Parking planning method, device, vehicle and storage medium

Abstract

The application discloses a parking planning method and device, a vehicle and a storage medium. The method comprises the following steps: acquiring a parking area corresponding to a target parking space; if the parking area meets a preset size condition, determining a plurality of induction areas in the parking area and different search priorities corresponding to each induction area; searching for a planning track of the vehicle parking in the parking area based on each induction area and the search priority corresponding to the induction area, and controlling the vehicle to park in the parking area according to the searched planning track. By determining a plurality of induction areas in the parking area corresponding to the target parking space, searching for the planning track of the vehicle parking in the parking area according to the search priority of each induction area, the vehicle can successfully search for the planning track of parking in the target parking space with low trafficability, and the search stability and success rate of the planning track are improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle control, and more specifically, to a parking planning method, device, vehicle, and storage medium. Background Art

[0002] In recent years, with the gradual development of autonomous driving technology, the automatic parking function of vehicles has become increasingly mature. Typically, if a vehicle searches for a planned trajectory to park in a target parking space, it will first determine a target position point in the target parking space. Based on the target position point, the planned trajectory for the vehicle to park in the target parking space is searched. After the vehicle completes parking according to the planned trajectory, the center of the vehicle's rear axle is exactly located at the target position point. However, this trajectory search method can often only obtain a planned trajectory for the vehicle to park in the target parking space once. In reality, there may be obstacles around the target parking space, and the area actually available for vehicle parking may be smaller than the area formed by the parking space lines. If the vehicle cannot search for a planned trajectory to park in the target parking space once, it will often abandon the target parking space and look for other parking spaces. This will result in a waste of parking space resources and is not suitable for actual parking environments. Summary of the Invention

[0003] In view of the above problems, the present application proposes a parking planning method, device, vehicle and storage medium, which can improve the success rate of planning the parking trajectory of the vehicle.

[0004] In a first aspect, an embodiment of the present application provides a parking planning method, the method comprising: obtaining a parkingable area corresponding to a target parking space, the parkingable area being the parking area of ​​a vehicle in the target parking space; if the parkingable area meets a preset size condition, determining a plurality of induction areas within the parkingable area and a different search priority corresponding to each of the induction areas, the induction area being the maximum movement area corresponding to the center of the rear axle of the vehicle within the parkingable area; based on each of the induction areas and its corresponding search priority, searching for a planned trajectory for the vehicle to park into the parkingable area, and controlling the vehicle to park into the parkingable area according to the searched planned trajectory.

[0005] In a second aspect, an embodiment of the present application provides a parking planning device, comprising: a first area acquisition module, a second area determination module, and a trajectory search module, wherein the first area acquisition module is used to acquire a parking area corresponding to a target parking space, wherein the parking area is the parking area of ​​the vehicle in the target parking space; the second area determination module is used to determine a plurality of inducing areas and a different search priority corresponding to each inducing area within the parking area if the parking area meets a preset size condition, wherein the inducing area is the maximum movement area corresponding to the rear axle center of the vehicle within the parking area; the trajectory search module is used to search for a planned trajectory for the vehicle to park into the parking area based on each inducing area and its corresponding search priority, and control the vehicle to park into the parking area according to the searched planned trajectory.

[0006] In a third aspect, an embodiment of the present application provides a vehicle comprising: one or more processors; a memory; and one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the parking planning method provided in the first aspect above.

[0007] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a program code is stored. The program code can be called by a processor to execute the parking planning method provided in the first aspect above.

[0008] The solution provided by this application obtains a parking area corresponding to a target parking space, where the parking area is the parking area of ​​the vehicle in the target parking space. If the parking area meets a preset size requirement, multiple guiding areas are determined within the parking area, along with different search priorities corresponding to each guiding area. The guiding area is the maximum movement area of ​​the vehicle's rear axle center within the parking area. Based on each guiding area and its corresponding search priority, a planned trajectory for the vehicle to park in the parking area is searched, and the vehicle is controlled to park in the parking area according to the searched planned trajectory. By determining multiple guiding areas within the parking area corresponding to the target parking space and searching for the planned trajectory of the vehicle to park in the parking area according to the search priority of each guiding area, the vehicle can successfully search for a planned trajectory for a target parking space with lower traffic access, and improves the stability and success rate of the planned trajectory search. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A bird's-eye view of the environment in which the vehicle is located in an embodiment of the present application is shown.

[0011] Figure 2 A schematic diagram showing the recognition results of the vehicle's environment in an embodiment of the present application is shown.

[0012] Figure 3 A flowchart of a parking planning method provided by an embodiment of the present application is shown.

[0013] Figure 4 A flowchart of a parking planning method provided in another embodiment of the present application is shown.

[0014] Figure 5 A schematic diagram of multiple induction regions in an embodiment of the present application is shown.

[0015] Figure 6 A specific flow chart of step S240 in another embodiment of the present application is shown.

[0016] Figure 7 A specific flow chart of step S250 in another embodiment of the present application is shown.

[0017] Figure 8 A schematic diagram showing the specific process of step S251 in another embodiment of the present application is shown.

[0018] Figure 9 Another specific flow chart of step S250 in another embodiment of the present application is shown.

[0019] Figure 10 A flowchart of a parking planning method provided in yet another embodiment of the present application is shown.

[0020] Figure 11 A schematic diagram of a virtual boundary in an embodiment of the present application is shown.

[0021] Figure 12 A schematic diagram of a target parking area in an embodiment of the present application is shown.

[0022] Figure 13 A schematic diagram of the structure of a parking planning device provided in an embodiment of the present application is shown.

[0023] Figure 14A structural block diagram of a vehicle provided in an embodiment of the present application is shown.

[0024] Figure 15 A structural block diagram of a computer-readable storage medium provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0026] The following introduces the application scenarios of the parking planning method provided in the embodiments of the present application.

[0027] The parking planning method provided in the embodiment of the present application is applied to vehicles in an automatic parking scenario. Generally, if a vehicle needs to automatically park into a target parking space, the vehicle can obtain environmental images of the vehicle's environment based on pre-installed onboard surround-view cameras. The vehicle can be equipped with at least four surround-view cameras to obtain environmental images around the vehicle and the target parking space. The vehicle can then stitch together the environmental images obtained by each camera to obtain a bird's-eye view of the vehicle's environment, such as Figure 1 The vehicle can identify the passable area and obstacle boundaries and parking space corners based on this bird's-eye view. The recognition results are shown as follows: Figure 2 In this case, if the target parking space has a traversable area boundary and an obstacle boundary around it, the vehicle can determine the size parameters of the parking area in the target parking space based on the recognition results. In this case, the size parameters of the parking area in the target parking space may be smaller than the size parameters of the target parking space, making it difficult for the vehicle to search for a planned trajectory that can park in the parking area in one go.

[0028] Therefore, the inventors proposed the parking planning method, device, vehicle and storage medium provided in the embodiments of the present application. Multiple induction areas can be determined within the parkingable area corresponding to the target parking space, and the planned trajectory of the vehicle parking in the parkingable area can be searched according to the search priority of each induction area, so that the vehicle can successfully search for the planned trajectory for parking in the target parking space with lower traffic access, and the search stability and success rate of the planned trajectory can be improved.

[0029] The parking planning method provided in the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0030] See also Figure 3 , Figure 3 A flow chart of a parking planning method according to an embodiment of the present application is shown. Figure 3 The process shown is described in detail. The parking planning method may specifically include the following steps:

[0031] Step S110: Acquire a parking area corresponding to a target parking space, where the parking area is a parking area for a vehicle in the target parking space.

[0032] In an embodiment of the present application, after determining a target parking space for automated parking, the vehicle can determine the actual available parking area within the target parking space based on the traversable area and obstacle identification results of the vehicle's surroundings. It is understood that in real-world environments, obstacles may exist within the target parking space, rendering some areas unavailable for parking. Therefore, the vehicle can first determine a portion of the target parking space within the target parking space that is available for parking, defining it as the available parking area, and simultaneously determining the dimensions of the available parking area. Obviously, the dimensions of the available parking area corresponding to the target parking space must be smaller than or equal to the dimensions of the target parking space. It is understood that if the available parking area is smaller than the target parking space, the vehicle may not be able to search for a planned trajectory that can park in the target parking space in one go. Therefore, the vehicle can subsequently determine multiple guiding areas within the available parking area and search for the vehicle's planned trajectory based on the guiding areas. This allows the vehicle's planned trajectory for parking in the available parking area to be divided into multiple segments, ultimately successfully searching for a planned trajectory that can park in the target parking space.

[0033] In some embodiments, if the size parameters of the parking area corresponding to the target parking space are smaller than the size parameters of the vehicle itself, it is obvious that the vehicle cannot be parked in the parking area at this time. In this case, the vehicle can select another target parking space in the environment and perform the above process of obtaining the parking area corresponding to the target parking space again. At the same time, the vehicle can also inform the user through a human-computer interaction interface such as a large screen on the vehicle computer that the vehicle cannot be parked in the target parking space at this time, so that the user can handle it more easily.

