Automatic parking path planning method, device, electronic device and storage medium

Abstract

The present application provides an automatic parking path planning method, device, electronic device, and storage medium, belonging to the field of vehicle path planning technology. The method includes: when the vehicle travels to the preset starting area of ​​the target parking space, the projection point of the designated part of the vehicle in the preset starting area is determined as the starting point of parking, wherein the target parking space is a parallel parking space; based on the preset size parameters, preset constraints, and polynomial fitting algorithm of the vehicle, the parking trajectory of the vehicle from the starting point to the end point in the target parking space is determined, wherein the parking trajectory includes a continuous first segment, a second segment, and a third segment, wherein the third segment is the path of the designated part after traveling a preset angle with the minimum turning radius of the vehicle. In this way, the geometric method and the polynomial fitting algorithm can be used to realize the trajectory planning of automatic parking, simplify the calculation process of automatic parking, and facilitate the realization of automatic parking of the vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle path planning, and in particular to an automatic parking path planning method, device, electronic device and storage medium. Background Art

[0002] Intelligent driving is a rapidly developing field. Automatic parking systems, a key component of automotive intelligent driving, have been widely developed, designed, and mass-produced. These systems primarily include subsystem modules such as parking space detection, path planning, and path tracking. This paper primarily optimizes the path planning module's method for finding a horizontal parking path.

[0003] In parking systems, commonly used parking path planning methods for horizontal parking spaces include spline curve methods and intelligent optimization algorithms. Spline curve methods (such as B-spline curves) often have many constraints and path curve parameters, resulting in a complex solution process. Typical intelligent optimization algorithms (such as the rapidly expanding random tree (RRT) algorithm) are difficult to apply in practical parking systems. Summary of the Invention

[0004] In view of this, the purpose of the embodiments of the present application is to provide an automatic parking path planning method, device, electronic device and storage medium, which can improve the problems of automatic parking path planning such as large computational complexity and difficulty in application.

[0005] To achieve the above technical objectives, the technical solutions adopted in this application are as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for automatic parking path planning, the method comprising:

[0007] When the vehicle drives into a preset starting area of ​​a target parking space, the projection point of the designated part of the vehicle within the preset starting area is determined as the starting point of parking, wherein the target parking space is a parallel parking space;

[0008] Based on preset dimensional parameters of the vehicle, preset constraints, and a polynomial fitting algorithm, a parking trajectory of the vehicle from the starting point to the end point in the target parking space is determined, wherein the parking trajectory includes a first trajectory segment, a second trajectory segment, and a third trajectory segment, wherein the third trajectory segment is the path of the designated portion after the vehicle travels a preset angle with a minimum turning radius.

[0009] In conjunction with the first aspect, in some optional embodiments, determining a parking trajectory of the vehicle from the starting point to the end point in the target parking space based on preset size parameters of the vehicle, preset constraints, and a polynomial fitting algorithm includes:

[0010] Based on the preset size parameters of the vehicle, determining that the path of the designated portion after traveling the preset angle from the starting point with a unequal radius corresponding to the preset constraint condition and with the first designated point corresponding to the target parking space as the center is the first initial trajectory;

[0011] Determine a path in which the designated part travels in a straight line from the end point of the first initial trajectory to a distance corresponding to the preset constraint condition as the second initial trajectory;

[0012] Determine the path of the designated portion after the vehicle travels the preset angle with a minimum turning radius with the second designated point corresponding to the target parking space as the center as the third initial trajectory;

[0013] The first initial trajectory, the second initial trajectory, and the third initial trajectory are fitted according to the polynomial fitting algorithm to obtain the parking trajectory, wherein the first trajectory is the trajectory after fitting the first initial trajectory, the second trajectory is the trajectory after fitting the second initial trajectory, and the third trajectory is the trajectory after fitting the third initial trajectory.

[0014] In conjunction with the first aspect, in some optional embodiments, the first designated point is located on a first straight line perpendicular to an entrance edge line of the target parking space in a plane where the target parking space is located, and the first straight line passes through the starting point, and the distance between the first designated point and the starting point is the first distance corresponding to the preset constraint condition, and the first designated point is close to the entrance edge line;

[0015] The second designated point is located on a second straight line in the plane of the target parking space, which is perpendicular to the entrance edge line and passes through the end point of the third segment of the trajectory. The distance between the second designated point and the end point of the third segment of the trajectory is the minimum turning radius of the vehicle, and the second designated point is close to the entrance edge line.

