sub-areas according to the material information corresponding to the sub-areas in the ground area where the vehicle is located; wherein, the driving priority characterizes the recommended degree of the vehicle passing through the sub-areas when driving.

[0015] Determine at least one target area according to the driving priorities of each sub-area.

[0016] In a possible implementation manner, determining the candidate parking path of the vehicle from the starting point to the ending point from the target area based on a preset path planning algorithm includes:

[0017] Determine path nodes from the target area based on a preset path planning algorithm; wherein, the path nodes characterize the possible positions that the vehicle may pass through when parking.

[0018] Determine the material cost value corresponding to the material information of the path nodes according to a preset association relationship; wherein, the preset association relationship characterizes the association relationship between the material information and the material cost value, and the material cost value characterizes the influence degree of the ground material on the vehicle driving.

[0019] Determine the target cost value of the path nodes according to the position of the starting point, the position of the ending point, the position of the path nodes, and the material cost value corresponding to the material information of the path nodes; wherein, the target cost value characterizes the quality degree of the path nodes.

[0020] Determine the candidate parking path of the vehicle from the starting point to the ending point according to the target cost value of the path nodes.

[0021] In a possible implementation manner, the target cost value includes a heuristic cost value, and the heuristic cost value characterizes the estimated cost from the path node to the ending point; the determining the target cost value of the path nodes according to the position of the starting point, the position of the ending point, the position of the path nodes, and the material cost value corresponding to the material information of the path nodes includes:

[0022] Determine the distance information between the path node and the ending point according to the position of the ending point and the position of the path node.

[0023] Determine the heuristic cost value of the path node according to the distance information between the path node and the end point, the material cost value corresponding to the material information of the path node, and a preset first weight.

[0024] In a possible implementation, the target cost value includes an actual cost value, and the actual cost value represents the actual path cost from the starting point to the path node; the determining of the target cost value of the path node according to the position of the starting point, the position of the end point, the position of the path node, and the material cost value corresponding to the material information of the path node includes:

[0025] Determine the path length between the starting point and the path node according to the position of the starting point and the position of the path node;

[0026] Determine the actual cost value of the path node according to the path length between the starting point and the path node, the material cost value corresponding to the material information of the path node, and a preset second weight.

[0027] In a possible implementation, the path information includes at least one of a path length, a number of gear shifts, and a driving time; determining a target parking path from each of the candidate parking paths according to the path information of each of the candidate parking paths includes:

[0028] Determine the path efficiency value of the candidate parking path according to the path information of the candidate parking path; wherein, the path efficiency value represents the driving efficiency of the candidate parking path;

[0029] Determine a target parking path from each of the candidate parking paths according to the path efficiency values of each of the candidate parking paths.

[0030] In a possible implementation, each candidate parking path corresponds to a target area, the target area includes one or more sub-areas, and each sub-area corresponds to a driving priority; determining a target parking path from each of the candidate parking paths according to the path efficiency values of each of the candidate parking paths includes:

[0031] Determine the path priority of the candidate parking path according to the driving priority of the sub-areas in the target area;

[0032] If there are at least two candidate parking paths with path priorities, then determine a first parking path and a second parking path from the candidate parking paths; wherein, the path priority of the first parking path is higher than the path priority of the second parking path;

[0033] Determine a target parking path from the first parking path and the second parking path according to the path efficiency values of the first parking path and the second parking path.

[0034] In a possible implementation, the driving priorities include a first priority, a second priority, and a third priority, where the first priority is higher than the second priority, and the second priority is higher than the third priority; determining the path priority of the candidate parking path according to the driving priorities of the sub-regions in the target region includes:

[0035] If only the sub-regions with the first priority are included in the target region, determine that the path priority of the candidate parking path is the first level;

[0036] If the sub-regions with the second priority are included in the target region and the sub-regions with the third priority are not included, determine that the path priority of the candidate parking path is the second level;

[0037] If the sub-regions with the third priority are included in the target region, determine that the path priority of the candidate parking path is the third level.

[0038] In a possible implementation, determining the target parking path from the first parking path and the second parking path according to the path efficiency values of the first parking path and the second parking path includes:

[0039] If the path efficiency value of the first parking path is less than the path efficiency value of the second parking path, determine the difference between the path efficiency values of the first parking path and the second parking path;

[0040] If the difference is less than or equal to a preset difference threshold, determine that the first parking path is the target parking path.

[0041] In a possible implementation, dividing the ground area where the vehicle is located into at least one sub-region according to the material information in the ground area where the vehicle is located includes:

[0042] Determine the material boundary in the ground area where the vehicle is located according to the material information in the ground area where the vehicle is located; where the material boundary represents the boundary between different material information;

[0043] Divide the ground area where the vehicle is located according to the material boundary to obtain a plurality of sub-regions.

[0044] In a possible implementation, determining the material information in the ground area where the vehicle is located according to the ground image includes:

[0045] If there is an occluded area in the ground area in the ground image, determine the material information of the occluded area in the ground area as the preset material information.

[0046] In a second aspect, an embodiment of the present application provides a parking path planning device, including:

[0047] A material determination unit, configured to obtain a ground image of the ground area where the vehicle is located, and determine material information in the ground area where the vehicle is located according to the ground image; wherein, the material information characterizes the ground materials contained in the ground area where the vehicle is located;

[0048] An area division unit, configured to divide the ground area where the vehicle is located into at least one sub-area according to the material information in the ground area where the vehicle is located; wherein, one type of material information corresponds to one or more sub-areas;

[0049] A path determination unit, configured to determine a target parking path of the vehicle from a starting point to an ending point according to the material information corresponding to each sub-area in the ground area where the vehicle is located; wherein, the target parking path is used to instruct the vehicle to perform automatic parking.

[0050] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0051] The memory stores computer-executable instructions;

[0052] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementation manners of the first aspect.

[0053] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, they are used to implement the above first aspect and / or various possible implementation manners of the first aspect.

[0054] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the above first aspect and / or various possible implementation manners of the first aspect.

[0055] A method, apparatus, electronic device, and storage medium for planning a parking path provided by an embodiment of the present application obtain a ground image of the ground area where the vehicle is located, perform image recognition processing on the ground image to determine the ground material contained in the ground area where the vehicle is located, that is, obtain material information, and achieve the distinction of the ground material. According to the material information in the ground area where the vehicle is located, the ground area is divided into different sub-areas, and each sub-area can correspond to a ground material. According to the ground materials in different sub-areas, path planning is performed to obtain a target parking path, so that the vehicle can park automatically according to the target parking path. This avoids the vehicle from running over areas that are not suitable for driving, adapts to complex environments, reduces the impact on the environment, improves the personalization ability and safety of parking, and enhances the parking efficiency and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0057] Figure 1 It is a schematic flowchart of a method for planning a parking path provided by an embodiment of the present application;

[0058] Figure 2 It is a schematic diagram of the ground image provided by an embodiment of the present application;

[0059] Figure 3 It is a schematic diagram of path planning provided by an embodiment of the present application;

[0060] Figure 4 It is a schematic flowchart of a method for planning a parking path provided by an embodiment of the present application;

[0061] Figure 5 It is a schematic structural diagram of a device for planning a parking path provided by an embodiment of the present application;

[0062] Figure 6 It is a schematic structural diagram of the electronic device provided by an embodiment of the present application.