[0034] In some embodiments, the target parking space is typically a rectangular area. The vehicle can also process the parkingable area corresponding to the target area as a rectangular area, with the long and short sides of this rectangular area parallel to the long and short sides of the target parking space, respectively. In other words, if the vehicle's recognition results indicate an irregular obstacle boundary on the long side of the target parking space, the vehicle can select the line parallel to the long side that intersects the obstacle boundary and is farthest from the long side of the target parking space as the line on which the long side of the parkingable area lies. Similarly, the line on which the short side of the parkingable area lies can be determined, thereby determining the parkingable area corresponding to the target parking space.

[0035] Step S120: If the parking area meets the preset size condition, a plurality of inducing areas are determined within the parking area, and a different search priority is corresponding to each of the inducing areas.

[0036] In the embodiments of the present application, the induction area is a maximum movement area corresponding to the rear axle center of the vehicle in the parkable area. That is, when the parkable area meets the preset size condition, the maximum movement area corresponding to the rear axle center of the vehicle during the process of parking the vehicle in the parkable area is determined as the multiple induction areas corresponding to the parkable area, so as to subsequently search for the planning track of parking the vehicle in the parkable area based on the multiple induction areas. The vehicle determines the traffic condition of the parkable area, that is, whether the parkable area is easy to park, by the preset size condition. If the size parameter of the parkable area meets the preset size condition, it is considered that the vehicle can park in the parkable area, but the traffic condition of the parkable area is low, and it is difficult for the vehicle to search for a planning track directly parking in the parkable area. At this time, the vehicle can determine multiple induction areas in the parkable area, and determine a corresponding search priority for each induction area, so as to subsequently search for the planning track of parking the vehicle in the parkable area based on the multiple induction areas and the corresponding search priorities.

[0037] In some embodiments, the vehicle can not only determine the traffic condition of the parkable area by comparing the size parameter of the parkable area with the preset size condition, but also determine the traffic condition of the parkable area by the distance between the parking edge of the parkable area and the nearest obstacle boundary or the passable area boundary. Obviously, the vehicle enters the parkable area from the parking edge. If the parking edge of the parkable area is close to the obstacle boundary or the passable area boundary, the obstacle boundary or the passable area boundary may affect the traffic condition of the parkable area, resulting in that the vehicle cannot park in the parkable area at one time, that is, the parkable area belongs to a low-traffic parking space. Therefore, the vehicle can also obtain the distance between the parking edge of the parkable area and the nearest obstacle boundary or the nearest passable area boundary. If the distance is less than a preset distance, it is determined that the parkable area belongs to a low-traffic parking space, and then multiple induction areas are determined in the parkable area for parking planning. Specifically, the preset distance for determining the traffic condition of the parkable area can be set to 4 m. That is, if the distance between the parking edge of the parkable area and the nearest obstacle boundary or the nearest passable area boundary is less than 4 m, it is considered that the parkable area is a low-traffic parking space at this time.

[0038] In some embodiments, a vehicle can determine preset size conditions based on its own size parameters. For example, a vehicle can use the vehicle's width + 0.3m as the first width in the preset size conditions, and the vehicle's length + 0.3m as the first length in the preset size conditions. If the length of the target parking space's accessible area is less than the first length (vehicle length + 0.3m), or the width of the accessible area is less than the first width (vehicle width + 0.3m), the accessible area is considered to meet the preset size conditions and is a low-traffic parking space. The vehicle can then assist in parking planning by determining multiple guiding areas within the accessible area. Obviously, if the length of the accessible area is greater than or equal to the first length, and the width of the accessible area is greater than or equal to the first width, then there is a high probability that the vehicle can park in the accessible area all at once, meaning that the accessible area is a normal parking space. It should be understood that if the length or width of the parking area is less than the minimum parking requirement for the vehicle, that is, the length of the parking area is less than the length of the vehicle body or the width of the parking area is less than the width of the vehicle body, that is, the vehicle cannot park in the parking area no matter what, then the vehicle can output a prompt message to inform the user that the target parking space is too small to accommodate the vehicle, and select another parking space whose size parameters meet the minimum parking requirements as the target parking space.

[0039] Step S130 : searching for a planned trajectory for the vehicle to park in the parkable area based on each of the inducing areas and the corresponding search priority, and controlling the vehicle to park in the parkable area according to the searched planned trajectory.

[0040] In an embodiment of the present application, after determining multiple guiding zones within a parking area and the different search priorities associated with each guiding zone, the vehicle can search for a planned trajectory for the vehicle to enter the parking area based on the guiding zones and their corresponding search priorities. It is understood that if the size parameters of the parking area meet preset size requirements, the vehicle may not be able to search for a planned trajectory that can park in the parking area all at once. Therefore, the vehicle can sequentially search for feasible planned trajectories based on the multiple guiding zones. While controlling the vehicle to move along the currently searched planned trajectory, the vehicle can search in real time for a more optimal planned trajectory that is closer to the target parking point based on the guiding zones with higher search priorities. The vehicle can then move along the searched more optimal planned trajectory, ultimately enabling the vehicle to successfully park in the parking area.

[0041] Specifically, the planned trajectory for a one-time parking zone searched by the vehicle refers to a planned trajectory that directly uses the target parking point in the zone as the endpoint and searches for a parking trajectory from the vehicle's current position into the zone. However, due to the low accessibility of the zone, the vehicle cannot directly search for such a planned trajectory. Therefore, based on the search priority, the target point within the decoy zone closer to the parking edge is selected as the endpoint and a planned trajectory is searched for from the vehicle's current position into the decoy zone. While controlling the vehicle along the searched planned trajectory, the vehicle searches for planned trajectories into higher-priority decoy zones in real time until a planned trajectory is found that can park into the highest-priority decoy zone. At this point, the vehicle can successfully park in the zone by following this planned trajectory.

[0042] The lower the search priority of the guidance area, the closer it is to the parking edge of the available area, and the higher the probability of finding a planned trajectory for parking in the guidance area. It is worth noting that if the vehicle only searches for a planned trajectory for parking in a guidance area that is not of the highest priority, then after the vehicle moves along the planned trajectory, the vehicle body may not be able to park completely in the available area, and there may be parts of the area outside the available area. Therefore, when the vehicle moves along the planned trajectory corresponding to the guidance area that is not of the highest priority, as the distance from the target location gradually decreases, it can also search in real time whether there is a planned trajectory for parking in a guidance area with a higher priority. If so, it can move along the planned trajectory for parking in the guidance area with a higher priority. Repeating this process will allow the vehicle to eventually park in the guidance area with the highest priority, at which point the vehicle will also be parked in the available area.

[0043] The parking planning method provided in an embodiment of the present application obtains a parking area corresponding to a target parking space, where the parking area is the parking area of ​​the vehicle in the target parking space. If the parking area meets a preset size requirement, multiple guiding areas are determined within the parking area, and each guiding area has a different search priority. The guiding area is the maximum movement area of ​​the rear axle center of the vehicle within the parking area. Based on each guiding area and its corresponding search priority, a planned trajectory for the vehicle to park in the parking area is searched, and the vehicle is controlled to park in the parking area according to the searched planned trajectory. By determining multiple guiding areas within the parking area corresponding to the target parking space and searching for the planned trajectory of the vehicle to park in the guiding areas according to the priority order of the guiding areas, the search for the vehicle's planned trajectory is suitable for narrow parking spaces with low traffic volume, thereby improving the stability and success rate of trajectory search.

[0044] See also Figure 4 , Figure 4A flow chart of a parking planning method according to another embodiment of the present invention is shown. Figure 4 The process shown is described in detail. The parking planning method may specifically include the following steps:

[0045] Step S210: Acquire a parking area corresponding to a target parking space, where the parking area is a parking area for a vehicle in the target parking space.

[0046] In the embodiment of the present application, step S210 can refer to the contents of other embodiments and will not be repeated here.

[0047] Step S220: If the length of the parking area is less than a first preset length and the width of the parking area is less than a first preset width, it is determined that the parking area meets a preset size condition.

[0048] In an embodiment of the present application, the first preset length is the minimum parking space length required for the vehicle to park in the target parking space in one go, and the first preset width is the minimum parking space width required for the vehicle to park in the target parking space in one go. After determining the parkingable area corresponding to the target parking space, the vehicle can obtain the coordinate data of the reference corner of the parkingable area in the world coordinate system, thereby determining the length and width of the parkingable area. The vehicle can also determine the parkingable area by comparing the length and width of the parkingable area with the minimum parking space length and width required for the vehicle to park in the target parking space in one go. Obviously, if the length of the parkingable area is less than the first preset length and the width is also less than the first preset width, that is, the parkingable area meets the preset size requirements, it indicates that it is difficult for the vehicle to park in the parkingable area in one go under normal circumstances. In this case, the parking planning method provided by the present application can be used to determine multiple guiding areas within the parkingable area, and then, based on the multiple guiding areas, a planned trajectory is obtained that allows the vehicle to ultimately park in the parkingable area.

