An automatic parking method and device, electronic equipment and storage medium

Abstract

The application discloses an automatic parking method and device, electronic equipment and storage medium, comprising: obtaining target objects and pose information of the target objects around a vehicle to be parked through a millimeter wave radar, the target objects including parking spaces and obstacle objects; when detecting an idle parking space, determining a target parking space from the idle parking space, and establishing a plane coordinate system with the current position of the vehicle to be parked as the origin; obtaining a projection area of the obstacle objects in the plane coordinate system to obtain a first area; for each obstacle object, performing region expansion on the first area according to the pose information of the obstacle object to obtain a second area; taking the second area as an obstacle avoidance area, controlling the vehicle to be parked to travel from the current position to the target parking space, and performing region expansion on the original first area where the obstacle object is located, so that the edge of the obtained obstacle avoidance area is a virtual edge, the distance between the vehicle and the obstacle object is increased, and the safety and feasibility of the millimeter wave radar applied to automatic parking are improved.

Description

Technical Field

[0001] This invention relates to the field of parking positioning technology, and more particularly to an automatic parking method, apparatus, electronic device, and storage medium. Background Technology

[0002] In current automated parking applications, location detection technology plays a crucial role. On one hand, it effectively characterizes the real-time location of the vehicle during parking; on the other hand, it identifies the positions of parking spaces, pedestrians, and other obstacles within the parking environment. These two aspects provide the basis for the vehicle to plan its driving path. Currently, sensors such as GPS and LiDAR are generally used to locate the vehicle and its surroundings. However, in underground parking lots, the accuracy of GPS and other positioning devices drops significantly, resulting in larger positioning errors and making it difficult to accurately achieve automated parking.

[0003] LiDAR boasts high obstacle detection capabilities, accuracy, and resolution, but it is expensive. Millimeter-wave radar, on the other hand, is less expensive and suitable for mass production and application. Its longer wavelength and lower frequency allow it to penetrate smoke and dust effectively, making it a better choice for obstacle detection in automated parking systems in underground parking lots. However, millimeter-wave radar has lower accuracy and resolution compared to LiDAR, potentially leading to friction and collisions between vehicle edges and obstacle edges during parking. Summary of the Invention

[0004] This invention provides an automatic parking method to address the problem that when detecting obstacles using millimeter-wave radar, the low accuracy and resolution of millimeter waves can lead to friction and collisions with the vehicle.

[0005] In a first aspect, the present invention provides an automatic parking method, wherein a millimeter-wave radar is installed on the vehicle to be parked, the method comprising:

[0006] The millimeter-wave radar is used to acquire the target objects around the vehicle waiting to be parked and the position and pose information of the target objects, including parking spaces and obstacle objects.

[0007] When an empty parking space is detected, the target parking space is determined from the empty parking spaces, and a planar coordinate system is established with the current location of the vehicle waiting to park as the origin.

[0008] The projection region of the obstacle object in the planar coordinate system is obtained to obtain the first region;

[0009] For each obstacle object, the first region is expanded according to the pose information of the obstacle object to obtain the second region;

[0010] Using the second area as an obstacle avoidance zone, control the vehicle waiting to park to move from its current position to the target parking space.

[0011] In a second aspect, the present invention provides an automatic parking device, comprising:

[0012] The data acquisition module is used to acquire target objects around the vehicle waiting to be parked and the position and pose information of the target objects through millimeter-wave radar. The target objects include parking spaces and obstacle objects.

[0013] An initialization module is used to determine the target parking space from the available parking spaces when an available parking space is detected, and to establish a planar coordinate system with the current location of the vehicle waiting to park as the origin.

[0014] The first region acquisition module is used to acquire the projection region of the obstacle object in the planar coordinate system to obtain the first region;

[0015] The second region acquisition module is used to dilate the first region for each obstacle object according to the pose information of the obstacle object to obtain a second region.

[0016] The parking control module is used to control the vehicle waiting to be parked to move from its current position to the target parking space, using the second area as the obstacle avoidance area.