[0016] In combination with the first aspect, in some optional implementations, the preset constraint condition includes the minimum position coordinate (X) of the starting point in the preset coordinate system corresponding to the target parking space. min , Y min ) and the maximum position coordinate (X max , Y max ), the calculation formula is as follows:

[0017] X min =L min -L safe -0.5*W*sin(θ)+R min *sin(θ)

[0018] Y min=0.5*W*cos(θ)+R min *(1-cos(θ))

[0019] X max =R min *sin(θ)+(Y max -R min *(1-cos(θ))-Y 31 +tan(θ)*X 31 ) / tan(θ)

[0020] Y max =R min +L road -sqrt(pow((R min +0.5*W),2)+pow((l car +L ff ),2))

[0021] X min Refers to the horizontal coordinate of the minimum position coordinate;

[0022] Y min Refers to the vertical coordinate of the minimum position coordinate;

[0023] L min Refers to the minimum parking space length;

[0024] L safe Refers to the safe distance between the corner point of the vehicle and the corner point of the target parking space;

[0025] W refers to the width of the vehicle;

[0026] θ refers to the preset angle;

[0027] R min Refers to the minimum turning radius of the vehicle;

[0028] X max Refers to the horizontal coordinate of the maximum position coordinate;

[0029] Y max Refers to the vertical coordinate of the maximum position coordinate;

[0030] L road Refers to the width of the road;

[0031] sqrt refers to the program's square root operation;

[0032] pow refers to the program's square operation;

[0033] l car Refers to the vehicle's wheelbase;

[0034] L ff Refers to the front overhang length of the vehicle;

[0035] Y 31 refers to the ordinate of the starting point in the third trajectory;

[0036] X 31 Refers to the horizontal coordinate of the starting point in the third trajectory.

[0037] In conjunction with the first aspect, in some optional implementations, before determining the projection point of the designated part of the vehicle within the preset starting area as the starting point of parking, the method further includes:

[0038] The vehicle's radar module and / or camera collects scene data of the target parking space to determine whether the target parking space is a vacant parking space. When the target parking space is a vacant parking space, a step is executed to determine the projection point of the designated part of the vehicle within the preset starting area as the starting point of parking.

[0039] In conjunction with the first aspect, in some optional implementations, before determining the projection point of the designated part of the vehicle within the preset starting area as the starting point of parking, the method further includes:

[0040] When the target parking space is not a vacant parking space, controlling the vehicle to traverse along the road of the parking lot;

[0041] When the vehicle determines that there is a vacant parking space in the parking lot through the collected scene data during traversal driving, the vacant parking space is determined as the new target parking space, and the vehicle is controlled to drive to the preset starting area of ​​the new target parking space.

[0042] In conjunction with the first aspect, in some optional implementations, the method further includes:

[0043] Control the vehicle to travel along the parking trajectory to the target parking space.

[0044] In a second aspect, an embodiment of the present application further provides an automatic parking path planning device, the device comprising:

[0045] a starting point determination unit, configured to determine, when the vehicle drives into a preset starting area of ​​a target parking space, a projection point of a designated part of the vehicle within the preset starting area as a parking starting point, wherein the target parking space is a parallel parking space;

[0046] A trajectory planning unit is configured to determine a parking trajectory of the vehicle from the starting point to the end point in the target parking space based on preset dimensional parameters of the vehicle, preset constraints, and a polynomial fitting algorithm, wherein the parking trajectory includes a first trajectory segment, a second trajectory segment, and a third trajectory segment, wherein the third trajectory segment is a path taken by the designated portion after the vehicle has traveled a preset angle with a minimum turning radius of the vehicle.

[0047] In a third aspect, an embodiment of the present application further provides an electronic device, comprising a processor and a memory coupled to each other, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the electronic device executes the above method.

[0048] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium. When the computer program is run on a computer, the computer executes the above method.

[0049] The invention adopting the above technical solution has the following advantages:

[0050] In the technical solution provided in the present application, based on the preset size parameters, preset constraints and polynomial fitting algorithm of the vehicle, the first, second and third continuous trajectories from the starting point to the end point in the target parking space can be determined as the parking trajectory of the vehicle. In this way, the geometric method and polynomial fitting algorithm can be used to realize the trajectory planning of automatic parking, simplify the parking calculation process, and make automatic parking easier to apply to vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The present application may be further illustrated by the non-limiting embodiments provided in the accompanying drawings. It should be understood that the following drawings illustrate only certain embodiments of the present application and are therefore not to be construed as limiting the scope of the present application. It is understood that a person skilled in the art can derive other relevant drawings from these drawings without inventive effort.

[0052] Figure 1 A flowchart of the automatic parking path planning method provided in an embodiment of the present application.