[0063] Through the above-mentioned accompanying drawings, specific embodiments of the present application have been shown, and there will be more detailed descriptions hereinafter. These drawings and text descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0065] Glossary:

[0066] Home-zone Parking Assist (HPA): When the user sets the parking path during the first parking, the system saves these settings in the map and automatically calls them every time parking subsequently.

[0067] Automatic Parking Assist (APA): During the automatic parking process of the vehicle, the parking path is dynamically adjusted according to the distribution of obstacles in the environment and the user's instructions.

[0068] Remote Parking Assist (RPA): The user starts the parking function through a remote control device to plan the parking path.

[0069] Automated Valet Parking (AVP): During the automated valet parking process of the vehicle, the parking path is autonomously planned according to the distribution of obstacles in the environment.

[0070] Heuristic cost: The estimated cost from the current node to the target node. The heuristic cost is usually based on a certain heuristic function, such as the Euclidean distance or Manhattan distance, and is used to estimate the minimum possible cost from the current node to the target node.

[0071] Actual cost: The actual path cost from the starting node to the current node, usually the path length or the cumulative cost of each action on the path.

[0072] Total cost: The sum of the actual cost and the heuristic cost.

[0073] With the development of intelligent vehicle technology, the automatic parking function has become one of the important configurations of modern vehicles. Technologies such as home-zone parking assist, automatic parking assist, remote parking assist, and automated valet parking provide users with a convenient parking experience. Current automatic parking systems mainly sense the surrounding environment through sensors and perform path planning by combining preset rules or traditional algorithms. Although these methods can achieve automatic parking to a certain extent, when planning the path, they usually regard all drivable areas as equally important and ignore the impact of the ground material on the driving safety and comfort of the vehicle.

[0074] In other words, the current automatic parking system lacks the ability to distinguish ground materials and cannot adjust the parking path according to ground materials (such as cement, asphalt, lawn, puddles, etc.). This may cause the vehicle to run over areas that are not suitable for driving, affecting the environment or vehicle safety, and cannot meet users' needs for parking safety and ease of use.

[0075] The present application provides a path planning method, device, equipment and storage medium based on automatic parking, which aims to solve the above technical problems of the prior art and is applicable to various vehicles with automatic parking functions, including memory parking, automatic parking, remote control parking and autonomous parking, as well as various parking environments such as parking lots, communities, and commercial plazas.

[0076] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0077] Figure 1 The present invention provides a flow chart of a parking path planning method provided in an embodiment of the present invention. The method can be executed by a parking path planning device. Figure 1 As shown, the method includes:

[0078] S101. Acquire a ground image of a ground area where a vehicle is located, and determine material information in the ground area where the vehicle is located based on the ground image; wherein the material information represents the ground material contained in the ground area where the vehicle is located.

[0079] For example, a vehicle may be equipped with a variety of sensors, such as surround view cameras, perimeter cameras, front and rear view cameras, and other image acquisition device types. The sensors on the vehicle can acquire environmental images at various angles in the surrounding environment. For example, ground images can be acquired.

[0080] When the user needs to park the vehicle, an automatic parking command can be issued. For example, the automatic parking command can be issued through the vehicle computer, or through the user's own terminal device. The user's terminal device can be installed with a preset client, and through the preset client, the terminal device can be associated and bound with the vehicle computer, so as to control the vehicle through the terminal device.

[0081] The automatic parking instruction is used to instruct the vehicle to perform automatic parking. The automatic parking instruction may include the final parking position of the vehicle. For example, the user may input the final parking position through the vehicle computer or terminal device, so that the vehicle can automatically park from the current position, that is, the starting point, to the final parking position. The user may issue the automatic parking instruction by voice or by clicking on the control on the screen. In this embodiment, the method of issuing the automatic parking instruction is not specifically limited.

[0082] The sensors on the vehicle can collect ground images within a preset range in real time or at a fixed time, and after responding to the automatic parking command, the ground images collected in real time can be obtained. For example, the ground images within the area with the vehicle as the center and a preset distance as the radius can be obtained.

[0083] After obtaining the ground image, a preset image processing algorithm can be used to perform image recognition processing on the ground image to identify the material of the ground. In this embodiment, the preset image processing algorithm is not specifically limited. For example, features such as texture information and color information of the ground can be obtained from the ground image, and material information can be determined based on the extracted features. The material information characterizes the ground material. The ground material can be a cement floor, asphalt road, lawn, puddle, mud, etc. A variety of material information can be identified in a ground image, that is, the ground around the vehicle may have a variety of materials. Figure 2 Schematic diagram of the ground image. Figure 2 In the figure, the material information of the oblique line area indicates that the ground is a cement road, and the material information of the grid area indicates that the ground is a lawn.

[0084] In this embodiment, material information in the ground area where the vehicle is located is determined based on the ground image, including: if there is an obscured area in the ground area in the ground image, the material information of the obscured area in the ground area is determined as preset material information.

[0085] Specifically, the ground around the vehicle may be blocked, for example, the ground may be blocked by surrounding pillars, trees, etc. For the blocked area in the ground area, the material information of the area cannot be identified, so default material information can be preset, and when the blocked area is identified in the ground image, the material information of the blocked area can be determined as the default material information.

[0086] For the occluded area, when the ground cannot be observed, the ground material is an unknown attribute, and the unknown attribute corresponds to the preset default material information. When the ground of the occluded area is observed, the material information of the area can be updated to the actual material information.

[0087] If there are coverings on the ground, resulting in the inability to observe the ground material, the material information of the area with coverings can also be determined as the default material information, or the category of the covering can be identified and used as the material information. For example, if the ground is covered with snow, the snow can be considered as a type of ground material.

[0088] The beneficial effect of such a setting is that the recognition range of the sensors on the vehicle is limited. For unmonitored areas and occluded areas, default material information can be preset to ensure comprehensive recognition of the materials in the ground area, facilitate subsequent path planning, and improve the feasibility of automatic parking.

[0089] S102. Divide the ground area where the vehicle is located into at least one sub-area according to the material information in the ground area where the vehicle is located; among them, one material information corresponds to one or more sub-areas.

[0090] Exemplarily, the ground area where the vehicle is located may contain multiple material information. According to the material information in the ground area, the ground area can be divided into multiple sub-areas, and each sub-area constitutes the overall ground area. In this embodiment, the shape of the sub-area is not specifically limited.

