Parallel parking automatic parking trajectory planning method, system, medium and equipment
By combining collision detection and RS curve algorithms to calculate the trajectory inside and outside the parking space in the automatic parking trajectory planning of parallel parking spaces, the problems of computational complexity and poor robustness in the existing technology are solved, and efficient obstacle avoidance parking trajectory planning under low computing power requirements is realized.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- WUHAN KOTEI INFORMATICS
- Filing Date
- 2023-06-25
- Publication Date
- 2026-06-16
AI Technical Summary
Existing automatic parking trajectory planning algorithms are computationally complex and have poor robustness when parking in parallel spaces. In particular, the Hybrid A search algorithm has high computational requirements, and the RS curve does not consider the collision problem.
The trajectory of the target parking space is calculated by collision detection and search, and then the trajectory outside the parking space is calculated by RS curve algorithm. The two trajectories are combined to form a complete vehicle parking trajectory.
It achieves highly robust parking trajectory planning with low computing power requirements, and also has obstacle avoidance function, improving the efficiency and reliability of trajectory planning.
Smart Images
Figure CN117022249B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of parking trajectory technology, and in particular to a method, system, medium, and device for automatic parallel parking trajectory planning. Background Technology
[0002] Currently, the main automatic parking trajectory planning algorithms are Hybrid A Search, RS curves, other geometric algorithms, etc., including Hybrid A It has high computational requirements, long trajectory planning time, and RS curves do not consider collisions. In particular, the trajectories generated by parallel parking spaces will collide with obstacles. Other geometric algorithms have problems such as computational complexity and poor robustness.
[0003] Based on the above issues, how can we balance Hybrid A The computational complexity of search algorithms and the collision issues that occur when RS curves collide with parallel parking spaces are problems that urgently need to be addressed in order to plan a robust parking trajectory. Summary of the Invention
[0004] This invention provides a method, system, medium, and device for automatic parallel parking trajectory planning, in order to solve the problem of collisions in parallel parking spaces caused by RS curve-planned trajectories, as well as the problem of high computing power requirements and long trajectory planning time for pure search algorithms.
[0005] Firstly, a method for automatic parallel parking trajectory planning is provided, including the following steps:
[0006] Obtain the target parking space and the starting point of parking;
[0007] Using the parking space target point as the exit starting point, the vehicle's exit trajectory is obtained based on preset collision detection conditions as it travels from the parking space target point until the front right corner of the vehicle exits the parking space.
[0008] Taking the end point of the exit trajectory as the starting point and the parking starting point as the exit endpoint, the exit trajectory outside the parking space is obtained based on the RS curve algorithm and preset collision detection conditions.
[0009] The vehicle parking trajectory is obtained based on the trajectory inside and outside the parking garage.
[0010] According to the first aspect, in a first possible implementation of the first aspect, the step of "taking the parking space target point as the exit starting point and obtaining the exit trajectory of the vehicle from the parking space target point to the right front corner of the vehicle exiting the parking space based on preset collision detection conditions" specifically includes the following steps:
[0011] Taking the target point of the parking space as the starting point for exiting the parking space, the vehicle moves forward according to preset driving conditions to obtain the first segment of the curved trajectory; when a collision between the vehicle and an obstacle in front is detected based on preset collision detection conditions, a trajectory point before the vehicle collides with the obstacle in front is selected as the first endpoint of the first segment of the curved trajectory.
[0012] Starting from the first endpoint, reverse the vehicle according to preset driving conditions to obtain the second curved trajectory; when a collision between the vehicle and the right rear obstacle is detected based on preset collision detection conditions, select a trajectory point before the vehicle collides with the right rear obstacle as the second endpoint of the second curved trajectory.
[0013] Starting from the second endpoint, the process of moving forward and reversing according to preset driving conditions is repeated sequentially until the right front corner of the vehicle is detected to be exiting the parking space, thus obtaining a trajectory point corresponding to the right front corner of the vehicle exiting the parking space and each subsequent curve trajectory.
