A HybridA star planning method and system based on linear step search strategy

Abstract

The present invention relates to the technical field of path planning for automatic parking systems, and in particular to a Hybrid A-star planning method and system based on a linear step search strategy. Determine the coordinates of the vehicle starting point and the parking space target point; determine the starting point and target node of the path search; select the node with the smallest cost as the current node; use the RS curve to connect the target point; adjust the step length to expand the adjacent nodes. This dynamic adjustment can use a larger step length to speed up the search when far away from the target point and the starting point, avoiding excessive invalid expansion caused by too small a step length in the fixed step length strategy, thereby reducing computing time and resource consumption. When approaching the target point and the starting point, the step length is reduced to avoid path jumps or omissions caused by too large a step length, improve the search accuracy, and also limit the minimum step length to avoid extending the search time due to too small a step length, thereby improving the overall efficiency of path planning.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning for an automatic parking system, and in particular to a Hybrid A-star planning method and system based on a linear step search strategy. Background Art

[0002] In the automatic parking system, the choice of search strategy plays a vital role in the flexibility and efficiency of path planning. At present, the fixed step search strategy and the local adjustment step search strategy are two commonly used search methods in the HybridA star algorithm. The fixed step search strategy lacks flexibility and has low path planning efficiency. The fixed step search strategy searches and generates path points through a preset fixed distance. This method is not flexible enough because the fixed step cannot be adjusted dynamically and lacks adaptability to different environments, resulting in low path planning efficiency. The local adjustment step search strategy has a relatively high computational complexity and depends on the accuracy of the sensor, resulting in a large consumption of computing resources in practical applications. The present invention mainly improves the problem of the lack of flexibility of the fixed step search strategy in the path planning algorithm and the low path planning efficiency. By proposing a new search strategy, it aims to improve the flexibility and efficiency of path planning while maintaining moderate computational complexity. Summary of the invention

[0003] In view of the above problems existing in the prior art, the present invention is proposed.

[0004] Therefore, the present invention provides a HybridA star planning method based on a linear step search strategy, which can solve the problems of insufficient dynamic adjustment capability, low mode conversion efficiency, difficulty in optimizing the charging and discharging process, and insufficient health status monitoring existing in the traditional method.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a Hybrid A star planning method based on a linear step search strategy, comprising: determining the coordinates of a vehicle starting point and a parking space target point;

[0006] Calculate the shortest distance between the vehicle's starting point and target point and known obstacles, and make judgments based on the calculation results;

[0007] Select the node with the smallest cost value as the current node;

[0008] According to the node with the minimum cost, the smooth path connecting the current node to the target point is calculated while satisfying the motion constraints. If the connection is successful, the path is output. If the connection fails, the surrounding adjacent nodes are searched.

[0009] Calculate the distance between the current node and the starting node and the target point, and make a judgment based on the distance results between the current node and the target point or the starting node.

[0010] As a preferred solution of the Hybrid A-star planning method based on the linear step search strategy described in the present invention, wherein: the determination of the vehicle starting point coordinates and the parking space target point coordinates includes: obtaining a sensing and positioning module to establish a parking space coordinate system with the parking space entry corner point as the origin, and in the parking space coordinate system, according to the relative distance between the vehicle starting position and the parking space, calculating the vehicle at the starting point coordinate (X s ,Y s ), in the parking space coordinate system, obtain the coordinates of the four corner points of the parking space according to the length and width of the parking space, and calculate the coordinates of the parking space target point (X g ,Y g ).

[0011] As a preferred solution of the Hybrid A-star planning method based on the linear step search strategy described in the present invention, the judgment based on the calculation results includes judging the distances between the vehicle starting point and the parking space target point and the obstacle. If the vehicle starting point is close to the obstacle, the vehicle starting point is used as the starting node of the search and the parking space target point is used as the target node; if the parking space target point is closer to the obstacle, the parking space target point is used as the starting node of the search and the vehicle starting point is used as the target node.

[0012] As a preferred solution of the Hybrid A star planning method based on the linear step search strategy described in the present invention, wherein: the distance between the current node and the starting node and the target point is calculated as follows: the distance Distancestart between the current node N and the starting node S and the distance Distancegoal between the target point G are calculated, and the current node coordinates (X n ,Y n ), starting node coordinates (X s ,Y s ), target node coordinates (X g ,Y g ):

[0013]

[0014] As a preferred solution of the Hybrid A-star planning method based on a linear step search strategy described in the present invention, the judgment based on the distance result between the current node and the target point or the starting node includes: if the current node is far away from the target point or the starting node, the search step is increased to accelerate the search process; if the current node is close to the target point or the starting node, the search step is reduced. By dynamically adjusting the step, it is ensured that a feasible path is found under different distance conditions.