[0017] Thirdly, the present invention provides an electronic device, the electronic device comprising:

[0018] At least one processor; and

[0019] A memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the automatic parking method described in the first aspect of the invention.

[0021] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the automatic parking method described in the first aspect of the present invention.

[0022] The automatic parking method provided in this invention involves a millimeter-wave radar installed on the vehicle waiting to park. The millimeter-wave radar acquires the positional information of target objects and obstacles surrounding the vehicle. When an empty parking space is detected, the target parking space is determined from the empty spaces, and a planar coordinate system is established with the current position of the vehicle waiting to park as the origin. The projection area of ​​the obstacle object in the planar coordinate system is acquired to obtain a first region. For each obstacle object, the first region is expanded according to the obstacle object's positional information to obtain a second region. Using the second region as the obstacle avoidance region, the vehicle is controlled to move from its current position to the target parking space. When acquiring the second region (i.e., the obstacle avoidance region), the original first region containing the obstacle object is expanded, resulting in a virtual edge for the obtained obstacle avoidance region. Even if the vehicle approaches this virtual edge, no friction or expansion will occur, improving the safety and feasibility of applying millimeter-wave radar to automatic parking. Furthermore, the expansion of the first region is combined with the positional information of the obstacle object, allowing for different degrees of expansion for different obstacle objects based on their positional characteristics, thus improving the flexibility and safety of automatic parking.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, 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 the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of an automatic parking method provided in Embodiment 1 of the present invention;

[0026] Figure 2 This is a schematic diagram of a region expansion method provided in Embodiment 1 of the present invention;

[0027] Figure 3 This is a flowchart of an automatic parking method provided in Embodiment 2 of the present invention;

[0028] Figure 4 This is a schematic diagram of a method for expanding the first region of a moving obstacle object according to Embodiment 2 of the present invention;

[0029] Figure 5 This is a schematic diagram of the structure of an automatic parking device provided in Embodiment 3 of the present invention;

[0030] Figure 6 This is a schematic diagram of the structure of the electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] Example 1

[0033] Figure 1 This is a flowchart of an automatic parking method provided in Embodiment 1 of the present invention. This embodiment is applicable to the use of millimeter-wave radar for automatic parking in underground parking lots. The vehicle to be parked is equipped with millimeter-wave radar. Specifically, the millimeter-wave radar can be installed on the top or around the vehicle. By emitting millimeter waves and receiving their reflected signals, the millimeter-wave radar can obtain information such as the distance, speed, azimuth angle and height of the target object, thereby realizing the measurement and positioning of the target position.

[0034] This method can be executed by an automatic parking device, which can be implemented in hardware and / or software and can be configured in an electronic device.

[0035] like Figure 1 As shown, the automatic parking method includes:

[0036] S101. Obtain the position and pose information of target objects around the vehicle waiting to be parked using millimeter-wave radar. Target objects include parking spaces and obstacle objects.

[0037] The obstacles can include restricted areas, load-bearing walls, railings, pedestrians, and other vehicles.

[0038] When the element is an irregularly shaped or large object, the pose can be a set of poses of the element's contour points. The pose describes the position and orientation of an object in three-dimensional space. Pose information includes position information (coordinates) and orientation information (azimuth).

[0039] Optionally, the detection height range of the millimeter radar can be set to the ground to a preset height, which is slightly greater than the top of the vehicle (e.g., a redundancy height of 30cm). This can reduce the amount of point cloud data collected, save computing resources required for data processing, and improve data processing speed.

[0040] S102. When an empty parking space is detected, the target parking space is determined from the empty parking spaces, and a planar coordinate system is established with the current location of the vehicle waiting to park as the origin.

[0041] Vacant parking spaces can be identified based on the pose information detected by millimeter-wave radar. Specifically, starting from the entrance of the parking space, the internal vacancy distance is detected. When the detected internal vacancy distance is greater than a preset distance, the parking space is considered vacant, for example, the preset distance is 1 meter. The detection range of millimeter-wave radar is usually greater than the overall length of the vehicle body; for example, the radius of the detection range is usually not less than 50 meters. Therefore, millimeter-wave radar can detect a wide range, and the number of vacant parking spaces it can detect may be multiple.