[0014] The first curve trajectory, the second curve trajectory, and each subsequent curve trajectory are combined and connected in sequence to obtain the outbound trajectory.
[0015] According to the first possible implementation of the first aspect, in the second possible implementation of the first aspect, the preset collision detection conditions include:
[0016] In a curved trajectory, track points are taken at a preset driving distance. A rectangular frame is generated based on the track points to enclose the vehicle. It is then determined whether the rectangular frame collides with an obstacle.
[0017] According to the first possible implementation of the first aspect, in the third possible implementation of the first aspect, after the step of "taking the parking space target point as the exit starting point and obtaining the exit trajectory of the vehicle from the parking space target point to the right front corner of the vehicle exiting the parking space based on preset collision detection conditions", the following steps are specifically included:
[0018] If the number of curved tracks within the outbound trajectory exceeds a preset number, the acquisition of vehicle parking trajectories will be stopped.
[0019] According to the first aspect, in the fourth possible implementation of the first aspect, the step of "taking the end point of the exit trajectory as the starting point and the parking starting point as the exit endpoint, and obtaining the exit trajectory based on the RS curve algorithm and preset collision detection conditions" specifically includes the following steps:
[0020] The endpoint of the exit trajectory is a trajectory point corresponding to the right front corner of the vehicle exiting the parking space;
[0021] Taking the end point of the exit trajectory as the starting point and the parking start point as the exit end point, multiple RS curves are obtained according to preset driving conditions and based on the RS curve algorithm;
[0022] RS curves are selected one by one in order of increasing length for vehicle collision detection until one RS curve is selected as the outbound trajectory when the vehicle and the obstacle are not detected to have collided based on the preset collision detection conditions.
[0023] According to the first aspect, in the fifth possible implementation of the first aspect, the step of "obtaining the vehicle parking trajectory based on the in-depot trajectory and the out-of-depot trajectory" specifically includes the following steps:
[0024] The outbound trajectory is obtained by combining and connecting the inbound trajectory and the outbound trajectory.
[0025] The parking origin is taken as the starting point of the exit trajectory, the parking space target point is taken as the ending point of the exit trajectory, and the vehicle parking trajectory is obtained along the trajectory extension route of the exit trajectory.
[0026] Secondly, a parallel parking space automatic parking trajectory planning system is provided, including:
[0027] The point acquisition module is used to acquire the target parking space and the parking starting point;
[0028] The exit trajectory module is communicatively connected to the point acquisition module and is used to acquire the exit trajectory of the vehicle from the parking space target point to the right front corner of the vehicle exiting the parking space, based on preset collision detection conditions, with the parking space target point as the exit starting point.
[0029] The outbound external trajectory module, communicatively connected to the outbound internal trajectory module and the point acquisition module, is used to acquire the outbound external trajectory based on the RS curve algorithm and preset collision detection conditions, with the end point of the outbound internal trajectory as the starting point and the parking start point as the outbound end point; and,
[0030] The vehicle parking trajectory module is communicatively connected to the in-exit trajectory module and the out-of-exit trajectory module, and is used to obtain the vehicle parking trajectory based on the in-exit trajectory and the out-of-exit trajectory.
[0031] Thirdly, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the parallel parking space automatic parking trajectory planning method as described in any of the preceding claims.
[0032] Fourthly, an electronic device is provided, including a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, wherein the processor, when executing the computer program, implements the parallel parking space automatic parking trajectory planning method as described above.
[0033] Compared with the prior art, the advantages of the present invention are as follows: by searching and calculating the parking space target point exit trajectory - exit trajectory inside the parking space through collision detection, and then using the RS curve algorithm to calculate the trajectory from the exit point to the parking starting point - exit trajectory outside the parking space, the two trajectories are combined and then viewed in reverse to obtain the complete vehicle parking trajectory; therefore, the present invention does not require high computing power, has good robustness, and also has obstacle avoidance function, and has high practical value. Attached Figure Description
[0034] Figure 1 This is a flowchart illustrating an embodiment of an automatic parallel parking trajectory planning method of the present invention;
[0035] Figure 2 This is a schematic diagram of the vehicle parking trajectory of the present invention;
[0036] Figure 3 This is a schematic diagram of the structure of an automatic parallel parking trajectory planning system according to the present invention.
