Parking control method and device, vehicle and storage medium

Abstract

This application discloses a parking control method, device, vehicle, and storage medium. The method determines the boundaries of the passable area, obstacle boundaries, and parking space corners based on surrounding image information obtained by the vehicle; based on the parking space corners, it determines the virtual boundary corresponding to the target parking space; it fuses the virtual boundary, the passable area boundary, and the obstacle boundary to obtain a target parking area; and based on the target parking area, it controls the vehicle to park in the target parking space. Determining the virtual boundary corresponding to the target parking space based on the parking space corners and fusing the virtual boundary with the passable area boundary and obstacle boundary yields a more stable target parking area. Simultaneously, by searching for the planned parking trajectory within the target parking area, the search range of the trajectory is reduced, improving the search efficiency of the parking trajectory.

Description

Technical Field

[0001] This application relates to the field of vehicle control, and more specifically, to a parking control method, apparatus, vehicle, and storage medium. Background Technology

[0002] In recent years, with the gradual development of vehicle control technology, the application of automatic parking has become increasingly mature. Typically, if a user requests automatic parking, the vehicle uses sensors such as radar or cameras to acquire images of its surroundings, identifies obstacles, and then searches for a passable parking trajectory within the identified images. However, the search range for this trajectory detection method is usually the maximum detection range that the vehicle's sensors can acquire. Since the maximum detection range of a vehicle's sensors varies in different real-world environments, the efficiency of trajectory detection is easily affected by the environment, thus impacting the vehicle's parking control. Summary of the Invention

[0003] In view of the above problems, this application proposes a parking control method, device, vehicle and storage medium, which can perform parking control in a more stable target parking area and improve the search efficiency of parking trajectory.

[0004] In a first aspect, embodiments of this application provide a parking control method, the method comprising: 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 obstacle identification of the environment in which the vehicle is located, and the parking space corner points include the location points of all parking spaces obtained by parking space corner point identification of the environment in which the vehicle is located; determining a virtual boundary corresponding to a target parking space based on the parking space corner points, wherein the virtual boundary is the minimum trajectory search area for the vehicle to perform parking control; fusing the virtual boundary, the passable area boundary, and the obstacle boundary to obtain a target parking area; and controlling the vehicle to park in the target parking space based on the target parking area.

[0005] Secondly, embodiments of this application provide a parking control device, the device comprising: a first area acquisition module, a second area determination module, an area fusion module, and a trajectory search module, wherein the first area acquisition module is used to determine the boundary of a passable area, the boundary of an obstacle, and the corner points of a parking space based on the surrounding image information obtained by the vehicle, the boundary of the passable area being the boundary of the maximum passable area detected by the vehicle, the boundary of the obstacle being the boundary of the area obtained by obstacle identification of the environment in which the vehicle is located, and the corner points of the parking space including the location points of all parking spaces obtained by corner point identification of the environment in which the vehicle is located; the second area determination module is used to determine the virtual boundary corresponding to the target parking space based on the corner points of the parking space, the virtual boundary being the minimum trajectory search area for the vehicle to perform parking control; the area fusion module is used to fuse the virtual boundary, the boundary of the passable area, and the boundary of the obstacle to obtain a target parking area; the trajectory search module is used to control the vehicle to park in the target parking space based on the target parking area.

[0006] Thirdly, embodiments of this application provide a vehicle, including: one or more processors; a memory; and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more application programs are configured to perform the parking control method provided in the first aspect above.

[0007] Fourthly, embodiments of this application provide a computer-readable storage medium storing program code, which can be invoked by a processor to execute the parking control method provided in the first aspect.

[0008] The solution provided in this application determines the boundaries of the passable area, obstacle boundaries, and parking space corners based on 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 identification of the vehicle's environment, and the parking space corners include the location points of all parking spaces obtained by parking space corner point identification of the vehicle's environment. Based on the parking space corners, a virtual boundary corresponding to the target parking space is determined, which is the minimum trajectory search area for parking control of the vehicle. The virtual boundary, the passable area boundary, and the obstacle boundary are fused to obtain the target parking area. Based on the target parking area, the vehicle is controlled to park in the target parking space. By determining the virtual boundary corresponding to the target parking space based on the parking space corners and fusing the virtual boundary with the passable area boundary and obstacle boundary, a more stable target parking area is obtained. At the same time, by searching the planned trajectory within the target parking area, the search range of the planned trajectory is reduced, and the trajectory search efficiency is improved. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

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

[0011] Figure 2 This illustration shows a schematic diagram of the result of a vehicle recognizing a bird's-eye view in an embodiment of this application.

[0012] Figure 3 A schematic flowchart of a parking control method provided in one embodiment of this application is shown.

[0013] Figure 4 A flowchart illustrating a parking control method provided in another embodiment of this application is shown.

[0014] Figure 5 A schematic diagram of the specific process of step S220 in another embodiment of this application is shown.

[0015] Figure 6 A schematic diagram of the specific process of step S230 in another embodiment of this application is shown.

[0016] Figure 7 A schematic diagram of the virtual boundary determined in an embodiment of this application is shown.

[0017] Figure 8 A schematic diagram of the target parking area determined in an embodiment of this application is shown.