[0015] As a preferred solution of the Hybrid A-star planning method based on the linear step search strategy described in the present invention, the dynamically adjusted step size is expressed as:

[0016]

[0017] Calculate the linearly adjusted search step size, expressed as:

[0018] Step start =Step min +K start *Distance start

[0019] Step goal =Step min +K goal *Distaste goal ;

[0020] Among them, K start Represented as the starting node distance adjustment step factor, K goal Represents the step size factor for adjusting the distance to the target node, Step max Indicates the maximum step length allowed for path extension, Step min It is the minimum step length allowed for path expansion, Distance start_max Indicates the maximum value allowed for the calculated distance between the current node N and the starting node S. When the distance exceeds the specified range, the calculated result is limited to Distance start_max , Distance goal_max It represents the maximum value allowed for the calculated distance between the current node N and the target node S. When the distance exceeds the specified range, the calculated result is limited to Distance goal_max .

[0021] As a preferred solution of the Hybrid A-star planning method based on the linear step search strategy described in the present invention, wherein: the method of ensuring that a feasible path is found under different distance conditions includes selecting the step length Step by taking the minimum value of Stepgoal and Stepstart as the final search step length, so that when the step length is far away from the target node or the starting node, the step length is increased, the search times are reduced, and the search efficiency is accelerated; when it is close to the target node or the starting node, the step length is reduced to improve the accuracy of the path, which is expressed as:

[0022] Step=min{Step goal , Step s tart}.

[0023] As a preferred solution of the Hybrid A star planning system based on the linear step search strategy described in the present invention, it includes: a coordinate positioning module, a path planning preprocessing module, an optimal node selection module, an RS curve generation module, and a node expansion adjustment module;

[0024] The coordinate positioning module determines the coordinates of the vehicle starting point and the parking space target point;

[0025] The path planning preprocessing module determines the starting point and target node of the path search;

[0026] The optimal node selection module selects a node with the smallest cost as the current node;

[0027] The RS curve generation module uses the RS curve to connect the target points;

[0028] The node expansion adjustment module adjusts the step length to expand adjacent nodes.

[0029] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of any one of the methods in a Hybrid A star planning method based on a linear step search strategy are implemented.

[0030] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of any one of the methods in a Hybrid A-star planning method based on a linear step search strategy are implemented.

[0031] The beneficial effects of the present invention are as follows: in different parking environments, there are both forward searches from the vehicle starting point to the parking space target point and reverse searches from the parking space target point to the vehicle starting point, so the starting node and the target node of the path search may be converted. In the face of obstacles that may exist around the vehicle starting point and the relatively narrow parking space environment, the linear step search strategy dynamically adjusts the step size according to the distance between the current node and the target point and the starting point during the path planning process. This dynamic adjustment can use a larger step size to speed up the search when far away from the target point and the starting point, avoiding excessive invalid expansion caused by too small a step size in the fixed step size strategy, thereby reducing computing time and resource consumption. When approaching the target point and the starting point, the step size is reduced to avoid path jumps or omissions caused by too large a step size, improve search accuracy, and also limit the minimum step size to avoid extending the search time due to too small a step size, thereby improving the overall efficiency of path planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0033] Figure 1 A schematic flow chart of a Hybrid A-star planning method based on a linear step search strategy is provided for one embodiment of the present invention.

[0034] Figure 2 A schematic diagram of a path search of a Hybrid A-star planning method based on a linear step search strategy is provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0036] Example 1

[0037] Reference Figure 1 , which is the first embodiment of the present invention, and which provides a HybridA star planning method based on a linear step search strategy, comprising:

[0038] S1: Determine the coordinates of the vehicle starting point and the parking space target point.