[0037] Explanation of reference numerals in the attached figures:
[0038] 100. Parallel parking space automatic parking trajectory planning system; 110. Point acquisition module; 120. In-parking trajectory module; 130. Out-of-parking trajectory module; 140. Vehicle parking trajectory module. Detailed Implementation
[0039] Referring now to specific embodiments of the invention, examples of which are illustrated in the accompanying drawings. Although the invention will be described in conjunction with specific embodiments, it will be understood that it is not intended to limit the invention to the described embodiments. Rather, it is intended to cover variations, modifications, and equivalents included within the spirit and scope of the invention as defined by the appended claims. It should be noted that the method steps described herein can be implemented by any functional block or functional arrangement, and any functional block or functional arrangement can be implemented as a physical entity or a logical entity, or a combination of both.
[0040] To enable those skilled in the art to better understand the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0041] Note: The examples described below are merely specific examples and are not intended to limit the embodiments of the present invention to the specific steps, values, conditions, data, order, etc. Those skilled in the art can utilize the concept of the present invention to construct more embodiments not mentioned herein by reading this specification.
[0042] See Figure 1 As shown, this embodiment of the invention provides a method for automatic parallel parking trajectory planning, including the following steps:
[0043] S100, obtain the target parking space and the starting point of parking;
[0044] S200, taking the parking space target point as the exit starting point, and based on preset collision detection conditions, obtain the exit trajectory of the vehicle from the parking space target point until the right front corner of the vehicle exits the parking space.
[0045] S300: Taking the end point of the exit trajectory as the starting point and the parking starting point as the exit endpoint, the exit trajectory outside the parking space is obtained based on the RS curve algorithm and preset collision detection conditions.
[0046] S400: Obtain the vehicle parking trajectory based on the in-warehouse trajectory and the out-of-warehouse trajectory.
[0047] Specifically, in this embodiment, the automatic parking trajectory planning algorithm mainly includes Hybrid A Search, RS curves, other geometric algorithms, etc., including Hybrid A The RS curve method for automatic parallel parking requires high computing power and has a long trajectory planning time. It does not consider collisions, especially since the trajectory generated for parallel parking spaces will collide with obstacles. Other geometric algorithms have problems such as computational complexity and poor robustness. Therefore, in order to address the above problems, the parallel parking automatic parking trajectory planning method of this invention solves the problem that the trajectory planned by RS curve will collide in parallel parking spaces, as well as the problem that pure search algorithms have high computing power requirements and long trajectory planning time.
[0048] Therefore, this invention calculates the parking space target point exit trajectory - the exit trajectory inside the parking space by collision detection search, and then uses the RS curve algorithm to calculate the trajectory from the exit point to the parking starting point - the exit trajectory outside the parking space. By combining the two trajectories and looking at them in reverse, the complete vehicle parking trajectory can be obtained. Therefore, this invention does not require high computing power, has good robustness, and also has obstacle avoidance function, and has high practical value.
[0049] See Figure 2As shown, a coordinate system is established with the target parking space as the origin, the forward driving direction of the vehicle as the positive x-axis, and the left side of the vehicle as the positive y-axis. The yaw angle is the counterclockwise angle with the positive x-axis. Along the parking space lines, a 10-meter long and 10-meter wide obstacle rectangle is created in front of the parking space, behind the parking space, and to the right of the parking space, a 0.5-meter wide obstacle rectangle is created. On the left side of the road, a 20-meter long and 0.5-meter wide obstacle rectangle is created along the left edge of the road. Using the center point of the vehicle's rear axle as the vehicle's location, a rectangle with the vehicle's length as its length and width as its width is calculated using the coordinates of this point and the yaw angle.