[0018] Figure 9 A schematic diagram of the specific process of step S270 in another embodiment of this application is shown.

[0019] Figure 10 A schematic diagram of the first collision detection algorithm in an embodiment of this application is shown.

[0020] Figure 11 A schematic diagram of the second collision detection algorithm in an embodiment of this application is shown.

[0021] Figure 12 A schematic diagram of the third collision detection algorithm in an embodiment of this application is shown.

[0022] Figure 13 A schematic diagram of the parking control device provided in an embodiment of this application is shown.

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

[0024] Figure 15 A structural block diagram of a computer-readable storage medium provided in an embodiment of this application is shown. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0026] The following describes the application scenarios of the parking control method provided in the embodiments of this application.

[0027] The parking control method provided in this application is applied to vehicles in an automatic parking scenario. Typically, if a vehicle needs to park automatically, it can acquire environmental images of its surroundings using pre-installed surround-view cameras. The vehicle can be equipped with at least four surround-view cameras to obtain images of the environment around the vehicle. The vehicle can then stitch together the environmental images acquired by each camera to obtain a bird's-eye view of the vehicle's environment, such as... Figure 1 As shown, the bird's-eye view was used to identify the boundaries of passable areas, obstacles, and parking spaces. The identification results are as follows. Figure 2 As shown. Normally, in automatic parking mode, the vehicle can... Figure 2 Parking control is performed within the detection range shown. Specifically, the detection range is divided into multiple grids according to a preset step size. Starting from the grid where the vehicle is currently located, the system sequentially searches for passable grids adjacent to the current grid. If passable, it further searches for passable grids adjacent to the passable grid. After traversing all grids within the detection range, the vehicle obtains one or more passable parking trajectories, and parking control can then be performed according to one of these trajectories. However, in this case, the detection range for trajectory detection is usually determined based on the maximum range that the surround-view camera can capture. The boundaries of this detection range may change significantly due to vehicle movement or occlusion by environmental obstacles. Therefore, the parking trajectories detected by the vehicle have poor consistency, thus reducing the efficiency of parking control.

[0028] Therefore, the inventors have proposed a parking control method, device, computer equipment, and storage medium provided in the embodiments of this application. The virtual boundary corresponding to the target parking space can be determined based on the corner point of the parking space. The virtual boundary is then fused with the boundary of the passable area and the boundary of the obstacle to obtain a more stable target parking area. At the same time, by searching the planned parking trajectory within the target parking area, the search range of the trajectory is reduced and the search efficiency of the parking trajectory is improved.

[0029] The parking control method provided in the embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0030] Please see Figure 3 , Figure 3 This paper illustrates a flowchart of a parking control method provided in one embodiment of this application. The following will focus on... Figure 3 The process shown is described in detail. The parking control method may specifically include the following steps:

[0031] Step S110: Determine the boundaries of the passable area, the boundaries of obstacles, and the corner points of parking spaces based on the surrounding image information obtained by the vehicle.

[0032] In this embodiment, 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 of the vehicle's environment, and the parking space corner points include the location points of all parking spaces obtained by parking space corner point identification of the vehicle's environment. When the vehicle performs parking control, it can acquire image information of the vehicle's surroundings using the onboard surround-view camera, and based on this image information, determine the passable area boundary, obstacle boundary, and parking space corner points around the vehicle. This allows the vehicle to subsequently determine a smaller and more stable area suitable for parking control, thereby improving parking control efficiency. Among them, the accessible area boundary determined by the vehicle based on image information refers to the boundary of the largest accessible area that the vehicle can currently detect. Obviously, the accessible area boundary is limited by the acquisition range of the vehicle's surround-view cameras and the location of obstacles in the current environment. The obstacle boundary refers to the area obtained by identifying obstacles in the vehicle's environment. The obstacle boundary can mark the boundaries of all obstacles that obstruct the vehicle's passage within the accessible area boundary, so that the vehicle can bypass these obstacle boundaries when searching its trajectory later. The parking space corner points refer to the corner point data of all parking spaces that can be used for parking within the vehicle's accessible area. This can include information such as the coordinate data of the corner points of all parking spaces in the world coordinate system.

[0033] In some implementations, the vehicle can use a pre-trained accessible area recognition model to identify surrounding image information acquired by the vehicle, thereby obtaining the accessible area boundary output by the model; it can also use a pre-trained obstacle recognition model to identify obstacle areas in the surrounding image information, obtaining the obstacle boundary output by the model; and it can also use a pre-trained parking space corner recognition model to identify surrounding image information, 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 through installed surround-view cameras. First, the vehicle can use the maximum range represented by the surrounding image information as a potential accessible area boundary. For example, if the maximum environmental image range that the vehicle can acquire is 50m*50m, then the vehicle will first use this 50m*50m range boundary as the accessible area boundary. Subsequently, the vehicle can use the accessible area recognition model and the obstacle recognition model to obtain all accessible area boundaries and obstacle boundaries within the 50m*50m range. Finally, the vehicle can perform parking space corner recognition within the accessible area boundary range to obtain the location points of all parking spaces within the accessible area boundary. That is, to obtain such Figure 2 The recognition results are shown.