[0049] Step S230 : If the parking area meets the preset size condition, determining the first boundary area within the parking area based on the width of the parking area and the width of the vehicle.

[0050] In an embodiment of the present application, if the parking area corresponding to the target parking space meets the preset size conditions, it indicates that the vehicle can be parked in the parking area, but it may not be possible to search for a planned trajectory for parking in the parking area in one go. At this time, the vehicle can determine a first boundary area within the parking area, so as to facilitate the subsequent determination of multiple induction areas based on the first boundary area, and then search for a planned trajectory for the vehicle to park in the parking area based on the induction area. The first boundary area within the parking area refers to the maximum movement area of ​​the rear axle center of the vehicle within the parking area after the vehicle has parked in the parking area. Figure 5As shown, the area formed by the left boundary threshold, the right boundary threshold, and the front and rear edges of the parking area is the first boundary area corresponding to the vehicle within the parking area. It can be understood that if the vehicle has parked in the parking area and the center of the vehicle's rear axle is above the left boundary threshold, this indicates that the left boundary of the vehicle body has contacted the left boundary of the parking area. To ensure that the vehicle body is not scratched during parking, the vehicle is no longer offset to the left. In other words, the left boundary threshold is the maximum range within which the center of the vehicle's rear axle can move to the left after the vehicle enters the parking area. Similarly, the right boundary threshold is the maximum range within which the center of the vehicle's rear axle can move to the right after the vehicle enters the parking area. After determining the left and right boundary thresholds, the vehicle can use the area formed by the left and right boundary thresholds and the front and rear edges of the parking area as the first boundary area.

[0051] It's understandable that to prevent the vehicle from colliding with the left and right boundaries of the parking area during parking, a left boundary threshold and a right boundary threshold are determined within the parking area to limit the vehicle's left and right movement during parking. However, the vehicle will inevitably enter the parking area from the parking edge, which means it will inevitably collide with the parking edge. Furthermore, the first boundary area is only used to determine the scope of the guidance area, so that when the vehicle searches for a planned trajectory using any point within the guidance area as the target point, the planned trajectory will not lead the vehicle into a collision with the left or right boundaries of the parking area. Therefore, the first boundary area determined by the vehicle can only limit the left and right movement range of the rear axle center, without having to limit the front and rear movement range. In other words, after determining the left and right boundary thresholds, the vehicle can directly determine the first boundary area corresponding to the parking area based on the front and rear boundaries of the parking area.

[0052] Specifically, in Figure 5 In the parking space coordinate system shown, the left boundary threshold and the right boundary threshold in the first boundary area corresponding to the parking area can be determined by the following formula:

[0053] Left boundary threshold = -(actual parking space width - vehicle width) / 2

[0054] Right boundary threshold = (actual parking space width - vehicle width) / 2

[0055] Step S240: Based on the target parking spot in the parkable area and the first boundary area, a plurality of the guiding areas and a different search priority corresponding to each of the guiding areas are determined.

[0056] In this embodiment of the present application, the target parking point is the position of the rear axle center within the parkable area after the vehicle has parked in the parkable area. Parking in the parkable area may mean the vehicle is located in the exact center of the area, meaning that the front and rear edges of the vehicle are equidistant from the boundary line of the parkable area, and the left and right edges of the vehicle are also equidistant from the boundary line of the parkable area. In this case, the point corresponding to the rear axle center within the parkable area can be used as the target parking point, thereby defining multiple guidance areas within the first boundary area based on the target parking point within the parkable area. Obviously, the target parking point within the parkable area must be located within the first boundary area, as the first boundary area is used to limit the maximum range of movement of the rear axle center within the parkable area after the vehicle has parked in the parkable area, and this area clearly includes the target parking point. At the same time, the target parking point should be located inside the induction area with the highest search priority. Therefore, the distance between the parking end point of the planned trajectory corresponding to the induction area with the highest search priority and the target parking point is closer than the distance between the parking end point and the target parking point of the planned trajectory obtained by searching in other induction areas.

[0057] In some embodiments, as Figure 6 As shown, the method of determining multiple guiding areas and different search priorities corresponding to each guiding area within the first boundary area based on the target parking point in step S240 can be implemented by the following steps:

[0058] Step S241: determining a plurality of reference induction domains based on the size of the first boundary area.

[0059] In the embodiments of the present application, the size parameters of parking spaces in different locations are not the same, and after the vehicle identifies the environmental bird's-eye view of the parking space, the size parameters of the target parking space corresponding to the parkable area obtained can also be different, and the length and width of different vehicles are also not the same. Therefore, the size parameters of the first boundary region determined by the vehicle in the parkable area are also not the same. Obviously, the size of the first boundary region is related to the actual width of the vehicle and the width of the parkable area. It can be understood that if the size of the first boundary region is larger, it indicates that the vehicle can allow a larger range of left and right deviation after parking in the parkable area, and at this time the vehicle can obtain a planning track of an induced area with a higher search priority, and can also be parked in the parkable area more easily. In this case, the vehicle can set the range of the induced area to be smaller and the number of the induced area to be less, so as to simplify the search process of the planning track. Therefore, the number and size of the induced area corresponding to the parkable area can be determined by the vehicle according to the size of the first boundary region, which is not limited here. Specifically, the vehicle can first determine a plurality of reference induced domains based on the size of the first boundary region, and then obtain a plurality of induced areas corresponding to the parkable area based on each reference induced domain. The number of reference induced domains is the same as the number of induced areas.

[0060] In some embodiments, the method for determining a plurality of reference induced domains based on the size of the first boundary region can also be implemented in the following manner:

[0061] determining a plurality of reference center points based on the size of the first boundary region; determining an induced radius corresponding to each reference center point based on a second distance between each reference center point and the target parking point, the induced radius corresponding to each reference center point being positively correlated with the second distance; and determining a plurality of reference induced domains by respectively taking each reference center point as the center and each induced radius corresponding to each reference center point as the radius.

[0062] Specifically, each reference induced domain can be a circular region, and the vehicle determines the number of reference induced domains and the center position of each reference induced domain based on the size of the first boundary region, and determines the radius of each reference induced domain based on the distance between the center position and the target parking point. The number of reference induced domains can be negatively correlated with the size of the first boundary region, that is, the smaller the size of the first boundary region, the more the number of reference center points and the number of reference induced domains. The size of the induced radius is positively correlated with the second distance between the reference center point and the target parking point, that is, the farther the distance between the reference center point and the target parking point, the larger the induced radius of the reference induced domain.

[0063] After the vehicle determines each reference induction domain center (reference center point) and radius (induction radius) based on the size of the first boundary region, the reference induction domain is obtained. Specifically, as shown in Figure 5 the vehicle can establish a parking space coordinate system with the target parking point as the origin, and after determining the number of reference induction domains, determine the reference center point corresponding to each reference induction domain on the Y-axis of the parking space coordinate system, and determine the induction radius corresponding to each reference center point based on the distance between each reference center point and the origin of the coordinate system (target parking point), thereby obtaining multiple reference induction domains. Wherein, each reference induction domain does not overlap, so as to avoid the repetition of the randomly selected target position points in different induction regions subsequently, therefore, the vehicle can determine the induction radius corresponding to the reference center point with larger Y-axis coordinate value based on the distance between the adjacent two reference center points on the Y-axis.

[0064] In some other embodiments, each reference induction domain can also be a rectangular region, and after the vehicle determines multiple reference center points based on the size of the first boundary region, the length of each reference induction domain can be determined based on the distance between each reference center point and the target parking point, and then multiple reference induction domains are obtained on the Y-axis of the parking space coordinate system.

[0065] Step S242: determining the intersection region corresponding to each reference induction domain and the first boundary region respectively, and taking each intersection region as the induction region to obtain multiple induction regions.

[0066] In the embodiments of the present application, the multiple reference induction domains obtained by the vehicle based on the size of the first boundary region do not necessarily completely lie within the first boundary region, that is, there can be a part of the reference induction domain outside the first boundary region. At this time, if the vehicle directly searches for the planning trajectory of the vehicle from the current position to the parking point in the reference induction domain based on any target position point within the reference induction domain, if the target position point is outside the first boundary region, the vehicle can collide with the boundary of the parkable region during the travel process, causing the vehicle to scratch. Therefore, after the vehicle determines multiple reference induction domains, the range of the first boundary region needs to be further limited to obtain multiple induction regions that can be searched for trajectories. Specifically, the vehicle can take the intersection region corresponding to each reference induction domain and the first boundary region respectively as the induction region to obtain multiple induction regions.

[0067] Step S243: determining the search priority corresponding to each induction region based on the first distance of each induction region from the target parking point, wherein the search priority corresponding to the induction region is negatively correlated with the first distance.

