A method and system for automatic generation of a reversing route
By using an improved reverse RRT algorithm and path smoothing technology, the optimal reversing path is generated, solving the problem of parking difficulties for ordinary vehicle users in narrow parking spaces and improving parking safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHERY AUTOMOBILE CO LTD
- Filing Date
- 2024-12-17
- Publication Date
- 2026-07-10
AI Technical Summary
In existing technologies, automatic parking functions require multiple expensive sensors and controllers, making it difficult for ordinary vehicle users to operate when parking in narrow parking spaces, resulting in poor vehicle feel and a risk of collision.
An improved reverse RRT algorithm is used to generate an initial reversing path, and a search function is used to select the parent node of the target pose until all nodes reach the end parking pose. Combined with smoothing processing, the optimal reversing path is generated and displayed in the holographic imaging system.
It reduces the vehicle collision rate, improves reversing safety, and helps users park smoothly in vehicles lacking automatic parking functions.
Smart Images
Figure CN119642847B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of autonomous driving technology, and in particular to a method and system for automatically generating reversing routes. Background Technology
[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.
[0003] With the increasing popularity of automobiles and the rapid development of the automotive industry, driver assistance functions have become standard equipment on almost all new models from various OEMs, and their application rate is growing rapidly. Reversing radar and panoramic imaging have become standard features on many models. However, automatic parking is generally only available on high-end models, requiring 12 ultrasonic sensors and 4 surround-view cameras, as well as a separate parking controller, making it relatively expensive. For users without automatic parking and those with poor car handling skills, parking in narrow parking spaces remains a challenge. Summary of the Invention
[0004] To address the technical problems mentioned above, this invention provides a method and system for automatically generating reversing routes. This invention generates an initial reversing path using an improved reverse RRT algorithm and smooths the initial reversing path to obtain an optimal reversing path, which can reduce the collision rate of the vehicle to be reversed and improve the safety of the vehicle to be reversed.
[0005] To achieve the above objectives, the present invention adopts the following technical solution:
[0006] The first aspect of the present invention provides a method for automatically generating reversing routes.
[0007] A method for automatically generating reversing routes includes:
[0008] The system acquires the map before the vehicle reverses, the starting pose before reversing, and the pose of the final parking space. It then uses the reverse RRT algorithm to generate the initial reversing path. During the optimization process of the reverse RRT algorithm, a search function is used to select the node corresponding to the minimum value of the search function as the parent node of the target pose. This process continues until all node poses in the random tree have reached the pose of the final parking space. Finally, the initial reversing path is extracted based on the parent node relationships in the random tree.
[0009] The initial reversing path is smoothed to obtain the optimal reversing path, which is then displayed in the holographic imaging system.
[0010] Furthermore, the initial and final parking positions of the vehicle before reversing both include the vehicle's position information and heading angle.
[0011] Furthermore, the location information is collected by radar, and the map before the vehicle reverses is collected by cameras deployed around the vehicle and generated by the controller.
[0012] Furthermore, the search function is expressed by the following formula:
[0013] T(m)=A(m)+B(m)+λ1C(m)+λ2D(m)+λ3E(m)
[0014] Where A(m) represents the actual path length from the starting point to node m, B(m) represents the expected cost from node m to the target destination, λ1, λ2, and λ3 represent the weights of angle change, direction change, and reversing permission, respectively, and C(m), D(m), and E(m) represent the costs of angle change, direction change, and reversing, respectively.
[0015] Furthermore, the initial reversing path is smoothed to obtain the optimal reversing path; the method includes:
[0016] Step 1: Import the initial reversing path RRT_path;
[0017] Step 2: Let the smooth path be smooth_path, and node smooth_path(1) = RRT_path(1);
[0018] Step 3: Let i be the maximum number of nodes in RRT_path;
[0019] Step 4: Determine whether the line connecting RRT_path(i) and smooth_path(end) collides with an obstacle or whether the line length is greater than the smooth length D. If so, set i = i-1 and repeat step 4; otherwise, go to step 5.
[0020] Step 5: Add RRT_path(i) to the end of smooth_path(end);
[0021] Step 6: Determine whether the connection between smooth_path(end) and RRT_path(end) collides with an obstacle or whether the length of the connection is greater than the smooth length D. If so, delete nodes 1 to i of RRT_path and go to step 3; otherwise, go to step 7.