[0053] Figure 2 A schematic diagram of the parking trajectory of the center point of the rear axle of a vehicle provided in an embodiment of the present application.

[0054] Figure 3 A simplified structural diagram of a vehicle provided in an embodiment of the present application.

[0055] Figure 4 A parking simulation diagram of the center point of the vehicle's rear axle provided in an embodiment of the present application.

[0056] Figure 5 A schematic diagram of the starting area in a parking lot provided in an embodiment of the present application.

[0057] Figure 6 This is a schematic diagram of an optimized preset starting area of ​​a parking path provided in an embodiment of the present application.

[0058] Figure 7 Schematic diagrams of two parking methods provided in the embodiments of the present application.

[0059] Figure 8 A block diagram of an automatic parking path planning device provided in an embodiment of the present application.

[0060] Icon: 200 - automatic parking path planning device; 210 - starting point determination unit; 220 - trajectory planning unit. DETAILED DESCRIPTION

[0061] The present application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that similar or identical parts in the drawings or descriptions are numbered the same. Implementations not shown or described in the drawings are known to those of ordinary skill in the art. In the description of this application, the terms "first," "second," etc. are used solely to distinguish descriptions and are not to be construed as indicating or implying relative importance.

[0062] An embodiment of the present application provides an electronic device, which may include a processing module and a storage module. The storage module stores a computer program, which, when executed by the processing module, enables the electronic device to perform corresponding steps in the following automatic parking path planning method.

[0063] Electronic devices can be used in vehicles. For example, the electronic device is a hardware device installed in the vehicle. The electronic device may also include a central control display and other hardware modules. The hardware modules included in the electronic device can be flexibly determined based on actual conditions. For example, the electronic device may be an onboard computer.

[0064] Please refer to Figure 1 The present application also provides an automatic parking path planning method, which can be applied to the above-mentioned electronic device, and each step of the method is executed or implemented by the electronic device. The automatic parking path planning method can include the following steps:

[0065] Step 110: When the vehicle enters a preset starting area of ​​a target parking space, a projection point of a designated part of the vehicle within the preset starting area is determined as a parking starting point, wherein the target parking space is a parallel parking space.

[0066] Step 120 : Based on preset dimensional parameters of the vehicle, preset constraints, and a polynomial fitting algorithm, a parking trajectory of the vehicle from the starting point to the end point in the target parking space is determined, wherein the parking trajectory includes a first trajectory segment, a second trajectory segment, and a third trajectory segment, wherein the third trajectory segment is the path of the designated portion after the vehicle travels a preset angle with the vehicle's minimum turning radius.

[0067] The following is a detailed description of the steps in the automatic parking path planning method:

[0068] The vehicle can be driven automatically or manually to reach a preset starting area of ​​the target parking space, wherein the preset starting area can be flexibly determined according to actual conditions.

[0069] For example, an electronic device pre-stores a high-definition map of a parking lot, which contains road network data such as lane markings and parking spaces. The driver can trigger the vehicle's HMI (Human Machine Interface) module to select a target parking space, which can be any space in the parking lot. Based on the high-definition map and the selected target space, the vehicle automatically drives to the preset starting area of ​​the target space, facilitating subsequent automated parking.

[0070] Please refer to Figure 2 、 Figure 3 、 Figure 4 and Figure 5 In this embodiment, the target parking space is a parallel parking space, not a vertical parking space. Figure 2 In the figure, the rectangle formed by abcd is the schematic diagram of the parallel parking space. Figure 2 and Figure 3 In the figure, rectangles ABCD refer to the simplified structural diagram of the vehicle.

[0071] In step 110, the designated part of the vehicle can be any part of the vehicle body. For the convenience of calculation, the designated part can be the center point of the rear axle of the vehicle. When the vehicle travels to the preset starting area, the projection point of the rear axle center point of the vehicle in the preset starting area can be used as the starting point. For example, Figure 2 In the example, O1 is a starting point.

[0072] In step 120, please refer to Figure 3 The preset size parameters of the vehicle may include but are not limited to the vehicle body length L car , vehicle width W, wheelbase l car 、Front overhang distance L ff , rear overhang distance L rr , maximum front wheel equivalent turning angle and other parameters. The preset size parameters can be determined according to the vehicle's own structure.

[0073] Please refer to Figure 2 In the parking trajectory, the first segment is the curve segment from O1 to O2; the second segment is the straight segment from O2 to O3; and the third segment is the curve segment from O3 to O4.

[0074] In this embodiment, the preset constraint conditions can be flexibly determined according to actual conditions.

