Parking path planning method and system, readable storage medium and intelligent equipment

Abstract

The invention provides a parking path planning method and system, a readable storage medium and intelligent equipment, and the method comprises the following steps: S1, starting the parking path planning, and enabling a vehicle to obtain the positioning information of the vehicle, the position information of a target parking space, and the road boundary information; s2, taking the target parking position as a planning starting point, and reversely planning a final parking path according to the parking space boundary constraint and the road boundary constraint; and S3, according to the heading information of the end point of the warehousing path, judging whether warehouse rubbing is needed or not, if so, entering step S4, and otherwise, entering step S5. According to the method, the problem that a parking path planning method based on a geometric curve is poor in environmental space adaptability to different parking spaces is solved, and meanwhile the advantages of high calculation efficiency and easy development and parameter adjustment of the parking path planning method are fully utilized; compared with the prior art, the method has the advantages of being high in garage position posture adaptability, high in path planning calculation efficiency and the like.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving vehicles, and in particular to an autonomous driving vertical parking path planning method with adaptive parking position posture. Background Art

[0002] With the development of autonomous driving technology, autonomous driving is considered to be a promising technology. In recent years, autonomous driving technologies for various designated scenarios have gradually begun to be implemented. Among them, automatic parking technology has been widely used in mass-produced passenger cars of many brands, which helps to reduce the burden of parking problems faced by drivers, such as insufficient driving experience, small parking space or insufficient time.

[0003] However, there are still many problems to be solved when automatic parking technology is put into practical application. As an important part of automatic parking technology, the parking path generated by the path planning module directly affects the actual operation effect of the automatic parking system. At present, major manufacturers mainly use the path planning method based on the A* algorithm to generate parking paths. Although this type of method can flexibly adapt to the non-structured parking space environment, it takes a long time to calculate, the planning results are easily affected by the initial vehicle position, the generated path morphology is relatively random, and the parameters are difficult to adjust during the algorithm development and debugging process. The parking path planning method based on geometric curves has a simple structure, stable planning results, low calculation time, and convenient parameter development. However, due to its relatively fixed algorithm structure, it has poor adaptability to the environmental space of different parking spaces.

[0004] Therefore, developing a parking path planning method with strong adaptability to storage position posture, stable results and rapid calculation is an urgent problem to be solved by technical personnel in this field. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a parking path planning method, system, readable storage medium and intelligent device.

[0006] In a first aspect, the present invention provides a parking path planning method, comprising the following steps: Step S1: Start parking path planning, obtain vehicle positioning information, target parking space location information and road boundary information; Step S2: Taking the target parking location as the planning starting point, reversely plan the final warehousing path according to the storage location boundary constraints and road boundary constraints; Step S3: According to the heading information of the end point of the storage path, determine whether the storage needs to be kneaded, if so, proceed to step S4, otherwise, proceed to step S5; Step S4: According to the storage location boundary constraints and the road boundary constraints, a storage path is planned, including two paths, a backward storage path and a forward storage path, and then returning to step S3; Step S5: planning a forward path according to the end point of the currently planned path and the current actual location of the vehicle to form a complete feasible path; Step S6: Reverse the planned complete feasible path to generate the final actual parking path, and end the path planning.

[0007] Furthermore, in step S1, the vehicle obtains the current vehicle posture state in the earth global coordinate system, including the rear axle center coordinates x, y, heading angle , as well as the position and posture status of the target parking space, including the coordinates and heading of the parking end point and the coordinates of the four parking space corner points.

[0008] Furthermore, in step S2, the coordinates and heading of the parking end point are used as the planning starting point state, and the storage path is planned based on straight lines and arcs according to the storage location boundary constraints and road boundary constraints.

[0009] Furthermore, in step S3, whether the warehouse needs to be rubbed is determined based on the absolute value of the difference between the heading of the end point of the warehousing path and the heading of the outer boundary of the storage location. If the difference is less than a certain threshold, it is considered that the warehouse is not needed, otherwise it is considered that it is needed.