[0091] Each sub-area can correspond to one material information, and the material information corresponding to different sub-areas can be the same. For example, Figure 2 the ground area in [example] can be divided into three sub-areas. Among them, the annular diagonal area is one sub-area, and the rectangular grid area is two sub-areas. The material information of the diagonal sub-area is a cement road surface, and the material information of the grid sub-area is a lawn.

[0092] In this embodiment, dividing the ground area where the vehicle is located into at least one sub-area according to the material information in the ground area where the vehicle is located includes: determining the material boundary in the ground area where the vehicle is located according to the material information in the ground area where the vehicle is located; among them, the material boundary represents the boundary between different material information; dividing the ground area where the vehicle is located according to the material boundary to obtain multiple sub-areas.

[0093] Specifically, an image recognition algorithm can be preset, and the image recognition algorithm can be used to recognize the material information in the ground image. For example, the material information can be determined by recognizing the texture features in the ground image. In this embodiment, the preset image recognition algorithm is not specifically limited.

[0094] By identifying the material information in the ground image, the material boundary of different ground materials in the ground image can be determined. The material boundary represents the boundary between different material information. That is, the boundary between two adjacent different materials can be determined as the material boundary. For example, the ground image contains two materials, cement and lawn, and the junction between cement and lawn is the material boundary.

[0095] The sub-regions are divided according to the boundaries of the ground material. For example, the area surrounded by the material boundary can be used as a sub-region. For the same material, if the material is dispersed on the ground, the material can correspond to multiple sub-regions.

[0096] The beneficial effect of such a setting is that by identifying material boundaries, the sub-areas can be accurately divided, thereby improving the planning accuracy of the parking path.

[0097] S103. Determine a target parking path for the vehicle from a starting point to an end point based on material information corresponding to each sub-area in the ground area where the vehicle is located; wherein the target parking path is used to instruct the vehicle to perform automatic parking.

[0098] For example, different ground materials may have different effects on vehicle driving. For example, a vehicle is more suitable for driving on cement ground or asphalt roads, but not suitable for driving on puddles or lawns. When performing automatic parking, the vehicle can be controlled to drive on cement ground or asphalt roads as much as possible, and reduce driving on puddles or lawns.

[0099] The material information corresponding to each sub-area is determined, and a parking path is planned according to the material information of each sub-area to obtain a target parking path, so that the vehicle can travel from a starting point to an end point according to the target parking path. The starting point may be the current position of the vehicle in response to the automatic parking command, and the end point may be the position of the parking destination set by the user.

[0100] When performing path planning, the priority of each sub-area can be determined according to the material information of the sub-area. Different material information can be pre-associated with different priorities. For example, the priority of the sub-area whose material information is cement pavement is higher, and the priority of the sub-area whose material information is lawn is lower. Using a preset path planning algorithm, path planning is performed according to the priority of each sub-area, and the path length of the target parking path in the low-priority sub-area is reduced. In this embodiment, the preset path planning algorithm is not specifically limited. Figure 3 A schematic diagram of the route planning. Figure 3 In the example, two paths can be planned from the starting point to the end point of the vehicle, namely path A and path B. Path A passes through the lawn sub-area with a lower priority. Therefore, the target parking path can be path B.

[0101] The automatic parking system of the vehicle completes the parking operation according to the target parking path and stores the target parking path. During subsequent parking, if the environment remains unchanged, the system can refer to the stored path for parking, further improving the parking efficiency.

[0102] The parking path planning method provided by the embodiments of the present application realizes the differentiation of ground materials by obtaining the ground image of the ground area where the vehicle is located, performing image recognition processing on the ground image, and determining the ground materials contained in the ground area where the vehicle is located, that is, obtaining the material information. According to the material information in the ground area where the vehicle is located, the ground area is divided into different sub-areas, and each sub-area can correspond to one kind of ground material. According to the ground materials in different sub-areas, path planning is performed to obtain the target parking path, so that the vehicle can perform automatic parking according to the target parking path. It avoids the vehicle from running over areas that are not suitable for driving, adapts to complex environments, reduces the impact on the environment, improves the personalization ability and safety of parking, and enhances the parking efficiency and user experience.

[0103] Figure 4 It is a schematic flow chart of a parking path planning method provided by the embodiments of the present application. As Figure 4 shown, in this embodiment, on the basis of the Figure 1 embodiment, the parking path planning method is described in detail.

[0104] In this embodiment, according to the material information corresponding to each sub-area in the ground area where the vehicle is located, determining the target parking path of the vehicle from the starting point to the end point includes: determining the target area from the ground area where the vehicle is located according to the material information corresponding to the sub-areas in the ground area where the vehicle is located; wherein, the target area includes one or more sub-areas; based on a preset path planning algorithm, determining the candidate parking path of the vehicle from the starting point to the end point from the target area; according to the path information of each candidate parking path, determining the target parking path from each candidate parking path; wherein, the path information characterizes the driving situation of the vehicle when driving along the candidate parking path.

[0105] As Figure 4 shown, the method includes:

[0106] S401. Obtain the ground image of the ground area where the vehicle is located, and determine the material information in the ground area where the vehicle is located according to the ground image; wherein, the material information characterizes the ground materials contained in the ground area where the vehicle is located.

[0107] Exemplarily, this step can refer to the above step S101 and will not be elaborated here.

[0108] S402. Divide the ground area where the vehicle is located into at least one sub-area according to the material information in the ground area where the vehicle is located; wherein, one kind of material information corresponds to one or more sub-areas.

[0109] Exemplarily, this step can refer to step S102 above and will not be elaborated here.

[0110] S403. Determine a target area from the ground area where the vehicle is located according to the material information corresponding to each sub - area in the ground area where the vehicle is located; wherein, the target area includes one or more sub - areas.

[0111] Exemplarily, determine the material information corresponding to each sub - area in the ground area. According to the material information of each sub - area, determine one or more sub - areas from all the sub - areas. The determined sub - areas are used as the target area. That is, the target area can include one or more sub - areas. For example, the sub - area with a specified material can be determined as the target area.

[0112] In this embodiment, determining the target area from the ground area where the vehicle is located according to the material information corresponding to the sub - areas in the ground area where the vehicle is located includes: determining the driving priority of the sub - areas according to the material information corresponding to the sub - areas in the ground area where the vehicle is located; wherein, the driving priority represents the recommended degree of the vehicle passing through the sub - area during driving; and determining at least one target area according to the driving priorities of the sub - areas.

[0113] Specifically, for each sub - area, determine the driving priority of the sub - area according to the material information corresponding to the sub - area. The driving priority represents the recommended degree of the vehicle passing through the sub - area during driving, that is, whether it is recommended that the vehicle pass through the sub - area during driving. The higher the driving priority, the more recommended it is for the vehicle to pass through the sub - area, and the lower the driving priority, the less recommended it is for the vehicle to pass through the sub - area. The association relationship between the material information and the driving priority can be preset. For example, the driving priority corresponding to the cement road surface is higher, and the driving priority corresponding to the lawn is lower. According to the preset association relationship, the driving priority of the sub - area can be determined.