[0050] Preferably, in another embodiment of this application, the step "S200, taking the parking space target point as the exit starting point, and obtaining the exit trajectory of the vehicle from the parking space target point to the right front corner of the vehicle exiting the parking space based on preset collision detection conditions" specifically includes the following steps:
[0051] S210, taking the parking space target point as the starting point for exiting the parking space, proceeding according to preset driving conditions, and obtaining the first segment of curved trajectory; when a collision between the vehicle and an obstacle in front is detected based on preset collision detection conditions, then a trajectory point before the vehicle collides with the obstacle in front is selected as the first endpoint of the first segment of curved trajectory.
[0052] S220, starting from the first endpoint, reverse according to preset driving conditions to obtain the second curved trajectory; when a collision between the vehicle and the right rear obstacle is detected based on preset collision detection conditions, select a trajectory point before the vehicle collides with the right rear obstacle as the second endpoint of the second curved trajectory.
[0053] S230, taking the second endpoint as the starting point, repeat the forward and reverse driving according to the preset driving conditions in sequence until the right front corner of the car is detected to be out of the parking space, and obtain a trajectory point corresponding to the right front corner of the car being out of the parking space and each subsequent curve trajectory.
[0054] S240, the first segment of the curve trajectory, the second segment of the curve trajectory, and each subsequent segment of the curve trajectory are combined and connected in sequence to obtain the outbound trajectory.
[0055] Preferably, in another embodiment of this application, the preset collision detection conditions include:
[0056] In a curved trajectory, track points are taken at a preset driving distance. A rectangular frame is generated based on the track points to enclose the vehicle. It is then determined whether the rectangular frame collides with an obstacle.
[0057] Specifically, in this embodiment,
[0058] Assuming the vehicle is already at the target parking space point, it exits the space at a speed of 1 km / h with a minimum turning radius R. The vehicle then moves in a circle, taking a point every 0.05 m. The bounding box of the vehicle at that point is calculated, and collision detection is performed using this bounding box against the obstacle box ahead. If the vehicle is about to collide with the obstacle box, the exit point point_1 before the vehicle collides with the obstacle is selected, resulting in the trajectory trajectory_1 from the target parking space point to point_1.
[0059] Starting from point_1, assuming the vehicle is reversing to the right at a speed of 1 km / h and a minimum turning radius R, a point is taken every 0.05 m. The bounding box of the vehicle at that point is calculated, and collision detection is performed using this bounding box and the bounding boxes of the right and rear obstacles. When a collision is imminent, a point_2, the exit point before the vehicle collides with the right rear obstacle, is selected, and the trajectory trajectory_2 from point_1 to point_2 is obtained.
[0060] Starting from point_2, assume the vehicle exits the parking space at a speed of 1 km / h with a minimum turning radius R; repeat this process until the front right corner of the vehicle is detected as exiting the parking space. At this point, the exit point point_n and trajectory trajectory_n are obtained.
[0061] Preferably, in another embodiment of this application, after the step "S200, taking the parking space target point as the exit starting point, and obtaining the exit trajectory of the vehicle from the parking space target point to the right front corner of the vehicle exiting the parking space based on preset collision detection conditions", the following steps are specifically included:
[0062] If the number of curved tracks within the outbound trajectory exceeds a preset number, the acquisition of vehicle parking trajectories will be stopped.
[0063] Specifically, in this embodiment, when the front right corner of the vehicle is detected to be exiting the parking space, the final exit point point_n and trajectory trajectory_n are obtained. If n>5, the parking fails and the acquisition of the vehicle parking trajectory is stopped.