[0068] In an embodiment of the present application, after determining multiple guidance areas, the vehicle can determine the search priority corresponding to each guidance area based on the first distance between each guidance area and the target parking point. Specifically, each guidance area is the intersection of the reference guidance domain and the first boundary area, and the centerline of the first boundary area is the Y-axis of the parking space coordinate system. At the same time, the reference center point of each reference guidance domain is also on the Y-axis of the parking space coordinate system. Therefore, the vehicle can use the distance between the reference center point in each guidance area and the origin of the parking space coordinate system as the first distance between each guidance area and the target parking point. Obviously, if the distance between the guidance area and the target parking point is close, then the planned trajectory for parking in the guidance area searched by the vehicle can allow the vehicle to park more accurately in the parkingable area, so the search priority of the guidance area can be higher. Among them, the search priority of the guidance area including the target parking point is the highest priority among all guidance areas.

[0069] Step S250: Based on each of the inducing areas and the corresponding search priorities, searching for a planned trajectory for the vehicle to park in the parkable area, and controlling the vehicle to park in the parkable area according to the searched planned trajectory.

[0070] In some embodiments, the vehicle may search for a planned trajectory for parking in a parking area in the following manner:

[0071] Step S251: searching for a planned trajectory of the vehicle from the current position into each of the guidance areas in descending order of the search priority until a first planned trajectory of the vehicle from the current position into the target parking area is found.

[0072] In this embodiment of the present application, the target parking area is any one of the multiple inductive areas. After the vehicle has determined the multiple inductive areas and their corresponding search priorities, it can then search for a planned trajectory for the vehicle to park in the available parking area based on the inductive areas, in descending order of search priority. It is understood that the reason the vehicle sets up multiple inductive areas within the available parking area and plans its trajectory based on these inductive areas is because the size parameters of the available parking area corresponding to the target parking space are relatively small, making it impossible for the vehicle to directly search for a planned trajectory with the target parking point as the parking endpoint. Therefore, the vehicle sets up multiple inductive areas near the parking edge within the available parking area and searches for a planned trajectory using random points within the inductive areas as target locations. This method has a higher success rate for finding a feasible planned trajectory than searching directly based on the target parking point. Furthermore, while the vehicle is driving along the planned trajectory for the parking area, it can also search in real time for planned trajectories in inductive areas that are closer to the target parking point and update the planned trajectory, thereby ultimately parking the vehicle in the available parking area. Therefore, when there are multiple guidance areas, the vehicle will prioritize trajectory search based on the guidance area closer to the target parking point, that is, it will search the planned trajectories in order of search priority from high to low. If the first planned trajectory that parks in the target parking area has been searched, the vehicle will no longer search for the planned trajectory of the guidance area with a lower search priority than the target parking area.

[0073] For example Figure 5 As shown, the vehicle determines four reference guidance domains based on the size parameters of the first boundary region, resulting in four guidance regions. The search priority between guidance regions 1 and 4 gradually decreases. Guiding region 1 is formed by the intersection of the reference guidance domain, formed with the target parking point as the origin, and the first boundary region. The vehicle will preferentially select a target location within guidance region 1 as the parking destination and search for a planned trajectory from the current location to the target location. If not, a different target location is selected within guidance region 2 as the parking destination and a planned trajectory from the current location to the target location is searched for. If not, the vehicle continues to search for planned trajectories into guidance regions 3 and 4. If so, guidance region 2 is selected as the target parking region and the planned trajectory into guidance region 2 is used as the first planned trajectory. The vehicle is then controlled to travel along the first planned trajectory and no longer searches for planned trajectories in guidance regions 3 and 4. While the vehicle is moving along the first planned trajectory, the vehicle can also search in real time whether there is a planned trajectory from the current position to any target position point within the induction area 1. If so, the planned trajectory is updated and the vehicle can park in the induction area 1 according to the new planned trajectory.

[0074] In some embodiments, as Figure 8As shown, the vehicle can search for the first planned trajectory in the following manner:

[0075] Step S2511: sorting the plurality of induced regions based on the order of the search priority from high to low to obtain a sorting result.

[0076] Step S2512: Using the first guidance area in the sorting result as a reference parking area and the target location point in the reference parking area as a parking destination, searching for a planned trajectory of the vehicle from the current position to park in the reference parking area.

[0077] In this embodiment of the present application, the target location is any location within the target parking area. The vehicle can sort the multiple induction areas in descending order of search priority, with the first in the sorted results being the induction area with the highest search priority, i.e., the induction area closest to the target parking point. While searching for a planned trajectory to enter the parking area, the vehicle can select any target location within each induction area based on the sorted results, and search for a planned trajectory for the vehicle to enter the induction area from its current location.

[0078] It should be understood that the target parking spot must be included in the induction area with the highest search priority, but the planned trajectory obtained by the vehicle based on the search of the induction area with the highest search priority will not necessarily park the vehicle accurately at the target parking spot in the parking area. This is because even if the vehicle searches for a feasible planned trajectory for the vehicle in the induction area with the highest search priority, the parking end point of this planned trajectory is a random position point in the induction area, and not necessarily the target parking point in the induction area. However, this search method of randomly selecting a planned trajectory with a parking end point in the induction area can reduce the amount of calculation during the search and improve the search efficiency of the planned trajectory. Of course, in some embodiments, when searching for a planned trajectory in the induction area with the highest search priority, the vehicle can also directly use the target parking point therein as the target position point to search for the planned trajectory.

[0079] Step S2513: If no planned trajectory is found this time, the next guidance area in the sorted result is used as the reference parking area, and the process returns to the step of searching for a planned trajectory for the vehicle from the current position to the reference parking area with the target location within the reference parking area as the parking destination, until a first planned trajectory for the vehicle from the current position to the target parking area is found.

[0080] In the embodiment of the present application, if the vehicle fails to find the first planned trajectory for parking from the current position to the target parking area based on the reference parking point within the reference parking area, the vehicle may use the next guidance area in the sorted result as the reference parking area and re-execute the step of searching for the planned trajectory for parking from the current position to the reference parking area with the target position within the reference parking area as the parking destination. Figure 5 As shown, the vehicle first searches for the highest-priority parking zone, Zone 1, as a reference parking zone. It then selects any target location within the zone as the parking destination and searches for a planned trajectory. If no planned trajectory is found, Zone 2 is used as a reference parking zone, and a planned trajectory from the current location into the reference parking zone is searched again. This continues until a planned trajectory that enters the target parking zone is found, which is then used as the first planned trajectory.

[0081] Step S252: If the search priority corresponding to the target parking area is not the highest priority, controlling the vehicle to park at a first target position in the target parking area according to the first planned trajectory.

[0082] In this embodiment of the present application, the distance between the first target position and the endpoint position of the first planned trajectory is less than a first preset distance. If the vehicle searches for a first planned trajectory, but the search priority of the target parking area corresponding to the first planned trajectory is not the highest priority, for example, the vehicle searches for a first planned trajectory for parking guidance area 2 or guidance area 3, but does not search for a planned trajectory for parking guidance area 1. In other words, the vehicle may be limited by its own posture data and unable to obtain a planned trajectory for parking guidance area 1. In this case, the vehicle can first move according to the first planned trajectory, change the vehicle's posture data, and after reaching the first target position in the target parking area, the vehicle can search for a planned trajectory for parking guidance area 1 based on real-time position data.

[0083] Step S253: updating the current position to the first target position, returning to the step of searching for the planned trajectory of the vehicle from the current position into each of the guidance areas in descending order of the search priority, until the first planned trajectory of the vehicle from the current position into the next target parking area is found.

[0084] In an embodiment of the present application, after the vehicle has reached the first target location based on the first planned trajectory, the vehicle can re-search the planned trajectories for parking in each parking guidance area from the current location according to the search priority order from high to low, until the vehicle has found the first planned trajectory for parking in the next target parking area from the current location. For example, if the vehicle searches sequentially according to the search priority order and finds the first planned trajectory for parking in guidance area 3, the vehicle can first travel along the first planned trajectory to the first target location that is less than a first preset distance from the parking end point. At this point, the vehicle can again begin searching for trajectories according to the search priority order to determine whether there is a planned trajectory for parking in guidance area 1 or guidance area 2.

[0085] Step S254: If the search priority corresponding to the target parking area is the highest priority, the vehicle is controlled to park in the target parking area according to the first planned trajectory.

[0086] In this embodiment of the present application, if the search priority corresponding to the target parking area is the highest priority, it indicates that the first planned trajectory obtained by the vehicle search at this time can guide the vehicle to park in the parking area, and the vehicle can then move according to the first planned trajectory.

[0087] In other embodiments, Figure 9 As shown, the vehicle can also search for a planned trajectory for parking in a parking area in the following ways:

[0088] Step S255: searching for a planned trajectory of the vehicle from the current position to each of the guidance areas in descending order of the search priority until a second planned trajectory of the vehicle from the current position to the target parking area is found.

[0089] In the embodiment of the present application, the target docking area is any one of the plurality of inducing areas. Step S255 can refer to the contents of other embodiments and will not be described in detail here.