[0042] Optionally, in one use case, all parking spaces in a parking lot are the same size and all can be used to park the vehicle. In this scenario, at least a portion of the parking area with a preset length is within the environmental perception module. Therefore, the nearest parking space can be selected as the target parking space. Furthermore, since vehicles typically have a human-machine interface, all available parking spaces can be sent to the interface in a distributed map format, allowing the user to select the target parking space.

[0043] Optionally, in another use case, parking spaces in a parking lot vary in size to accommodate vehicles of different sizes. When an empty parking space is detected, the target parking space is determined from among the available spaces. This includes: acquiring the size parameters of the vehicle waiting to park and the size parameters of the empty parking space; and determining the target parking space from among the available spaces based on the size parameters of the vehicle waiting to park and the empty parking space. In this type of use case, when detecting the size of an empty parking space, the entire area of ​​the empty parking space needs to be within the detection range of the millimeter-wave radar. This allows the size parameters of the parking space, i.e., its length and width, to be calculated based on the contour pose of the parking space. The vehicle's size parameters can be obtained from the factory specifications provided by the vehicle manufacturer, including the vehicle's length and width. It is easy to understand that for a parking space to be used to park a vehicle, the length and width of the parking space must be greater than the length and width of the vehicle. Based on this principle, qualified parking spaces can be determined from vacant parking spaces. When the number of qualified parking spaces is greater than one, the qualified parking space closest to the vehicle can be used as the target parking space, or the user can choose it.

[0044] When establishing a planar coordinate system with the current location of the vehicle waiting to park as the origin, the center point of the vehicle's rear axle is usually used as the reference point, and this reference point is used as the origin of the coordinate system. It should be noted that various elements in a parking lot are usually three-dimensional, but in this solution, obstacles such as vehicles and parking spaces are all located on the ground. Therefore, parking planning can be regarded as a two-dimensional planar problem, and only a two-dimensional planar coordinate system needs to be constructed.

[0045] S103. Obtain the projection area of ​​the obstacle object in the planar coordinate system to obtain the first region.

[0046] Specifically, the area enclosed by the edge contour of the obstacle object is the first region obtained by projection.

[0047] Optionally, before executing S103, the acquired pose information (point cloud data) can be clustered and filtered to remove abnormal pose information, such as reflective point clouds, so as to avoid abnormal pose information interfering with the edge contour of the obstacle object and reducing the accuracy of obstacle object positioning, thereby further improving the safety of automatic parking.

[0048] S104. For each obstacle object, perform region dilation on the first region based on the pose information of the obstacle object to obtain the second region.

[0049] The first region is expanded primarily to account for potential accuracy issues with millimeter-wave radar detection. To reduce friction and collisions between vehicles and obstacles during parking, the first region is expanded. The boundary of the expanded second region is a virtual boundary, meaning that even if a vehicle approaches this virtual edge, no friction or expansion will occur, thus improving the safety and feasibility of applying millimeter-wave radar to automatic parking.

[0050] The pose information of an obstacle can represent its movement characteristics and the size of its footprint. Therefore, the expansion coefficient (or weighting coefficient) of each first region can be set based on the pose information of the obstacle.

[0051] In an optional embodiment A, for each obstacle object, a second region is obtained by performing region dilation on a first region based on the pose information of the obstacle object, including: determining whether the obstacle object has moved based on the pose information of the obstacle object; if so, determining the weighting coefficient corresponding to the obstacle object as a first coefficient; if not, determining the weighting coefficient corresponding to the obstacle object as a second coefficient; and performing region dilation on the first region based on the weighting coefficient of the obstacle object to obtain the second region.