[0010] Furthermore, in the step S4, a storage path is planned, including two arc paths, a backward storage path and a forward storage path. The backward storage path is planned until the storage location boundary constraint is reached, and the forward storage path is planned until the road boundary constraint is reached. The two paths are combined to generate a storage path, and step S3 is entered again to determine whether it is necessary to continue the storage path.

[0011] Furthermore, in step S5, according to the terminal position information of the currently planned path and the current actual position information of the vehicle, the forward path is planned based on the Bezier curve to form a complete feasible path.

[0012] Furthermore, in step S6, the current actual position of the vehicle is taken as the path starting point, the target parking position is taken as the path end point, the planned complete feasible path is reversed, the final actual parking path is generated, and then the path planning is ended.

[0013] In a second aspect, the present invention provides an automatic driving parking path planning system, comprising: Information acquisition module: used to start parking path planning, the vehicle obtains its own vehicle positioning information, target parking space location information and road boundary information; Planning module: It is used to plan the final entry path in reverse based on the target parking location and road boundary constraints. Judgment module: used to judge whether the warehouse needs to be rubbed according to the heading information of the end point of the warehouse entry path. If so, it enters the return module, otherwise, it enters the formation module; Return module: used to plan a warehouse path according to the warehouse boundary constraints and road boundary constraints, including two paths: backward warehouse path and forward warehouse path, and return to the judgment module; Formation module: used to plan the forward path according to the end point of the currently planned path and the current actual location of the vehicle to form a complete feasible path; Generation module: used to reverse the planned complete feasible path, generate the final actual parking path, and end the path planning.

[0014] In a third aspect, the present invention provides a readable storage medium having an application program stored thereon, which implements the steps of the above-mentioned parking path planning method when executed by a processor.

[0015] In a third aspect, the present invention provides an intelligent device, comprising a memory, a processor, and an application program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned parking path planning method when executing the program.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention solves the problem of poor adaptability of the parking path planning method based on geometric curves to the environmental space of different parking spaces, while making full use of its advantages of high computational efficiency and easy development and parameter adjustment; compared with the prior art, the present invention also has the advantages of strong adaptability to parking space postures and high computational efficiency in path planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0018] Figure 1 This is a process flow chart of the parking path planning method of the present invention.

[0019] Figure 2 Schematic diagram of autonomous driving vehicles and parking spaces.

[0020] Figure 3 The diagram shows the parking planning path and its constraints with the parking location corner point P1.

[0021] Figure 4 Schematic diagram of the parking path planned and its constraints with the road boundaries.

[0022] Figure 5 This is a schematic diagram of the constraint of the storage location corner point P4. DETAILED DESCRIPTION

[0023] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the embodiments of the present invention, and should not be construed as limiting the present invention.

[0024] The present invention provides a first embodiment, such as Figure 1 As shown, this embodiment provides a parking path planning method, comprising the following steps: Step S1: Start parking path planning, the vehicle obtains the vehicle positioning information, the target parking space location information and the road boundary information; It can be understood that the vehicle obtains the current self-vehicle posture state in the earth's global coordinate system, including the rear axle center coordinates x, y, heading angle , and the position and posture status of the target parking space, including the coordinates and heading of the parking end point and the coordinates of the four parking space corner points; Specifically, the parking path planning starts, and the vehicle obtains the current self-vehicle posture state in the earth's global coordinate system, such as Figure 2 As shown, including the coordinates x, y, and heading angle of the rear axle center Sv of the vehicle , and the position and posture of the target parking space, including the coordinates and heading of the parking end point S1 and the coordinates of the four parking corner points P1, P2, P3, and P4; Step S2: Taking the target parking location as the planning starting point, reversely plan the final warehousing path according to the storage location boundary constraints and road boundary constraints; It can be understood that the coordinates and heading of the parking end point are used as the planning starting point state, and the entry path is planned based on straight lines and arcs according to the storage location boundary constraints and road boundary constraints; Specifically, Figure 3 and Figure 4 As shown, the coordinates of the parking end point S1 ( x 1, y 1) With heading As the planning starting point, according to the storage location boundary constraints and road boundary constraints, the storage entry path S1-S2-S3 is planned based on straight lines and arcs, where S1-S2 is a straight line and S2-S3 is an arc curve. The S2-S3 arc curve must meet the requirements of the vehicle's right boundary and the storage location corner point during the vehicle's driving along S2-S3. The minimum distance must be greater than the safety distance LS 1, thus, we can get the coordinates of the S2 waypoint ( , )for:

[0025] ,

[0026] in, W 1 represents the width of the berth, that is, the length of P4-P1, and R is the minimum turning radius of the vehicle. The specific coordinates of S3 can be calculated based on the collision constraint conditions between the front boundary of the vehicle and the road boundary. The collision condition can be expressed as:

[0027] Where W is the width of the vehicle, L f Indicates the distance from the front of the vehicle to the rear axle of the vehicle. It is the y-direction position of the center O3 corresponding to the S2-S3 arc curve.

[0028] Step S3: According to the heading information of the end point of the storage path, determine whether the storage needs to be kneaded, if so, proceed to step S4, otherwise, proceed to step S5; It can be understood that whether the warehouse needs to be rubbed is determined based on the absolute value of the difference between the heading of the end point of the entry path and the heading of the outer boundary of the storage location. If the difference is less than a certain threshold, it is considered that rubbed warehouse is not needed, otherwise it is considered that it is needed.

[0029] Specifically, according to the end point S of the inbound path 3+2k The absolute value of the difference between the heading angle of the destination S3 of the first planned un-kneaded storage path and the heading angle of the outer boundary P4-P1 of the storage location , to determine whether the library needs to be kneaded. If the absolute value of the difference is less than a certain threshold =5°, it is considered that kneading the warehouse is not necessary and the process goes to step S5; otherwise, it is considered that kneading is necessary and the process goes to step S4; Step S4: According to the storage location boundary constraints and the road boundary constraints, a storage path is planned, including two paths, a backward storage path and a forward storage path, and then returning to step S3; Specifically, Figure 5 As shown, a kneading path is planned, k represents the number of kneading times, that is, the kth time enters step S4, including the backward kneading path S 3+2k-2 -S 4+2k-2 and forward kneading library path S 4+2k-2 -S 3+2k Two arc paths, backward kneading path S 3+2k-2 -S 4+2k-2 The forward storage path S is set until the rear boundary or left boundary of the vehicle reaches the collision constraint condition with the storage corner point P4, that is, the x-direction distance between the rear boundary of the vehicle and the storage corner point P4 reaches Ls3. 4+2k-2 -S 3+2k The two paths are combined to generate a storage path S until the front boundary of the vehicle reaches the road boundary constraint similar to that in step S2.3+2k-2 -S 4+2k-2 -S 3+2k , the center angles of the two kneading arc curves 4+k-1 and 3+k The following conditions are met:

[0030] in, 4+2k-2 and 3+2k They represent the backward kneading path S 3+2k-2 -S 4+2k-2 The central angle of the arc curve and the forward kneading path S 4+2k-2 -S 3+2k The center angle of the arc curve. Then, go to step S3 again and set the waypoint S 3+2k As the end point of the path, determine whether it is necessary to continue kneading the warehouse, and record the number of kneading times k when the kneading warehouse condition in step S3 is no longer met as n; Step S5: planning a forward path according to the end point of the currently planned path and the current actual location of the vehicle to form a complete feasible path; It can be understood that according to the terminal position information of the currently planned path and the current actual position information of the vehicle, the forward path is planned based on the Bezier curve to form a complete feasible path.