[0114] According to the driving priorities of the sub - areas, the target area can be determined from these sub - areas. The target area can include one or more sub - areas. Multiple target areas can be determined, and the sub - areas in different target areas can overlap. The target area refers to the area that the vehicle needs to pass through during automatic parking. For the areas other than the target area, the vehicle cannot pass through during automatic parking.

[0115] The driving priorities of each sub-region in the target area can be the same or different. For example, all sub-regions with the highest driving priorities can be determined as one target area, and then all sub-regions with the highest driving priorities and all sub-regions with the second highest driving priorities can be determined as another target area. That is, two target areas are determined. Among them, the driving priorities of the sub-regions in the first target area are the same, the driving priorities of the sub-regions in the second target area are different, and there are duplicates between the sub-regions in the first target area and the sub-regions in the second target area.

[0116] The beneficial effect of such a setting is that different materials can correspond to different driving priorities. According to the level of driving priorities, a part of the sub-regions can be selected as the target area, so as to plan the path in the target area, so that the final parking path can meet the comfort requirements of actual road driving, avoid the vehicle passing through unsuitable driving areas, and improve the accuracy and safety of automatic parking.

[0117] S404. Based on a preset path planning algorithm, determine a candidate parking path for the vehicle from the starting point to the ending point in the target area.

[0118] Exemplarily, determine the material information corresponding to each sub-region in the ground area, and determine the target area according to the material information of each sub-region. Based on a preset path planning algorithm, path points can be generated in the target area, so as to obtain one or more parking paths from the starting point to the ending point as candidate parking paths. For example, path points can be generated in the target area of the cement road surface, so that the candidate parking path passes through the cement road surface as much as possible.

[0119] A path planning algorithm is preset. For each target area, one or more candidate parking paths can be determined according to the preset path planning algorithm. Each candidate parking path is a path from the starting point to the ending point, and the area passed by the candidate parking path is the corresponding target area.

[0120] In this embodiment, based on a preset path planning algorithm, a candidate parking path for the vehicle from the starting point to the ending point is determined from the target area, including: determining path nodes from the target area based on the preset path planning algorithm, where the path nodes represent possible positions that the vehicle may pass through during parking; determining a material cost value corresponding to the material information of the path nodes according to a preset association relationship, where the preset association relationship represents the association between the material information and the material cost value, and the material cost value represents the degree of influence of the ground material on the vehicle's driving; determining the target cost value of the path nodes according to the position of the starting point, the position of the ending point, the position of the path nodes, and the material cost value corresponding to the material information of the path nodes, where the target cost value represents the quality of the path nodes; and determining the candidate parking path for the vehicle from the starting point to the ending point according to the target cost value of the path nodes.

[0121] Specifically, the preset path planning algorithm can be a hybrid A* algorithm, a Rapidly-exploring Random Trees (RRT) algorithm, a geometric method, etc. For the hybrid A* algorithm, the positions of the starting point, the ending point, and the position range of the target area can be input into the algorithm. By running the hybrid A* algorithm, path nodes can be determined in the target area. For example, multiple path nodes can be determined, screened from these path nodes, and a candidate parking path can be obtained according to the path nodes retained after screening. In this embodiment, the running process of the hybrid A* algorithm is not specifically limited.

[0122] When running the hybrid A* algorithm, the area where the path nodes are located is restricted, that is, path nodes can only be generated in the target area. After obtaining the path nodes, calculate the cost value of the path nodes, determine whether to retain the path nodes according to the calculated cost value, and obtain the candidate parking path according to the retained path nodes.

[0123] When calculating the cost value of a path node, the sub-region to which the path node belongs can be determined, and then the material information of the sub-region can be determined. The association relationship between the material information and the material cost value is preset in advance. The material cost value represents the influence degree of the ground material on the vehicle driving. The larger the material cost value is, the greater the influence of the ground material on the vehicle driving is. According to the preset association relationship, the material cost value corresponding to the material information of the sub-region where the path node is located can be determined. According to the material cost value, the position of the starting point, the position of the ending point, and the position of the path node, the target cost value of the path node is determined. The target cost value represents the quality degree of the path node. The larger the target cost value is, the better the path node is. That is, the vehicle can perform more efficient automatic parking according to this path node, and this path node needs to be retained. For example, the closer the path node is to the center point of the target area, the larger the target cost value is, and the better the path node is. According to the target cost value, it is judged whether to retain the path node, so as to obtain the candidate parking path of the vehicle from the starting point to the ending point. For example, if the target cost value is less than the preset cost value threshold, this path node is screened out.

[0124] The beneficial effect of such a setting is that the hybrid A* algorithm is used for path planning, which improves the efficiency and accuracy of path planning, and further improves the efficiency and accuracy of automatic parking.

[0125] In this embodiment, according to the position of the starting point, the position of the ending point, the position of the path node, and the material cost value corresponding to the material information of the path node, the target cost value of the path node is determined, including: according to the position of the ending point, the position of the path node, and the material cost value corresponding to the material information of the path node, the heuristic cost value of the path node is determined; wherein, the heuristic cost value represents the estimated cost from the path node to the ending point; according to the position of the starting point, the position of the path node, and the material cost value corresponding to the material information of the path node, the actual cost value of the path node is determined; wherein, the actual cost value represents the actual path cost from the starting point to the path node; according to the heuristic cost value and the actual cost value, the target cost value of the path node is determined.

[0126] Specifically, the target cost value can be composed of the heuristic cost value and the actual cost value. The heuristic cost value represents the estimated cost from the path node to the ending point, and the actual cost value represents the actual path cost from the starting point to the path node. Therefore, the heuristic cost value can be determined according to the position of the ending point, the position of the path node, and the material cost value corresponding to the material information of the path node; the actual cost value can be determined according to the position of the starting point, the position of the path node, and the material cost value corresponding to the material information of the path node. The calculation formulas of the heuristic cost value and the actual cost value can be preset in advance. In this embodiment, the calculation formulas are not specifically limited.

[0127] After obtaining the heuristic cost value and the actual cost value, the heuristic cost value and the actual cost value can be added together to obtain the target cost value. That is, the calculation formula for the target cost value can be:

[0128] f = g + h;

[0129] Among them, f is the target cost value, g is the actual cost value, and h is the heuristic cost value.

[0130] The beneficial effect of such a setting is that in the hybrid A* algorithm, the cost usually refers to the evaluation value of the path from the starting node to the target node. By determining the target cost value through the heuristic cost value and the actual cost value, a more practical and feasible parking path can be generated, improving the feasibility of automatic parking.

[0131] In this embodiment, the target cost value includes the heuristic cost value, and the heuristic cost value represents the estimated cost from the path node to the end point; according to the position of the starting point, the position of the end point, the position of the path node, and the material cost value corresponding to the material information of the path node, the target cost value of the path node is determined, including: determining the distance information between the path node and the end point according to the position of the end point and the position of the path node; determining the heuristic cost value of the path node according to the distance information between the path node and the end point, the material cost value corresponding to the material information of the path node, and a preset first weight.

