A parking path planning method, device, equipment and storage medium

Abstract

The application discloses a parking path planning method and device, equipment and a storage medium, which are applied to a vehicle with multiple target detection devices, positioning modes of the multiple target detection devices include absolute positioning and relative positioning, and the method comprises the following steps: acquiring first parking space information in an initial device coordinate system; determining a parking map coordinate system and a first coordinate conversion relationship based on the first parking space information; acquiring a first vehicle coordinate and first obstacle target information in the initial device coordinate system; converting the first parking space information, the first vehicle coordinate and the first obstacle target information to the parking map coordinate system according to the first coordinate conversion relationship; and generating a collision-free parking path in the parking map coordinate system. The application realizes decoupling of path planning and positioning modes, and can make information collected by devices adopting different positioning modes to be mutual backups while only one set of parking system is adopted.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and more particularly to the fields of autonomous parking, valet parking, and assisted parking technology, specifically to a parking path planning method, apparatus, device, and storage medium. Background Technology

[0002] An Automatic Parking System (APS) is a comprehensive system integrating environmental perception, decision-making and planning, intelligent control and execution, and is an important component of intelligent driving assistance systems. The APS acquires positioning or perception information based on high-precision maps, visual SLAM, radar, surround view, and ultrasonic sensors. Based on this positioning and perception information, it plans a parking path and controls the vehicle to drive into the parking space along the planned path.

[0003] The devices used to acquire positioning and perception information include those employing absolute positioning methods such as high-precision maps and visual SLAM, as well as those using relative positioning methods such as radar, surround view, and ultrasonic sensors. Existing automatic parking methods typically require the development of corresponding parking path planning modules for devices with different positioning methods, reducing their versatility. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a parking path planning method, apparatus, device and storage medium for vehicle systems with devices having different positioning methods, so that devices using absolute positioning and devices using relative positioning can share a single parking path planning system.

[0005] To address the aforementioned technical problems, the first aspect of this invention proposes a parking path planning method, applied to a vehicle equipped with multiple target detection devices, wherein the positioning methods employed by the multiple target detection devices include absolute positioning and relative positioning, and the method includes:

[0006] The parking space information of the target parking space is obtained in the initial device coordinate system as the first parking space information; wherein, the initial device coordinate system is the coordinate system of the target detection device at the initial time;

[0007] Based on the first parking space information, a parking map coordinate system and a first coordinate transformation relationship are determined; wherein, the first coordinate transformation relationship is used for coordinate transformation from the initial device coordinate system to the parking map coordinate system;

[0008] In the initial device coordinate system, the vehicle coordinates at the initial moment are obtained as the first vehicle coordinates, and the obstacle target information at the initial moment is obtained as the first obstacle target information;

[0009] Based on the first coordinate transformation relationship, the first parking space information, the first vehicle coordinates, and the first obstacle target information in the initial device coordinate system are transformed to obtain the second parking space information, the second vehicle coordinates, and the second obstacle target information in the parking map coordinate system.

[0010] Based on the second parking space information, the second vehicle coordinates, and the second obstacle target information in the parking map coordinate system, a collision-free parking path is generated for the vehicle to park in the target parking space.

[0011] Furthermore, after generating the collision-free parking path for the vehicle to park in the target parking space, the method further includes:

[0012] The vehicle coordinates at the current moment are obtained in the current device coordinate system as the third vehicle coordinates; wherein, the current device coordinate system is the coordinate system of the target detection device at the current moment;

[0013] Perform coordinate transformation on the third vehicle coordinates in the current device coordinate system to obtain the fourth vehicle coordinates in the parking map coordinate system;

[0014] Based on the fourth vehicle coordinates and the second parking space information, determine whether the vehicle has been parked in the target parking space;

[0015] If not, obtain the obstacle target information at the current moment in the current device coordinate system as the third obstacle target information;

[0016] The coordinates of the third obstacle target information in the current device coordinate system are transformed to obtain the fourth obstacle target information in the parking map coordinate system;

[0017] Determine whether the fourth obstacle target information and the parking path meet the preset no-collision constraint conditions;

[0018] If not, update the parking path based on the second parking space information, the fourth vehicle coordinates, and the fourth obstacle target information to obtain an updated collision-free parking path; then proceed to the step of determining whether the vehicle has been parked in the target parking space.

[0019] Furthermore, the target detection device uses absolute positioning.

[0020] The step of performing coordinate transformation on the third vehicle coordinates in the current device coordinate system to obtain the fourth vehicle coordinates in the parking map coordinate system includes: performing coordinate transformation on the third vehicle coordinates in the current device coordinate system according to the first coordinate transformation relationship to obtain the fourth vehicle coordinates in the parking map coordinate system;

[0021] The step of performing coordinate transformation on the third obstacle target information in the current device coordinate system to obtain the fourth obstacle target information in the parking map coordinate system includes: performing coordinate transformation on the third obstacle target information in the current device coordinate system according to the first coordinate transformation relationship to obtain the fourth obstacle target information in the parking map coordinate system.

[0022] Furthermore, the target detection device uses relative positioning; the coordinate transformation of the third obstacle target information in the current device coordinate system to obtain the fourth obstacle target information in the parking map coordinate system includes:

[0023] The third obstacle target information in the current device coordinate system is transformed according to the second coordinate transformation relationship to obtain the fifth obstacle target information in the initial device coordinate system; wherein, the second coordinate transformation relationship is used for coordinate transformation from the current device coordinate system to the initial device coordinate system;

[0024] Based on the first coordinate transformation relationship, the fifth obstacle target information in the initial device coordinate system is transformed to obtain the fourth obstacle target information in the parking map coordinate system.