[0031] Specifically, according to the end point S of the currently planned path 3+2k The location information and the current actual location of the vehicle Sv are used to plan the forward path S based on the 5th degree Bezier curve 3+2k -S v , its starting point ( x (0), y (0), (0)) and the end point ( x (T), y (T), (T)) is constrained to:

[0032] Where T represents the maximum number of path points of the generated 5th degree Bezier curve. Then, a complete feasible path S1-S2-S3-S4-S is formed. 3+2 -S 4+2 -S 3+4 …S 4+2k-2 -S 3+2k +…S 4+2n-2 -S 3+2n -S v , n represents the number of times of kneading the warehouse that finally satisfies the condition that no kneading is required in step S3; Step S6: Reverse the planned complete feasible path to generate the final actual parking path, and end the path planning.

[0033] It can be understood that in step S6, the current actual position of the vehicle is taken as the path starting point, the target parking position is taken as the path end point, the planned complete feasible path is reversed, the final actual parking path is generated, and then the path planning is ended.

[0034] Specifically, the current actual position of the vehicle Sv is taken as the path starting point, the target parking position S1 is taken as the path end point, and the planned complete feasible path is reversed to generate the final actual parking path S v -S 3+2n -S 4+2n-2 -S 3+2n-2 …S 3+4 -S 4+2 -S 3+2 -S4-S3-S2-S1, end of path planning.

[0035] The present invention provides a second embodiment, which provides an automatic driving parking path planning system, including: Information acquisition module: used to start parking path planning, the vehicle obtains its own vehicle positioning information, target parking space location information and road boundary information; Planning module: It is used to plan the final entry path in reverse based on the target parking location and road boundary constraints. Judgment module: used to judge whether the warehouse needs to be rubbed according to the heading information of the end point of the warehouse entry path. If so, it enters the return module, otherwise, it enters the formation module; Return module: used to plan a warehouse path according to the warehouse boundary constraints and road boundary constraints, including two paths: backward warehouse path and forward warehouse path, and return to the judgment module; Formation module: used to plan the forward path according to the end point of the currently planned path and the current actual location of the vehicle to form a complete feasible path; Generation module: used to reverse the planned complete feasible path, generate the final actual parking path, and end the path planning.

[0036] Furthermore, the information acquisition module is specifically used for: the vehicle obtains the current vehicle posture state in the earth global coordinate system, including the rear axle center coordinates x, y, heading angle , and the position and posture status of the target parking space, including the coordinates and heading of the parking end point and the coordinates of the four parking space corner points; Furthermore, the planning module is specifically used to: use the coordinates and heading of the parking end point as the planning starting point state, and plan the entry path based on straight lines and arcs according to the storage location boundary constraints and road boundary constraints; Furthermore, the judgment module is specifically used to: judge whether the warehouse needs to be rubbed according to the absolute value of the difference between the heading of the end point of the storage path and the heading of the outer boundary of the storage location, if the difference is less than a certain threshold, it is considered that the warehouse does not need to be rubbed, otherwise it is considered that it is needed; Furthermore, the return module is specifically used to: plan a warehouse kneading path, including two arc paths, a backward warehouse kneading path and a forward warehouse kneading path, the backward warehouse kneading path ends at the warehouse location boundary constraint, and the forward warehouse kneading path ends at the road boundary constraint, the two paths are combined to generate a warehouse kneading path, and the judgment module is entered again to judge whether it is necessary to continue kneading the warehouse; Furthermore, the forming module is specifically used to: plan a forward path based on a Bezier curve according to the terminal position information of the currently planned path and the current actual position information of the vehicle to form a complete feasible path; Furthermore, the generation module is specifically used to: take the current actual position of the vehicle as the path starting point, the target parking position as the path end point, reverse the planned complete feasible path, generate the final actual parking path, and then end the path planning.

[0037] The present invention provides a third embodiment, which provides a readable storage medium having an application program stored thereon, and the program, when executed by a processor, implements the steps of the parking path planning method in the first embodiment.