[0039] 1. Establish a coordinate system based on the selected parking space: After selecting the target parking space, the perception and positioning module establishes a parking space coordinate system with the parking space entry corner as the origin;

[0040] 2. Calculate the coordinates of the vehicle starting point (X s ,Y s ): In the parking space coordinate system, the coordinates of the vehicle at the starting point (X s ,Y s );

[0041] 3. Calculate the parking space target point coordinates (X g ,Y g ): In the parking space coordinate system, obtain the coordinates of the four corner points of the parking space according to the length and width of the parking space, and then calculate the coordinates of the parking space target point (X g ,Y g ).

[0042] Obtain the coordinates of the vehicle starting point and the corner points of the parking space provided by the perception and positioning module, and determine the coordinates of the parking space target point. Determining the location of the parking space target point by using the coordinates of the four corner points can reduce the inaccuracy caused by single-point coordinate estimation and prevent calculation deviations in the path planning process. In addition, the method of using the coordinates of the four corner points to calculate the destination point can adapt to parking spaces of various shapes and angles, thereby enhancing the applicability and flexibility of the path planning algorithm in complex parking scenarios.

[0043] S2: Determine the starting point and target node of the path search.

[0044] Calculate the shortest distance between the vehicle starting point and the surrounding known obstacles. Calculate the shortest distance between the parking space target point and the surrounding known obstacles. Determine the distance between the vehicle starting point and the parking space target point and the obstacle. If the vehicle starting point is closer to the obstacle, use the vehicle starting point as the starting node of the search and the parking space target point as the target node; if the parking space target point is closer to the obstacle, use the parking space target point as the starting node of the search and the vehicle starting point as the target node. According to the relative position of the vehicle and parking space target point and the obstacle, the search direction can be flexibly adjusted to reduce the risk of collision with obstacles. At the same time, this adaptive search method avoids the expansion of invalid paths and improves the efficiency and success rate of path search.

[0045] S3: Select the node with the smallest cost as the current node.

[0046] If the vehicle starting point is used as the starting node of the path search, select forward search: If the vehicle starting point is close to the obstacle, start from the vehicle starting point, first store the vehicle starting point in the open list, expand the nodes around, and search the path forward towards the parking space target point.

[0047] If the parking space target point is used as the starting node of the path search, select reverse search: if the parking space target point is close to the obstacle, start from the parking space target point, first store the parking space target point in the open list, expand the nodes around it, and search the path in reverse direction towards the vehicle starting point.

[0048] Calculate the cost of the surrounding expanded nodes: Each time you expand a node, calculate the distance between the expanded node and the target node. Calculate the cost of the surrounding expanded nodes based on the sum of the actual path cost from the current node to the starting point and the heuristic estimate from the current node to the target point. At the same time, store these nodes in an open list, indicating that the cost of these nodes has been calculated, to avoid repeated calculations when expanding the nodes next time.

[0049] Select the node with the smallest cost as the current node: Compare the cost values ​​of all nodes in the open list, select the node with the smallest cost as the final expanded node, and use it as the current node (Xn, Yn) for the next expansion. Since the nodes in the open list are all candidate nodes for expansion, the node selected as the final expansion will be removed from the open list.

[0050] According to the distance between the vehicle starting point, the parking target point and the obstacle, if the vehicle starting point is closer to the obstacle, choose the forward search from the vehicle starting point to the parking target point; if the parking target point is closer to the obstacle, choose the reverse search from the parking target point to the vehicle starting point. Store the starting node S in the open list. When searching for a path, store the extended nodes that are not in the open list in the open list, and calculate or update the cost of the nodes in the open list through the heuristic function:

[0051] f(N)=g(N)+h(N)

[0052] Among them, g(N) is the actual cost from the starting node S to the current node N, h(N) is the estimated cost from the current node N to the target point G, and the node N with the smallest f(N) value is selected from the open list as the current node, and the current node is removed from the open list and stored in the closed list. By selecting the node with the smallest cost value for expansion, the optimality and efficiency of the search process are ensured. This method can reduce the exploration of invalid paths, thereby speeding up the search and reducing the consumption of computing resources.

[0053] S4: Use RS curve to connect the target points.

[0054] After selecting the node N with the smallest f(N) value from the open list as the current node, try to calculate the RS curve from the current node to the target point. The RS curve can generate a smoother path, which is suitable for parking path planning in a narrow space and improves the feasibility and safety of the path. If the connection is successful, the path is output. If the connection fails, enter S5 to adjust the search step size, and then return to S3 to continue expanding the node to ensure the continuity of the search.

[0055] S5: Adjust the step size to expand adjacent nodes.