[0132] Specifically, when determining the heuristic cost value, the position of the end point and the position of the path node need to be used. According to the position of the end point and the position of the path node, the distance information between the path node and the end point is determined. The distance information can represent the Euclidean distance between the path node and the end point.

[0133] A first weight is preset in advance to balance the influence of the Euclidean distance and the material cost value. The calculation formula for the heuristic cost value can be:

[0134] h = d E + α × C;

[0135] Among them, d E represents the distance information, α is the first weight, and C is the material cost value.

[0136] For different target areas, different first weights can be preset. For example, if all sub-areas in the target area are sub-areas with the highest driving priority, the first weight can be set smaller; if the target area includes sub-areas with lower driving priority, the first weight can be set larger.

[0137] The beneficial effects of such a setting are as follows. The heuristic cost is used to estimate the path cost from the current path node to the end point, improving the determination accuracy of the candidate parking path. Moreover, by setting different first weights, it can ensure that the path planning result meets the requirements of vehicle driving safety and efficiency, enhancing the user's parking experience.

[0138] In this embodiment, the target cost value includes the actual cost value, and the actual cost value represents the actual path cost from the starting point to the path node. The target cost value of the path node is determined according to the position of the starting point, the position of the end point, the position of the path node, and the material cost value corresponding to the material information of the path node, including: determining the path length between the starting point and the path node according to the position of the starting point and the position of the path node; determining the actual cost value of the path node according to the path length between the starting point and the path node, the material cost value corresponding to the material information of the path node, and a preset second weight.

[0139] Specifically, when determining the actual cost value, the positions of the starting point and the path node are required. According to the positions of the starting point and the path node, the path length between the starting point and the path node is determined.

[0140] A second weight is preset in advance to balance the influence of the path length and the material cost value. The calculation formula of the actual cost value can be:

[0141] g = L + β × C;

[0142] where L represents the path length, β is the second weight, and C is the material cost value.

[0143] For different target areas, different second weights can be preset. For example, if all sub-areas in the target area are sub-areas with the highest driving priority, the second weight can be set smaller; if the sub-areas in the target area include sub-areas with a lower driving priority, the second weight can be set larger.

[0144] The beneficial effects of such a setting are as follows. The actual cost is used to calculate the actual path cost from the starting point to the current path node, improving the determination accuracy of the candidate parking path. Moreover, by setting different second weights, it can ensure that the path planning result meets the requirements of vehicle driving safety and efficiency, enhancing the user's parking experience.

[0145] In this embodiment, when using the RRT algorithm, the material cost value of the ground material can be introduced to adjust the sampling strategy and path cost evaluation. When sampling, sub-areas with a higher driving priority are preferentially selected. When evaluating the path cost, different weights are set according to the ground material, and the higher the driving priority, the lower the weight setting.

[0146] In the geometric method, when calculating the path through a geometric model, the material cost value of the ground material can also be introduced to adjust the feasibility and priority of the path. When evaluating the path cost, different weights are set according to the ground material. The higher the driving priority, the lower the weight setting. In this embodiment, the calculation processes of the RRT algorithm and the geometric method are not specifically limited.

[0147] S405. Determine a target parking path from each candidate parking path according to the path information of each candidate parking path; wherein, the path information characterizes the driving situation of the vehicle when driving along the candidate parking path.

[0148] Exemplarily, after obtaining multiple candidate parking paths, the path information of each candidate parking path can be determined. The path information can characterize the driving situation of the vehicle when driving along the candidate parking path. For example, the path information can include the total length of the path, the driving time required by the vehicle, the number of turns, etc.

[0149] Select a candidate parking path from each candidate parking path as the target parking path according to the path information of each candidate parking path. For example, the candidate parking path with the shortest path length can be determined as the target parking path.

[0150] In this embodiment, the path information includes at least one of the path length, the number of gear shifts, and the driving time; determining a target parking path from each candidate parking path according to the path information of each candidate parking path includes: determining a path efficiency value of the candidate parking path according to the path information of the candidate parking path; wherein, the path efficiency value characterizes the driving efficiency of the candidate parking path; determining a target parking path from each candidate parking path according to the path efficiency values of each candidate parking path.

[0151] Specifically, the path information includes the path length, the number of gear shifts, the driving time, etc., and the driving time is the time length required for the vehicle to drive along the path. For each candidate parking path, determine the path efficiency value of the candidate parking path according to the path information of the candidate parking path. The path efficiency value can characterize the driving efficiency of the candidate parking path, that is, the parking efficiency when the vehicle drives along the candidate parking path. The larger the path efficiency value, the better the candidate parking path.

[0152] The calculation formula of the path efficiency value can be:

[0153] S = i·x + j·y + k·z;

[0154] wherein, S is the path efficiency value, i, j, and k are all preset weights, x represents the path length, y represents the number of gear shifts, and z represents the driving time.

[0155] Determine the path efficiency values of each candidate parking path, and determine the target parking path from each candidate parking path according to the path efficiency values of each candidate parking path. For example, the candidate parking path with the maximum path efficiency value can be determined as the target parking path.

[0156] The beneficial effect of such a setting is that, according to the path efficiency value of the candidate path, a target parking path with high efficiency is selected to improve the efficiency of automatic parking.

[0157] In this embodiment, each candidate parking path corresponds to a target area, the target area includes one or more sub-areas, and each sub-area corresponds to a driving priority; determining the target parking path from each candidate parking path according to the path efficiency values of each candidate parking path includes: determining the path priority of the candidate parking path according to the driving priority of the sub-areas in the target area; if there are at least two candidate parking paths with different path priorities, determining a first parking path and a second parking path from the candidate parking paths; wherein, the path priority of the first parking path is higher than that of the second parking path; determining the target parking path from the first parking path and the second parking path according to the path efficiency values of the first parking path and the second parking path.

[0158] Specifically, there can be multiple candidate parking paths corresponding to one target area, and each candidate parking path corresponds to a target area. One target area can include one or more sub-areas, and each sub-area corresponds to its own driving priority. For each candidate parking path, determine the target area corresponding to the candidate parking path. Determine the path priority of the candidate parking path according to the driving priority of the sub-areas in the target area. The path priority can represent the quality of the candidate parking path. For example, the higher the driving priority of the sub-areas in the target area, the higher the path priority of the candidate parking path. For different candidate parking paths corresponding to the same target area, the path priorities can be the same.

[0159] For all candidate parking paths, if the path priorities of all candidate parking paths are the same, then the candidate parking path with the maximum path efficiency value is determined as the target parking path; if there are candidate parking paths with at least two path priorities, then the first parking path and the second parking path are determined from the candidate parking paths, and the path priority of the first parking path is different from that of the second parking path. For example, among all candidate parking paths, the candidate parking path with the highest path priority can be determined as the first parking path, and the candidate parking path with the second highest path priority can be determined as the second parking path. If there are multiple candidate parking paths with the highest path priority, then the candidate parking path with the maximum path efficiency value among them can be determined as the first parking path; if there are multiple candidate parking paths with the second highest path priority, then the candidate parking path with the maximum path efficiency value among them can be determined as the second parking path.