[0064] Preferably, in another embodiment of this application, the step "S300, taking the end point of the exit trajectory as the starting point and the parking start point as the exit end point, and obtaining the exit trajectory based on the RS curve algorithm and preset collision detection conditions" specifically includes the following steps:
[0065] The endpoint of the exit trajectory is a trajectory point corresponding to the right front corner of the vehicle exiting the parking space;
[0066] S310, taking the end point of the exit trajectory as the starting point and the parking starting point as the exit end point, multiple RS curves are obtained according to preset driving conditions and based on the RS curve algorithm;
[0067] S320, select RS curves one by one in order of increasing length for vehicle collision detection, until one RS curve is selected as the outbound trajectory when the vehicle and the obstacle are not detected to have collided based on the preset collision detection conditions.
[0068] Specifically, in this embodiment, the RS (Reeds-Shepp) curve is a route planning method. Assuming that the vehicle can turn with a fixed radius and can move forward and backward, the Reeds-Shepp curve is the shortest path from the starting point to the destination under the above conditions. This curve not only ensures that the vehicle can reach the destination, but also ensures that the vehicle's angle reaches the expected angle at the destination.
[0069] There are 48 possible combinations of Reeds Shepp curves. Starting from point_n and ending at the parking start point, with a minimum turning radius of R, 48 RS curves are calculated and sorted by trajectory length before collision detection. The default collision detection condition is to take a point every 0.05m, calculate the bounding box of the vehicle, and perform collision detection with the bounding boxes of surrounding obstacles. If no collision-free trajectory is found, parking fails; otherwise, the number of collision-free trajectories is increased by trajectory_n+1.
[0070] Preferably, in another embodiment of this application, the step "S400, obtaining the vehicle parking trajectory based on the trajectory inside the parking garage and the trajectory outside the parking garage" specifically includes the following steps:
[0071] S410, combine and connect the inbound trajectory and the outbound trajectory to obtain the outbound trajectory;
[0072] S420, taking the parking starting point as the starting point of the exit trajectory and the parking space target point as the ending point of the exit trajectory, and obtaining the vehicle parking trajectory along the trajectory extension route of the exit trajectory.
[0073] Specifically, in this embodiment, the exit trajectory can be obtained by connecting the trajectory_1, trajectory_2, ..., trajectory_n, and trajectory_n+1. Since the present invention is to obtain the vehicle parking trajectory, it is only necessary to regard the starting point of the exit trajectory as the ending point of the vehicle parking trajectory and the ending point of the exit trajectory as the starting point of the vehicle parking trajectory, and the trajectory route remains unchanged.
[0074] See also Figure 3As shown, this embodiment of the invention also provides an automatic parallel parking trajectory planning system 100, including: a point acquisition module 110, an in-parking trajectory module 120, an out-parking trajectory module 130, and a vehicle parking trajectory module 140.
[0075] Point acquisition module 110 is used to acquire the target point of the parking space and the starting point of the parking space;
[0076] The exit trajectory module 120 is communicatively connected to the point acquisition module 110 and is used to acquire the exit trajectory of the vehicle from the parking space target point to the right front corner of the vehicle exiting the parking space, based on preset collision detection conditions, with the parking space target point as the exit starting point.
[0077] The outbound external trajectory module 130 is communicatively connected to the outbound internal trajectory module 120 and the point acquisition module 110. It is used to acquire the outbound external trajectory based on the RS curve algorithm and preset collision detection conditions, with the end point of the outbound internal trajectory as the starting point and the parking starting point as the outbound end point.
[0078] The vehicle parking trajectory module 140 is communicatively connected to the in-exit trajectory module 120 and the out-of-exit trajectory module 130, and is used to obtain the vehicle parking trajectory based on the in-exit trajectory and the out-of-exit trajectory.
[0079] Therefore, this invention calculates the parking space target point exit trajectory - the exit trajectory inside the parking space by collision detection search, and then uses the RS curve algorithm to calculate the trajectory from the exit point to the parking starting point - the exit trajectory outside the parking space. By combining the two trajectories and looking at them in reverse, the complete vehicle parking trajectory can be obtained. Therefore, this invention does not require high computing power, has good robustness, and also has obstacle avoidance function, and has high practical value.
[0080] Specifically, this embodiment corresponds one-to-one with the above method embodiments. The functions of each module have been described in detail in the corresponding method embodiments, so they will not be repeated here.