[0034] In some implementations, after the vehicle identifies obstacle boundaries based on surrounding image information, if some obstacle boundaries are entirely within the passable area boundary, the vehicle can fit these obstacle boundaries within the passable area boundary. This involves determining the smallest polygonal region that can enclose these obstacle regions and replacing the internal obstacle boundaries with the boundary of this polygonal region. Therefore, when performing parking control, the vehicle can directly use the polygonal region boundary as the obstacle region boundary, improving collision detection efficiency and thus enhancing parking control efficiency.

[0035] Step S120: Based on the corner point of the parking space, determine the virtual boundary corresponding to the target parking space. The virtual boundary is the minimum trajectory search area for the vehicle to perform parking control.

[0036] In this embodiment, the parking space corner point can include the coordinate data corresponding to the location points of all parking spaces within the passable area. When the vehicle performs parking control, it first needs to select a target parking space from all parking spaces, and then determine the virtual boundary corresponding to the target parking space based on the coordinate data corresponding to the corner point of the target parking space. That is, it determines the minimum trajectory search area for the vehicle to perform parking control. It is understood that the passable area boundary and obstacle boundary determined by the vehicle are easily affected by the viewing angle limitation of the vehicle's surround view camera and the position change caused by vehicle movement, and the obtained area range is not stable. However, the virtual boundary determined by the vehicle can be a closed area formed by connecting multiple location points in a fixed position in sequence. Its size is preset, and its position is associated with a fixed target parking space and will not move or change. Therefore, after obtaining the parking space corner point, the vehicle can determine a stable virtual boundary based on the corner point of the target parking space and multiple preset location points, so that the target parking area for vehicle parking control can be obtained based on this stable virtual boundary.

[0037] Step S130: Merge the virtual boundary, the passable area boundary, and the obstacle boundary to obtain the target parking area.

[0038] In this embodiment, after obtaining the accessible area boundary, obstacle boundary, and virtual boundary corresponding to the target parking space, the vehicle can merge the accessible area boundary, obstacle boundary, and virtual boundary to obtain a target parking area that can be used for parking control. It is understood that the virtual boundary determined by the vehicle based on the corner point of the target parking space is merely a fixed-size area within a preset range, with the location of the target parking space as a reference. In other words, the virtual boundary corresponding to the target parking space determined by the vehicle does not include the accessible area boundary and obstacle boundary. Therefore, the virtual boundary corresponding to the target parking space cannot indicate whether there are obstacles within 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 corresponding virtual boundary based on the corner point of the target parking space, the vehicle can further merge the virtual boundary with the accessible area boundary and obstacle boundary, thereby enabling the vehicle to perform effective parking control within the merged target parking area.

[0039] Step S140: Based on the target parking area, control the vehicle to park in the target parking space.

[0040] In this embodiment, after fusing the virtual boundary, the passable area boundary, and the obstacle boundary to determine the target parking area for parking control, the vehicle can search for a planned trajectory for parking into the target parking space within the target parking area. Specifically, the vehicle can first determine the planned trajectory for parking into the target parking space within the target parking area, and then perform collision detection on each planned trajectory sequentially based on multiple collision detection algorithms. That is, it determines whether the vehicle body will collide with the boundary area of ​​the target parking area while traveling along the planned trajectory. If the vehicle can ultimately obtain a planned trajectory from multiple planned trajectories that will never cause any collisions, then the vehicle can travel to the target parking space according to this planned trajectory and successfully complete the parking control.

[0041] The parking control method provided in this application determines the boundaries of the passable area, obstacle boundaries, and parking space corner points based on 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 identification of the vehicle's environment, and the parking space corner points include the location points of all parking spaces obtained by parking space corner point identification of the vehicle's environment. Based on the parking space corner points, a virtual boundary corresponding to the target parking space is determined, and the virtual boundary is the minimum trajectory search area for the vehicle to perform parking control. The virtual boundary, the passable area boundary, and the obstacle boundary are fused to obtain the target parking area. Based on the target parking area, the vehicle is controlled to park in the target parking space. Thus, the virtual boundary corresponding to the target parking space is determined based on the parking space corner points, and the virtual boundary is fused with the passable area boundary and obstacle boundary to obtain a more stable target parking area. At the same time, by searching the planned parking trajectory within the target parking area, the search range of the trajectory is reduced, and the search efficiency of the parking trajectory is improved.

[0042] Please see Figure 4 , Figure 4 A flowchart illustrating another embodiment of the parking control method provided in this application is shown below. Figure 4 The process shown is described in detail. The parking control method may specifically include the following steps:

[0043] Step S210: Determine the boundaries of the passable area, the boundaries of obstacles, and the corner points of parking spaces based on the surrounding image information obtained by the vehicle.

[0044] In this embodiment, step S210 can be referred to the content of other embodiments, and will not be repeated here.

[0045] Step S220: Based on the target corner point corresponding to the target parking space among the parking space corner points, determine 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.

[0046] In this embodiment, the parking space corner point determined by the vehicle based on 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. Before performing parking control, the vehicle can first select a target parking space 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 of the target corner point in the world coordinate system, the target position corresponding to the rear axle center of the vehicle after parking 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 of the rear axle center of the vehicle in the world coordinate system assuming that the vehicle has already parked in the target parking space. However, since the vehicle has not actually parked in the target parking space, the vehicle cannot directly obtain the coordinate data of the rear axle center through methods such as the Global Positioning System. Instead, it needs to indirectly calculate and determine the first coordinate data corresponding to the target position by using the coordinate data of the target corner point of the target parking space in the world coordinate system.