[0052] In this system, the first coefficient is greater than the second coefficient, and both the first and second coefficients are greater than 1. This means the area of ​​the expanded second region is necessarily larger than the area of ​​the unexpanded first region, and the expansion degree of moving obstacles is greater than that of fixed obstacles. For moving obstacles, such as pedestrians, vehicles, or animals, considering the uncertainty of their movement which may interfere with parking, a larger expansion coefficient is set for moving obstacles, while a smaller expansion coefficient can be set for fixed obstacles. This provides redundant movement space for moving obstacles, reducing the possibility of collisions during parking. However, it should be noted that vehicles in underground parking lots typically travel at low speeds, and other vehicles will not move at a relatively high speed compared to the vehicles waiting to park. When the obstacle is another vehicle, setting an expansion coefficient to increase the area occupied by other vehicles is also applicable.

[0053] Based on the above embodiment A, in another optional example, the first region can be enlarged proportionally, so that each boundary point of the first region is extended away from the center point. This method can make the expanded second region exactly the same as the "graphics" of the original first region. This expansion method is more reasonable. If the boundary outline of the first region is circular, then the boundary outline of the second region is also circular.

[0054] Based on the above embodiment A, in an optional example, the first region is expanded based on the weighting coefficient of the obstacle object to obtain the second region, including: determining the smallest rectangle surrounding the first region as the initial rectangle; determining the length and width of the initial rectangle; calculating the product of the length and width of the initial rectangle and the weighting coefficient of the obstacle object to obtain the length and width of the expanded rectangle; and taking the expanded rectangle whose center point coincides with the center point of the initial rectangle as the second region.

[0055] Figure 2 This is a schematic diagram of a region expansion method, such as... Figure 2 As shown, t1 is the first region, t2 is the smallest rectangle surrounding the first region, and t3 is the second region after expansion. Since the obstacle object may be an irregular object, transforming the first region of the obstacle object into a rectangle before expanding the region simplifies the edge determination process after expansion, simplifies data processing, and improves data processing speed.

[0056] Based on the above embodiment A, in another optional example, the first region is expanded based on the weighted coefficient of the obstacle object to obtain a second region. This includes: determining the center point of the corresponding first region for each obstacle object; selecting boundary points at preset intervals on the boundary of the first region; obtaining the line connecting the boundary point and the center point for each boundary point to obtain an initial line; calculating the product of the length of the initial line and the weighted coefficient of the obstacle object to obtain an extension length; extending the initial line away from the center point to the extension length, and determining the end point reached by the extended initial line; after setting the end point corresponding to each boundary point, the area enclosed by each end point is taken as the second region. The interval distance of the boundary points can be set according to the actual size and regularity of the obstacle object. The larger the area of ​​the obstacle object or the better its regularity, the larger the interval distance; the smaller the area of ​​the obstacle object or the worse its regularity, the smaller the interval distance. In this way, the area of ​​the region expansion can be reduced while uniformly expanding the area of ​​the first region, and the number of points selected on the boundary can also be reduced, making the "graphics" of the expanded second region more similar to the original first region.

[0057] In another alternative embodiment B, the detection accuracy is higher for obstacles with a large footprint because a smaller expansion coefficient can be set. Conversely, the detection accuracy is lower for obstacles with a small footprint because a larger expansion coefficient can be set. This reduces the edge detection error of the millimeter-wave radar for smaller obstacles and improves the safety of automatic parking.

[0058] S105. Using the second area as the obstacle avoidance zone, control the waiting vehicle to move from its current position to the target parking space.

[0059] Once the obstacle avoidance area is determined, the route can be planned with the target parking space as the endpoint, and the vehicle can be controlled to drive to the target parking space.

[0060] The automatic parking method provided in this invention involves a millimeter-wave radar installed on the vehicle waiting to park. The millimeter-wave radar acquires the positional information of target objects and obstacles surrounding the vehicle. When an empty parking space is detected, the target parking space is determined from the empty spaces, and a planar coordinate system is established with the current position of the vehicle waiting to park as the origin. The projection area of ​​the obstacle object in the planar coordinate system is acquired to obtain a first region. For each obstacle object, the first region is expanded according to the obstacle object's positional information to obtain a second region. Using the second region as the obstacle avoidance region, the vehicle is controlled to move from its current position to the target parking space. When acquiring the second region (i.e., the obstacle avoidance region), the original first region containing the obstacle object is expanded, resulting in a virtual edge for the obtained obstacle avoidance region. Even if the vehicle approaches this virtual edge, no friction or expansion will occur, improving the safety and feasibility of applying millimeter-wave radar to automatic parking. Furthermore, the expansion of the first region is combined with the positional information of the obstacle object, allowing for different degrees of expansion for different obstacle objects based on their positional characteristics, thus improving the flexibility and safety of automatic parking.