[0025] Furthermore, the target detection device uses relative positioning; the coordinate transformation of the third vehicle coordinates in the current device coordinate system to obtain the fourth vehicle coordinates in the parking map coordinate system includes:

[0026] The third vehicle coordinates in the current device coordinate system are transformed according to the second coordinate transformation relationship to obtain the fifth vehicle coordinates in the initial device coordinate system; wherein, the second coordinate transformation relationship is used for coordinate transformation from the current device coordinate system to the initial device coordinate system;

[0027] Based on the first coordinate transformation relationship, the coordinates of the fifth vehicle in the initial device coordinate system are transformed to obtain the coordinates of the fourth vehicle in the parking map coordinate system.

[0028] Further, determining the parking map coordinate system and the first coordinate transformation relationship based on the first parking space information includes:

[0029] Extract the coordinate information of each corner point of the parking space from the first parking space information;

[0030] The origin and coordinate axes of the parking map coordinate system are determined based on the corner points of each parking space;

[0031] The parking map coordinate system is constructed based on the origin and coordinate axes of the parking map coordinate system;

[0032] The first coordinate transformation relationship is calculated based on the coordinates of the origin of the parking map coordinate system in the initial device coordinate system and the angle of the x-axis of the parking map coordinate system in the initial device coordinate system.

[0033] Further, the step of generating a collision-free parking path for the vehicle to park in the target parking space based on the second parking space information, the second vehicle coordinates, and the second obstacle target information in the parking map coordinate system includes:

[0034] Determine the coordinates of the parking target point based on the second parking space information;

[0035] A collision-free parking path is planned from the second vehicle coordinates to the parking target point coordinates in the parking map coordinate system; wherein the vehicle outline and the obstacle target boundary do not intersect at each trajectory point on the collision-free parking path.

[0036] A second aspect of the present invention provides a parking path planning device for use in a vehicle equipped with multiple target detection devices, wherein the positioning methods employed by the multiple target detection devices include absolute positioning and relative positioning. The device comprises:

[0037] The parking space information acquisition module is used to acquire the parking space information of the target parking space as the first parking space information in the initial device coordinate system; wherein, the initial device coordinate system is the coordinate system of the target detection device;

[0038] A coordinate system establishment module is used to determine a parking map coordinate system and a first coordinate transformation relationship based on the first parking space information; wherein, the first coordinate transformation relationship is used for coordinate transformation from the initial device coordinate system to the parking map coordinate system;

[0039] The initial coordinate acquisition module is used to acquire the vehicle coordinates at the initial moment as the first vehicle coordinates and the obstacle target information at the initial moment as the first obstacle target information in the initial device coordinate system.

[0040] The coordinate transformation module is used to perform coordinate transformation on the first parking space information, the first vehicle coordinates and the first obstacle target information in the initial device coordinate system according to the first coordinate transformation relationship, so as to obtain the second parking space information, the second vehicle coordinates and the second obstacle target information in the parking map coordinate system.

[0041] The parking path planning module is used to generate a collision-free parking path for a vehicle to park in the target parking space based on the second parking space information, the second vehicle coordinates, and the second obstacle target information in the parking map coordinate system.

[0042] A third aspect of the present invention provides an electronic device comprising a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set, or an instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the parking path planning method proposed in the first aspect of the present invention.

[0043] A fourth aspect of the present invention provides a computer-readable storage medium storing at least one instruction, at least one program, a code set, or an instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the parking path planning method proposed in the first aspect of the present invention.

[0044] The implementation of this invention has the following beneficial effects:

[0045] This invention provides a parking path planning method, apparatus, device, and storage medium. By transforming information collected by detection devices using absolute positioning and those using relative positioning into a unified parking map coordinate system through coordinate transformation, and then performing path planning in the parking map coordinate system, the path planning and positioning methods are decoupled. On the one hand, this allows the parking system to be deployed on vehicle systems using different positioning, radar, and sensor devices. On the other hand, it allows parking space information inputs from multiple positioning, radar, and sensor devices to serve as backups for each other while using only one parking system.

[0046] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the 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.

[0048] Figure 1 This is a flowchart of a parking path planning method provided in an embodiment of the present invention;

[0049] Figure 2 This is a flowchart of step S120 provided in an embodiment of the present invention;

[0050] Figure 3 This is a schematic diagram of the parking map coordinate system provided in an embodiment of the present invention;

[0051] Figure 4This is a flowchart of step S150 provided in an embodiment of the present invention;

[0052] Figure 5 This is a schematic diagram illustrating the principle of determining the coordinates of a parking target point according to an embodiment of the present invention;

[0053] Figure 6 This is another flowchart of the parking path planning method provided in this embodiment of the invention;

[0054] Figure 7 This is a structural block diagram of a parking path planning device provided in an embodiment of the present invention. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout.

[0056] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0057] Example

[0058] The parking path planning method provided in this invention is applied to vehicles equipped with multiple target detection devices. These devices acquire data such as vehicle coordinates, parking space information, and obstacle target information. The positioning methods used by these target detection devices can be absolute positioning based on high-precision maps and visual SLAM, or relative positioning based on radar, surround view, panoramic view, and ultrasonic sensors. Alternatively, it can be RTK inertial navigation fusion positioning based on high-precision maps, which can be either lidar or multi-vision inertial navigation fusion positioning.