[0047] In some implementations, such as Figure 5 As shown, in step S220, based on the target corner point corresponding to the target parking space among the corner points of the parking space, the target position corresponding to the rear axle center of the vehicle after parking and the first coordinate data of the target position in the world coordinate system can also be determined in the following way:

[0048] Step S221: Based on the second coordinate data of the target corner point in the world coordinate system, determine the first length corresponding to the target parking space.

[0049] In this embodiment, after the vehicle identifies parking space corner points from surrounding image information, it can use the coordinate data of the target corner point corresponding to the target parking space in the world coordinate system as the second coordinate data. Then, based on the second coordinate data corresponding to each target corner point, the first length of the target parking space is determined. This first length is used to determine the target position corresponding to the rear axle center of the vehicle after it parks in the target parking space, and the first coordinate data corresponding to the target position. Specifically, the formula for calculating the first length is as follows:

[0050]

[0051] Where d represents the first length corresponding to the target parking space, the coordinate data of the two corner points of the parking edge of the target parking space in the world coordinate system are (x1, y1) and (x2, y2) respectively, and the coordinate data of the other two corner points of the target parking space are (x3, y3) and (x4, y4).

[0052] In some implementations, if the vehicle's results of identifying parking space corners from surrounding image information do not fully include the four target corners corresponding to the target parking space, meaning the vehicle may only be able to obtain the second coordinate data of some of the four target corners due to obstruction, then the vehicle cannot directly determine the first length of the target parking space based on the second coordinate data corresponding to each of the four target corners. In this case, the vehicle can set the actual length of the target parking space to a pre-set parking space length, such as the parking space length stipulated by regulations.

[0053] Step S222: Based on the first length, the second length of the vehicle body, and the third length between the front center and the rear axle center of the vehicle, determine the first angle and the fourth length. 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 rear axle center and the parking edge.

[0054] In this embodiment, if a vehicle is parked in the target parking space, the vehicle's central axis will be perpendicular to the parking edge of the target parking space. The second length of the vehicle body and the third length between the rear axle center and the front center are known data from the vehicle's manufacturing process. Based on the first length of the target parking space, the second length of the vehicle body, and the third length, the distance between the rear axle center of the vehicle and the parking edge of the target parking space (as the fourth length) and the first angle corresponding to the angle between the parking edge of the target parking space and the X-axis of the world coordinate system are determined. These are then used to further determine the target position corresponding to the rear axle center of the vehicle and the first coordinate data of the target position in the world coordinate system when the vehicle is parked in the target parking space, based on the fourth length and the first angle. Specifically, the first angle and the fourth length can be calculated using the following formula:

[0055]

[0056] 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 rear axle center and the front axle center of the vehicle, l is the fourth length, which is the distance between the rear axle center 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.

[0057] Step S223: Determine the first coordinate data based on the first angle and the fourth length.

[0058] In this embodiment of the application, after obtaining the first angle and the fourth length based on the above steps, the first coordinate data (x, y) of the rear axle center of the vehicle in the world coordinate system can be calculated using the following formula when the vehicle is parked in the target parking space:

[0059]

[0060] Step S230: Based on the first coordinate data and the boundary position points, determine the virtual boundary corresponding to the target parking space. The boundary position points are determined by the minimum trajectory search area based on the vehicle for parking control.

[0061] In this embodiment, after determining the first coordinate data corresponding to the target position after the vehicle has parked in the target parking space, the virtual boundary corresponding to the target parking space can be determined based on the first coordinate data and 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 sequentially. 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 rear axle center of the vehicle. Thus, after determining the target parking space and the target position of the vehicle in the target parking space based on the surrounding image information, the vehicle can directly determine the virtual boundary corresponding to the target parking space based on the preset relative positional relationship between each boundary position point and the target position.

[0062] In some implementations, such as Figure 6 As shown, the method for determining the virtual boundary corresponding to the target parking space based on the first coordinate data and the boundary position points in step S230 can be implemented through the following steps:

[0063] Step S231: Establish a parking space coordinate system with the target location as the origin.

[0064] In this embodiment, the vehicle determines the coordinate data corresponding to each boundary point within the virtual boundary based on the virtual boundary determined by the target parking space, that is, based on the first coordinate data corresponding to the target position obtained after the vehicle parks in the target parking space. Therefore, after determining the first coordinate data, the vehicle can establish a parking space coordinate system with the target position as the origin. This system is used to obtain the coordinate data of each boundary point in the virtual boundary in the world coordinate system based on the relative positional relationship between the pre-determined boundary point and the target position, and then connect them to obtain the virtual boundary. Specifically, as follows... Figure 7As shown, after the vehicle determines the target position corresponding to the center of the rear axle of the vehicle after parking in the target parking space, a parking space coordinate system can be established based on the target position. That is, the parking space coordinate system is established with the target position as the origin, the direction parallel to the parking side of the target parking space as the X-axis, and the direction perpendicular to the parking side as the Y-axis.