[0061] Example 2

[0062] Figure 3 This is a flowchart of an automatic parking method provided in Embodiment 2 of the present invention. This embodiment is an optimization based on Embodiment 1 described above, such as... Figure 3 As shown, the automatic parking method includes:

[0063] S301. Acquire target objects and their pose information around the vehicle waiting to be parked using millimeter-wave radar. Target objects include parking spaces and obstacles.

[0064] S302. When an empty parking space is detected, the target parking space is determined from the empty parking spaces, and a planar coordinate system is established with the current location of the vehicle waiting to park as the origin.

[0065] S303. Obtain the projection area of ​​the obstacle object in the planar coordinate system to obtain the first region.

[0066] S301-S303 are similar to S101-S103 in Embodiment 1, and you can refer to the relevant descriptions of S101-S103 for details.

[0067] S304. Determine whether the obstacle has moved based on its pose information.

[0068] If yes, then execute S305; otherwise, execute S306.

[0069] Specifically, the pose information includes position information; determining whether the obstacle has moved based on its pose information includes: determining the moving speed of the obstacle based on its position information within the most recent preset time period; determining whether the moving speed is greater than a preset speed threshold; if so, determining that the obstacle has moved; if not, determining that the obstacle is fixed.

[0070] Since the vehicles waiting to park will detect and update the pose information of obstacles in real time, it is also possible to determine whether the obstacles are moving in real time. Therefore, for obstacles with a high moving speed (such as other vehicles with a high moving speed), their motion uncertainty is also high, and the real-time detection requirements for vehicles waiting to park are high. Therefore, they are classified as moving objects for subsequent processing. On the other hand, for obstacles with a low moving speed (such as pedestrians walking in place) or fixed obstacles, their motion uncertainty is low, and the real-time detection requirements for vehicles waiting to park are low. Therefore, they are classified as fixed objects. In the subsequent steps of this embodiment, the region expansion method for moving objects is more complex than that for fixed objects. Therefore, by setting the moving speed, the number of moving objects can be reasonably limited to maximize data processing efficiency.

[0071] S305. The weighting coefficients for the obstacle object are determined as the first coefficient and the third coefficient.

[0072] S306. Determine the weighting coefficient of the obstacle object as the first coefficient.

[0073] The third coefficient is greater than the first coefficient, and both the first and third coefficients are greater than 1. This shows that the weighting coefficient for moving obstacles is higher than that for fixed obstacles.

[0074] Optionally, the third coefficient is also greater than or equal to the second coefficient in Example 1.

[0075] It should be noted that S307 and S308 are executed after the weighting coefficients of all obstacle objects have been set.

[0076] S307. For each moving obstacle object, perform region dilation on the first region based on the first coefficient, the third coefficient, and the pose of the obstacle object to obtain the second region.

[0077] In an optional example, for each moving obstacle object, a second region is obtained by dilating the first region based on a first coefficient, a third coefficient, and the pose of the obstacle object. This includes: determining the movement direction of the obstacle object for each moving obstacle object; dilating the first region based on the first coefficient to obtain a transition region; determining two straight lines parallel to the movement direction and passing through only one point on the transition region as target lines; connecting the intersection of the target lines and the transition region to divide the transition region into two sub-regions; designating the sub-region closer to the movement direction as the first sub-region and the sub-region farther from the movement direction as the second sub-region; dilating the first sub-region based on the third coefficient with the target lines as the boundary to obtain a third sub-region; and merging the third sub-region and the second sub-region into the second region.