[0059] Figure 1 This is a flowchart of a parking path planning method provided in an embodiment of the present invention. This specification provides the operational steps of the method as described in the embodiments or flowchart, but based on conventional or non-inventive labor, more or fewer operational steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual system or server product execution, the method can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment) as shown in the embodiments or drawings. Specifically, as shown... Figure 1 As shown, the method may include:

[0060] S110: Obtain the parking space information of the target parking space in the initial device coordinate system as the first parking space information;

[0061] The initial device coordinate system refers to the device coordinate system of the target detection device at the initial moment. The initial moment refers to the moment when the parking map coordinate system is established. The target detection device is installed on the vehicle, and it moves with the vehicle as the vehicle parks in the target parking space. That is, the device coordinate system of the target detection device is a moving coordinate system fixed on the target detection device.

[0062] When the target detection equipment uses absolute positioning, its coordinate system can specify a point as the origin, with the eastward direction of that point as the positive x-axis and the northward direction as the positive y-axis. In other words, when the target detection equipment uses absolute positioning, the origin of its coordinate system changes with the vehicle's movement; the origin changes at different times, while the positive x-axis and positive y-axis remain constant.

[0063] When the target detection equipment uses a relative positioning method, its coordinate system can be defined with the rear axle center of the vehicle as the origin, the direction pointing forward from that point as the positive x-axis, and the direction pointing to the left of the vehicle as the positive y-axis. In other words, when the target detection equipment uses a relative positioning method, the origin of its coordinate system changes with the vehicle's movement, and the positive x-axis and positive y-axis directions may also change. Therefore, the origin, positive x-axis, and positive y-axis directions of the coordinate system may all change at different times.

[0064] When the target detection device uses absolute positioning, the parking space information of the target parking space can be obtained from the map module; when the target detection device uses relative positioning, the parking space information of the target parking space can be obtained from the perception module.

[0065] S120: Determine the parking map coordinate system and the first coordinate transformation relationship based on the first parking space information;

[0066] The parking map coordinate system is a static coordinate system that is fixed to the ground and stationary relative to the ground.

[0067] Specifically, the initial device coordinate system is a two-dimensional coordinate system, the parking map coordinate system is a two-dimensional coordinate system, and the first coordinate transformation relationship is used for coordinate transformation from the initial device coordinate system to the parking map coordinate system.

[0068] When the target detection device adopts different positioning methods, the corresponding coordinate transformation formulas for the first coordinate transformation relationship are also different.

[0069] When the target detection device uses absolute positioning, the first coordinate transformation relationship for converting the absolute positioning coordinate system to the parking map coordinate system is expressed as the absolute coordinate transformation formula Tran1.

[0070] When the target detection device adopts the relative positioning method, the first coordinate transformation relationship for transforming the initial relative positioning coordinate system to the parking map coordinate system is expressed as the relative coordinate transformation formula Tran2.

[0071] Figure 2 This is a flowchart of step S120 provided in an embodiment of the present invention, specifically as follows: Figure 2 As shown, in one embodiment, determining the parking map coordinate system based on the first parking space information may include the following steps:

[0072] S121: Extract the coordinate information of each corner point of the parking space from the first parking space information;

[0073] Based on parking space information collected by target detection devices using different positioning methods, the coordinates of the parking space corner points in the initial device coordinate system are obtained. The parking space information may include the parking space number and the coordinates of the parking space corner points, specifically the four corner points of the parking space. The first parking space information may include the parking space number and the coordinates of each corner point of the target parking space in the initial device coordinate system.

[0074] S122: Determine the origin and coordinate axes of the parking map coordinate system based on the corner points of the parking space;

[0075] Figure 3 This is a schematic diagram of the parking map coordinate system provided in an embodiment of the present invention, specifically as follows: Figure 3 As shown, in one embodiment, the origin of the parking map coordinate system can be the upper left corner of the parking space, the positive x-axis of the parking map coordinate system points from the upper left corner of the parking space to the upper right corner, and the positive y-axis of the parking map coordinate system points from the lower left corner of the parking space to the upper left corner.

[0076] The origin of the parking map coordinate system can be any one of the corner points of the parking space, or it can be other coordinate points calculated based on the four corner points of the parking space. These other coordinate points can be coordinate points located on, inside or outside the border of the target parking space enclosed by the corner points of the parking space, and preferably the center point of the target parking space.

[0077] It should be noted that the parking map coordinate system includes, but is not limited to, those used in other contexts. Figure 3 As shown, by changing any one or more of the origin position, the positive x-axis direction, and the positive y-axis direction, other variations of the parking map coordinate system can be obtained. For example, the parking map coordinate system can also be exemplified as having the upper left corner of the parking space as the origin, the positive x-axis direction as the direction from the upper left corner of the parking space to the lower left corner, and the positive y-axis direction as the direction from the upper right corner of the parking space to the upper left corner.

[0078] S123: Construct a parking map coordinate system based on the origin and coordinate axes of the parking map coordinate system.

[0079] After determining the parking map coordinate system based on the first parking space information, the process also includes determining the first coordinate transformation relationship, which may include the following steps:

[0080] The translation vector from the initial device coordinate system to the parking map coordinate system is determined based on the coordinates of the origin of the parking map coordinate system in the initial device coordinate system.