[0022] Step 7: Add RRT_path(end) to the end of smooth_path(end).
[0023] Furthermore, if the vehicle is equipped with a TBOX module, a path planning experience base can be generated based on the vehicle's historical reversing records, continuously learning and optimizing the learning parameters of the reverse RRT algorithm.
[0024] A second aspect of the present invention provides an automatic reversing route generation system.
[0025] A reversing route automatic generation system includes:
[0026] The path generation module is configured to: acquire the map before the vehicle reverses, the starting pose of the vehicle before reversing, and the pose of the destination parking space; generate an initial reversing path using the reverse RRT algorithm; during the optimization process of the reverse RRT algorithm, a search function is used to select the node corresponding to the minimum value of the search function as the parent node of the target pose; until all node poses in the random tree have reached the pose of the destination parking space; and extract the initial reversing path based on the parent node relationship in the random tree.
[0027] The smoothing module is configured to smooth the initial reversing path to obtain the optimal reversing path and display it in the holographic imaging system.
[0028] A third aspect of the present invention provides a computer-readable storage medium.
[0029] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the automatic reversing route generation method as described in the first aspect above.
[0030] A fourth aspect of the present invention provides a computer device.
[0031] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of the automatic reversing route generation method as described in the first aspect above.
[0032] The fifth aspect of the present invention provides a computer program product or a computer program.
[0033] This invention provides a computer program product or computer program comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps of the automatic reversing route generation method as described in the first aspect above.
[0034] Compared with the prior art, the beneficial effects of the present invention are:
[0035] This invention acquires a map of the vehicle before reversing, its initial pose, and the final parking space pose. It then uses a reverse Reversing Tracking (RRT) algorithm to generate an initial reversing path. During the RRT optimization process, a search function is used, and the node corresponding to the minimum value of the search function is selected as the parent node of the target pose. This process continues until all node poses in the random tree have reached the final parking space pose. The initial reversing path is extracted based on the parent-node relationships in the random tree. The initial reversing path is then smoothed to obtain the optimal reversing path, which is displayed in a holographic imaging system. This allows users without automatic parking functions and with poor car handling skills to drive along the generated optimal reversing path, reducing the collision rate of the vehicle waiting to reverse and improving the safety of reversing.
[0036] This invention can help users with parking difficulties and poor car sense avoid obstacles and complete parking maneuvers even when there are only a few sensors, cameras, radars, etc. on the vehicle. Attached Figure Description
[0037] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.
[0038] Figure 1 This is a flowchart illustrating the automatic generation method for reversing routes shown in this invention;
[0039] Figure 2 This is a schematic diagram of the display UI shown in this invention;
[0040] Figure 3 This is a structural diagram of the automatic reversing route generation system shown in this invention;
[0041] Figure 4 This is a structural diagram of the related hardware involved in this invention. Detailed Implementation
[0042] The present invention will be further described below with reference to the accompanying drawings and embodiments.
[0043] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.
[0044] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.
[0045] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and systems according to various embodiments of this disclosure. It should be noted that each block in a flowchart or block diagram may represent a module, segment, or portion of code, which may include one or more executable instructions for implementing the logical functions specified in the various embodiments. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutively represented blocks may actually be executed substantially in parallel, or they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, may be implemented using a dedicated hardware-based system that performs the specified functions or operations, or using a combination of dedicated hardware and computer instructions.
[0046] Example 1
[0047] like Figure 1 As shown, this embodiment provides a method for automatically generating reversing routes. This embodiment uses the application of this method to a server as an example for illustration. It is understood that this method can also be applied to terminals, and can also be applied to systems including terminals, servers, and other components, and is implemented through interaction between the terminal and the server. The server can be an independent physical server, a server cluster composed of multiple physical servers, or a distributed system. It can also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network servers, cloud communication, middleware services, domain name services, CDN security services, and big data and artificial intelligence platforms. The terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. The terminal and server can be directly or indirectly connected via wired or wireless communication, which is not limited herein. In this embodiment, the method includes the following steps:
[0048] The system acquires the map before the vehicle reverses, the starting pose before reversing, and the pose of the final parking space. It then uses the reverse RRT algorithm to generate the initial reversing path. During the optimization process of the reverse RRT algorithm, a search function is used to select the node corresponding to the minimum value of the search function as the parent node of the target pose. This process continues until all node poses in the random tree have reached the pose of the final parking space. Finally, the initial reversing path is extracted based on the parent node relationships in the random tree.