[0056] When the RS curve connection fails, when expanding adjacent nodes, the distance between the current node and the start node and the target node is calculated, the step adjustment factor is calculated, and the search step is calculated based on the linear formula. The adjusted step is used to expand the adjacent nodes. The flexibility of the search is ensured by dynamically adjusting the step. When far away from the target, the step is increased to reduce the number of search iterations. When close to the target, the step is reduced to improve the accuracy of the path.

[0057] 5.1 Calculate the distance Distancestart between the current node N and the starting node S and the distance Distancegoal between the target point G, the current node coordinates (Xn, Yn), the starting node coordinates (Xs, Ys), and the target node coordinates (Xg, Yg). The distance calculation with the starting point and the target point provides a basis for step adjustment and provides data for subsequent adjustment of the step size in the path search process.

[0058]

[0059]

[0060] 5.2 Calculation of step size adjustment factor

[0061] Kstart and Kgoal are linear proportional coefficients, which are used as factors to adjust the step length to control the rate of increase and decrease of the step length as the distance changes. Among them, Stepmax and Stepmin are the maximum and minimum values ​​of the step length respectively, and Distancestart_max and Distancegoal_max are the maximum distances from the starting point and the target point respectively. When the distance from the starting point or the target point is far and reaches the maximum distance, the step length will not exceed Stepmax. The introduction of the adjustment factor makes the step length change more reasonable, ensuring that the step length is too large to cause the search to jump at a long distance, and the step length is too small to cause the search speed to be too slow at a close distance, which improves the robustness and efficiency of the search.

[0062]

[0063] 5.3 Calculate the search step size after linear adjustment

[0064] The step size Stepstart and Stepgoal are calculated based on the distance from the start node or the target node. When the distance Distancestart and Distancegoal increase, the step size Stepstart and Stepgoal increase proportionally. When the distance decreases, the step size will also decrease. The lower limit Stepmin of the step size reduction is set to avoid the step size being too small and causing the search time to be too long.

[0065] Step start =Step min +K start *Distance start

[0066] Step goal =Step min +K goal *Distance goal

[0067] The step size Step is selected by taking the minimum value of Stepgoal and Stepstart as the final search step size, so that when the step size is far away from the target node or the starting node, the step size is increased, the search times are reduced, and the search efficiency is accelerated. When it is close to the target node or the starting node, the step size is reduced to improve the accuracy of the path.

[0068] Step=min{Step goal , Step start}.

[0069] Example 2

[0070] The second embodiment of the present invention provides a Hybrid A star planning system based on a linear step search strategy, characterized in that it includes a coordinate positioning module, a path planning preprocessing module, an optimal node selection module, an RS curve generation module, and a node expansion adjustment module;

[0071] The coordinate positioning module determines the coordinates of the vehicle starting point and the parking space target point;

[0072] The path planning preprocessing module determines the starting point and target node of the path search;

[0073] The optimal node selection module selects a node with the smallest cost as the current node;

[0074] The RS curve generation module uses the RS curve to connect the target points;

[0075] The node expansion adjustment module adjusts the step length to expand adjacent nodes.

[0076] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0077] 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.

[0078] 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.

[0079] 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, a plurality of 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.

[0080] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0081] Example 3

[0082] As the third embodiment of the present invention, a Hybrid A star planning method based on a linear step search strategy is provided. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0083] After the automatic parking function is turned on, in order to avoid collisions between the vehicle and the surrounding vehicles or obstacles during parking, the vehicle will usually try to avoid running over the parking space line when parking. Therefore, the parking space line will be regarded as an obstacle when planning the path, so that the parking path planned by the algorithm is as safe as possible. As shown in the figure, the distance between the current parking space target point and the obstacle (parking space line) is closer than the distance between the parking space starting point and the surrounding obstacles. Therefore, the parking space target point is used as the starting node of the search to start the reverse search. The distance to the starting node and the target node is calculated each time the expansion is performed, and the length of the search step is dynamically adjusted. At the beginning, since the expanded node is closer to the starting node, in order to avoid collisions between the expanded node and the obstacle (parking space line), a smaller step is used. As the distance increases, the larger the space that can be searched, the step is linearly increased. Each time, the node with the smallest cost value is selected from the expanded node as the current node, and an attempt is made to use the RS curve to connect to the target node. If the connection fails, the node continues to be expanded. When the distance to the target node is closer, the step is linearly reduced. When the target point is searched, the search process ends.