[0081] The rotation matrix for transforming from the initial device coordinate system to the parking map coordinate system is determined based on the angle θ of the x-axis of the parking map coordinate system in the initial device coordinate system. For example, the coordinates (x1, y1) of a point on the x-axis of the parking map coordinate system are obtained, and their coordinates (x2, y2) in the initial device coordinate system are calculated using the arctangent formula θ = tan... -1 (x1-x2, y1-y2) can be used to calculate the angle of the x-axis of the parking map coordinate system in the initial device coordinate system, where y1 = 0.

[0082] The first coordinate transformation relationship from the initial device coordinate system to the parking map coordinate system is constructed based on the translation vector and the rotation matrix, namely the absolute coordinate transformation formula Tran1 and the relative coordinate transformation formula Tran2 described below.

[0083] For example, if the origin (0, 0) of the parking map coordinate system has coordinates (xo, yo) in the initial device coordinate system. T The translation vector from the initial device coordinate system to the parking map coordinate system is T = (xo, yo). T ;

[0084] The angle of the x-axis of the parking map coordinate system in the initial device coordinate system is θ. The rotation matrix for transforming from the initial device coordinate system to the parking map coordinate system is:

[0085] Let the coordinates of a point in the initial device coordinate system be (xi, yi). T The coordinates of in the parking map coordinate system are (xj, yj). T Then the first coordinate transformation relationship is:

[0086] (xj,yj) T =R·((xi,yi) T -T)

[0087] Where R is the rotation matrix and T is the translation vector.

[0088]

[0089]

[0090] S130: In the initial device coordinate system, obtain the vehicle coordinates at the initial moment as the first vehicle coordinates, and obtain the obstacle target information at the initial moment as the first obstacle target information;

[0091] The initial device coordinate system is the device coordinate system of the target detection device at the initial moment. The first vehicle coordinate system is the vehicle coordinate system acquired at the initial moment in the initial device coordinate system, specifically the coordinates of a specific position of the vehicle, including but not limited to the rear axle center point, the geometric center of the vehicle, and the center of gravity of the vehicle. The first obstacle target information is the obstacle target information acquired at the initial moment in the initial device coordinate system.

[0092] The initial time is the moment when the parking map coordinate system is established, and the initial position of the vehicle is the initial vehicle position.

[0093] Specifically, obstacle target information includes target number, target type, and target bounding box. The English name for the target bounding box is bounding box, which specifically refers to the several sides that make up the target's outer shape.

[0094] It should be noted that steps S110, S120, and S130 can also be performed in other orders or simultaneously. For example, step S130 can be performed simultaneously with steps S110 and S120; step S130 can also occur before step S110; or step S130 can occur after step S110 and before step S120.

[0095] S140: Perform coordinate transformation on the first parking space information, first vehicle coordinates and first obstacle target information in the initial equipment coordinate system according to the first coordinate transformation relationship to obtain the second parking space information, second vehicle coordinates and second obstacle target information in the parking map coordinate system;

[0096] Specifically, when the initial device coordinate system is an absolute coordinate system, step S140 includes:

[0097] The first parking space information is transformed into the parking map coordinate system according to the absolute coordinate transformation formula Tran1, and the second parking space information in the parking map coordinate system is obtained.

[0098] The first vehicle coordinates are transformed to the parking map coordinate system using the absolute coordinate transformation formula Tran1, resulting in the second vehicle coordinates in the parking map coordinate system.

[0099] The first obstacle target information is transformed into the parking map coordinate system using the absolute coordinate transformation formula Tran1, thus obtaining the second obstacle target information in the parking map coordinate system.

[0100] Specifically, when the initial device coordinate system is a relative coordinate system, step S140 includes:

[0101] The first parking space information is transformed into the parking map coordinate system using the relative coordinate transformation formula Tran2, thus obtaining the second parking space information in the parking map coordinate system.

[0102] The first vehicle coordinates are transformed to the parking map coordinate system using the relative coordinate transformation formula Tran2, resulting in the second vehicle coordinates in the parking map coordinate system.

[0103] The first obstacle target information is transformed into the parking map coordinate system using the relative coordinate transformation formula Tran2, thus obtaining the second obstacle target information in the parking map coordinate system.

[0104] This invention transforms the input data (including positioning information and / or perception information) obtained by target detection devices based on different positioning methods (including absolute positioning and relative positioning) into the parking map coordinate system through coordinate transformation, and performs path planning in the newly established parking map coordinate system, thereby decoupling parking path planning from the positioning method.

[0105] S150: Generate a collision-free parking path for the vehicle to park in the target parking space based on the second parking space information, the second vehicle coordinates, and the second obstacle target information in the parking map coordinate system.

[0106] Specifically, the collision-free parking path starts at the second vehicle coordinates and ends at the second parking space information. The collision-free parking path and the second obstacle target information satisfy preset collision-free constraints. The preset collision-free constraints include that the vehicle's outer frame and the obstacle's outer frame do not intersect at each trajectory point on the collision-free parking path.

[0107] The collision-free parking path for a vehicle to enter the target parking space is uniformly performed under the parking map coordinate system. Specifically, it can be generated using a path planning method based on motion dynamics and / or a path planning method based on curves.

[0108] Path planning methods based on motion dynamics include, but are not limited to, Hybrid A* algorithm, Kinodynamic RRT* algorithm, State Lattice Search algorithm, and Optimal Boundary Value Problem (OBVP) algorithm.

[0109] Curve-based planning methods include, but are not limited to, Bezier curves, B-spline curves, Dubins curves, and Reeds-Shepp curves.