[0078] Figure 4 This is a schematic diagram of a method for expanding the first region of a moving obstacle object. Figure 4 In the figure, Figures (a)-(c) represent different stages. As shown in Figure (a), Y1 is the transition region after expansion. The arrow indicates the direction of movement of the obstacle object. As shown in Figure (b), L1 and L2 are two straight lines parallel to the direction of movement and passing through only one point on the transition region. The intersection of L1 and the transition region Y1 is M, and the intersection of L2 and the transition region Y1 is N. The line connecting MN divides the transition region Y1 into the first sub-region Y11 and the second sub-region Y12. As shown in Figure (c), based on Figure (b), the first sub-region Y11 is expanded according to the third coefficient to obtain the third region Y13, which is the shaded part in Figure (c). With L1 and L2 as the limiting boundary, the third region Y13 cannot exceed L1 and L2.

[0079] As can be seen, in this example, after the first area is expanded, a secondary expansion is performed on the area near the direction of movement, and a boundary line parallel to the direction of movement is set to limit the range of the secondary expansion. In addition to reducing the friction and collision between the obstacle and the waiting vehicle, an additional redundant space is set for the direction of movement of the obstacle. Thus, the planned parking path can provide sufficient reaction time for the current waiting vehicle, reduce the possibility of collision and friction, and improve parking safety.

[0080] S308. For each fixed obstacle object, expand the first region based on the first coefficient to obtain the second region.

[0081] The region expansion method of S308 can refer to the region expansion method of Embodiment 1, which will not be described in detail here.

[0082] S309. Using the second area as the obstacle avoidance zone, control the waiting vehicle to move from its current position to the target parking space.

[0083] S309 is similar to S105 in Embodiment 1, and S105 can be referred to for details.

[0084] In the automatic parking method of this invention, when expanding the first area, for moving obstacles, in addition to expanding the original first area once, a second expansion is performed on a portion of the area in the direction of movement. That is, additional redundant space is set for the direction of movement of the obstacle. Thus, the planned parking path can provide sufficient reaction time for the current waiting vehicle, reduce the possibility of collision and friction, and improve parking safety.

[0085] Example 3

[0086] Figure 5 This is a schematic diagram of an automatic parking device provided in Embodiment 3 of the present invention. Figure 5 As shown, the automatic parking device includes:

[0087] Data acquisition module 501 is used to acquire target objects around the vehicle waiting to be parked and the position and pose information of the target objects through millimeter-wave radar. The target objects include parking spaces and obstacle objects.

[0088] The initialization module 502 is used to determine the target parking space from the available parking spaces when an available parking space is detected, and to establish a planar coordinate system with the current location of the vehicle waiting to park as the origin.

[0089] The first region acquisition module 503 is used to acquire the projection region of the obstacle object in the planar coordinate system to obtain the first region;

[0090] The second region acquisition module 504 is used to dilate the first region for each obstacle object according to the pose information of the obstacle object to obtain a second region.

[0091] The parking control module 505 is used to control the vehicle waiting to be parked to drive from its current position to the target parking space, using the second area as the obstacle avoidance area.

[0092] Optionally, initialization module 502 includes:

[0093] The size parameter acquisition submodule is used to acquire the size parameters of the vehicle waiting to park and the size parameters of the empty parking space when an empty parking space is detected.

[0094] The target parking space determination submodule is used to determine the target parking space from the available parking spaces based on the size parameters of the vehicle to be parked and the available parking spaces.

[0095] Optionally, the second region acquisition module 504 includes:

[0096] The first submodule for determining movement is used to determine whether the obstacle object has moved based on its pose information; if so, the content of the first submodule for determining coefficients is executed; if not, the content of the second submodule for determining coefficients is executed.

[0097] The coefficient determination first submodule is used to determine the weighted coefficient corresponding to the obstacle object as the first coefficient if the obstacle object moves;

[0098] The second submodule for determining coefficients is used to determine the weighted coefficient corresponding to the obstacle object as the second coefficient if the obstacle object is fixed.

[0099] The second region acquisition submodule is used to perform region expansion on the first region based on the weighting coefficient of the obstacle object to obtain the second region.

[0100] Wherein, the first coefficient is greater than the second coefficient, and both the first coefficient and the second coefficient are greater than 1.