[0075] For example, see Figure 5 The preset constraint condition may include the minimum position coordinate (X min , Y min ) and the maximum position coordinate (X max , Y max ), namely the first and second constraints mentioned below. The preset coordinate system can be flexibly determined according to the actual situation, for example, Figure 5 In the example, the corner point d of the target parking space abcd can be used as the origin of the coordinate system to establish a rectangular coordinate system d-XY. This rectangular coordinate system is the preset coordinate system. Figure 5 In the example, the minimum position coordinate point is O 1min , the maximum position coordinate point is O 1max .

[0076] In other embodiments, the corner point c of the target parking space may be used as the origin of the preset coordinate system. The relative position of the preset coordinate system and the target parking space is not specifically limited here.

[0077] Expanding the parking starting area can provide a better parking experience. Figure 5 and Figure 6 In order to obtain a larger parking starting area, the range of the initial position O1 can be optimized. According to the first pre-set parking constraint: the selection of the lower limit position points of O1 and O2 should ensure that when the vehicle travels along O1O2, the side of the vehicle body does not collide with the target parking space vertex a. Therefore, according to reasoning, the minimum value O of the initial position O1 can be obtained. 1min The value of (X min , Y min Vertex a is the endpoint of the entrance edge of the target parking space close to the preset starting area.

[0078] In addition, according to the second parking constraint condition set in advance: when the car moves along the trajectory O1O2, it is necessary to ensure that the left end point A of the car body does not collide with the left side of the road. Therefore, according to the reasoning, the maximum value O of the initial position O1 can be obtained. 1max The value of (X max , Y max Endpoint A is the vertex on the front end of the vehicle that is away from the target parking space.

[0079] In this embodiment, the minimum position coordinate (X min , Y min ) and the maximum position coordinate (X max , Y max ) can be calculated as follows:

[0080] X min =L min -Lsafe -0.5 * W * sin(θ) + R min * sin(θ) (1)

[0081] Y min = 0.5 * W * cos(θ) + R min * (1 - cos(θ)) (2)

[0082] X max =R min *sin(θ)+(Y max -R min * (1-cos(θ))-Y 31 +tan(θ)*X 31 ) / tan(θ) (3)

[0083] Y max =R min +L road -sqrt(pow((R min +0.5*W),2)+pow((l car +L ff ),twenty four)

[0084] In the above formula, X min Refers to the horizontal coordinate of the minimum position coordinate;

[0085] Y min Refers to the vertical coordinate of the minimum position coordinate;

[0086] L min Refers to the minimum parking space length;

[0087] L safe Refers to the safe distance between the corner point of the vehicle and the corner point of the target parking space;

[0088] W refers to the width of the vehicle;

[0089] θ refers to the preset angle;

[0090] R min Refers to the minimum turning radius of the vehicle;

[0091] X max Refers to the horizontal coordinate of the maximum position coordinate;

[0092] Y max Refers to the vertical coordinate of the maximum position coordinate;

[0093] L road Refers to the width of the road;

[0094] sqrt refers to the program's square root operation;

[0095] pow refers to the program's square operation;

[0096] l car Refers to the vehicle's wheelbase;

[0097] L ff Refers to the front overhang length of the vehicle;

[0098] Y 31 refers to the ordinate of the starting point in the third trajectory;

[0099] X 31 Refers to the horizontal coordinate of the starting point in the third trajectory.

[0100] exist Figure 5 In the figure, the starting point of the third trajectory is O3.

[0101] Step 120 may include:

[0102] Based on the preset size parameters of the vehicle, determining that the path of the designated portion after traveling the preset angle from the starting point with a unequal radius corresponding to the preset constraint condition and with the first designated point corresponding to the target parking space as the center is the first initial trajectory;

[0103] Determine a path in which the designated part travels in a straight line from the end point of the first initial trajectory to a distance corresponding to the preset constraint condition as the second initial trajectory;

[0104] Determine the path of the designated portion after the vehicle travels the preset angle with a minimum turning radius with the second designated point corresponding to the target parking space as the center as the third initial trajectory;

[0105] The first initial trajectory, the second initial trajectory, and the third initial trajectory are fitted according to the polynomial fitting algorithm to obtain the parking trajectory, wherein the first trajectory is the trajectory after fitting the first initial trajectory, the second trajectory is the trajectory after fitting the second initial trajectory, and the third trajectory is the trajectory after fitting the third initial trajectory. The polynomial fitting algorithm may be a preset quintic polynomial curve fitting algorithm.