[0110] Figure 4 This is a flowchart of step S150 provided in an embodiment of the present invention, specifically as follows: Figure 4 As shown, in one embodiment, generating a collision-free parking path for a vehicle to park in a target parking space based on the second parking space information, the second vehicle coordinates, and the second obstacle target information in the parking map coordinate system may include the following steps:

[0111] S151: Determine the coordinates of the parking target point based on the second parking space information;

[0112] The second parking space information may include the parking space number and the coordinates of each corner point of the target parking space in the parking map coordinate system; Figure 5 This is a schematic diagram showing the coordinates of each corner point of the parking space in the parking map coordinate system provided in this embodiment of the invention, specifically as follows: Figure 5 As shown, in the parking map coordinate system, the coordinates of the top left corner of the parking space are (x1, y1), the coordinates of the bottom left corner are (x2, y2), the coordinates of the top right corner are (x4, y4), and the coordinates of the bottom right corner are (x3, y3). The coordinates of each corner point of the parking space in the parking map coordinate system can be calculated based on the coordinates of each corner point in the initial device coordinate system and the first coordinate transformation relationship.

[0113] A parking target point describes the desired pose of the vehicle upon completion of parking. The coordinates of the parking target point in the parking map coordinate system can be determined based on the corner coordinates of the target parking space, vehicle size information, and the positional relationship between the vehicle and the target parking space. Upon completion of parking, the parking target point coincides with a specific position of the vehicle in the xOy plane, where the xOy plane is defined by the x-axis and y-axis of the parking map coordinate system. The specific position of the vehicle includes, but is not limited to, the rear axle center point, the vehicle's geometric center, and the vehicle's center of gravity. Other points on the vehicle can also be used as specific positions in this application.

[0114] The parking target point can be calculated based on the corner points of the parking space and the vehicle's dimensions. By substituting the corner point coordinates from the second parking space information into the parking target point calculation formula, the coordinates of the parking target point can be calculated.

[0115] For example, the coordinates of the parking target point can be represented as (gx, gy, θ), and the formula for calculating the parking target point can be expressed as:

[0116] gx = (x1 + x4) / 2;

[0117] gy = y² + lr + b;

[0118] θ = tan -1 (x1-x2, y1-y2);

[0119] lr is a known value, representing the distance from the center of the rear axle to the rear of the vehicle;

[0120] b is a known value, representing the distance from the rear of the vehicle to the bottom line of the parking space;

[0121] gx represents the x-coordinate of the target point;

[0122] gy represents the y-coordinate of the target point;

[0123] θ represents the angle between the target point and the x-axis;

[0124] θ = tan -1 (x1-x2, y1-y2) represents the angle between the target point and the x-axis obtained by using the arctangent.

[0125] S152: Plan a collision-free parking path from the second vehicle coordinates to the parking target point coordinates in the parking map coordinate system; wherein, at each trajectory point of the collision-free parking path, the vehicle outline and the obstacle target bounding box do not intersect.

[0126] In one embodiment, step S152 includes: generating a collision-free parking path for the vehicle to park in the target parking space based on the second parking space information, the second vehicle coordinates, and the second obstacle target information in the parking map coordinate system using a path planning method based on motion dynamics. The path planning methods based on motion dynamics that can be applied in this paper include, but are not limited to, Hybrid A* algorithm, Kinodynamic RRT* algorithm, State Lattice Search algorithm, and Optimal Boundary Value Problem (OBVP) algorithm.

[0127] In one embodiment, step S152 includes: generating a collision-free parking path for the vehicle to park in the target parking space based on the second parking space information, the second vehicle coordinates, and the second obstacle target information in the parking map coordinate system using a curve-based path planning method. The curve-based planning methods applicable herein include, but are not limited to, Bezier curves, B-spline curves, Dubins curves, and Reeds-Shepp curves.

[0128] In one embodiment, step S152 includes: generating a collision-free parking path for the vehicle to park in the target parking space based on the second parking space information, the second vehicle coordinates, and the second obstacle target information in the parking map coordinate system using a path planning method based on motion dynamics and a path planning method based on curves.

[0129] In other words, in practical applications, parking path planning can be performed using either the motion dynamics-based path planning method alone, or the curve-based path planning method alone, or a combination of the two methods can be used.

[0130] Figure 6 This is another flowchart of the parking path planning method provided in this embodiment of the invention, specifically as follows: Figure 6 As shown, in one embodiment, after generating a collision-free parking path for the vehicle to park in the target parking space, the following steps may also be included:

[0131] S210: Obtain the vehicle coordinates at the current moment in the current device coordinate system as the third vehicle coordinates;

[0132] Here, the current device coordinate system refers to the device coordinate system of the target detection device at the current moment. The current device coordinate system and the initial device coordinate system are device coordinate systems of the target detection device corresponding to different points in time. The initial device coordinate system refers to the device coordinate system of the target detection device at the initial moment, and the current device coordinate system refers to the device coordinate system of the target detection device at the current moment. In this way, the device coordinate systems of the target detection device at different points in time can be distinguished in the description.

[0133] When the device coordinate system is an absolute positioning coordinate system, the device coordinate system can specify a point as the origin, take the direction pointing east from that point as the positive x-axis direction, and the direction pointing north as the positive y-axis direction.