[0101] Optionally, the second region acquisition submodule includes:

[0102] The center point determination unit is used to determine the center point of the corresponding first region for each of the obstacle objects;

[0103] A boundary point determination unit is used to select boundary points on the boundary of the first region at preset intervals.

[0104] An initial line determination unit is used to obtain the line connecting the boundary point and the center point for each boundary point to obtain an initial line;

[0105] The stretch length calculation unit is used to calculate the product of the length of the initial line and the weighting coefficient of the obstacle object to obtain the stretch length;

[0106] The end point determination unit is used to extend the initial line in a direction away from the center point to the stretch length, and determine the end point reached by the extended initial line;

[0107] The second region determination unit is used to define the region enclosed by each end point as the second region after the end point corresponding to each boundary point is set.

[0108] Optionally, the second region acquisition module 504 also includes:

[0109] The second submodule for movement determination is used to determine whether the obstacle object has moved based on its pose information; if so, the content of the third submodule for coefficient determination is executed; if not, the content of the fourth submodule for coefficient determination is executed.

[0110] The third submodule for determining coefficients is used to determine the weighting coefficients of the obstacle object as the first coefficient and the third coefficient;

[0111] The fourth submodule for determining coefficients is used to determine the weighting coefficient of the obstacle object as the first coefficient.

[0112] The first submodule for region expansion is used to expand the first region based on the first coefficient, the third coefficient, and the pose of the obstacle object for each moving obstacle object to obtain a second region.

[0113] The second submodule for region expansion is used to expand the first region based on the first coefficient for each fixed obstacle object to obtain a second region;

[0114] Wherein, the third coefficient is greater than the first coefficient, and both the first coefficient and the third coefficient are greater than 1.

[0115] Optional, the first submodule of region expansion includes:

[0116] A movement direction determination unit is used to determine the movement direction of each moving obstacle object;

[0117] A transition region determination unit is used to perform region expansion on the first region based on the first coefficient to obtain a transition region.

[0118] The target line determination unit is used to determine two straight lines that are parallel to the direction of movement and pass through only one point in the transition region, as target lines;

[0119] The sub-region division unit is used to connect the intersection points of the target line and the transition region, thereby dividing the transition region into two sub-regions;

[0120] The second sub-region acquisition unit is used to designate the sub-region closer to the direction of movement as the first sub-region and the sub-region farther from the direction of movement as the second sub-region.

[0121] The third sub-region determination unit is used to expand the first sub-region based on the third coefficient, using the target straight line as the limiting boundary, to obtain the third sub-region.

[0122] The second region acquisition unit is used to merge the third sub-region and the second sub-region into a second region.

[0123] Optionally, the pose information includes position information; the second submodule for movement determination includes:

[0124] A moving speed determination unit is used to determine the moving speed of the obstacle object based on the location information of the obstacle object within the most recent preset time period;

[0125] The speed determination unit is used to determine whether the moving speed is greater than a preset speed threshold; if yes, the content of the movement determination unit is executed; if no, the content of the fixation determination unit is executed.

[0126] A movement determination unit is used to determine the movement of the obstacle object;

[0127] A fixed determination unit is used to determine that the obstacle object is fixed.

[0128] The automatic parking device provided in this embodiment of the invention can execute the automatic parking method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0129] Example 4

[0130] Figure 6 A schematic diagram of an electronic device 40 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0131] like Figure 6 As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42 or a random access memory (RAM) 43, communicatively connected to the at least one processor 41. The memory stores computer programs executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer program stored in the ROM 42 or loaded into the RAM 43 from storage unit 48. The RAM 43 may also store various programs and data required for the operation of the electronic device 40. The processor 41, ROM 42, and RAM 43 are interconnected via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0132] Multiple components in electronic device 40 are connected to I / O interface 45, including: input unit 46, such as keyboard, mouse, etc.; output unit 47, such as various types of monitors, speakers, etc.; storage unit 48, such as disk, optical disk, etc.; and communication unit 49, such as network card, modem, wireless transceiver, etc. Communication unit 49 allows electronic device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0133] Processor 41 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as automatic parking methods.