[0160] Determine the path efficiency values of the first parking path and the second parking path, and determine the target parking path from the first parking path and the second parking path according to the path efficiency values of the first parking path and the second parking path. For example, the path with the higher path efficiency value among the first parking path and the second parking path can be determined as the target parking path.

[0161] The beneficial effect of such a setting is that the path priorities are determined. If there are paths with multiple priorities, then two better paths can be selected from them for comparison, and then the target parking path is determined, effectively improving the accuracy of automatic parking.

[0162] In this embodiment, the driving priorities include a first priority, a second priority, and a third priority, the first priority is higher than the second priority, and the second priority is higher than the third priority; determining the path priority of the candidate parking path according to the driving priority of the sub-region in the target area includes: if the target area only includes sub-regions with the first priority, then determine the path priority of the candidate parking path as the first level; if the target area includes sub-regions with the second priority and does not include sub-regions with the third priority, then determine the path priority of the candidate parking path as the second level; if the target area includes sub-regions with the third priority, then determine the path priority of the candidate parking path as the third level.

[0163] Specifically, the driving priorities can include a first priority, a second priority, and a third priority, where the first priority is the highest and the third priority is the lowest. The sub-regions with the first priority are areas recommended for vehicle driving, such as cement ground, asphalt road surface, etc., which are suitable for vehicle driving and have high safety; the sub-regions with the second priority are drivable areas, such as unmarked hard ground surfaces, which are suitable for vehicle driving but have a lower priority; the sub-regions with the third priority are areas not recommended for driving, such as lawns, water beaches, muddy lands, etc., which are not suitable for vehicle driving and should be avoided as much as possible.

[0164] If the target area only includes sub-areas of the first priority, then determine that the path priority of the candidate parking path for this target area is the first level, that is, the highest path priority. If the target area includes sub-areas of the second priority and does not include sub-areas of the third priority, for example, the target area includes sub-areas of the first priority and sub-areas of the second priority, then determine that the path priority of the candidate parking path for this target area is the second level. If the target area includes sub-areas of the third priority, for example, the target area includes sub-areas of the first priority, sub-areas of the second priority, and sub-areas of the third priority, then determine that the path priority of the candidate parking path is the third level, that is, the lowest path priority.

[0165] That is to say, it is possible to only use the recommended driving area for path planning to give priority to ensuring the safety and comfort of the path; it is also possible to combine the recommended driving area and the drivable area for path planning to take into account the feasibility and efficiency of the path; when necessary, the non-recommended driving area can also be considered to ensure the reachability of the path, but the driving distance in these areas should be minimized.

[0166] The beneficial effect of such a setting is that according to the driving priority of the sub-areas in the target area, the corresponding path priority is determined, so as to determine a better target parking path and improve the safety and comfort of automatic parking.

[0167] In this embodiment, determining the target parking path from the first parking path and the second parking path according to the path efficiency values of the first parking path and the second parking path includes: if the path efficiency value of the first parking path is less than the path efficiency value of the second parking path, then determine the difference between the path efficiency values of the first parking path and the second parking path; if the difference is less than or equal to a preset difference threshold, then determine the first parking path as the target parking path.

[0168] Specifically, after determining the first parking path and the second parking path, compare the path efficiency value of the first parking path with the path efficiency value of the second parking path. If the path efficiency value of the first parking path is equal to or greater than the path efficiency value of the second parking path, then since the path priority of the first parking path itself is higher than that of the second parking path, the first parking path can be directly determined as the target parking path.

[0169] If the path efficiency value of the first parking path is less than the path efficiency value of the second parking path, the difference in path efficiency values ​​between the first parking path and the second parking path is determined. A difference threshold is preset. If the difference is less than or equal to the preset difference threshold, it means that the path efficiency values ​​of the first parking path and the second parking path are not much different, and the first parking path can be determined as the target parking path; if the difference is greater than the preset difference threshold, the second parking path is determined as the target parking path, and a prompt message can also be issued on the vehicle screen or the user's terminal device, and the user confirms whether to select the second parking path as the target parking path. If there are no first-level and second-level candidate parking paths, the third-level candidate parking path is directly selected as the target parking path, and a prompt message can also be issued on the vehicle screen or the user's terminal device, and the user confirms whether to select the third parking path as the target parking path.

[0170] For example, if the path level of the first parking path is the first level, the path level of the second parking path is the second level, and the path efficiency value of the first parking path is lower than the path efficiency value of the second parking path, but the difference between the path efficiency values ​​of the two does not exceed a preset difference threshold, the first parking path is selected as the target parking path.

[0171] The beneficial effect of such a setting is that high-level candidate parking paths are given priority, the vehicle is prevented from passing through areas that are not suitable for driving as much as possible, and the safety and comfort of automatic parking are improved.

[0172] In this embodiment, the various weight coefficients in the path planning can be dynamically adjusted according to the real-time environment and user preferences, thereby improving the personalization capability of automatic parking, reducing the amount of real-time calculations, and improving the efficiency of automatic parking.

[0173] The parking path planning method provided in the embodiment of the present application obtains a ground image of the ground area where the vehicle is located, performs image recognition processing on the ground image, determines the ground material contained in the ground area where the vehicle is located, that is, obtains material information, and realizes the distinction of ground materials. According to the material information in the ground area where the vehicle is located, the ground area is divided into different sub-areas, and each sub-area can correspond to a ground material. According to the ground materials in different sub-areas, path planning is performed to obtain the target parking path, so that the vehicle can automatically park according to the target parking path. Avoid vehicles running over areas that are not suitable for driving, adapt to complex environments, reduce the impact on the environment, improve the personalization ability and safety of parking, and improve parking efficiency and user experience.

[0174] Figure 5 A schematic diagram of a parking path planning device provided in this application, such as Figure 5 As shown, the parking path planning device 50 provided in this embodiment includes:

[0175] A material determination unit 501 is configured to obtain a ground image of the ground area where the vehicle is located, and determine material information in the ground area where the vehicle is located according to the ground image; wherein, the material information represents the ground materials contained in the ground area where the vehicle is located.

[0176] A region division unit 502 is configured to divide the ground area where the vehicle is located into at least one sub-region according to the material information in the ground area where the vehicle is located; wherein, one type of material information corresponds to one or more sub-regions.

[0177] A path determination unit 503 is configured to determine a target parking path of the vehicle from a starting point to an ending point according to the material information corresponding to each sub-region in the ground area where the vehicle is located; wherein, the target parking path is used to instruct the vehicle to perform automatic parking.

[0178] In a possible implementation manner, the path determination unit 503 includes:

[0179] A target determination module is configured to determine a target area from the ground area where the vehicle is located according to the material information corresponding to the sub-regions in the ground area where the vehicle is located; wherein, the target area includes one or more sub-regions.