[0084] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A HybridA star planning method based on a linear step search strategy, characterized in that: include, Determine the coordinates of the vehicle starting point and the parking space target point; Calculate the shortest distance between the vehicle's starting point and target point and known obstacles, and make judgments based on the calculation results; Select the node with the smallest cost value as the current node; According to the node with the minimum cost, the smooth path connecting the current node to the target point is calculated while satisfying the motion constraints. If the connection is successful, the path is output. If the connection fails, the surrounding adjacent nodes are searched. Calculate the distance between the current node and the starting node and the target point, and make a judgment based on the distance results between the current node and the target point or the starting node.

2. The HybridA star planning method based on a linear step search strategy as claimed in claim 1, characterized in that: The method of determining the coordinates of the vehicle starting point and the parking space target point includes: obtaining a sensing and positioning module to establish a parking space coordinate system with the parking space entry corner as the origin, and in the parking space coordinate system, calculating the vehicle starting point coordinate (X s ,Y s ), in the parking space coordinate system, obtain the coordinates of the four corner points of the parking space according to the length and width of the parking space, and calculate the coordinates of the parking space target point (X g ,Y g ).

3. The HybridA star planning method based on a linear step search strategy as claimed in claim 2, characterized in that: The determination according to the calculation result includes determining the distance between the vehicle starting point and the parking space target point and the obstacle. If the vehicle starting point is close to the obstacle, the vehicle starting point is used as the starting node of the search and the parking space target point is used as the target node. If the parking space target point is closer to the obstacle, the parking space target point is used as the starting node of the search and the vehicle starting point is used as the target node.

4. The HybridA star planning method based on a linear step search strategy as claimed in claim 3, characterized in that: The calculation of the distance between the current node and the starting node and the target point is expressed as: calculating the distance Distancestart between the current node N and the starting node S and the distance Distancegoal between the target point G, the current node coordinates (X n ,Y n ), starting node coordinates (X s ,Y s ), target node coordinates (X g ,Y g ):

5. The Hybrid A-star planning method based on a linear step search strategy as claimed in claim 4, characterized in that: The judgment based on the distance result between the current node and the target point or the starting node includes: if the current node is far away from the target point or the starting node, the search step size is increased to speed up the search process; if the current node is close to the target point or the starting node, the search step size is reduced. By dynamically adjusting the step size, it is ensured that a feasible path is found under different distance conditions.

6. The Hybrid A-star planning method based on a linear step search strategy as claimed in claim 5, characterized in that: The dynamic adjustment step size is expressed as, Calculate the linearly adjusted search step size, expressed as: Stepstart=Stepmun+Ks. tart*1Dist0Rcestart Step goal =Step min +K goal *Distance goal ; Among them, K start Represented as the starting node distance adjustment step factor, K goal Represents the step size factor for adjusting the distance to the target node, Step max Indicates the maximum step length allowed for path extension, Step min It is the minimum step length allowed for path expansion. start_max Indicates the maximum value allowed for the calculated distance between the current node N and the starting node S. When the distance exceeds the specified range, the calculated result is limited to Distance start_max , Distance goal_max It represents the maximum value allowed for the calculated distance between the current node N and the target node S. When the distance exceeds the specified range, the calculated result is limited to Distance goal_max .

7. The HybridA star planning method based on a linear step search strategy as claimed in claim 6, characterized in that: The method of ensuring that a feasible path can be found under different distance conditions includes selecting a step length Step by taking the minimum value of Stepgoal and Stepstart as the final search step length. When the step length is far away from the target node or the starting node, the step length is increased to reduce the number of searches and speed up the search efficiency. When it is close to the target node or the starting node, the step length is reduced to improve the accuracy of the path, which is expressed as: Step = min{StePgoatStepstart} 8. A system based on the Hybrid A-star planning method based on a linear step search strategy according to any one of claims 1 to 7, characterized in that: Including coordinate positioning module, path planning preprocessing module, optimal node selection module, RS curve generation module, node expansion adjustment module; The coordinate positioning module determines the coordinates of the vehicle starting point and the parking space target point; The path planning preprocessing module determines the starting point and target node of the path search; The optimal node selection module selects a node with the smallest cost as the current node; The RS curve generation module uses the RS curve to connect the target points; The node expansion adjustment module adjusts the step length to expand adjacent nodes.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images