[0090] Step S256: If the search priority corresponding to the target parking area is not the highest priority, the current position is updated to the target position of the second planned trajectory, and the process returns to the step of searching for the planned trajectory of the vehicle from the current position to each of the guidance areas in descending order of the search priority until the second planned trajectory of the vehicle from the current position to the next target parking area is found.

[0091] In this embodiment of the present application, the distance between the target position and the endpoint of the second planned trajectory is less than a second preset distance. If the target parking area that the vehicle is parking into based on the second planned trajectory is not the highest priority guidance area, indicating that the vehicle may not be able to fully park into the available parking area based on the second planned trajectory, the vehicle may further search for a second planned trajectory that allows the vehicle to park from the target position into the next target parking area, based on the order of search priority from highest to lowest, at a location near the endpoint of the second planned trajectory, i.e., the target position on the second planned trajectory. For example, if the vehicle can only search for the second planned trajectory that allows the vehicle to park into guidance area 2, then the vehicle may not be able to fully park into the available parking area based on the second planned trajectory. Therefore, the vehicle may search for a planned trajectory that allows the vehicle to park from the target position into each guidance area, based on the order of search priority from highest to lowest, at a target position on the second planned trajectory that is less than the second preset distance from the endpoint, until a second planned trajectory is found that allows the vehicle to park from the target position into the next target parking area.

[0092] Step S257: If the search priority corresponding to the target parking area is the highest priority, a planned trajectory for the vehicle to park in the parkable area is determined based on all the second planned trajectories currently obtained, and the vehicle is controlled to park in the parkable area according to the searched planned trajectory.

[0093] In the embodiments of the present application, the process of obtaining the second planned trajectory through the above steps may be repeated, and each time the steps are repeated, the vehicle will obtain a different second planned trajectory. That is, while searching for the second planned trajectory, the vehicle may update its current position multiple times and repeat the above steps multiple times to obtain multiple different second planned trajectories. Alternatively, it may only obtain a single second planned trajectory, directly obtaining a second planned trajectory that parks in the induction zone with the highest search priority. If the vehicle repeats the above steps multiple times, obtaining multiple different second planned trajectories, the vehicle may process the second planned trajectories obtained in each cycle to obtain a final planned trajectory that parks in the permitted parking area. Specifically, if the vehicle obtains multiple second planned trajectories, the vehicle may delete the trajectory between the target position and the parking end point from each second planned trajectory before the last obtained second planned trajectory, thereby obtaining a single planned trajectory that parks from the vehicle's current position into the induction zone with the highest search priority. If the vehicle obtains only one second planned trajectory, the vehicle may directly use the second planned trajectory as the planned trajectory for parking in the permitted parking area.

[0094] The parking planning method provided in an embodiment of the present application determines the length and width of the parking area corresponding to the target parking space to determine whether the parking area meets preset size requirements. If the preset size requirements are met, multiple guiding areas are determined within the parking area. A first planned trajectory for the vehicle to park from the current position into the target parking area is searched sequentially according to the search priority corresponding to each guiding area from high to low. If the search priority corresponding to the target parking area is not the highest priority, the vehicle is controlled to travel to the first target position based on the first planned trajectory. A first planned trajectory for the vehicle to park from the first target position into the next target parking area is searched again sequentially according to the search priority from high to low. By sorting the search priorities of the guiding areas from high to low, the planned trajectory for the vehicle to park into the parking area is divided into multiple segments for search, enabling the vehicle to park in parking areas with lower traffic flow and improving the search success rate and stability of the planned trajectory.

[0095] See also Figure 10 , Figure 10 A flow chart of a parking planning method according to another embodiment of the present application is shown. Figure 10 The process shown is described in detail. The parking planning method may specifically include the following steps:

[0096] Step S310: Acquire a parking area corresponding to a target parking space, where the parking area is a parking area for a vehicle in the target parking space.

[0097] Step S320: If the parking area meets the preset size conditions, multiple guidance areas and different search priorities corresponding to each guidance area are determined within the parking area. The guidance area is the maximum movement area corresponding to the center of the rear axle of the vehicle within the parking area.

[0098] In the embodiment of the present application, step S310 and step S320 can refer to the contents of other embodiments and will not be repeated here.

[0099] Step S330: Determine the passable area boundary, obstacle boundary and parking space corner points based on the surrounding image information obtained by the vehicle, wherein the passable area boundary is the boundary of the maximum passable area detected by the vehicle, the obstacle boundary is the area boundary obtained by obstacle identification in the environment where the vehicle is located, and the parking space corner points include the position points of all parking spaces obtained by parking space corner point identification in the environment where the vehicle is located.

[0100] In the embodiment of the present application, when the vehicle is performing parking control, the vehicle can obtain image information of the vehicle's surroundings based on the vehicle's surround view camera, such as Figure 1Based on these image information, the boundaries of the passable area around the vehicle, the boundaries of obstacles and the corner points of the parking space are determined, as shown in Figure 2 As shown, subsequent vehicles can determine a smaller and more stable area that can be used for parking control based on this information, thereby improving the efficiency of parking control. Among them, the passable area boundary determined by the vehicle based on image information refers to the boundary of the maximum passable area that the vehicle can currently detect. Obviously, the passable area boundary is limited by factors such as the acquisition range of the vehicle's surround-view camera and the position of obstacles in the current environment; the obstacle boundary refers to the area obtained by obstacle recognition in the vehicle's environment. The obstacle boundary can mark the boundaries of all obstacles that hinder the vehicle's passage within the passable area boundary corresponding to the vehicle, so that the vehicle can bypass these obstacle boundaries during subsequent trajectory search; the parking space corner point refers to the parking space corner point data corresponding to all parking spaces that can be used for parking within the vehicle's passable area, which may include information such as the coordinate data of the corner points of all parking spaces in the world coordinate system.

[0101] In some embodiments, a vehicle can use a pre-trained traversable area recognition model to identify surrounding image information captured by the vehicle, thereby obtaining a traversable area boundary output by the model. A pre-trained obstacle recognition model can also be used to identify obstacle areas on the surrounding image information, thereby obtaining an obstacle boundary output by the model. A pre-trained parking space corner point recognition model can also be used to identify surrounding image information, thereby obtaining the location points corresponding to all parking spaces around the vehicle, as output by the model. Specifically, the vehicle can obtain surrounding image information from an installed surround camera. First, the vehicle can use the maximum range represented by the surrounding image information as a pending traversable area boundary. For example, if the maximum environmental image range that the vehicle can capture is 50m*50m, the vehicle will first use this 50m*50m range boundary as the traversable area boundary. Subsequently, the vehicle can use the traversable area recognition model and the obstacle recognition model to obtain all traversable area boundaries and obstacle boundaries within the 50m*50m range. Finally, the vehicle can perform parking space corner point recognition within the traversable area boundary to obtain the location points of all parking spaces within the traversable area boundary. That is to say, Figure 2 The recognition results are shown.

[0102] In some embodiments, after a vehicle identifies obstacle boundaries based on surrounding image information, if portions of the obstacle boundaries are completely within the traversable area boundary, the vehicle can perform a fitting operation on the obstacle boundaries within the traversable area boundary. This involves determining a minimum polygonal area that encompasses the obstacle area and replacing the internal obstacle boundary with the boundary of this polygonal area. This allows the vehicle to directly use the polygonal area boundary as the obstacle boundary when performing parking control, improving collision detection efficiency when determining whether the vehicle will collide with the obstacle boundary, and thereby improving the efficiency of parking control.

[0103] Step S340: Based on the parking space corner point, a virtual boundary corresponding to the target parking space is determined, where the virtual boundary is a minimum trajectory search area for parking control of the vehicle.

[0104] In an embodiment of the present application, the parking space corner points may include coordinate data corresponding to the position points of all parking spaces within the passable area. When performing parking control, the vehicle must first select a target parking space from among all parking spaces. Then, based on the coordinate data corresponding to the parking space corner points of the target parking space, the vehicle determines the virtual boundary corresponding to the target parking space. This determines the minimum trajectory search area within which the vehicle can perform parking control. It is understandable that the passable area boundary and obstacle boundary determined by the vehicle are susceptible to changes due to factors such as the viewing angle of the vehicle's surround-view camera and changes in position caused by vehicle movement, resulting in unstable areas. However, the virtual boundary determined by the vehicle can be a closed area formed by sequentially connecting multiple fixed position points. Its size is pre-set, and its position is associated with the fixed target parking space, which is not subject to movement or other changes. Therefore, after obtaining the parking space corner points, the vehicle can determine a stable virtual boundary based on the parking space corner points of the target parking space and the pre-set multiple position points. This stable virtual boundary can then be used to determine the target parking area for vehicle parking control.