[0180] A candidate determination module is configured to determine a candidate parking path of the vehicle from the starting point to the ending point from the target area based on a preset path planning algorithm.

[0181] A target determination module is configured to determine a target parking path from each of the candidate parking paths according to the path information of each of the candidate parking paths; wherein, the path information represents the driving condition of the vehicle when driving along the candidate parking path.

[0182] In a possible implementation manner, the target determination module is specifically configured to:

[0183] Determine the driving priority of the sub-region according to the material information corresponding to the sub-regions in the ground area where the vehicle is located; wherein, the driving priority represents the recommended degree of the vehicle passing through the sub-region when driving.

[0184] Determine at least one target area according to the driving priorities of each sub-region.

[0185] In a possible implementation manner, the candidate determination module is specifically configured to:

[0186] Determine path nodes from the target area based on a preset path planning algorithm; wherein, the path nodes represent the possible positions that the vehicle may pass through when parking.

[0187] Determine the material cost value corresponding to the material information of the path node according to the preset association relationship; wherein, the preset association relationship represents the association relationship between the material information and the material cost value, and the material cost value represents the influence degree of the ground material on the vehicle driving;

[0188] Determine the target cost value of the path node according to the position of the starting point, the position of the ending point, the position of the path node, and the material cost value corresponding to the material information of the path node; wherein, the target cost value represents the quality degree of the path node;

[0189] Determine the candidate parking path of the vehicle from the starting point to the ending point according to the target cost value of the path node.

[0190] In a possible implementation manner, the target cost value includes a heuristic cost value, and the heuristic cost value represents the estimated cost from the path node to the ending point; the candidate determination module is specifically configured to:

[0191] Determine the distance information between the path node and the ending point according to the position of the ending point and the position of the path node;

[0192] Determine the heuristic cost value of the path node according to the distance information between the path node and the ending point, the material cost value corresponding to the material information of the path node, and the preset first weight.

[0193] In a possible implementation manner, the target cost value includes an actual cost value, and the actual cost value represents the actual path cost from the starting point to the path node; the candidate determination module is specifically configured to:

[0194] Determine the path length between the starting point and the path node according to the position of the starting point and the position of the path node;

[0195] Determine the actual cost value of the path node according to the path length between the starting point and the path node, the material cost value corresponding to the material information of the path node, and the preset second weight.

[0196] In a possible implementation manner, the path information includes at least one of the path length, the number of gear shifts, and the driving time; the target determination module is specifically configured to:

[0197] Determine the path efficiency value of the candidate parking path according to the path information of the candidate parking path; wherein, the path efficiency value represents the driving efficiency of the candidate parking path;

[0198] Determine the target parking path from each of the candidate parking paths according to the path efficiency values of each candidate parking path.

[0199] In a possible implementation, each candidate parking path corresponds to a target area, and the target area includes one or more sub-areas, and each sub-area corresponds to a driving priority; the target determination module is specifically configured to:

[0200] Determine the path priority of the candidate parking path according to the driving priorities of the sub-areas in the target area;

[0201] If there are candidate parking paths with at least two path priorities, determine a first parking path and a second parking path from the candidate parking paths; wherein, the path priority of the first parking path is higher than that of the second parking path;

[0202] Determine the target parking path from the first parking path and the second parking path according to the path efficiency values of the first parking path and the second parking path.

[0203] In a possible implementation, the driving priorities include a first priority, a second priority, and a third priority, the first priority is higher than the second priority, and the second priority is higher than the third priority; the target determination module is specifically configured to:

[0204] If the target area only includes sub-areas with the first priority, determine that the path priority of the candidate parking path is the first level;

[0205] If the target area includes sub-areas with the second priority and does not include sub-areas with the third priority, determine that the path priority of the candidate parking path is the second level;

[0206] If the target area includes sub-areas with the third priority, determine that the path priority of the candidate parking path is the third level.

[0207] In a possible implementation, the target determination module is specifically configured to:

[0208] If the path efficiency value of the first parking path is less than the path efficiency value of the second parking path, determine the difference between the path efficiency values of the first parking path and the second parking path;

[0209] If the difference is less than or equal to a preset difference threshold, determine the first parking path as the target parking path.

[0210] In a possible implementation, the area division unit 502 is specifically configured to:

[0211] Determine the material boundary in the ground area where the vehicle is located according to the material information in the ground area where the vehicle is located; wherein, the material boundary represents the boundary between different material information;

[0212] Divide the ground area where the vehicle is located according to the material boundary to obtain a plurality of sub-areas.

[0213] In a possible implementation, the material determination unit 501 is specifically configured to:

[0214] If there is an occluded area in the ground area of the ground image, determine the material information of the occluded area in the ground area as the preset material information.

[0215] The parking path planning device provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0216] Figure 6 It is a schematic structural diagram of an electronic device provided in an embodiment of the present application. As Figure 6 shown, the electronic device 60 provided in this embodiment includes: at least one processor 601 and a memory 602. Optionally, the device 60 further includes a communication component 603. Among them, the processor 601, the memory 602, and the communication component 603 are connected through a bus 604.

[0217] In a specific implementation process, at least one processor 601 executes the computer execution instructions stored in the memory 602, so that at least one processor 601 executes the above method.

[0218] The specific implementation process of the processor 601 can refer to the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0219] In the above embodiment, it should be understood that the processor may be a central processing unit (English: Central Processing Unit, abbreviated: CPU), and may also be other general-purpose processors, digital signal processors (English: Digital Signal Processor, abbreviated: DSP), application specific integrated circuits (English: Application Specific Integrated Circuit, abbreviated: ASIC), etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0220] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0221] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the buses in the accompanying drawings of this application are not limited to only one bus or one type of bus.

[0222] This application also provides a computer program product, including a computer program which, when executed by a processor, implements the above method.

[0223] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above method.

[0224] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk or an optical disk. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0225] An exemplary readable storage medium is coupled to the processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an Application Specific Integrated Circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0226] The division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0227] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0228] In addition, each functional unit in the various embodiments of the present invention may be integrated into one processing unit, may exist physically separately for each unit, or two or more units may be integrated into one unit.

[0229] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, etc., all kinds of media that can store program codes.

[0230] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When this program is executed, it executes the steps including the above method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disks, or optical discs, etc., all kinds of media that can store program codes.

[0231] Finally, it should be noted that: After considering the specification and practicing the invention disclosed herein, those skilled in the art will easily think of other implementation schemes of the present invention. The present invention aims to cover any variations, uses, or adaptive changes of the present invention. These variations, uses, or adaptive changes follow the general principles of the present invention and include common general knowledge or conventional technical means in the technical field not disclosed in the present invention. It is not limited to the precise structures already described and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A method for planning a parking path, characterized in that, Including: Obtain a ground image of the ground area where the vehicle is located, and determine the material information in the ground area where the vehicle is located according to the ground image; wherein, the material information characterizes the ground materials contained in the ground area where the vehicle is located; Divide the ground area where the vehicle is located into at least one sub-area according to the material information in the ground area where the vehicle is located; wherein, one kind of material information corresponds to one or more sub-areas; Determine a target parking path of the vehicle from the starting point to the ending point according to the material information corresponding to each sub-area in the ground area where the vehicle is located; wherein, the target parking path is used to instruct the vehicle to perform automatic parking.