[0038] The present invention provides a fourth embodiment, which provides an intelligent device, including a memory, a processor, and an application stored in the memory and executable on the processor, wherein the processor implements the steps of the parking path planning method in the first embodiment when executing the program.

[0039] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0040] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0041] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0042] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A parking path planning method, characterized in that: The following steps are involved: Step S1: Start parking path planning, obtain vehicle positioning information, target parking space location information and road boundary information; Step S2: Taking the target parking location as the planning starting point, reversely plan the final warehousing path according to the storage location boundary constraints and road boundary constraints; Step S3: According to the heading information of the end point of the storage path, determine whether the storage needs to be kneaded, if so, proceed to step S4, otherwise, proceed to step S5; Step S4: According to the storage location boundary constraints and the road boundary constraints, a storage path is planned, including two paths, a backward storage path and a forward storage path, and then returning to step S3; Step S5: planning a forward path according to the end point of the currently planned path and the current actual location of the vehicle to form a complete feasible path; Step S6: Reverse the planned complete feasible path to generate the final actual parking path, and end the path planning.

2. The parking path planning method according to claim 1, characterized in that: In step S1, the vehicle obtains the current vehicle posture state in the earth global coordinate system, including the rear axle center coordinates x, y, heading angle , as well as the position and posture status of the target parking space, including the coordinates and heading of the parking end point and the coordinates of the four parking space corner points.

3. The parking path planning method according to claim 1, characterized in that: In the step S2, the coordinates and heading of the parking end point are used as the planning starting point state, and the storage path is planned based on straight lines and arcs according to the storage location boundary constraints and road boundary constraints.

4. The parking path planning method according to claim 1, characterized in that: In step S3, whether the warehouse needs to be kneaded is determined based on the absolute value of the difference between the heading of the end point of the entry path and the heading angle of the outer boundary of the storage location. If the difference is less than a certain threshold, it is considered that the warehouse does not need to be kneaded, otherwise it is considered that it is needed.

5. The parking path planning method according to claim 1, characterized in that: In the step S4, a storage path is planned, including two arc paths, a backward storage path and a forward storage path. The backward storage path is planned until the storage location boundary constraint is reached, and the forward storage path is planned until the road boundary constraint is reached. The two paths are combined to generate a storage path, and step S3 is entered again to determine whether it is necessary to continue the storage path.

6. The parking path planning method according to claim 1, characterized in that: In the step S5, according to the terminal position information of the currently planned path and the current actual position information of the vehicle, the forward path is planned based on the Bezier curve to form a complete feasible path.

7. The parking path planning method according to claim 1, characterized in that: In step S6, the current actual position of the vehicle is taken as the path starting point, the target parking position is taken as the path end point, the planned complete feasible path is reversed, the final actual parking path is generated, and then the path planning is ended.

8. An automatic driving parking path planning system, characterized in that: include: Information acquisition module: used to start parking path planning, the vehicle obtains its own vehicle positioning information, target parking space location information and road boundary information; Planning module: It is used to plan the final entry path in reverse based on the target parking location and road boundary constraints. Judgment module: used to judge whether the warehouse needs to be rubbed according to the heading information of the end point of the warehouse entry path. If so, it enters the return module, otherwise, it enters the formation module; Return module: used to plan a warehouse path according to the warehouse boundary constraints and road boundary constraints, including two paths: backward warehouse path and forward warehouse path, and return to the judgment module; Formation module: used to plan the forward path according to the end point of the currently planned path and the current actual location of the vehicle to form a complete feasible path; Generation module: used to reverse the planned complete feasible path, generate the final actual parking path, and end the path planning.

9. A readable storage medium having an application stored thereon, characterized in that: When the program is executed by a processor, the steps of the parking path planning method as claimed in any one of claims 1 to 7 are implemented.

10. A smart device comprising a memory, a processor, and an application program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the parking path planning method according to any one of claims 1 to 7 are implemented.

Images