[0134] When the equipment coordinate system is a relative positioning coordinate system, the equipment coordinate system can take the center of the rear axle of the vehicle as the origin, take the direction pointing from that point to the front of the vehicle as the positive x-axis, and take the direction pointing to the left of the vehicle as the positive y-axis.

[0135] S220: Perform coordinate transformation on the third vehicle coordinates in the current device coordinate system to obtain the fourth vehicle coordinates in the parking map coordinate system;

[0136] Specifically, when the target detection device uses absolute positioning, the coordinates of the third vehicle in the current device coordinate system are transformed to obtain the coordinates of the fourth vehicle in the parking map coordinate system. This includes: transforming the coordinates of the third vehicle in the current device coordinate system according to the absolute coordinate transformation formula Tran1 to obtain the coordinates of the fourth vehicle in the parking map coordinate system.

[0137] Specifically, since the target detection equipment uses relative positioning, the coordinates of the third vehicle in the current equipment coordinate system are transformed to obtain the coordinates of the fourth vehicle in the parking map coordinate system, including:

[0138] The coordinates of the third vehicle in the current equipment coordinate system are transformed according to the second coordinate transformation relationship to obtain the coordinates of the fifth vehicle in the initial equipment coordinate system; wherein, the second coordinate transformation relationship is used for the coordinate transformation from the current equipment coordinate system to the initial equipment coordinate system; the second coordinate transformation relationship is expressed as the coordinate transformation formula Tran3.

[0139] Based on the first coordinate transformation relationship, the coordinates of the fifth vehicle in the initial device coordinate system are transformed to obtain the coordinates of the fourth vehicle in the parking map coordinate system. The first coordinate transformation relationship is expressed as the relative coordinate transformation formula Tran2.

[0140] The coordinate transformation formula from the current device coordinate system to the parking map coordinate system can be expressed as Tran3*Tran2.

[0141] Specifically, before performing coordinate transformation on the third vehicle coordinates in the current equipment coordinate system according to the second coordinate transformation relationship, the process also includes the step of determining the second coordinate transformation relationship. Determining the second coordinate transformation relationship may include the following steps:

[0142] The translation vector for transforming from the current device coordinate system to the initial device coordinate system is determined based on the coordinates of the origin of the initial device coordinate system in the current device coordinate system.

[0143] The rotation matrix for transforming from the current device coordinate system to the initial device coordinate system is determined based on the angle of the x-axis of the initial device coordinate system relative to the current device coordinate system. For example, the coordinates (x1, y1) of a point on the x-axis of the parking map coordinate system, and its coordinates (x2, y2) in the initial device coordinate system, are determined using the arctangent formula θ = tan... -1 (x1-x2, y1-y2) can be used to calculate the angle of the x-axis of the parking map coordinate system in the initial device coordinate system, where y1 = 0.

[0144] Based on the translation vector and rotation matrix, construct the second coordinate transformation relationship from the current device coordinate system to the initial device coordinate system, namely the coordinate transformation formula Tran3 described below;

[0145] For example, if the origin (0, 0) of the initial device coordinate system has coordinates (xo, yo) in the current device coordinate system. T The translation vector from the current device coordinate system to the initial device coordinate system is T = (xo, yo). T ;

[0146] The angle of the x-axis of the initial device coordinate system in the current device coordinate system is θ. The rotation matrix for transforming from the current device coordinate system to the initial device coordinate system is:

[0147] Let the coordinates of a point in the current device coordinate system be (xi, yi). T The coordinates of in the initial device coordinate system are (xj, yj). T Then the second coordinate transformation relationship is:

[0148] (xj,yj) T =R·((xi,yi) T -T)

[0149] Where R is the rotation matrix and T is the translation vector.

[0150]

[0151]

[0152] S230: Determine whether the vehicle has been parked in the target parking space based on the fourth vehicle coordinates and the second parking space information; if yes, end the process; if no, proceed to step S240.

[0153] The confirmation condition for a vehicle to have been parked in the target parking space can be set to the fourth vehicle coordinates and the parking target point coordinates meeting a preset distance condition, preferably the fourth vehicle coordinates and the parking target point coordinates coinciding.

[0154] Steps S210-S230 above are used to determine whether the vehicle has been parked in the target parking space in the parking map coordinate system. If the vehicle has not been parked in the target parking space, steps S240-S270 are executed to determine whether there is a possibility of collision between the parking path and the updated obstacle target information. If the current parking path collides with an obstacle, the parking path is replanned for real-time obstacle avoidance. Steps S210-S270 are repeated until the vehicle is parked in the target parking space.

[0155] S240: Obtain the obstacle target information at the current moment in the current device coordinate system as the third obstacle target information;

[0156] Preferably, the obstacle target information is acquired and updated in real time, or it can be acquired and updated at preset time intervals.

[0157] S250: Perform coordinate transformation on the third obstacle target information in the current device coordinate system to obtain the fourth obstacle target information in the parking map coordinate system;

[0158] Specifically, when the target detection device uses absolute positioning, step S250 may include: performing coordinate transformation on the third obstacle target information in the current device coordinate system (absolute coordinate system) according to the absolute coordinate transformation formula Tran1 to obtain the fourth obstacle target information in the parking map coordinate system.

[0159] Specifically, when the target detection device uses relative positioning, step S250 may include:

[0160] The coordinate transformation formula Tran3 is used to transform the third obstacle target information in the current device coordinate system to obtain the fifth obstacle target information in the initial device coordinate system. The coordinate transformation formula Tran3 is used to transform the current device coordinate system (relative coordinate system) to the initial device coordinate system (relative coordinate system).