[0081] Based on the same inventive concept, embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements all or part of the method steps of the above method.
[0082] The present invention can implement all or part of the processes in the above methods, or it can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content contained in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.
[0083] Based on the same inventive concept, embodiments of this application also provide an electronic device, including a memory and a processor. The memory stores a computer program that runs on the processor. When the processor executes the computer program, it implements all or part of the method steps described above.
[0084] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the computer device, connecting all parts of the computer device through various interfaces and lines.
[0085] Memory can be used to store computer programs and / or modules. The processor performs various functions of the computer device by running or executing the computer programs and / or modules stored in the memory, and by accessing data stored in the memory. Memory can primarily include a program storage area and a data storage area. The program storage area can store the operating system and at least one application program required for a function (e.g., sound playback, image playback, etc.); the data storage area can store data created based on the use of the mobile phone (e.g., audio data, video data, etc.). Furthermore, memory can include high-speed random access memory, and can also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, SmartMedia Cards (SMC), Secure Digital (SD) cards, Flash Cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.
[0086] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, servers, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.
[0087] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), servers, and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0088] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0089] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0090] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.
Claims
1. A method for automatic parking trajectory planning in parallel parking spaces, characterized in that, Includes the following steps: Obtain the target parking space and the starting point of parking; Using the parking space target point as the exit starting point, the vehicle's exit trajectory is obtained based on preset collision detection conditions as it travels from the parking space target point until the front right corner of the vehicle exits the parking space. Taking the end point of the exit trajectory as the starting point and the parking starting point as the exit endpoint, the exit trajectory outside the parking space is obtained based on the RS curve algorithm and preset collision detection conditions. Based on the in-warehouse trajectory and the out-of-warehouse trajectory, the vehicle parking trajectory is obtained; The step of obtaining the vehicle's trajectory from the parking space target point to the right front corner of the vehicle exiting the parking space, based on preset collision detection conditions and using the parking space target point as the exit starting point, specifically includes the following steps: Taking the target point of the parking space as the starting point for exiting the parking space, the vehicle moves forward according to preset driving conditions and obtains the first segment of the curved trajectory. When a collision between the vehicle and an obstacle in front is detected based on preset collision detection conditions, a trajectory point before the vehicle collides with the obstacle in front is selected as the first endpoint of the first segment of the curved trajectory. Starting from the first endpoint, reverse the vehicle according to preset driving conditions to obtain the second curved trajectory; when a collision between the vehicle and the right rear obstacle is detected based on preset collision detection conditions, select a trajectory point before the vehicle collides with the right rear obstacle as the second endpoint of the second curved trajectory. Starting from the second endpoint, the process of moving forward and reversing according to preset driving conditions is repeated sequentially until the right front corner of the vehicle is detected to be exiting the parking space. A trajectory point corresponding to the right front corner of the vehicle exiting the parking space and each subsequent curve trajectory are obtained. The first curve trajectory, the second curve trajectory, and each subsequent curve trajectory are combined and connected in sequence to obtain the outbound trajectory. The step of obtaining the external trajectory based on the RS curve algorithm and preset collision detection conditions, using the end point of the exit trajectory as the starting point and the parking start point as the exit end point, specifically includes the following steps: The endpoint of the exit trajectory is a trajectory point corresponding to the right front corner of the vehicle exiting the parking space; Taking the end point of the exit trajectory as the starting point and the parking start point as the exit end point, multiple RS curves are obtained according to preset driving conditions and based on the RS curve algorithm; RS curves are selected one by one in order of increasing length for vehicle collision detection until one RS curve is selected as the outbound trajectory when the vehicle and the obstacle are not detected to have collided based on the preset collision detection conditions.
2. The parallel parking space automatic parking trajectory planning method as described in claim 1, characterized in that, The preset collision detection conditions include: In a curved trajectory, track points are taken at a preset driving distance. A rectangular frame is generated based on the track points to enclose the vehicle. It is then determined whether the rectangular frame collides with an obstacle.