[0065] Step S232: Based on the relative positional relationship between the boundary position point and the target position, determine the third coordinate data of the boundary position point in the parking space coordinate system.

[0066] In this embodiment, after the vehicle establishes a parking space coordinate system with the target location, it can determine the third coordinate data corresponding to each boundary position point in the parking space coordinate system based on the relative positional relationship between each boundary position point in the pre-determined virtual boundary and the origin of the parking space coordinate system, which is the target location. Please refer again. Figure 7 In the diagram, corner points P1 to P10 represent the boundary points corresponding to the virtual boundaries with predetermined relative positions. After determining the target parking space and target location, the vehicle can obtain the third coordinate data of each boundary point in the parking space coordinate system based on the relative positional relationship between each boundary point and the target location.

[0067] In some implementations, the relative positional relationships between various boundary points within the virtual boundary can be predetermined. For example, as... Figure 7 The virtual boundary points P1 to P10 shown can be pre-set so that P1, P6, P7, and P10 are on the straight line of the parking edge of the target parking space. P1 is 1 meter from the right corner of the parking edge, P6 is 1 meter from the left corner, P7 is 9 meters outward from P6, and P10 is 9 meters outward from P1. P2, P3, P4, and P5 are all on the parking lines on both sides of the target parking space. P2 is 1 meter from the right corner of the parking edge, and P5 is 1 meter from the left corner. P3 and P4 are the corner points of the parking line behind the target parking space, and P8 and P9 are both 8 meters from the parking edge of the target parking space. Therefore, based on the pre-determined relative positions of the boundary points, after establishing the parking space coordinate system, the vehicle can determine the corresponding third coordinate data of each boundary point in the parking space coordinate system based on the target location. Subsequently, the vehicle can sequentially connect the various boundary points to obtain the virtual boundary corresponding to the target parking space. For example... Figure 7 As shown, after establishing a parking space coordinate system based on the target location and determining the third coordinate data of multiple boundary position points such as P1 to P10 in the parking space coordinate system, the boundary position points of P1 to P10 can be connected in sequence to form a closed area boundary, which is the virtual boundary corresponding to the target parking space.

[0068] Step S233: Based on the first coordinate data of the target position in the world coordinate system, convert the third coordinate data corresponding to the boundary position point into the fourth coordinate data in the world coordinate system to obtain the virtual boundary corresponding to the target parking space.

[0069] In this embodiment, since the accessible area boundary and obstacle boundary acquired by the vehicle are both area boundaries in the world coordinate system, to facilitate the subsequent fusion of the virtual boundary with the accessible area boundary and obstacle boundary to determine the target parking area for parking control, after determining the third coordinate data corresponding to each boundary position point included in the virtual boundary in the parking space coordinate system, the vehicle can also convert the third coordinate data into fourth coordinate data in the world coordinate system. Specifically, through the above calculation process, the vehicle can determine the first coordinate data of the target position in the world coordinate system. At the same time, the parking space coordinate system corresponding to the target parking space is a coordinate system established with the target position as the origin, that is, the coordinate data of the target position in the parking space coordinate system is (0, 0). Thus, the vehicle can obtain different coordinate data corresponding to the same position point (target parking point) in the world coordinate system and the parking space coordinate system, and then obtain the conversion relationship between the world coordinate system and the parking space coordinate system based on these two different coordinate data. Meanwhile, the vehicle has obtained the third coordinate data of each boundary point of the virtual boundary in the parking space coordinate system through the above steps. Therefore, the fourth coordinate data of each boundary point of the virtual boundary in the world coordinate system can be obtained through the transformation relationship between the two coordinate systems.

[0070] Step S240: Obtain the first region boundary on the passable region boundary that is within the virtual boundary, and the second region boundary on the obstacle boundary that is within the virtual boundary.

[0071] In this embodiment, after the vehicle determines the virtual boundary corresponding to the target parking space, it can merge 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. See also... Figure 8 Vehicles can use the boundary of the passable area that is within the virtual boundary as the first area boundary, and the boundary of the obstacle that is within the virtual boundary as the second area boundary.

[0072] Step S250: Merge the first area boundary, the second area boundary, and the virtual boundary to obtain the target parking area.

[0073] In this embodiment, after determining the boundaries of the first and second regions, the vehicle can fuse these boundaries with a virtual boundary to obtain a relatively stable target parking area suitable for parking control. The vehicle can then search for the trajectory of parking into the target parking space within this target parking area. This target parking area ensures that the vehicle can find an effective parking planning trajectory and, through its stability, reduces the search range for over-planned trajectories, thus improving search efficiency.

[0074] Step S260: Determine the planned trajectory of the vehicle parking into the target parking space within the target parking area.

[0075] Step S270: Based on the target parking area, and through the first collision detection algorithm, the second collision detection algorithm, and the third collision detection algorithm, determine whether the planned trajectory is a valid trajectory.