[0161] The fifth obstacle target information in the initial device coordinate system (relative coordinate system) is transformed according to the relative coordinate transformation formula Tran2 to obtain the fourth obstacle target information in the parking map coordinate system.

[0162] The coordinate transformation formula from the current device coordinate system to the parking map coordinate system can be expressed as Tran3*Tran2.

[0163] S260: Determine whether the target information of the fourth obstacle and the parking path meet the preset no-collision constraint conditions; if yes, proceed to step S210; if no, proceed to step S270.

[0164] In one embodiment, step S260 may include the following steps:

[0165] Extract the target bounding box from the fourth obstacle target information;

[0166] Take the trajectory of the parking path for a future time period, and at each trajectory point, calculate whether the vehicle's outer frame and the obstacle's outer frame intersect;

[0167] Based on the calculation results, determine whether the vehicle's outer frame intersects with the obstacle's outer frame at each trajectory point of the collision-free parking path;

[0168] If they intersect, it means that if the vehicle continues to move along the parking path, it will collide with the obstacle. In this case, the fourth obstacle target information and the parking path do not meet the preset no-collision constraint conditions; otherwise, the fourth obstacle target information and the parking path meet the preset no-collision constraint conditions.

[0169] S270: Update the parking path based on the second parking space information, the fourth vehicle coordinates, and the fourth obstacle target information to obtain the updated collision-free parking path; turning step S210.

[0170] It should be noted that the present invention is not limited to the described order of actions, because according to the present invention, some steps may be performed in other orders or simultaneously.

[0171] This invention also proposes a parking path planning device, which is applied to a vehicle equipped with multiple target detection devices. The positioning methods used by these target detection devices include absolute positioning and relative positioning.

[0172] Figure 7 This is a structural block diagram of a parking path planning device provided in an embodiment of the present invention, specifically as follows: Figure 7 As shown, the device may include the following modules:

[0173] The parking space information acquisition module 310 is used to acquire the parking space information of the target parking space as the first parking space information in the initial device coordinate system;

[0174] The initial device coordinate system is the coordinate system of the target detection device at the initial moment.

[0175] The coordinate system establishment module 320 is used to determine the parking map coordinate system and the first coordinate transformation relationship based on the first parking space information; wherein, the first coordinate transformation relationship is used for coordinate transformation from the initial equipment coordinate system to the parking map coordinate system;

[0176] The initial coordinate acquisition module 330 is used to acquire the vehicle coordinates at the initial moment as the first vehicle coordinates and the obstacle target information at the initial moment as the first obstacle target information in the initial device coordinate system.

[0177] The coordinate transformation module 340 is used to perform coordinate transformation on the first parking space information, the first vehicle coordinates and the first obstacle target information in the initial device coordinate system according to the first coordinate transformation relationship, so as to obtain the second parking space information, the second vehicle coordinates and the second obstacle target information in the parking map coordinate system.

[0178] The parking path planning module 350 is used to generate a collision-free parking path for a vehicle to park in a target parking space based on the second parking space information, the second vehicle coordinates, and the second obstacle target information in the parking map coordinate system.

[0179] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0180] Embodiments of the present invention also provide a vehicle, including the parking path planning device provided in the device embodiment. It should be noted that, without departing from the scope of the embodiments of the present invention, the vehicle of the present invention can be a truck, a sport utility vehicle, a van, a motorhome, or any other type of vehicle.

[0181] Embodiments of the present invention also provide an electronic device, which includes a processor and a memory. The memory stores at least one instruction, at least one program, code set, or instruction set. The at least one instruction, at least one program, code set, or instruction set is loaded and executed by the processor to implement the parking path planning method as described in the method embodiment.

[0182] Embodiments of the present invention also provide a storage medium, which may be disposed in a server to store at least one instruction, at least one program, code set, or instruction set related to implementing the parking path planning method in the method embodiments. The at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the parking path planning method provided in the above method embodiments.

[0183] Optionally, in this embodiment, the storage medium may be located at at least one of the multiple network servers in a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0184] As can be seen from the embodiments of the parking path planning method, apparatus, device, or storage medium provided by the above embodiments of the present invention, the embodiments of the present invention decouple the path planning from the positioning method by transforming the information collected by the detection device using the absolute positioning method and the information collected by the detection device using the relative positioning method into the parking map coordinate system through coordinate transformation, and then performing path planning in the parking map coordinate system. On the one hand, the parking system can be deployed on vehicle systems using different positioning, radar, and sensor devices. On the other hand, the parking space information inputs of multiple positioning, radar, and sensor devices can be backed up while only one parking system is used.

[0185] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0186] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and server embodiments are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0187] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0188] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A parking path planning method characterized by comprising: The method is applied to a vehicle with multiple target detection devices, and positioning modes of the multiple target detection devices include absolute positioning and relative positioning, and the method comprises the following steps: acquiring, in an initial device coordinate system, parking space information of a target parking space as first parking space information, wherein the initial device coordinate system is a coordinate system of the target detection device at an initial time; determining a parking map coordinate system and a first coordinate conversion relationship based on the first parking space information, wherein the first coordinate conversion relationship is used for coordinate conversion from the initial device coordinate system to the parking map coordinate system; acquiring, in the initial device coordinate system, a vehicle coordinate at the initial time as a first vehicle coordinate and acquiring obstacle target information at the initial time as first obstacle target information; performing coordinate conversion on the first parking space information, the first vehicle coordinate and the first obstacle target information in the initial device coordinate system according to the first coordinate conversion relationship to obtain second parking space information, a second vehicle coordinate and second obstacle target information in the parking map coordinate system; generating a collision-free parking path for the vehicle to park into the target parking space according to the second parking space information, the second vehicle coordinate and the second obstacle target information in the parking map coordinate system.