[0049] The initial reversing path is smoothed to obtain the optimal reversing path, which is then displayed in the holographic imaging system.
[0050] The following is a detailed description of this embodiment:
[0051] Step 1: Obtain the map before the vehicle reverses, the starting position of the vehicle before reversing, and the final parking position.
[0052] The map before a vehicle reverses should include environmental information about the reversing area, such as parking space layout, obstacle locations, and road boundaries. This information helps the vehicle determine its reversing path and avoid collisions. If new obstacles or changes in parking spaces occur, moving objects can be captured in real time using sensors such as radar and cameras and added to the map to ensure its accuracy and timeliness.
[0053] The vehicle's initial and final parking positions before reversing include its position information and heading angle. Position information can be obtained through sensors such as GPS, cameras, and radar, while heading angle can be obtained through the vehicle's attitude sensors (such as gyroscopes and accelerometers).
[0054] Before reversing, a vehicle needs to perceive its surroundings, including the size and shape of the parking space and the location of obstacles. Through sensors such as cameras and radar, the vehicle can acquire this environmental information in real time and process and analyze it.
[0055] In addition to location information, the destination parking space position also includes the size information of the parking space, such as length and width.
[0056] Step 2: Use the reverse RRT algorithm to generate the initial reversing path; during the optimization process of the reverse RRT algorithm, a search function is used, and the node corresponding to the minimum value of the search function is selected as the parent node of the target pose; until all node poses in the random tree have reached the destination parking pose; extract the initial reversing path according to the parent node relationship in the random tree; specifically, this step includes:
[0057] Step 2.1: Import map, vehicle starting position, and destination parking space position information;
[0058] Step 2.2: Generate a random pose with a certain probability or use the destination berth pose as the target pose;
[0059] Step 2.3: Determine if the target pose is valid. If yes, proceed to step 2.4; otherwise, proceed to step 2.2.
[0060] Step 2.4: Use a search function to select the node corresponding to the minimum value of the search function as the parent node of the target pose;
[0061] Step 2.5: Determine whether the poses of all nodes in the random tree have reached the final berth pose. If not, proceed to step 2.2; if yes, proceed to step 2.6.
[0062] Step 2.6: Extract the initial reversing path based on the parent node relationships in the random tree.
[0063] In one or more implementations, the search function can be expressed by the following formula:
[0064] T(m)=A(m)+B(m)+λ1C(m)+λ2D(m)+λ3E(m)
[0065] Where A(m) represents the actual path length from the starting point to node m, B(m) represents the expected cost from node m to the target destination, λ1, λ2, and λ3 represent the weights of angle change, direction change, and reversing permission, respectively, and C(m), D(m), and E(m) represent the costs of angle change, direction change, and reversing, respectively.
[0066] Step 3: Smooth the initial reversing path to obtain the optimal reversing path; specifically, this step includes:
[0067] Step 3.1: Import the berthing path RRT_path;
[0068] Step 3.2: Let the smooth path be smooth_path, and the node smooth_path(1) = RRT_path(1);
[0069] Step 3.3: Let i be the maximum number of nodes in RRT_path;
[0070] Step 3.4: Determine whether the line connecting RRT_path(i) and smooth_path(end) collides with an obstacle or whether the line length is greater than the smooth length D. If so, let i = i-1 and repeat step 3.4; otherwise, go to step 3.5.
[0071] Step 3.5: Add RRT_path(i) to the end of smooth_path(end);
[0072] Step 3.6: Determine whether the connection between smooth_path(end) and RRT_path(end) collides with an obstacle or whether the length of the connection is greater than the smooth length D. If so, delete nodes 1 to i of RRT_path and go to step 3.3; otherwise, go to step 3.7.
[0073] Step 3.7: Add RRT_path(end) to the end of smooth_path(end).
[0074] To avoid interference from noise points in the initial path on the path smoothing, after the first smoothing, the entire path is flipped and then smoothed a second time. After the second smoothing process, the optimal reversing path is obtained.