[0105] In some implementations, the vehicle may obtain the virtual boundary corresponding to the parking area in the following manner:

[0106] Based on the target corner point corresponding to the target parking space among the parking space corner points, a target position corresponding to the center of the rear axle of the vehicle after the vehicle is parked and first coordinate data of the target position in a world coordinate system are determined; based on the first coordinate data and a boundary position point, a virtual boundary corresponding to the target parking space is determined, where the boundary position point is determined based on a minimum trajectory search area for parking control of the vehicle.

[0107] Specifically, the parking space corner points determined by the vehicle based on the surrounding image information may include information such as the coordinate data of all corner points corresponding to all parking spaces that can be collected around the vehicle in the world coordinate system. Figure 11 As shown, before the vehicle performs parking control, it can first select a target parking space for parking from all parking spaces, and use the corner point corresponding to this target parking space as the target corner point. Based on the coordinate data corresponding to the target corner point in the world coordinate system, the target position corresponding to the center of the rear axle of the vehicle after the vehicle is parked in the target parking space and the first coordinate data of the target position in the world coordinate system are determined. It can be understood that the target position is the coordinate data corresponding to the center of the rear axle of the vehicle in the world coordinate system under the assumption that the vehicle has been parked in the target parking space, but because the actual vehicle has not yet parked in the target parking space, the vehicle needs to indirectly calculate and determine the first coordinate data corresponding to the target position through the coordinate data corresponding to the target corner point of the fixed position in the world coordinate system. After determining the first coordinate data corresponding to the target position after the vehicle is parked in the target parking space, the vehicle can determine the virtual boundary corresponding to the target parking space based on the first coordinate data and the preset boundary position point. For details, please refer again. Figure 11 The virtual boundary corresponding to the target parking space can be an area formed by connecting multiple boundary position points in sequence. The vehicle can pre-determine the relative position relationship between each boundary position point corresponding to the virtual boundary and the target position corresponding to the center of the vehicle's rear axle. Therefore, after the vehicle determines the target parking space based on the surrounding image information and determines the target position corresponding to the vehicle in the target parking space, it can directly determine the virtual boundary corresponding to the target parking space based on the pre-set relative position relationship between each boundary position point and the target position.

[0108] Specifically, the vehicle may determine the first length corresponding to the target parking space based on the second coordinate data of the target corner point in the world coordinate system:

[0109]

[0110] Among them, d is used to represent the first length corresponding to the target parking space. The coordinate data corresponding to the two corner points of the parking side of the target parking space in the world coordinate system are (x1, y1) and (x2, y2), and the coordinate data corresponding to the other two corner points of the target parking space are (x3, y3) and (x4, y4).

[0111] Thereafter, the vehicle may determine a first angle and a fourth length based on the first length, the second length of the vehicle body, and the third length between the center of the front end of the vehicle and the center of the rear axle, wherein the first angle is the angle between the parking edge of the target parking space and the X-axis of the world coordinate system, and the fourth length is the distance between the center of the rear axle and the parking edge:

[0112]

[0113] Where d is the first length of the target parking space, L is the second length of the vehicle body, r is the third length between the center of the rear axle and the center of the front end of the vehicle, l is the fourth length, which is the distance between the center of the rear axle of the vehicle and the parking edge of the target parking space when the vehicle is parked in the target parking space, and θ is the first angle, which is the angle between the parking edge of the target parking space and the X-axis of the world coordinate system.

[0114] Finally, the vehicle can determine the first coordinate data based on the first angle and the fourth length. Specifically, after obtaining the first angle and the fourth length based on the above steps, the first coordinate data (x, y) of the center of the rear axle of the vehicle in the world coordinate system when the vehicle is parked in the target parking space can be calculated using the following formula:

[0115]

[0116] After the vehicle determines the first coordinate data corresponding to the target position after parking in the target parking space, it can determine the virtual boundary corresponding to the target parking space based on the first coordinate data and the preset boundary position points. Specifically, the virtual boundary corresponding to the target parking space can be an area formed by connecting multiple boundary position points in sequence. The vehicle can pre-determine the relative positional relationship between each boundary position point corresponding to the virtual boundary and the target position corresponding to the center of the vehicle's rear axle. Therefore, after the vehicle determines the target parking space based on the surrounding image information and determines the target position of the vehicle in the target parking space, it can directly determine the virtual boundary corresponding to the target parking space based on the pre-set relative positional relationship between each boundary position point and the target position.

[0117] Step S350: Fusing the virtual boundary, the passable area boundary, and the obstacle boundary to obtain a target parking area.

[0118] In the embodiments of the present application, after obtaining the virtual boundary corresponding to the passable area boundary, the obstacle boundary and the target parking space respectively, the vehicle can fuse the passable area boundary, the obstacle boundary and the virtual boundary to obtain a target parking area that can be used for parking control, so as to subsequently search for a planned track of the vehicle parking into the target parking space in the target parking area. It can be understood that the virtual boundary determined by the vehicle based on the angle point of the target parking space is only a region in a preset range and with a fixed size, which is drawn with the position of the target parking space as a reference. That is to say, the virtual boundary corresponding to the target parking space determined by the vehicle does not include the passable area boundary and the obstacle boundary, and at this time, the virtual boundary corresponding to the target parking space cannot represent whether there is an obstacle in the virtual boundary, and the vehicle cannot directly perform effective parking control based on the virtual boundary corresponding to the target parking space. Therefore, after determining the virtual boundary corresponding to the target parking space based on the angle point of the target parking space, the vehicle can fuse the virtual boundary with the passable area boundary and the obstacle boundary, so that the vehicle can search for a planned track in the target parking area after fusion.

[0119] In some embodiments, the vehicle can determine a target parking area for searching for a planned track in the following manner:

[0120] obtain a first area boundary on the passable area boundary that is in the virtual boundary and a second area boundary on the obstacle boundary that is in the virtual boundary; and fuse the first area boundary, the second area boundary and the virtual boundary to obtain the target parking area.

[0121] Specifically, after determining the virtual boundary corresponding to the target parking space, the vehicle can fuse the virtual boundary with the passable area boundary and the obstacle boundary to obtain a target parking area that can be used for parking control. As shown in Figure 12 , the vehicle can take the area boundary on the passable area boundary that is in the virtual boundary as a first area boundary, and take the boundary on the obstacle boundary that is in the virtual boundary as a second area boundary. After determining the first area boundary and the second area boundary, the vehicle can fuse the first area boundary, the second area boundary and the virtual boundary to obtain a relatively stable target parking area that can be used for parking control. Subsequently, the vehicle can search for a track of the vehicle parking into the target parking space in the target parking area, which can not only ensure that the vehicle can search for an effective parking planned track, but also reduce the search range of the planned track through the stability of the area and improve the search efficiency.

[0122] Step S360: searching, based on each of the inducing areas and the corresponding search priority, a planning trajectory of the vehicle parking into the parkable area in the target parking area, and controlling the vehicle to park into the parkable area according to the searched planning trajectory.

[0123] In the embodiments of the present application, after the vehicle determines the target parking area corresponding to the parkable area through the above steps, the vehicle can search, in the target parking area, a planning trajectory of the vehicle parking into the parkable area based on the multiple inducing areas in the parkable area. As can be known from the determination process of the target parking area, the vehicle searches for the planning trajectory in the target parking area, which can ensure that at least one feasible planning trajectory can be obtained, and can avoid problems such as instability of the searched planning trajectory, time-consuming of the search process, and degradation of the calculation amount of the search process, thereby improving the search efficiency of the planning trajectory.

[0124] In some embodiments, the vehicle can perform collision detection on the planning trajectory corresponding to the vehicle in the target parking area, and determine the planning trajectory of the vehicle parking into the parkable area based on the result of the collision detection. Specifically, after determining the target parking area, the vehicle can search for a planning trajectory in the target parking area, and determine at least one planning trajectory of the vehicle parking into the target parking space. Then, the vehicle can perform collision detection on all the determined planning trajectories based on the passable area boundary, the obstacle boundary and the virtual boundary in the target parking area, that is, determine whether the vehicle will collide with the obstacle boundary, the passable area boundary or the virtual boundary in the target parking area during the travel according to the planning trajectory. Obviously, if the detection result shows that the vehicle will collide with any boundary, the planning trajectory is invalid, that is, the vehicle cannot park into the parkable area according to the planning trajectory. If the detection result shows that the vehicle will not collide with any boundary, the vehicle can take the planning trajectory as a valid trajectory and park into the parkable area according to the valid trajectory.

[0125] The parking planning method provided in an embodiment of the present application determines the traversable area boundary, obstacle boundary, and parking space corner points based on the surrounding image information obtained from the vehicle; determines the virtual boundary corresponding to the target parking space based on the parking space corner points; fuses the virtual boundary, the traversable area boundary, and the obstacle boundary to obtain a target parking area; and searches the target parking area for the planned trajectory of the vehicle parking in the traversable area based on each of the inducing areas within the traversable area and its corresponding search priority. Thus, the virtual boundary area corresponding to the target parking space is determined based on the parking space corner points, and then a stable target parking area is determined based on the traversable area boundary and the virtual boundary, thereby reducing the trajectory search range and improving trajectory search efficiency. Furthermore, different collision detection algorithms are used for different types of area boundaries within the target parking area, which can reduce the computational complexity of trajectory detection and improve parking trajectory detection efficiency.