3. The automatic parking trajectory planning method for parallel parking spaces as described in claim 1, characterized in that, After the step of taking the parking space target point as the exit starting point and obtaining the vehicle's exit trajectory from the parking space target point to the right front corner of the vehicle exiting the parking space based on preset collision detection conditions, the specific steps include: If the number of curved tracks within the outbound trajectory exceeds a preset number, the acquisition of vehicle parking trajectories will be stopped.
4. The automatic parallel parking trajectory planning method as described in claim 1, characterized in that, The step of obtaining the vehicle parking trajectory based on the trajectory inside and outside the parking garage specifically includes the following steps: The outbound trajectory is obtained by combining and connecting the inbound trajectory and the outbound trajectory. The parking origin is taken as the starting point of the exit trajectory, the parking space target point is taken as the ending point of the exit trajectory, and the vehicle parking trajectory is obtained along the trajectory extension route of the exit trajectory.
5. A parallel parking space automatic parking trajectory planning system, characterized in that, include: The point acquisition module is used to acquire the target parking space and the parking starting point; The exit trajectory module is communicatively connected to the point acquisition module and is used to acquire the exit trajectory of the vehicle from the parking space target point to the right front corner of the vehicle exiting the parking space, based on preset collision detection conditions, with the parking space target point as the exit starting point. The outbound external trajectory module, communicatively connected to the outbound internal trajectory module and the point acquisition module, is used to acquire the outbound external trajectory based on the RS curve algorithm and preset collision detection conditions, with the end point of the outbound internal trajectory as the starting point and the parking start point as the outbound end point; and, The vehicle parking trajectory module is communicatively connected to the in-exit trajectory module and the out-of-exit trajectory module, and is used to obtain the vehicle parking trajectory based on the in-exit trajectory and the out-of-exit trajectory; The step of using the target parking space as the exit starting point and obtaining the vehicle's exit trajectory from the target parking space until the front right corner of the vehicle exits the parking space based on preset collision detection conditions specifically includes: Taking the target point of the parking space as the starting point for exiting the parking space, the vehicle moves forward according to preset driving conditions and obtains the first segment of the curved trajectory. When a collision between the vehicle and an obstacle in front is detected based on preset collision detection conditions, a trajectory point before the vehicle collides with the obstacle in front is selected as the first endpoint of the first segment of the curved trajectory. Starting from the first endpoint, reverse the vehicle according to preset driving conditions to obtain the second curved trajectory; when a collision between the vehicle and the right rear obstacle is detected based on preset collision detection conditions, select a trajectory point before the vehicle collides with the right rear obstacle as the second endpoint of the second curved trajectory. Starting from the second endpoint, the process of moving forward and reversing according to preset driving conditions is repeated sequentially until the right front corner of the vehicle is detected to be exiting the parking space. A trajectory point corresponding to the right front corner of the vehicle exiting the parking space and each subsequent curve trajectory are obtained. The first curve trajectory, the second curve trajectory, and each subsequent curve trajectory are combined and connected in sequence to obtain the outbound trajectory. The process of obtaining the external trajectory based on the RS curve algorithm and preset collision detection conditions, using the end point of the exit trajectory as the starting point and the parking start point as the exit endpoint, specifically includes: The endpoint of the exit trajectory is a trajectory point corresponding to the right front corner of the vehicle exiting the parking space; Taking the end point of the exit trajectory as the starting point and the parking start point as the exit end point, multiple RS curves are obtained according to preset driving conditions and based on the RS curve algorithm; RS curves are selected one by one in order of increasing length for vehicle collision detection until one RS curve is selected as the outbound trajectory when the vehicle and the obstacle are not detected to have collided based on the preset collision detection conditions.
6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the parallel parking space automatic parking trajectory planning method as described in any one of claims 1 to 4.
7. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that, When the processor runs the computer program, it implements the parallel parking space automatic parking trajectory planning method as described in any one of claims 1 to 4.