[0106] Please refer again Figure 2 In this embodiment, when calculating the parking trajectory, the third segment of the trajectory can be calculated first by reverse calculation. For example, the electronic device can first calculate the third segment of the initial trajectory based on the end point O4 in the target parking space. That is, with the second designated point M2 corresponding to the target parking space as the center, the third segment of the initial trajectory is calculated from O4 with the minimum turning radius (R2 or R minThe path after driving in the reverse direction by a preset angle θ is the path from O4 to O3. In other words, the path from O3 to O4 is the third initial trajectory. After obtaining the third initial trajectory, the second initial trajectory is a straight line segment. Therefore, a quintic polynomial can be used to perform curve fitting based on the initial point O1 and the preset constraints. Specifically, curve fitting is performed on points O1, O2, O3, and O4 to obtain the parking trajectory. This helps reduce the amount of computation.

[0107] Please refer to Figure 2 、 Figure 5 and Figure 6 The parking trajectory starts from the initial position O1 and moves at an angle of θ with the first designated point M1 as the center, then reaches O2, and then moves along the straight line O2O3 to O3. The unequal radius means: O1 with the maximum value 3*R min Calculation, that is, from O 1min to O 1max The calculation radius corresponding to different starting points is R min To 3*R min , the optimized starting area has unequal radius.

[0108] The preset starting area is set to the minimum radius R under the parking collision constraint. min From O 1min to O 1max (R); after optimization, the minimum radius R is 3 times min From O 1min to O 1max (3R), that is, from O 1min to O 1max The starting points of the path planning within the (3R) interval all meet the parking constraints.

[0109] Please refer again Figure 2 , the first designated point (M1) is located on a first straight line (the straight line where O1M1 is located) perpendicular to the entrance edge line (ad) of the target parking space in the plane where the target parking space is located, and the first straight line passes through the starting point (O1), and the distance between the first designated point and the starting point is the first distance (R1) corresponding to the preset constraint condition, and the first designated point is close to the entrance edge line;

[0110] The second designated point (M2) is located on a second straight line (the straight line where O4M2 is located) perpendicular to the entrance edge line and passing through the end point (O4) of the third segment of the trajectory in the plane of the target parking space, and the distance between the second designated point and the end point of the third segment of the trajectory is the minimum turning radius (R1 or R min ), and the second designated point is close to the entrance edge.

[0111] In order to obtain a trajectory with continuous curvature, a fifth-order polynomial can be used to fit the first, second and third initial trajectories to obtain smooth trajectories as parking trajectories. The experimental simulation effect is shown in the figure below. Figure 4 shown.

[0112] In actual parking, the success of parking is related to the size of the parking space. According to the simulation test results, the present invention found that the minimum parking space is related to the vehicle parameters and the target parking space parameters. If different target vehicle terminal parking methods are used.

[0113] For example, the dimensions of the vehicle may be:

[0114] Body length L car =4.2m;

[0115] Vehicle width W = 1.83m;

[0116] Wheelbase car =2.65m;

[0117] Front overhang distance L ff =0.85m;

[0118] Rear overhang distance L rr =0.7m;

[0119] The maximum front wheel equivalent turning angle δ = 30°. If the vertical coordinate position of the parking end point of the side corner point of the target vehicle is set to the upper boundary of the parking space, such as Figure 7 As shown in (a), the minimum parking space requirement is 6.4 meters. If the vertical coordinate position of the parking end point of the side corner point of the target vehicle is set at the center of the side of the parking space, as shown in Figure 7 As shown in (b), at this time, the minimum parking space requirement is 6.8 meters.

[0120] Based on the above design, a geometric method using a quintic polynomial fitting curve for parallel parking spaces can be used to implement parking path planning, reducing the amount of parking computation. By optimizing the parking starting area and the minimum parking space range for vehicles to park, it is helpful to shorten the minimum size of the parking space required, expand the applicable scope of parking, and reduce the difficulty of parking.

[0121] As an optional implementation, before step 110, the method may further include:

[0122] The vehicle's radar module and / or camera collects scene data of the target parking space to determine whether the target parking space is a vacant parking space. When the target parking space is a vacant parking space, a step is executed to determine the projection point of the designated part of the vehicle within the preset starting area as the starting point of parking.

[0123] Understandably, the vehicle can collect scene data of the target parking space through a radar module and / or a camera to determine whether the target parking space is a vacant parking space through the scene data. The method for detecting a vacant parking space is to detect whether there are obstacles (such as trash cans, parked vehicles) in the target parking space that affect parking through scene data. If there are obstacles in the target parking space, it is determined that the target parking space is not a vacant parking space; if there are no obstacles in the target parking space, it is determined that the target parking space is a vacant parking space. Then, when the vehicle drives into the preset starting area of ​​the target parking space, step 110 is executed.