2. The method according to claim 1, wherein, The determining the target parking path of the vehicle from the starting point to the ending point according to the material information corresponding to each sub-area in the ground area where the vehicle is located includes: Determine a target area from the ground area where the vehicle is located according to the material information corresponding to the sub-areas in the ground area where the vehicle is located; wherein, the target area includes one or more sub-areas; Based on a preset path planning algorithm, determine a candidate parking path of the vehicle from the starting point to the ending point from the target area; Determine a target parking path from each of the candidate parking paths according to the path information of each of the candidate parking paths; wherein, the path information characterizes the driving condition of the vehicle when driving along the candidate parking path.

3. The method according to claim 2, wherein The determining the target area from the ground area where the vehicle is located according to the material information corresponding to the sub-areas in the ground area where the vehicle is located includes: Determine the driving priority of the sub-area according to the material information corresponding to the sub-areas in the ground area where the vehicle is located; wherein, the driving priority characterizes the recommended degree of the vehicle passing through the sub-area when driving; Determine at least one target area according to the driving priorities of each sub-area.

4. The method according to claim 2, wherein The determining the candidate parking path of the vehicle from the starting point to the ending point from the target area based on a preset path planning algorithm includes: Based on a preset path planning algorithm, determine path nodes from the target area; wherein, the path nodes characterize the possible positions that the vehicle may pass through when parking; Determine a material cost value corresponding to the material information of the path node according to a preset association relationship; wherein, the preset association relationship characterizes the association relationship between the material information and the material cost value, and the material cost value characterizes the influence degree of the ground material on the vehicle driving; Determine the target cost value of the path node according to the position of the starting point, the position of the ending point, the position of the path node, and the material cost value corresponding to the material information of the path node; wherein, the target cost value characterizes the quality degree of the path node; Determine the candidate parking path of the vehicle from the starting point to the ending point according to the target cost value of the path node.

5. The method according to claim 4, wherein The target cost value includes a heuristic cost value, and the heuristic cost value characterizes the estimated cost from the path node to the ending point; the determining the target cost value of the path node according to the position of the starting point, the position of the ending point, the position of the path node, and the material cost value corresponding to the material information of the path node includes: Determine the distance information between the path node and the end point according to the position of the end point and the position of the path node; Determine the heuristic cost value of the path node according to the distance information between the path node and the end point, the material cost value corresponding to the material information of the path node, and a preset first weight.

6. The method according to claim 4, wherein The target cost value includes an actual cost value, and the actual cost value represents the actual path cost from the starting point to the path node; determining the target cost value of the path node according to the position of the starting point, the position of the end point, the position of the path node, and the material cost value corresponding to the material information of the path node includes: Determine the path length between the starting point and the path node according to the position of the starting point and the position of the path node; Determine the actual cost value of the path node according to the path length between the starting point and the path node, the material cost value corresponding to the material information of the path node, and a preset second weight.

7. The method according to claim 2, wherein The path information includes at least one of path length, number of gear shifts, and driving time; determining the target parking path from each of the candidate parking paths according to the path information of each of the candidate parking paths includes: Determine the path efficiency value of the candidate parking path according to the path information of the candidate parking path; wherein, the path efficiency value represents the driving efficiency of the candidate parking path; Determine the target parking path from each of the candidate parking paths according to the path efficiency values of each of the candidate parking paths.

8. The method according to claim 7, wherein Each candidate parking path corresponds to a target area, the target area includes one or more sub-areas, and each sub-area corresponds to a driving priority; determining the target parking path from each of the candidate parking paths according to the path efficiency values of each of the candidate parking paths includes: Determine the path priority of the candidate parking path according to the driving priority of the sub-areas in the target area; If there are at least two candidate parking paths with different path priorities, then determine a first parking path and a second parking path from the candidate parking paths; wherein, the path priority of the first parking path is higher than that of the second parking path; Determine the target parking path from the first parking path and the second parking path according to the path efficiency values of the first parking path and the second parking path.

9. The method according to claim 8, wherein The driving priority includes a first priority, a second priority, and a third priority, the first priority is higher than the second priority, and the second priority is higher than the third priority; Determining the path priority of the candidate parking path according to the driving priority of the sub-areas in the target area includes: If the target area only includes sub-areas with the first priority, then determine that the path priority of the candidate parking path is the first level; If the target area includes sub-areas with the second priority and does not include sub-areas with the third priority, then determine that the path priority of the candidate parking path is the second level; If the target area includes sub-areas of the third priority level, determine that the path priority of the candidate parking path is the third level.

10. The method according to claim 8, wherein The determining of the target parking path from the first parking path and the second parking path according to the path efficiency values of the first parking path and the second parking path includes: If the path efficiency value of the first parking path is less than the path efficiency value of the second parking path, determine the difference between the path efficiency values between the first parking path and the second parking path; If the difference is less than or equal to a preset difference threshold, determine the first parking path as the target parking path.

11. The method according to claim 1, wherein The dividing of the ground area where the vehicle is located into at least one sub-area according to the material information in the ground area where the vehicle is located includes: According to the material information in the ground area where the vehicle is located, determine the material boundary in the ground area where the vehicle is located; wherein, the material boundary represents the boundary between different material information; Divide the ground area where the vehicle is located according to the material boundary to obtain a plurality of sub-areas.

12. The method according to any one of claims 1-11, characterized in that, The determining of the material information in the ground area where the vehicle is located according to the ground image includes: If there is an occluded area in the ground area in the ground image, determine the material information of the occluded area in the ground area as the preset material information.

13. A parking path planning device, characterized in that, Includes: A material determination unit, configured to obtain a ground image of the ground area where the vehicle is located, and determine the material information in the ground area where the vehicle is located according to the ground image; wherein, the material information represents the ground material contained in the ground area where the vehicle is located; A region division unit, configured to divide the ground area where the vehicle is located into at least one sub-region according to the material information in the ground area where the vehicle is located; wherein, one material information corresponds to one or more sub-regions; A path determination unit, configured to determine a target parking path for the vehicle from the starting point to the ending point according to the material information corresponding to each sub-region in the ground area where the vehicle is located; wherein, the target parking path is used to instruct the vehicle to perform automatic parking.

14. An electronic device / computer-readable storage medium / computer program product, characterized in that The electronic device includes: a memory, a processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, so that the processor executes the method according to any one of claims 1-12; The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method according to any one of claims 1-12; and / or, The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the method according to any one of claims 1-12.

Images