[0126] See also Figure 13 , which shows a block diagram of a parking planning device 200 provided in one embodiment of the present application. The parking planning device 200 includes a first area acquisition module 210, a second area determination module 220, and a trajectory search module 230. The first area acquisition module 210 is configured to acquire a parking area corresponding to a target parking space. The parking area is the area where a vehicle is parked in the target parking space. The second area determination module 220 is configured to, if the parking area meets a preset size requirement, determine multiple guiding areas within the parking area and a different search priority for each guiding area. The guiding area is the maximum movement area of ​​the vehicle's rear axle center within the parking area. The trajectory search module 230 is configured to search for a planned trajectory for the vehicle to park in the parking area based on each guiding area and its corresponding search priority.

[0127] As a possible implementation, the second area determination module 220 includes a boundary determination unit and an area determination unit. The boundary determination unit is configured to determine a first boundary area within the parking area based on the width of the parking area and the width of the vehicle. The area determination unit is configured to determine multiple induction areas and corresponding search priorities based on a target parking point within the parking area and the first boundary area. The target parking point is the location of the rear axle center of the vehicle after parking.

[0128] As a possible implementation method, the area determination unit is also used to determine multiple reference induction domains based on the size of the first boundary area; determine the boundary area and each intersection area, and use the intersection area corresponding to each reference induction domain as the induction area to obtain multiple induction areas; based on the first distance between each induction area and the target parking point, determine the search priority corresponding to each induction area, wherein the search priority corresponding to the induction area is negatively correlated with the first distance.

[0129] As a possible implementation method, the area determination unit is also used to determine multiple reference center points based on the size of the first boundary area; determine the induction radius corresponding to each reference center point based on the second distance between each reference center point and the target parking point, and the induction radius corresponding to the reference center point is positively correlated with the second distance; and determine a circular area with each reference center point as the center of the circle and the induction radius corresponding to each reference center point to obtain multiple reference induction areas.

[0130] As a possible implementation, the trajectory detection device 200 further includes a conditional judgment module configured to determine that the parking area meets a preset size condition if the length of the parking area is less than a first preset length and the width of the parking area is less than a first preset width, wherein the first preset length is the minimum parking space length required for a vehicle to park in the target parking space in one go, and the first preset width is the minimum parking space width required for a vehicle to park in the target parking space in one go.

[0131] As a possible implementation, the trajectory search module 230 includes a trajectory search unit, a first judgment unit, a trajectory operation unit, and a second judgment unit. The trajectory search unit is configured to sequentially search for a planned trajectory for the vehicle from the current position into each of the guided parking areas in descending order of search priority until a first planned trajectory for the vehicle from the current position into a target parking area is found, where the target parking area is any of the multiple guided parking areas. The first judgment unit is configured to, if the search priority corresponding to the target parking area is not the highest priority, control the vehicle to park into a first target position in the target parking area according to the first planned trajectory, where the distance between the first target position and the end position of the first planned trajectory is less than a preset distance. The trajectory operation unit is configured to update the current position to the first target position and return to the step of sequentially searching for a planned trajectory for the vehicle from the current position into each of the guided parking areas in descending order of search priority until a first planned trajectory for the vehicle from the current position into the next target parking area is found. The second judgment unit is configured to, if the search priority corresponding to the target parking area is the highest priority, control the vehicle to park into the target parking area according to the first planned trajectory.

[0132] As a possible implementation, the trajectory search unit is further configured to sort the plurality of inducing areas based on a search priority order from high to low to obtain a sorting result; using the first inducing area in the sorting result as a reference parking area, and taking a target position point within the reference parking area as a parking end point, searching for a planned trajectory for the vehicle to be parked from the current position into the reference parking area, where the target position point is any position point within the target parking area; if no planned trajectory is found this time, using the next inducing area in the sorting result as the reference parking area, and returning to the step of searching for a planned trajectory for the vehicle to be parked from the current position into the reference parking area with the target position point within the reference parking area as the parking end point, until a first planned trajectory for the vehicle to be parked from the current position into the target parking area is found.

[0133] As a possible embodiment, the trajectory search module 230 further includes a trajectory search unit, a third judgment unit, and a fourth judgment unit. The trajectory search unit is configured to sequentially search for a planned trajectory for the vehicle from the current position into each of the guidance zones in descending order of search priority until a second planned trajectory for the vehicle from the current position into a target parking zone is found, where the target parking zone is any of the multiple guidance zones. The third judgment unit is configured to, if the search priority corresponding to the target parking zone is not the highest priority, update the current position to the target position of the second planned trajectory, and return to the step of sequentially searching for a planned trajectory for the vehicle from the current position into each of the guidance zones in descending order of search priority until a second planned trajectory for the vehicle from the current position into the next target parking zone is found, where the target position is less than a preset distance from the end point of the second planned trajectory. The fourth judgment unit is configured to, if the search priority corresponding to the target parking zone is the highest priority, determine a planned trajectory for the vehicle into the available parking zone based on all currently obtained second planned trajectories, and control the vehicle to park into the available parking zone according to the searched planned trajectory.

[0134] As a possible implementation, the trajectory search module 230 further includes a first boundary acquisition unit, a second boundary acquisition unit, a search area determination unit, and a trajectory search unit. The first boundary acquisition unit is configured to determine the passable area boundary, obstacle boundary, and parking space corner points based on the surrounding image information obtained by the vehicle. The passable area boundary is the boundary of the maximum passable area detected by the vehicle, the obstacle boundary is the boundary of the area obtained by obstacle recognition in the vehicle's environment, and the parking space corner points include the locations of all parking spaces obtained by parking space corner point recognition in the vehicle's environment. The second boundary acquisition unit is configured to determine a virtual boundary corresponding to the target parking space based on the parking space corner points. The virtual boundary is the minimum trajectory search area for vehicle parking control. The search area determination unit is configured to fuse the virtual boundary, passable area boundary, and obstacle boundary to obtain a target parking area. The trajectory search unit is configured to search for a planned trajectory for the vehicle to park in the passable area within the target parking area based on each induction area and its corresponding search priority.

[0135] As a possible implementation, the second boundary acquisition unit is further used to determine, based on the target corner point corresponding to the target parking space among the parking space corner points, the target position corresponding to the rear axle center of the vehicle after the vehicle is parked and the first coordinate data of the target position in the world coordinate system; based on the first coordinate data and the boundary position point, determine the virtual boundary corresponding to the target parking space, where the boundary position point is determined based on the minimum trajectory search area for parking control of the vehicle.

[0136] As a possible implementation, the search area determination unit is further used to obtain a first area boundary on the passable area boundary that is within the virtual boundary, and a second area boundary on the obstacle boundary that is within the virtual boundary; the first area boundary, the second area boundary and the virtual boundary are merged to obtain the target parking area.

[0137] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0138] In several embodiments provided in this application, the coupling between modules may be electrical, mechanical or other forms of coupling.

[0139] In addition, the functional modules in the various embodiments of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module. The above-mentioned integrated modules may be implemented in the form of hardware or software functional modules.

[0140] In summary, the solution provided by this application obtains a parking area corresponding to a target parking space, where the parking area is the parking area of ​​the vehicle in the target parking space. If the parking area meets preset size requirements, multiple guiding areas are determined within the parking area, along with different search priorities corresponding to each guiding area. The guiding area is the maximum movement area of ​​the vehicle's rear axle center within the parking area. Based on each guiding area and its corresponding search priority, a planned trajectory for the vehicle to park in the parking area is searched, and the vehicle is controlled to park in the parking area according to the searched planned trajectory. By determining multiple guiding areas within the parking area corresponding to the target parking space and searching for the planned trajectory of the vehicle to park in the parking area according to the search priority of each guiding area, the vehicle can successfully search for a planned trajectory for a target parking space with lower traffic access, and improves the stability and success rate of the planned trajectory search.

[0141] Please refer to Figure 14 , which shows a structural block diagram of a vehicle 400 provided in an embodiment of the present application. The vehicle 400 in the present application may include one or more of the following components: a processor 410, a memory 420, and one or more application programs, wherein the one or more application programs may be stored in the memory 420 and configured to be executed by the one or more processors 410, and the one or more programs are configured to execute the method described in the aforementioned method embodiment.

[0142] Processor 410 may include one or more processing cores. Processor 410 utilizes various interfaces and circuits to connect various components within the vehicle. It performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 420, as well as accessing data stored in memory 420. Optionally, processor 410 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). Processor 410 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem handles wireless communications. It is understood that the modem may not be integrated into processor 410 and may be implemented separately via a communications chip.

[0143] The memory 420 may include a random access memory (RAM) or a read-only memory (ROM). The memory 420 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 420 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the various method embodiments described below, etc. The data storage area may also store data created by the vehicle during use (such as a phone book, audio and video data, chat history data, etc.).