[0124] Before step 110, the method may further include:

[0125] When the target parking space is not a vacant parking space, controlling the vehicle to traverse along the road of the parking lot;

[0126] When the vehicle determines that there is a vacant parking space in the parking lot through the collected scene data during traversal driving, the vacant parking space is determined as the new target parking space, and the vehicle is controlled to drive to the preset starting area of ​​the new target parking space.

[0127] Specifically, the vehicle has a pre-stored high-definition map of the parking lot. Based on the road routes in the high-definition map, the vehicle can traverse various roads and continuously collect scene data during driving to determine whether there are vacant parking spaces around the vehicle. This vacant parking space is then identified as the new target parking space. This way, if the target parking space is unavailable, the vehicle can automatically search for an empty space and park there, facilitating automated parking in the parking lot.

[0128] In this embodiment, the method may further include:

[0129] Control the vehicle to travel along the parking trajectory to the target parking space.

[0130] Understandably, after determining the parking trajectory, the vehicle can adjust the turning angle of the vehicle based on the control parameters corresponding to the parking trajectory so that the vehicle travels along the parking trajectory until the center point of the rear axle of the vehicle reaches the end point O4 of the target parking space.

[0131] In addition, when the vehicle is parked in the target parking space and needs to move out of the parking space, the vehicle can automatically move out of the target parking space based on the parking trajectory. It can be understood that the process of automatically moving out of the target parking space is the opposite of the method of automatically parking into the parking space using the parking trajectory, which will not be described in detail here.

[0132] Please refer to Figure 8The present application also provides an automatic parking path planning device 200. The automatic parking path planning device 200 includes at least one software function module that can be stored in a storage module in the form of software or firmware, or embedded in an operating system (OS) of an electronic device. The processing module is configured to execute the executable modules stored in the storage module, such as the software function modules and computer programs included in the automatic parking path planning device 200.

[0133] The automatic parking path planning device 200 includes a starting point determination unit 210 and a trajectory planning unit 220 . The functions of each unit may be as follows:

[0134] a starting point determination unit 210 for determining, when the vehicle enters a preset starting area of ​​a target parking space, a projection point of a designated part of the vehicle within the preset starting area as a parking starting point, wherein the target parking space is a parallel parking space;

[0135] The trajectory planning unit 220 is configured to determine a parking trajectory of the vehicle from the starting point to the end point in the target parking space based on preset dimensional parameters of the vehicle, preset constraints, and a polynomial fitting algorithm, wherein the parking trajectory includes a first trajectory segment, a second trajectory segment, and a third trajectory segment, wherein the third trajectory segment is the path of the designated portion after the vehicle travels a preset angle with the vehicle's minimum turning radius.

[0136] Optionally, the trajectory planning unit 220 may also be used to:

[0137] Based on the preset size parameters of the vehicle, determining that the path of the designated portion after traveling the preset angle from the starting point with a unequal radius corresponding to the preset constraint condition and with the first designated point corresponding to the target parking space as the center is the first initial trajectory;

[0138] Determine a path in which the designated part travels in a straight line from the end point of the first initial trajectory to a distance corresponding to the preset constraint condition as the second initial trajectory;

[0139] Determine the path of the designated portion after the vehicle travels the preset angle with a minimum turning radius with the second designated point corresponding to the target parking space as the center as the third initial trajectory;

[0140] The first initial trajectory, the second initial trajectory, and the third initial trajectory are fitted according to the polynomial fitting algorithm to obtain the parking trajectory, wherein the first trajectory is the trajectory after fitting the first initial trajectory, the second trajectory is the trajectory after fitting the second initial trajectory, and the third trajectory is the trajectory after fitting the third initial trajectory.

[0141] Optionally, the automatic parking path planning device 200 may further include a judgment unit. Before the starting point determination unit 210 determines the projection point of the designated part of the vehicle within the preset starting area as the starting point for parking, the judgment unit is configured to collect scene data of the target parking space using the vehicle's radar module and / or camera to determine whether the target parking space is vacant. When the target parking space is vacant, the starting point determination unit 210 determines the projection point of the designated part of the vehicle within the preset starting area as the starting point for parking.

[0142] Optionally, the automatic parking path planning device 200 may further include a control unit. Before the starting point determination unit 210 determines the projection point of the designated part of the vehicle within the preset starting area as the starting point for parking, the control unit is configured to control the vehicle to traverse along the roads of the parking lot when the target parking space is not a vacant space; and when the vehicle determines that a vacant parking space exists in the parking lot based on the collected scene data during the traversal, determine the vacant parking space as a new target parking space and control the vehicle to travel to the preset starting area of ​​the new target parking space.