[0076] In this embodiment, after determining the target parking area, the vehicle can perform a trajectory search within the target parking area to determine at least one planned trajectory for the vehicle to park in the target parking space. Subsequently, the vehicle can perform collision detection on all determined planned trajectories based on the traversable area boundaries, obstacle boundaries, and virtual boundaries within the target parking area. This means determining whether the vehicle will collide with obstacle boundaries, traversable area boundaries, or virtual boundaries within the target parking area if it follows the planned trajectory. Obviously, if the detection result indicates that the vehicle will collide with any boundary, then the planned trajectory is invalid, meaning the vehicle cannot park in the target parking space according to this planned trajectory. If the detection result indicates that the vehicle will not collide with any boundary, then the vehicle can use this planned trajectory as a valid trajectory and park in the target parking space according to this valid trajectory.

[0077] In some implementations, such as Figure 9 As shown, the vehicle determines whether the planned trajectory is a valid trajectory based on the target parking area and through a first collision detection algorithm, a second collision detection algorithm, and a third collision detection algorithm. This can be achieved through the following steps:

[0078] Step S271: Based on the first collision detection algorithm, determine whether the planned trajectory collides with the virtual boundary in the target parking area, and obtain the first detection result.

[0079] Step S272: Based on the second collision detection algorithm, determine whether the planned trajectory collides with the boundary of the passable area within the target parking area, and obtain the second detection result.

[0080] Step S273: Based on the third collision detection algorithm, determine whether the planned trajectory collides with the boundary of the obstacle in the target parking area, and obtain the third detection result.

[0081] In this embodiment, the vehicle can use different algorithms for collision detection for different types of area boundaries within the target parking area, including virtual boundaries, passable area boundaries, and obstacle boundaries, to achieve higher trajectory detection efficiency. Specifically, the first collision detection algorithm used by the vehicle to detect whether the planned trajectory collides with the virtual boundary can be a ray-mapping method. Figure 10 As shown, the vehicle can select multiple marker points around its body. A horizontal line can be drawn from any marker point. If this horizontal line has an even number of corner points with the virtual boundary, it indicates that the planned trajectory will collide with the virtual boundary, and the planned trajectory is invalid. Furthermore, the second collision detection algorithm used by the vehicle to detect whether the planned trajectory collides with the boundary of the passable area can be a kd-tree search algorithm. For example... Figure 11 As shown, the Kd-tree can be searched with the vehicle's center as the center and the vehicle's diagonal as the diameter. If a node falls into the circle, it is further checked whether the node falls into the rectangle formed by the vehicle body. If the node falls into the rectangle, it indicates that the vehicle will collide with the boundary of the passable area, and the planned trajectory is invalid. Additionally, the third collision detection algorithm used to detect whether the planned trajectory collides with obstacle boundaries can be a matrix intersection algorithm. For example... Figure 12 As shown, a rectangular region can be determined based on the vehicle's boundary to represent the vehicle, and another rectangular region can be used to represent the irregular obstacle boundary. The matrix intersection algorithm is used to determine whether the rectangular region of the vehicle intersects with the rectangular region of the obstacle boundary. If they intersect, it indicates that the vehicle will collide with the obstacle boundary, and the planned trajectory is invalid.

[0082] Step S274: Based on the first detection result, the second detection result, and the third detection result, determine whether the planned trajectory is a valid trajectory.

[0083] In this embodiment, after the vehicle verifies the collision detection using different collision detection algorithms based on different types of area boundaries within the target parking area, the vehicle can use the first detection result, the second detection result, and the third detection result to select all planned trajectories that will not collide with any type of area boundary as valid trajectories.

[0084] Step S280: If it is a valid trajectory, control the vehicle to park in the target parking space according to the valid trajectory.

[0085] In this embodiment of the application, if a vehicle can determine an effective trajectory within the target parking area that will not collide with any area boundary, it indicates that if the vehicle parks according to the effective trajectory, it can successfully park in the target parking space. Therefore, the vehicle can be controlled to park in the target parking space based on the effective trajectory.

[0086] The parking control method provided in this application determines the boundaries of the passable area, obstacle boundaries, and parking space corners. Based on the parking space corners, it determines the virtual boundary corresponding to the target parking space. The virtual boundary is then merged with the passable area boundaries and obstacle boundaries to obtain a target parking area for parking control. Simultaneously, the vehicle can determine its planned trajectory for parking into the target parking space within the target parking area. Based on a first collision detection algorithm, a second collision detection algorithm, and a third collision detection algorithm, it is determined whether the planned trajectory is valid. If it is valid, the vehicle can park into the target parking space according to the valid trajectory. Thus, by determining the virtual boundary area corresponding to the target parking space through the parking space corners, and then determining a stable target parking area based on the passable area boundaries and the virtual boundary, the trajectory search range is reduced, and trajectory search efficiency is improved. Furthermore, different collision detection algorithms are used for different types of boundary areas within the target parking area, which reduces the computational load of trajectory detection and improves the detection efficiency of parking trajectories.

[0087] Please see Figure 13 This document illustrates a structural block diagram of a parking control device 200 provided in one embodiment of this application. The parking control device 200 includes: a first area acquisition module 210, a second area determination module 220, an area fusion module 230, and a trajectory search module 240. The first area acquisition module 210 determines the boundaries of the passable area, obstacle boundaries, and parking space corners based on 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 identification of the vehicle's environment, and the parking space corners include the location points of all parking spaces obtained by parking space corner identification of the vehicle's environment. The second area determination module 220 determines the virtual boundary corresponding to the target parking space based on the parking space corners. The virtual boundary is the minimum trajectory search area for parking control of the vehicle. The area fusion module 230 fuses the virtual boundary, the passable area boundary, and the obstacle boundary to obtain the target parking area. The trajectory search module 240 controls the vehicle to park in the target parking space based on the target parking area.