[0075] Step 4: Display the optimal reversing path in the holographic imaging system;
[0076] In the UI design, vehicle auxiliary lines are used to help users ensure consistency between the actual vehicle trajectory and the planned path. In the car model and single-side view of the AVM interface, the steering wheel angle signal magnitude on the main CAN bus is used to guide the movement of the vehicle along the planned path using blue lines. Figure 2 (As shown) indicates the tire's driving direction, while the planned path color can be represented by other colored lines, with the line texture displayed in the AVM interface. When two lines coincide, parking can be successfully completed.
[0077] The AVM interface displays obstacle distance information in real time via ultrasonic ranging. Additionally, if the vehicle has a limited number of radars, visual algorithms can compensate for this.
[0078] When the vehicle rolls off the production line, relevant dimensional parameters (vehicle length, width, height, track width, etc.) are written into the IHU (Integrated Human Hub) so that the system can locate its own boundaries when establishing environmental coordinates. While the user is driving at low speeds, the ultrasonic sensors and surround-view cameras continuously operate, locating and memorizing obstacles in the environment. When the user needs to use this function, they click to enter the AVM (Autonomous Vehicle Monitor) interface, then click the parking assist button at the top of the interface, select a specific parking space, and the system generates a planned reversing path based on the identified and memorized environmental information, combined with its own dimensional information, using a path planning algorithm. The user can easily park by following the animation guidance and using the obstacle distance information on the AVM interface. While the user is reversing according to the system's planned path, the system can update the route based on the latest conditions. Simultaneously, if the vehicle is equipped with a TBOX (Total Vehicle Module), user experience and feedback can be transmitted back to the system, forming a path planning experience library. This continuously learns and optimizes the learning parameters of the reverse RRT (Reverse Tracking) algorithm, thereby improving the accuracy of path generation.
[0079] Example 2
[0080] This embodiment provides an automatic reversing route generation system.
[0081] like Figure 3 As shown, an automatic reversing route generation system includes:
[0082] The path generation module is configured to: acquire the map before the vehicle reverses, the starting pose of the vehicle before reversing, and the pose of the destination parking space; generate an initial reversing path using the reverse RRT algorithm; during the optimization process of the reverse RRT algorithm, a search function is used to select the node corresponding to the minimum value of the search function as the parent node of the target pose; until all node poses in the random tree have reached the pose of the destination parking space; and extract the initial reversing path based on the parent node relationship in the random tree.
[0083] The smoothing module is configured to smooth the initial reversing path to obtain the optimal reversing path and display it in the holographic imaging system.
[0084] In some embodiments, the path generation module is further configured such that: the starting pose and the ending parking pose of the vehicle before reversing both include the vehicle's position information and heading angle; the position information is collected by radar, and the map of the vehicle before reversing is collected by cameras deployed around the vehicle and generated by the controller.
[0085] In some embodiments, the search function is expressed by the following formula:
[0086] T(m)=A(m)+B(m)+λ1C(m)+λ2D(m)+λ3E(m)
[0087] Where A(m) represents the actual path length from the starting point to node m, B(m) represents the expected cost from node m to the target destination, λ1, λ2, and λ3 represent the weights of angle change, direction change, and reversing permission, respectively, and C(m), D(m), and E(m) represent the costs of angle change, direction change, and reversing, respectively.
[0088] In some embodiments, the smoothing module is further configured to perform the following steps:
[0089] Step 1: Import the initial reversing path RRT_path;
[0090] Step 2: Let the smooth path be smooth_path, and node smooth_path(1) = RRT_path(1);
[0091] Step 3: Let i be the maximum number of nodes in RRT_path;
[0092] Step 4: Determine whether the line connecting RRT_path(i) and smooth_path(end) collides with an obstacle or whether the line length is greater than the smooth length D. If so, set i = i-1 and repeat step 4; otherwise, go to step 5.
[0093] Step 5: Add RRT_path(i) to the end of smooth_path(end);
[0094] Step 6: Determine whether the connection between smooth_path(end) and RRT_path(end) collides with an obstacle or whether the length of the connection is greater than the smooth length D. If so, delete nodes 1 to i of RRT_path and go to step 3; otherwise, go to step 7.
[0095] Step 7: Add RRT_path(end) to the end of smooth_path(end) to obtain the optimal reversing path.
[0096] In some embodiments, if the vehicle is equipped with a TBOX module, a path planning experience base is generated based on the vehicle's historical reversing records, and the learning parameters of the reverse RRT algorithm are continuously learned and optimized.