[0143] Optionally, the control unit may also be configured to control the vehicle to travel along the parking trajectory to the target parking space.

[0144] In this embodiment, the processing module can be an integrated circuit chip with signal processing capabilities. The above-mentioned processing module can be a general-purpose processor. For example, the processor can be a central processing unit (CPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application.

[0145] The storage module may be, but is not limited to, a random access memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, etc. In this embodiment, the storage module may be used to store parking lot road network data, high-precision maps, etc. Of course, the storage module may also be used to store programs, which the processing module executes upon receiving an execution instruction.

[0146] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the electronic device described above can refer to the corresponding processes of each step in the aforementioned method, and will not be elaborated here.

[0147] The present application also provides a computer-readable storage medium that stores a computer program, which, when executed on a computer, causes the computer to execute the automatic parking path planning method described in the above embodiment.

[0148] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented through hardware or by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, an electronic device, or a network device, etc.) to execute the methods described in each implementation scenario of the present application.

[0149] In summary, the present invention provides an automated parking path planning method, apparatus, electronic device, and storage medium. In this solution, based on the vehicle's preset dimensional parameters, preset constraints, and a polynomial fitting algorithm, a first, second, and third continuous trajectory segment from the vehicle's starting point to its destination in the target parking space can be determined as the parking trajectory. This allows for automated parking trajectory planning using geometric methods, simplifying the parking calculation process and making automated parking easier to implement on vehicles.

[0150] In the embodiments provided in the present application, it should be understood that the disclosed devices, systems and methods can also be implemented in other ways. The device, system and method embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of code, and a part of the module, program segment or code includes one or more executable instructions for implementing the specified logical function. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. In addition, the functional modules in the various embodiments of the present application can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0151] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for automatic parking path planning, characterized in that: The method comprises: When the vehicle drives into a preset starting area of ​​a target parking space, the projection point of the designated part of the vehicle within the preset starting area is determined as the starting point of parking, wherein the target parking space is a parallel parking space; Determining a parking trajectory of the vehicle from the starting point to the end point in the target parking space based on preset dimensional parameters of the vehicle, preset constraints, and a polynomial fitting algorithm, wherein the parking trajectory includes a first trajectory segment, a second trajectory segment, and a third trajectory segment, wherein the third trajectory segment is a path of the designated portion after the vehicle travels a preset angle with a minimum turning radius; The preset constraint condition includes the minimum position coordinate (X) of the starting point in the preset coordinate system corresponding to the target parking space. min , Y min ) and the maximum position coordinate (X max , Y max ), the calculation formula is as follows: X min =L min -L safe -0.5*W*sin(θ)+R min *sin(θ) Y min =0.5*W*cos(θ)+R min *(1-cos(θ)) X max =R min *sin(θ)+(Y max -R min *(1-cos(θ))-Y 31 +tan(θ)*X 31 ) / and(θ) Y max =R min +L road -sqrt(pow((R min +0.5*W),2)+pow((l car +L ff ),2)) X min Refers to the horizontal coordinate of the minimum position coordinate; Y min Refers to the vertical coordinate of the minimum position coordinate; L min Refers to the minimum parking space length; L safe Refers to the safe distance between the corner point of the vehicle and the corner point of the target parking space; W refers to the width of the vehicle; θ refers to the preset angle; R min Refers to the minimum turning radius of the vehicle; X max Refers to the horizontal coordinate of the maximum position coordinate; Y max Refers to the vertical coordinate of the maximum position coordinate; L road Refers to the width of the road; sqrt refers to the program's square root operation; pow refers to the program's square operation; l car Refers to the vehicle's wheelbase; L ff Refers to the front overhang length of the vehicle; Y 31 refers to the ordinate of the starting point in the third trajectory; X 31 Refers to the horizontal coordinate of the starting point in the third trajectory.

2. The method according to claim 1, characterized in that Determining a parking trajectory of the vehicle from the starting point to the end point in the target parking space based on preset size parameters of the vehicle, preset constraints, and a polynomial fitting algorithm includes: Based on the preset size parameters of the vehicle, determining that the path of the designated portion after traveling the preset angle from the starting point with a unequal radius corresponding to the preset constraint condition and with the first designated point corresponding to the target parking space as the center is the first initial trajectory; Determine a path in which the designated part travels in a straight line from the end point of the first initial trajectory to a distance corresponding to the preset constraint condition as the second initial trajectory; Determine the path of the designated portion after the vehicle travels the preset angle with a minimum turning radius with the second designated point corresponding to the target parking space as the center as the third initial trajectory; The first initial trajectory, the second initial trajectory, and the third initial trajectory are fitted according to the polynomial fitting algorithm to obtain the parking trajectory, wherein the first trajectory is the trajectory after fitting the first initial trajectory, the second trajectory is the trajectory after fitting the second initial trajectory, and the third trajectory is the trajectory after fitting the third initial trajectory.