[0134] In some embodiments, the automatic parking method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 40 via ROM 42 and / or communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the automatic parking method described above may be performed. Alternatively, in other embodiments, processor 41 may be configured to perform the automatic parking method by any other suitable means (e.g., by means of firmware).

[0135] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0136] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0137] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0138] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0139] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0140] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0141] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0142] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An automatic parking method, characterized in that, The method includes: A millimeter-wave radar is installed on the vehicle waiting to be parked. The millimeter-wave radar is used to acquire the target objects around the vehicle waiting to be parked and the position and pose information of the target objects, including parking spaces and obstacle objects. When an empty parking space is detected, the target parking space is determined from the empty parking spaces, and a planar coordinate system is established with the current location of the vehicle waiting to park as the origin. The projection region of the obstacle object in the planar coordinate system is obtained to obtain the first region; For each obstacle object, the first region is expanded according to the pose information of the obstacle object to obtain the second region; Using the second area as the obstacle avoidance zone, control the vehicle waiting to park to move from its current position to the target parking space; For each obstacle object, the first region is dilated based on the pose information of the obstacle object to obtain a second region, including: Determine whether the obstacle has moved based on its pose information; If so, then the weighting coefficients of the obstacle object are determined to be the first coefficient and the third coefficient; If not, then the weighting coefficient of the obstacle object is determined as the first coefficient; For each moving obstacle object, the first region is dilated based on the first coefficient, the third coefficient, and the pose of the obstacle object to obtain a second region; For each fixed obstacle object, the first region is expanded based on the first coefficient to obtain a second region; Wherein, the third coefficient is greater than the first coefficient, and both the first coefficient and the third coefficient are greater than 1.

2. The method as described in claim 1, characterized in that, When an available parking space is detected, the target parking space is determined from the available spaces, including: When an empty parking space is detected, the size parameters of the vehicle waiting to park and the size parameters of the empty parking space are obtained. The target parking space is determined from the available parking spaces based on the size parameters of the vehicle to be parked and the available parking spaces.

3. The method as described in claim 1, characterized in that, For each moving obstacle object, the first region is dilated based on the first coefficient, the third coefficient, and the pose of the obstacle object to obtain a second region, including: For each moving obstacle object, determine the direction of movement of the obstacle object; Based on the first coefficient, the first region is expanded to obtain a transition region; Two straight lines parallel to the direction of movement and passing through only one point in the transition region are identified as target straight lines; Connect the intersection of the target straight line and the transition region to divide the transition region into two sub-regions; The sub-region closer to the direction of movement is designated as the first sub-region, and the sub-region farther from the direction of movement is designated as the second sub-region. Using the target straight line as the limiting boundary, the first sub-region is expanded based on the third coefficient to obtain the third sub-region; The third sub-region and the second sub-region are merged into a second region.

4. The method as described in claim 1, characterized in that, The pose information includes position information; determining whether the obstacle object has moved based on its pose information includes: The movement speed of the obstacle is determined based on its location information within the most recent preset time period. Determine whether the moving speed is greater than a preset speed threshold; If so, then it is determined that the obstacle object has moved; If not, then the obstacle object is determined to be fixed.

5. An automatic parking device, characterized in that, The automatic parking device is used to perform the automatic parking method as described in any one of claims 1-4, the automatic parking device comprising: The data acquisition module is used to acquire target objects around the vehicle waiting to be parked and the position and pose information of the target objects through millimeter-wave radar. The target objects include parking spaces and obstacle objects. An initialization module is used to determine the target parking space from the available parking spaces when an available parking space is detected, and to establish a planar coordinate system with the current location of the vehicle waiting to park as the origin. The first region acquisition module is used to acquire the projection region of the obstacle object in the planar coordinate system to obtain the first region; The second region acquisition module is used to dilate the first region for each obstacle object according to the pose information of the obstacle object to obtain a second region. The parking control module is used to control the vehicle waiting to be parked to move from its current position to the target parking space, using the second area as the obstacle avoidance area.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the automatic parking method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the automatic parking method according to any one of claims 1-4.

Images