[0088] As one possible implementation, the trajectory search module 240 includes a trajectory determination unit, a trajectory detection unit, and a trajectory parking unit. The trajectory determination unit determines the planned trajectory for the vehicle to park in the target parking space within the target parking area; the trajectory detection unit determines whether the planned trajectory is valid based on the target parking area and using a first collision detection algorithm, a second collision detection algorithm, and a third collision detection algorithm; and the trajectory parking unit controls the vehicle to park in the target parking space according to the valid trajectory if it is a valid trajectory.

[0089] As one possible implementation, the trajectory detection unit is further configured to determine whether the planned trajectory collides with the virtual boundary within the target parking area based on a first collision detection algorithm, thereby obtaining a first detection result; determine whether the planned trajectory collides with the boundary of the passable area within the target parking area based on a second collision detection algorithm, thereby obtaining a second detection result; determine whether the planned trajectory collides with the boundary of an obstacle within the target parking area based on a third collision detection algorithm, thereby obtaining a third detection result; and determine whether the planned trajectory is a valid trajectory based on the first detection result, the second detection result, and the third detection result.

[0090] In one possible implementation, the second region determination module 220 includes a parking point determination unit and a second region determination unit. The parking point determination unit is used to determine the target position corresponding to the rear axle center of the vehicle after parking, and the first coordinate data of the target position in the world coordinate system, based on the target corner point corresponding to the target parking space among the parking space corner points. The second region determination unit is used to determine the virtual boundary corresponding to the target parking space based on the first coordinate data and boundary position points, where the boundary position points are determined by the minimum trajectory search area for parking control based on the vehicle.

[0091] As one possible implementation, the parking point determination unit is further configured to 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; determine the first angle and the fourth length based on the first length, the second length of the vehicle body, and the third length between the front center and the rear axle center of the vehicle, 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 rear axle center and the parking edge; and determine the first coordinate data based on the first angle and the fourth length.

[0092] As one possible implementation, the second region determination unit is also used to establish a parking space coordinate system with the target location as the origin; based on the relative positional relationship between the boundary location point and the target location, determine the third coordinate data of the boundary location point in the parking space coordinate system; based on the first coordinate data of the target location in the world coordinate system, convert the third coordinate data corresponding to the boundary location point into the fourth coordinate data in the world coordinate system to obtain the virtual boundary corresponding to the target parking space.

[0093] As one possible implementation, the area determination module 230 is also used to obtain a first area boundary within a virtual boundary on the boundary of the passable area, and a second area boundary within a virtual boundary on the boundary of the obstacle; and to merge the first area boundary, the second area boundary, and the virtual boundary to obtain the target parking area.

[0094] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device and module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0095] In the several embodiments provided in this application, the coupling between modules can be electrical, mechanical, or other forms of coupling.

[0096] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0097] In summary, the solution provided in this application determines the boundaries of the passable area, obstacle boundaries, and parking space corners 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 identification of the vehicle's environment, and the parking space corners include the location points of all parking spaces obtained by parking space corner point identification of the vehicle's environment. Based on the parking space corners, a virtual boundary corresponding to the target parking space is determined, which is the minimum trajectory search area for the vehicle to perform parking control. The virtual boundary, the passable area boundary, and the obstacle boundary are fused to obtain the target parking area. Based on the target parking area, the vehicle is controlled to park in the target parking space. Determining the virtual boundary corresponding to the target parking space based on the parking space corners and fusing the virtual boundary with the passable area boundary and obstacle boundary yields a more stable target parking area. Simultaneously, by searching the planned trajectory within the target parking area, the search range of the planned trajectory is reduced, improving the trajectory search efficiency.

[0098] Please refer to Figure 14The diagram illustrates a structural block diagram of a vehicle 400 provided in an embodiment of this application. The computer device 400 in this application may include one or more components such as a processor 410, a memory 420, and one or more application programs. The one or more application programs may be stored in the memory 420 and configured to be executed by one or more processors 410. The one or more programs are configured to perform the methods described in the foregoing method embodiments.

[0099] Processor 410 may include one or more processing cores. Processor 410 connects to various parts of the computer device using various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 420, and by calling data stored in memory 420. Optionally, processor 410 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 410 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 410 and may be implemented separately using a communication chip.

[0100] The memory 420 may include random access memory (RAM) or read-only memory (ROM). The memory 420 can be used to store instructions, programs, code, 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 touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the various method embodiments described below. The data storage area may also store data created during the use of the computer device (such as phone books, audio and video data, chat log data, etc.).

[0101] Please refer to Figure 15This diagram illustrates a structural block diagram of a computer-readable storage medium provided in an embodiment of this application. The computer-readable medium 800 stores program code that can be called by a processor to execute the methods described in the above method embodiments.