3. The method according to claim 2, characterized in that The first designated point is located on a first straight line perpendicular to the entrance edge of the target parking space in the plane where the target parking space is located, and the first straight line passes through the starting point. The distance between the first designated point and the starting point is the first distance corresponding to the preset constraint condition, and the first designated point is close to the entrance edge. The second designated point is located on a second straight line in the plane of the target parking space, which is perpendicular to the entrance edge line and passes through the end point of the third segment of the trajectory. The distance between the second designated point and the end point of the third segment of the trajectory is the minimum turning radius of the vehicle, and the second designated point is close to the entrance edge line.

4. The method according to claim 1, wherein Before determining the projection point of the designated part of the vehicle within the preset starting area as the starting point of parking, the method further includes: The vehicle's radar module and / or camera collects scene data of the target parking space to determine whether the target parking space is a vacant parking space. When the target parking space is a vacant parking space, a step is executed to determine the projection point of the designated part of the vehicle within the preset starting area as the starting point of parking.

5. The method according to claim 2, characterized in that Before determining the projection point of the designated part of the vehicle within the preset starting area as the starting point of parking, the method further includes: When the target parking space is not a vacant parking space, controlling the vehicle to traverse along the road of the parking lot; When the vehicle determines that there is a vacant parking space in the parking lot through the collected scene data during traversal driving, the vacant parking space is determined as the new target parking space, and the vehicle is controlled to drive to the preset starting area of ​​the new target parking space.

6. The method according to claim 1, characterized in that The method further comprises: Control the vehicle to travel along the parking trajectory to the target parking space.

7. An automatic parking path planning device, characterized in that: The device comprises: a starting point determination unit, configured to determine, when the vehicle drives into a preset starting area of ​​a target parking space, a projection point of a designated part of the vehicle within the preset starting area as a parking starting point, wherein the target parking space is a parallel parking space; a trajectory planning unit, configured to determine a parking trajectory of the vehicle from the starting point to the end point in the target parking space based on preset dimensional parameters of the vehicle, preset constraints, and a polynomial fitting algorithm, wherein the parking trajectory includes a first trajectory segment, a second trajectory segment, and a third trajectory segment, wherein the third trajectory segment is a path of the designated portion after the vehicle travels a preset angle with a minimum turning radius of the vehicle; The preset constraint conditions include the minimum position coordinates (Xmin, Ymin) and the maximum position coordinates (Xmax, Ymax) of the starting point in the preset coordinate system corresponding to the target parking space, and the calculation formula is as follows: Xmin=Lmin-Lsafe-0.5*W*sin(θ)+Rmin*sin(θ) Ymin=0.5*W*cos(θ)+Rmin*(1-cos(θ)) Xmax=Rmin*sin(θ)+(Ymax-Rmin*(1-cos(θ))-Y31+tan(θ)*X31) / tan(θ) Ymax=Rmin+Lroad-sqrt(pow((Rmin+0.5*W),2)+pow((lcar+Lff),2)) Xmin refers to the horizontal coordinate of the minimum position coordinate; Ymin refers to the vertical coordinate of the minimum position coordinate; Lmin refers to the minimum parking space length; Lsafe refers to the safe distance between the corner point of the vehicle and the corner point of the target parking space; W refers to the width of the vehicle; θ refers to the preset angle; Rmin refers to the minimum turning radius of the vehicle; Xmax refers to the abscissa of the maximum position coordinates; Ymax refers to the vertical coordinate of the maximum position coordinate; Lroad refers to the width of the road; sqrt refers to the program's square root operation; pow refers to the program's square operation; lcar refers to the wheelbase of the vehicle; Lff refers to the front overhang length of the vehicle; Y31 refers to the ordinate of the starting point of the third trajectory; X31 refers to the horizontal coordinate of the starting point in the third trajectory.

8. An electronic device, characterized in that: The electronic device includes a processor and a memory coupled to each other, wherein a computer program is stored in the memory. When the computer program is executed by the processor, the electronic device executes the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is run on a computer, the computer is caused to execute the method according to any one of claims 1 to 6.

Images