[0097] like Figure 4 As shown, the hardware system of the present invention includes: front, rear, left and right cameras (FC, RC, LC, RC), front bumper radar (F1, F2, F3, F4) and rear bumper radar (R1, R2, R3, R4), electric power steering controller (EPS), and entertainment host (IHU).
[0098] When the vehicle is traveling at low speed, obstacles in the surrounding area are detected by the vehicle's radar and cameras. The radar module transmits distance information to the IHU (Integrated Vehicle Hub) via the CAN bus. The user can view the specific distance values by opening the AVM (Autonomous View Monitor) interface. When the user begins parking, the system planning module inside the IHU plans a specific reversing route based on the surrounding environment, and the user follows the plan to park.
[0099] Example 3
[0100] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in the automatic reversing route generation method described in Embodiment 1 above.
[0101] Example 4
[0102] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the automatic reversing route generation method described in Embodiment 1 above.
[0103] Example 5
[0104] This embodiment provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps in the automatic reversing route generation method described in Embodiment 1.
[0105] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of hardware embodiments, software embodiments, or embodiments 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.
[0106] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), 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 illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0107] 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.
[0108] 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.
[0109] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.
[0110] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A method for automatically generating reversing routes, characterized in that, include: The map before the vehicle reverses, the starting pose of the vehicle before reversing, and the pose of the final parking space are obtained. The reverse RRT algorithm is used to generate the initial reversing path. In the reverse RRT algorithm optimization process, a search function is used, and the node corresponding to the minimum value of the search function is selected as the parent node of the target pose; until all node poses in the random tree have reached the final berth pose; the initial reversing path is extracted according to the parent node relationship in the random tree; The initial reversing path is smoothed to obtain the optimal reversing path, which is then displayed in the holographic imaging system. The starting and ending parking positions of the vehicle before reversing both include the vehicle's position information and heading angle; the position information is collected by radar, and the map before reversing is collected by cameras deployed around the vehicle and generated by the controller. The search function is expressed by the following formula: in, This represents the actual path length from the starting point to node m. This represents the estimated cost from node m to the target endpoint. , , These represent the weights for angle changes, direction changes, and reversing permissions, respectively. , , These represent the costs of changing the angle, changing the direction, and reversing, respectively.
2. The method for automatically generating reversing routes according to claim 1, characterized in that, The method for smoothing the initial reversing path to obtain the optimal reversing path includes: Step 1: Import the initial reversing path RRT_path; Step 2: Let the smooth path be smooth_path, and node smooth_path(1) = RRT_path(1); Step 3: Let i be the maximum number of nodes in RRT_path; Step 4: Determine whether the line connecting RRT_path(i) and smooth_path(end) collides with an obstacle or whether the line length is greater than the smooth length D. If so, set i = i-1 and repeat step 4; otherwise, go to step 5. Step 5: Add RRT_path(i) to the end of smooth_path(end); Step 6: Determine whether the connection between smooth_path(end) and RRT_path(end) collides with an obstacle or whether the length of the connection is greater than the smooth length D. If so, delete nodes 1 to i of RRT_path and go to step 3; otherwise, go to step 7. Step 7: Add RRT_path(end) to the end of smooth_path(end).
3. The method for automatically generating reversing routes according to claim 1, characterized in that, The vehicle is equipped with a TBOX module, which generates a path planning experience base based on the vehicle's historical reversing records, and continuously learns and optimizes the learning parameters of the reverse RRT algorithm.
4. A reversing route automatic generation system, characterized in that, The method for automatically generating reversing routes as described in any one of claims 1-3 includes: The path generation module is configured to: acquire the map before the vehicle reverses, the starting pose of the vehicle before reversing, and the pose of the destination parking space; generate an initial reversing path using the reverse RRT algorithm; during the optimization process of the reverse RRT algorithm, a search function is used to select the node corresponding to the minimum value of the search function as the parent node of the target pose; until all node poses in the random tree have reached the pose of the destination parking space; and extract the initial reversing path based on the parent node relationship in the random tree. The smoothing module is configured to smooth the initial reversing path to obtain the optimal reversing path and display it in the holographic imaging system.
5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the automatic reversing route generation method as described in any one of claims 1-3.
6. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the automatic reversing route generation method as described in any one of claims 1-3.
7. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps in the automatic reversing route generation method as described in any one of claims 1-3.