[0102] The computer-readable storage medium 800 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, 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 that performs any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code 810 may, for example, be compressed in a suitable form.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions 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 this application.

Claims

1. A parking control method characterized by, The method comprises: determining a passable region boundary, an obstacle boundary and a parking space corner point according to surrounding image information obtained by a vehicle, the passable region boundary being a boundary of a maximum passable region detected by the vehicle, the obstacle boundary being a region boundary obtained by obstacle recognition on an environment in which the vehicle is located, and the parking space corner point comprising position points of all parking spaces obtained by parking space corner point recognition on the environment in which the vehicle is located; determining a target position corresponding to a rear axle center of the vehicle after the vehicle is parked and first coordinate data of the target position in a world coordinate system based on a target corner point corresponding to a target parking space in the parking space corner point; determining a virtual boundary corresponding to the target parking space based on the first coordinate data and a boundary position point, the boundary position point being determined based on a minimum trajectory search region for parking control of the vehicle, and the virtual boundary being the minimum trajectory search region for parking control of the vehicle; fusing the virtual boundary, the passable region boundary and the obstacle boundary to obtain a target parking region; controlling the vehicle to park in the target parking space based on the target parking region.

2. The method of claim 1, wherein, The controlling the vehicle to park in the target parking space based on the target parking region comprises: determining a planned trajectory for the vehicle to park in the target parking space in the target parking region; determining whether the planned trajectory is a valid trajectory based on the target parking region and by using a first collision detection algorithm, a second collision detection algorithm and a third collision detection algorithm; if the planned trajectory is a valid trajectory, controlling the vehicle to park in the target parking space according to the valid trajectory.

3. The method of claim 2, wherein, The determining whether the planned trajectory is a valid trajectory based on the target parking region and by using the first collision detection algorithm, the second collision detection algorithm and the third collision detection algorithm comprises: determining whether the planned trajectory collides with the virtual boundary in the target parking region based on the first collision detection algorithm to obtain a first detection result; determining whether the planned trajectory collides with the passable region boundary in the target parking region based on the second collision detection algorithm to obtain a second detection result; determining whether the planned trajectory collides with the obstacle boundary in the target parking region based on the third collision detection algorithm to obtain a third detection result; determining whether the planned trajectory is a valid trajectory based on the first detection result, the second detection result and the third detection result.

4. The method of claim 1, wherein, The determining a target position corresponding to a rear axle center of the vehicle after the vehicle is parked and first coordinate data of the target position in a world coordinate system based on a target corner point corresponding to a target parking space in the parking space corner point comprises: determining a first length corresponding to the target parking space based on second coordinate data of the target corner point in the world coordinate system; determine a first angle and a fourth length based on the first length, a second length of the vehicle body, and a third length between a front end center and a rear axle center of the vehicle, the first angle being an included angle between a parking-in edge of the target parking space and an X axis of the world coordinate system, and the fourth length being a distance between the rear axle center and the parking-in edge; determine the first coordinate data based on the first angle and the fourth length.

5. The method of claim 1, wherein, determining the virtual boundary corresponding to the target parking space based on the first coordinate data and the boundary position point comprises: establishing a parking space coordinate system with the target position as an origin; determining third coordinate data of the boundary position point in the parking space coordinate system based on a relative position relationship between the boundary position point and the target position; converting the third coordinate data of the boundary position point into fourth coordinate data in the world coordinate system based on the first coordinate data of the target position in the world coordinate system, to obtain the virtual boundary corresponding to the target parking space.

6. The method according to any one of claims 1 to 5, characterized in that, fusing the virtual boundary, the passable region boundary, and the obstacle boundary to obtain a target parking region comprises: obtaining a first region boundary on the passable region boundary that is within the virtual boundary, and a second region boundary on the obstacle boundary that is within the virtual boundary; fusing the first region boundary, the second region boundary, and the virtual boundary to obtain the target parking region.

7. A parking control device, characterized by comprising: The apparatus comprises: a first region obtaining module configured to determine a passable region boundary, an obstacle boundary, and a parking space corner point based on peripheral image information obtained by a vehicle, the passable region boundary being a boundary of a maximum passable region detected by the vehicle, the obstacle boundary being a region boundary obtained by performing obstacle identification on an environment in which the vehicle is located, and the parking space corner point including position points of all parking spaces obtained by performing parking space corner point identification on the environment in which the vehicle is located; a second region determining module configured to determine a target position corresponding to a rear axle center of the vehicle after the vehicle parks and first coordinate data of the target position in a world coordinate system based on a target corner point corresponding to a target parking space in the parking space corner point, and determine a virtual boundary corresponding to the target parking space based on the first coordinate data and a boundary position point, the boundary position point being determined based on a minimum trajectory search region for parking control of the vehicle, and the virtual boundary being the minimum trajectory search region for the parking control of the vehicle; a region fusing module configured to fuse the virtual boundary, the passable region boundary, and the obstacle boundary to obtain a target parking region; a parking control module configured to control the vehicle to park in the target parking space based on the target parking region.

8. A vehicle characterized by comprising: comprise: one or more processors; a 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 1-6.

9. A computer readable storage medium, characterized in that, The computer readable storage medium stores program codes, which can be invoked by the processor to execute the method of any one of claims 1-6.

Images