2. The method of claim 1, wherein, After the generation of the collision-free parking path for the vehicle to park into the target parking space, the method further comprises the following steps: acquiring, in a current device coordinate system, a vehicle coordinate at a current time as a third vehicle coordinate, wherein the current device coordinate system is a coordinate system of the target detection device at the current time; performing coordinate conversion on the third vehicle coordinate in the current device coordinate system to obtain a fourth vehicle coordinate in the parking map coordinate system; determining whether the vehicle has parked into the target parking space according to the fourth vehicle coordinate and the second parking space information; if not, acquiring obstacle target information at the current time as third obstacle target information in the current device coordinate system; performing coordinate conversion on the third obstacle target information in the current device coordinate system to obtain fourth obstacle target information in the parking map coordinate system; determining whether the fourth obstacle target information and the parking path satisfy a preset collision-free constraint condition; if not, updating the parking path according to the second parking space information, the fourth vehicle coordinate and the fourth obstacle target information to obtain an updated collision-free parking path, and returning to the step of determining whether the vehicle has parked into the target parking space.

3. The method of claim 2, wherein, The positioning mode of the target detection device is absolute positioning. The coordinate conversion on the third vehicle coordinate in the current device coordinate system to obtain the fourth vehicle coordinate in the parking map coordinate system comprises performing coordinate conversion on the third vehicle coordinate in the current device coordinate system according to the first coordinate conversion relationship to obtain the fourth vehicle coordinate in the parking map coordinate system. The coordinate conversion of the third obstacle target information in the current device coordinate system to obtain fourth obstacle target information in the parking map coordinate system comprises: coordinate conversion of the third obstacle target information in the current device coordinate system according to the first coordinate conversion relationship to obtain the fourth obstacle target information in the parking map coordinate system.

4. The method of claim 2, wherein, The positioning mode of the target detection device is relative positioning; the coordinate conversion of the third vehicle coordinate in the current device coordinate system to obtain the fourth vehicle coordinate in the parking map coordinate system comprises: The second coordinate conversion relationship is used for coordinate conversion from the current device coordinate system to the initial device coordinate system; The first coordinate conversion relationship is used for coordinate conversion from the initial device coordinate system to the parking map coordinate system.

5. The method of claim 2, wherein, The positioning mode of the target detection device is relative positioning; the coordinate conversion of the third vehicle coordinate in the current device coordinate system to obtain the fourth vehicle coordinate in the parking map coordinate system comprises: The second coordinate conversion relationship is used for coordinate conversion from the current device coordinate system to the initial device coordinate system; The first coordinate conversion relationship is used for coordinate conversion from the initial device coordinate system to the parking map coordinate system.

6. The method of claim 1, wherein, The determination of the parking map coordinate system based on the first parking space information comprises: Extracting the coordinate information of each corner point of the first parking space information; Determining the origin and coordinate axis of the parking map coordinate system based on each corner point of the parking space; Constructing the parking map coordinate system based on the origin and coordinate axis of the parking map coordinate system.

7. The method of claim 1, wherein, The generation of the collision-free parking path of the vehicle parking into the target parking space based on the second parking space information, the second vehicle coordinate and the second obstacle target information in the parking map coordinate system comprises: Determining the parking target point coordinate according to the second parking space information; Planning a collision-free parking path from the second vehicle coordinate to the parking target point coordinate in the parking map coordinate system; wherein the vehicle outer frame and the obstacle target bounding box are not intersected at each trajectory point on the collision-free parking path.

8. A parking route planning apparatus characterized by comprising: The device is applied to a vehicle with multiple target detection devices, and the positioning modes of the multiple target detection devices include absolute positioning and relative positioning, and the device comprises: A parking space information acquisition module is configured to acquire parking space information of a target parking space in an initial device coordinate system as first parking space information; wherein the initial device coordinate system is a coordinate system of the target detection device at an initial time; The coordinate system establishing module is configured to determine a parking map coordinate system and a first coordinate conversion relationship based on the first parking space information, wherein the first coordinate conversion relationship is used for coordinate conversion from the initial device coordinate system to the parking map coordinate system. The initial coordinate obtaining module is configured to obtain a vehicle coordinate at an initial time as a first vehicle coordinate and obtain obstacle target information at the initial time as first obstacle target information in the initial device coordinate system. The coordinate conversion module is configured to perform coordinate conversion on the first parking space information, the first vehicle coordinate, and the first obstacle target information in the initial device coordinate system according to the first coordinate conversion relationship, to obtain second parking space information, a second vehicle coordinate, and second obstacle target information in the parking map coordinate system. The parking path planning module is configured to generate a collision-free parking path for the vehicle to park in the target parking space according to the second parking space information, the second vehicle coordinate, and the second obstacle target information in the parking map coordinate system.

9. An electronic device, comprising: The electronic device includes a processor and a memory, and the memory stores at least one instruction or at least one program, which is loaded and executed by the processor to implement the parking path planning method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The storage medium stores at least one instruction or at least one program, which is loaded and executed by the processor to implement the parking path planning method according to any one of claims 1 to 7.

Images