[0144] Please refer to Figure 15 , which shows a block diagram of a computer-readable storage medium provided in an embodiment of the present application. The computer-readable medium 800 stores program code, which can be called by a processor to execute the method described in the above method embodiment.

[0145] The computer-readable storage medium 800 can be an electronic memory such as a flash memory, an EEPROM (Electrically Erasable Programmable Read-Only Memory), an EPROM, a hard disk, or a ROM. Alternatively, the computer-readable storage medium 800 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 800 has storage space for program code 810 for executing any of the method steps described above. These program codes can be read from or written to one or more computer program products. The program code 810 can be compressed, for example, in a suitable form.

[0146] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A parking planning method, characterized in that: The method comprises: Obtaining a parking area corresponding to a target parking space, where the parking area is a parking area for a vehicle in the target parking space; If the parking area meets a preset size condition, determining a plurality of guiding areas within the parking area and a different search priority corresponding to each guiding area, wherein the guiding area is a maximum movement area of ​​the rear axle center of the vehicle within the parking area; Based on each of the inducing areas and the corresponding search priority, a planned trajectory for the vehicle to park in the parkable area is searched, and the vehicle is controlled to park in the parkable area according to the searched planned trajectory.

2. The method according to claim 1, characterized in that The step of determining a plurality of guiding areas within the parking area and a different search priority corresponding to each guiding area includes: determining a first boundary area within the parking area based on the width of the parking area and the width of the vehicle; Based on a target parking point in the parkable area and the first boundary area, a plurality of the induction areas and a different search priority corresponding to each of the induction areas are determined, wherein the target parking point is the position point of the center of the rear axle after the vehicle is parked.

3. The method according to claim 2, characterized in that The determining of the plurality of inducing areas and the different search priorities corresponding to each inducing area based on the target parking spot within the parkable area and the first boundary area includes: determining a plurality of reference induction domains based on a size of the first boundary region; Determine an intersection region corresponding to the first boundary region and each of the reference inducing domains, and use each of the intersection regions as the inducing region to obtain a plurality of the inducing regions; The search priority corresponding to each of the inducing areas is determined based on a first distance between each of the inducing areas and the target parking point, wherein the search priority corresponding to the inducing area is negatively correlated with the first distance.

4. The method according to claim 3, characterized in that The determining of a plurality of reference induction domains based on the size of the first boundary area includes: determining a plurality of reference center points based on a size of the first boundary area; determining an inductive radius corresponding to each reference center point based on a second distance between each reference center point and the target parking point, wherein the inductive radius corresponding to the reference center point is positively correlated with the second distance; A circular area is determined with each reference center point as the center of the circle and the induction radius corresponding to each reference center point to obtain multiple reference induction domains.

5. The method according to claim 1, wherein Before determining a plurality of inducing areas within the parking area and a different search priority corresponding to each inducing area if the parking area meets the preset size condition, the method further includes: If the length of the parkingable area is less than a first preset length and the width of the parkingable area is less than a first preset width, then the parkingable area is determined to meet the preset size conditions, where the first preset length is the minimum parking space length that the vehicle must meet in one parking space, and the first preset width is the minimum parking space width that the vehicle must meet in one parking space.

6. The method according to any one of claims 1 to 5, characterized in that The step of searching for a planned trajectory for the vehicle to park in the parkable area based on each of the inducing areas and the corresponding search priority, and controlling the vehicle to park in the parkable area according to the searched planned trajectory, includes: searching, in descending order of the search priorities, for a planned trajectory of the vehicle from the current position to park in each of the inducing areas until a first planned trajectory of the vehicle from the current position to park in a target parking area is found, where the target parking area is any one of the multiple inducing areas; If the search priority corresponding to the target parking area is not the highest priority, controlling the vehicle to park at a first target position in the target parking area according to the first planned trajectory, where the first target position is less than a first preset distance from an end position of the first planned trajectory; Updating the current position to the first target position, returning to the step of searching for a planned trajectory of the vehicle from the current position into each of the guidance areas in descending order of the search priority until a first planned trajectory of the vehicle from the current position into the next target parking area is found; If the search priority corresponding to the target parking area is the highest priority, the vehicle is controlled to park in the target parking area according to the first planned trajectory.

7. The method according to claim 6, characterized in that The method of searching for a planned trajectory of the vehicle from the current position to the target parking area in descending order of the search priority until a first planned trajectory of the vehicle from the current position to the target parking area is found includes: Sorting the plurality of induced regions based on the order of the search priorities from high to low to obtain a sorting result; Taking the first inducing area in the sorting result as a target parking area and a target location point within the target parking area as a parking destination, searching for a planned trajectory of the vehicle from the current position to park in the target parking area, wherein the target location point is any location point within the target parking area; If no planned trajectory is found this time, the next inducing area in the sorted result is used as the target parking area, and the process returns to the step of using the target position point within the target parking area as the parking end point to search for a planned trajectory for the vehicle to park from the current position into the target parking area, until a first planned trajectory for the vehicle to park from the current position into the target parking area is found.

8. The method according to any one of claims 1 to 5, characterized in that The step of searching for a planned trajectory for the vehicle to park in the parkable area based on each of the inducing areas and the corresponding search priority, and controlling the vehicle to park in the parkable area according to the searched planned trajectory, includes: searching, in descending order of the search priorities, for a planned trajectory of the vehicle from the current position to park in each of the inducing areas until a second planned trajectory of the vehicle from the current position to park in a target parking area is found, where the target parking area is any one of the plurality of inducing areas; If the search priority corresponding to the target parking area is not the highest priority, updating the current position to the target position of the second planned trajectory, and returning to the step of searching for the planned trajectory of the vehicle from the current position to each of the guidance areas in descending order of the search priorities until a second planned trajectory for the vehicle to park from the current position to the next target parking area is found, and the distance between the target position and the end position of the second planned trajectory is less than a second preset distance; If the search priority corresponding to the target parking area is the highest priority, a planned trajectory for the vehicle to park in the parkable area is determined based on all currently obtained second planned trajectories, and the vehicle is controlled to park in the parkable area according to the searched planned trajectory.

9. The method according to any one of claims 1 to 5, characterized in that The step of searching for a planned trajectory for the vehicle to park in the parkable area based on each of the inducing areas and the corresponding search priority, and controlling the vehicle to park in the parkable area according to the searched planned trajectory, includes: Determining a passable area boundary, an obstacle boundary, and parking space corner points based on surrounding image information obtained by the vehicle, wherein the passable area boundary is the boundary of the maximum passable area detected by the vehicle, the obstacle boundary is the boundary of the area obtained by performing obstacle recognition on the environment in which the vehicle is located, and the parking space corner points include the position points of all parking spaces obtained by performing parking space corner point recognition on the environment in which the vehicle is located; Determining a virtual boundary corresponding to the target parking space based on the parking space corner point, the virtual boundary being a minimum trajectory search area for parking control of the vehicle; fusing the virtual boundary, the passable area boundary, and the obstacle boundary to obtain a target parking area; Based on each of the inducing areas and its corresponding search priority, a planned trajectory for the vehicle to park in the parkable area is searched within the target parking area, and the vehicle is controlled to park in the parkable area according to the searched planned trajectory.

10. The method according to claim 9, characterized in that The determining of the virtual boundary corresponding to the target parking space based on the parking space corner point includes: determining, based on a target corner point corresponding to the target parking space among the parking space corner points, a target position corresponding to the rear axle center of the vehicle after the vehicle is parked and first coordinate data of the target position in a world coordinate system; A virtual boundary corresponding to the target parking space is determined based on the first coordinate data and a boundary position point, wherein the boundary position point is determined based on a minimum trajectory search area for parking control of the vehicle.

11. The method according to claim 9, characterized in that The step of fusing the virtual boundary, the passable area boundary, and the obstacle boundary to obtain a target parking area includes: Acquire a first area boundary on a passable area boundary that is within the virtual boundary, and a second area boundary on an obstacle boundary that is within the virtual boundary; The first area boundary, the second area boundary, and the virtual boundary are merged to obtain the target parking area.

12. A trajectory planning device, characterized in that: The device comprises: A first area acquisition module is configured to acquire a parking area corresponding to a target parking space, wherein the parking area is a parking area for a vehicle in the target parking space; a second area determination module configured to determine, if the parking area meets a preset size condition, a plurality of guiding areas within the parking area and a different search priority corresponding to each guiding area, wherein the guiding area is a maximum movement area of ​​the rear axle center of the vehicle within the parking area; The trajectory search module is configured to search for a planned trajectory for the vehicle to park in the parkable area based on each of the inducing areas and the corresponding search priority, and control the vehicle to park in the parkable area according to the searched planned trajectory.

13. A vehicle, characterized in that: include: one or more processors; Memory; One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to perform the method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program code, which can be called by a processor to execute the method according to any one of claims 1 to 11.

Images